kaveh commited on
Commit
d2a9154
·
1 Parent(s): bae9663

S2F v1.2.0

Browse files
Files changed (50) hide show
  1. .gitattributes +2 -1
  2. .gitignore +12 -0
  3. README.md +18 -4
  4. S2FApp/.streamlit/config.toml +25 -1
  5. S2FApp/Dockerfile +7 -2
  6. S2FApp/README.md +26 -8
  7. S2FApp/app.py +143 -53
  8. S2FApp/config/constants.py +24 -1
  9. S2FApp/download_ckp.py +0 -6
  10. S2FApp/predictor.py +78 -30
  11. S2FApp/requirements-docker.txt +1 -1
  12. S2FApp/requirements.txt +1 -1
  13. S2FApp/res/ss.png +2 -2
  14. S2FApp/static/s2f_styles.css +100 -55
  15. S2FApp/ui/heatmaps.py +25 -16
  16. S2FApp/ui/measure_tool.py +35 -84
  17. S2FApp/ui/result_display.py +207 -245
  18. S2FApp/utils/display.py +8 -22
  19. S2FApp/utils/report.py +226 -54
  20. S2FApp/utils/substrate_settings.py +3 -18
  21. S2FApp/utils/units.py +125 -0
  22. ckp/single_cell/ckp_singlecell_GN_image_only.pth +3 -0
  23. experiments/README.md +74 -0
  24. experiments/__init__.py +5 -0
  25. experiments/ablation_models.py +73 -0
  26. experiments/configs.py +85 -0
  27. experiments/evaluate.py +197 -0
  28. experiments/layout.py +26 -0
  29. experiments/losses.py +37 -0
  30. experiments/manifest_data.py +84 -0
  31. experiments/results/eval/model_params.csv +30 -0
  32. experiments/results/eval/per_image.csv +0 -0
  33. experiments/results/eval/summary.csv +0 -0
  34. experiments/run_all.py +93 -0
  35. experiments/splits/.gitkeep +0 -0
  36. experiments/splits/alltune_train.csv +281 -0
  37. experiments/splits/alltune_val.csv +82 -0
  38. experiments/splits/spheroid_train.csv +130 -0
  39. experiments/splits/spheroid_val.csv +29 -0
  40. experiments/splits/test_fibro_1kPa_setIII.csv +18 -0
  41. experiments/splits/test_fibro_DMSO_setI.csv +28 -0
  42. experiments/splits/test_fibro_DMSO_setII.csv +12 -0
  43. experiments/splits/test_fibro_TGFb_setI.csv +16 -0
  44. experiments/splits/test_fibro_Y27632_setI.csv +17 -0
  45. experiments/splits/test_fibro_Y27632_setII.csv +21 -0
  46. experiments/splits/test_fibro_fibronectin_setI.csv +41 -0
  47. experiments/splits/test_u2os_6kPa.csv +40 -0
  48. experiments/splits/zenodo_v1_test.csv +47 -0
  49. experiments/splits/zenodo_v1_train.csv +237 -0
  50. experiments/train.py +279 -0
.gitattributes CHANGED
@@ -36,4 +36,5 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
36
  *.tiff filter=lfs diff=lfs merge=lfs -text
37
  *.tif filter=lfs diff=lfs merge=lfs -text
38
  *.tiff filter=lfs diff=lfs merge=lfs -text
39
- *.png filter=lfs diff=lfs merge=lfs -text
 
 
36
  *.tiff filter=lfs diff=lfs merge=lfs -text
37
  *.tif filter=lfs diff=lfs merge=lfs -text
38
  *.tiff filter=lfs diff=lfs merge=lfs -text
39
+ *.png filter=lfs diff=lfs merge=lfs -text
40
+ *.csv text eol=lf
.gitignore CHANGED
@@ -9,5 +9,17 @@ S2FApp/.s2f_env/
9
  test/
10
  S2FApp/ckp/spheroid/ckp_spheroid_FN.pth
11
  S2FApp/ckp/single_cell/ckp_singlecell_GN.pth
 
12
  S2FApp/ckp/spheroid/ckp_spheroid_GN.pth
13
  S2FApp/*.docx
 
 
 
 
 
 
 
 
 
 
 
 
9
  test/
10
  S2FApp/ckp/spheroid/ckp_spheroid_FN.pth
11
  S2FApp/ckp/single_cell/ckp_singlecell_GN.pth
12
+ S2FApp/ckp/single_cell/ckp_singlecell_GN_image_only.pth
13
  S2FApp/ckp/spheroid/ckp_spheroid_GN.pth
14
  S2FApp/*.docx
15
+
16
+ # experiments: trained ablation checkpoints (large)
17
+ experiments/runs*/
18
+
19
+ outputs/*
20
+ !outputs/.gitkeep
21
+ S2F_results_v2/
22
+ S2F_results_*/
23
+
24
+ experiments/results/predictions
25
+ experiments/results/stiffness_readouts
README.md CHANGED
@@ -8,16 +8,24 @@ tags:
8
  - gan
9
  license: mit
10
  ---
 
11
 
12
  # Shape2Force (S2F)
13
 
14
- Predict force maps from bright-field microscopy images of single-cell or spheroid.
15
 
16
  If you find this software useful, please cite:
17
 
18
- Lautaro Baro#, Kaveh Shahhosseini#, Amparo Andrés-Bordería, Claudio Angione*, and Maria Angeles Juanes*. **"Shape-to-force (S2F): Predicting Cell Traction Forces from LabelFree Imaging"**, 2026.
19
 
 
20
 
 
 
 
 
 
 
21
 
22
  ---
23
 
@@ -35,14 +43,14 @@ streamlit run app.py
35
  1. Choose Model type: Single cell or Spheroid
36
  2. Place checkpoints (`.pth`) in `S2FApp/ckp/` for local use.
37
  3. Select a Checkpoint from `ckp/`
38
- 4. For single-cell: pick Substrate (e.g. fibroblasts_PDMS)
39
  5. Upload an image or pick from `samples/`
40
  6. Click Run prediction
41
 
42
  ---
43
  ### 2. Web App Online
44
 
45
- Use the [online app](https://huggingface.co/spaces/Angione-Lab/Shape2force) on Hugging Face.
46
 
47
  <p align="center">
48
  <img src="./S2FApp/res/ss.png" width="450" alt="Shape2Force Web App" />
@@ -97,3 +105,9 @@ python -m training.train \
97
 
98
  ---
99
 
 
 
 
 
 
 
 
8
  - gan
9
  license: mit
10
  ---
11
+ [![DOI](https://zenodo.org/badge/1164156159.svg)](https://doi.org/10.5281/zenodo.20759318)
12
 
13
  # Shape2Force (S2F)
14
 
15
+ Predict traction-stress maps from bright-field images of single cells and spheroids.
16
 
17
  If you find this software useful, please cite:
18
 
19
+ Lautaro Baro#, Kaveh Shahhosseini#, Amparo Andrés-Bordería, Claudio Angione*, and Maria Angeles Juanes*. **"Shape-to-Force (S2F): Predicting Cellular Traction Stress from Label-Free Imaging"**, 2026.
20
 
21
+ ## Checkpoints
22
 
23
+ | checkpoint | model | input |
24
+ |---|---|---|
25
+ | `ckp/single_cell/ckp_singlecell_GN.pth` | S2F + substrate | bright-field image and substrate setting |
26
+ | `ckp/single_cell/ckp_singlecell_GN_image_only.pth` | S2F | bright-field image |
27
+ | `ckp/spheroid/ckp_spheroid_GN.pth` | S2F | bright-field image |
28
+ | `ckp/spheroid/ckp_spheroid_FN.pth` | supervised attention U-Net (11.8 M parameters) | bright-field image |
29
 
30
  ---
31
 
 
43
  1. Choose Model type: Single cell or Spheroid
44
  2. Place checkpoints (`.pth`) in `S2FApp/ckp/` for local use.
45
  3. Select a Checkpoint from `ckp/`
46
+ 4. For S2F + substrate: choose the substrate setting (preset, default 6 kPa, or manual values)
47
  5. Upload an image or pick from `samples/`
48
  6. Click Run prediction
49
 
50
  ---
51
  ### 2. Web App Online
52
 
53
+ Use the [online app](https://huggingface.co/spaces/Angione-Lab/Shape2Force) (version 1.2.0) on Hugging Face.
54
 
55
  <p align="center">
56
  <img src="./S2FApp/res/ss.png" width="450" alt="Shape2Force Web App" />
 
105
 
106
  ---
107
 
108
+ ### 5. Baselines and Ablations
109
+
110
+ Evaluation of the released checkpoints and the baseline and ablation models: see [`experiments/README.md`](experiments/README.md).
111
+
112
+ ---
113
+
S2FApp/.streamlit/config.toml CHANGED
@@ -6,12 +6,36 @@ enableXsrfProtection = false
6
  # [client]
7
  # toolbarMode = "minimal"
8
 
 
 
 
9
  [theme]
10
  primaryColor = "#0d9488"
 
 
 
11
  backgroundColor = "#ffffff"
12
  secondaryBackgroundColor = "#f8fafc"
13
  textColor = "#1e293b"
14
- font = "sans serif"
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
15
 
16
  [logger]
17
  level = "error"
 
6
  # [client]
7
  # toolbarMode = "minimal"
8
 
9
+ # Shared accent. Light and dark palettes live in [theme.light] / [theme.dark]
10
+ # (Streamlit ≥1.51). With both set, the app follows the system setting and
11
+ # can still be overridden from the app menu (Settings).
12
  [theme]
13
  primaryColor = "#0d9488"
14
+ font = "sans serif"
15
+
16
+ [theme.light]
17
  backgroundColor = "#ffffff"
18
  secondaryBackgroundColor = "#f8fafc"
19
  textColor = "#1e293b"
20
+ borderColor = "#e2e8f0"
21
+
22
+ [theme.light.sidebar]
23
+ backgroundColor = "#f8fafc"
24
+ secondaryBackgroundColor = "#ffffff"
25
+ textColor = "#1e293b"
26
+
27
+ [theme.dark]
28
+ backgroundColor = "#0b1220"
29
+ secondaryBackgroundColor = "#111827"
30
+ textColor = "#e2e8f0"
31
+ borderColor = "#334155"
32
+ primaryColor = "#2dd4bf"
33
+
34
+ [theme.dark.sidebar]
35
+ backgroundColor = "#111827"
36
+ secondaryBackgroundColor = "#0b1220"
37
+ textColor = "#e2e8f0"
38
+ primaryColor = "#2dd4bf"
39
 
40
  [logger]
41
  level = "error"
S2FApp/Dockerfile CHANGED
@@ -18,9 +18,14 @@ COPY requirements.txt requirements-docker.txt ./
18
  # Install Python dependencies - CPU-only PyTorch to fit Space memory limits (avoids OOM)
19
  # (psutil removed from requirements-docker.txt — optional CPU/RAM widget not used in app)
20
  # PyTorch 2.2 + torchvision 0.17 (CPU) - match requirements.txt torch>=2.0
21
- # Install numpy first with compatible version (<2) so torch.from_numpy works
 
 
 
 
22
  RUN pip install --no-cache-dir "numpy>=1.20.0,<2.0" && \
23
- pip install --no-cache-dir torch==2.2.0 torchvision==0.17.0 --index-url https://download.pytorch.org/whl/cpu && \
 
24
  pip install --no-cache-dir -r requirements-docker.txt
25
 
26
  # Copy app code (chown for HF Spaces permissions)
 
18
  # Install Python dependencies - CPU-only PyTorch to fit Space memory limits (avoids OOM)
19
  # (psutil removed from requirements-docker.txt — optional CPU/RAM widget not used in app)
20
  # PyTorch 2.2 + torchvision 0.17 (CPU) - match requirements.txt torch>=2.0
21
+ # Install numpy first with compatible version (<2) so torch.from_numpy works.
22
+ # Pin the +cpu local version and use --extra-index-url (not --index-url) so pip
23
+ # still uses PyPI for dependencies. --index-url hides PyPI; the PyTorch index then
24
+ # serves typing-extensions/jinja2 wheels that current pip rejects ("inconsistent
25
+ # Name"), and the source fallback cannot find flit_core.
26
  RUN pip install --no-cache-dir "numpy>=1.20.0,<2.0" && \
27
+ pip install --no-cache-dir "torch==2.2.0+cpu" "torchvision==0.17.0+cpu" \
28
+ --extra-index-url https://download.pytorch.org/whl/cpu && \
29
  pip install --no-cache-dir -r requirements-docker.txt
30
 
31
  # Copy app code (chown for HF Spaces permissions)
S2FApp/README.md CHANGED
@@ -16,7 +16,7 @@ app_port: 8501
16
 
17
  # Shape2Force (S2F) App
18
 
19
- Predict force maps from bright-field microscopy images using deep learning.
20
 
21
  ## Quick Start
22
 
@@ -29,13 +29,31 @@ Checkpoints are downloaded automatically from the [Shape2Force model repo](https
29
 
30
  ## Usage
31
 
32
- 1. Choose **Model type**: Single cell or Spheroid
33
- 2. Select a **Checkpoint** from `ckp/`
34
- 3. For single-cell: pick **Conditions** (e.g. Fibroblasts_Fibronectin_6KPa)
35
- 4. Upload an image or pick from `samples/`
36
- 5. Click **Run prediction**
37
-
38
- Output: heatmap, cell force (sum), and basic stats.
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
39
 
40
  ## Full Project
41
 
 
16
 
17
  # Shape2Force (S2F) App
18
 
19
+ Predict traction-stress maps from bright-field microscopy images using deep learning (version 1.2.0).
20
 
21
  ## Quick Start
22
 
 
29
 
30
  ## Usage
31
 
32
+ 1. Choose **Model type**: Single cell or Spheroid.
33
+ 2. Select a **Checkpoint** from `ckp/`. The architecture is read from the checkpoint. Single cells:
34
+ `ckp_singlecell_GN.pth` (S2F + substrate, default) or `ckp_singlecell_GN_image_only.pth` (S2F, bright-field image
35
+ only). Spheroids: `ckp_spheroid_FN.pth` (default), a smaller supervised model (11.8 M parameters) with smoother
36
+ maps and similar accuracy, or `ckp_spheroid_GN.pth`, the adversarial S2F model (77 M parameters).
37
+ 3. Single cell (S2F + substrate): choose the **Substrate setting**, a preset (default 6 kPa) or manual values of the Young's modulus
38
+ and pixel size. Both are model inputs.
39
+ 4. Enter the **Image pixel size** (µm/px) of your bright-field image, for the scale bar, area and total force
40
+ (0.325 µm/px for the single-cell training images).
41
+ 5. Upload an image or pick one from `samples/`, then click **Run prediction**.
42
+
43
+ ## Output and units
44
+
45
+ - The model predicts a normalised map in [0, 1] that converts to **traction stress** as
46
+ T = 500 Pa x value (single cells) or 50 Pa x value (spheroids), the fixed colour limits of the TFM ground-truth
47
+ maps used for training. All maps carry a colourbar in Pa and a µm scale bar.
48
+ - Metrics: mean and maximum traction stress (Pa), area (µm²) and total force (nN = Σ stress x pixel area). By default
49
+ (*Measure force region only*) they are computed inside the region of high predicted stress (red contour), estimated
50
+ from the predicted map, so that the background does not dilute them; switch it off for the whole image.
51
+ S2F predicts magnitude only, not direction.
52
+ - **Display range** narrows the colour window (e.g. 0–250 Pa); stresses above it saturate. Display only.
53
+ - **Downloads**: map PNG (scale bar + colourbar), CSV with metrics and parameters, and a PDF report that records the
54
+ input file, model, checkpoint SHA-256, substrate setting, pixel size, display and force-region settings and app
55
+ version. Batch mode gives a PDF (summary table + one page per image), a CSV, and a ZIP with, per image, the PNG and a
56
+ TIFF whose pixel values are traction stress in Pa (for measurements in Fiji/ImageJ).
57
 
58
  ## Full Project
59
 
S2FApp/app.py CHANGED
@@ -1,6 +1,7 @@
1
  """
2
  Shape2Force (S2F) - GUI for force map prediction from bright field microscopy images.
3
  """
 
4
  import os
5
  import sys
6
  import traceback
@@ -17,18 +18,26 @@ S2F_ROOT = os.path.dirname(os.path.abspath(__file__))
17
  if S2F_ROOT not in sys.path:
18
  sys.path.insert(0, S2F_ROOT)
19
 
 
 
20
  from config.constants import (
 
21
  BATCH_INFERENCE_SIZE,
22
  BATCH_MAX_IMAGES,
23
  COLORMAPS,
 
24
  DEFAULT_SUBSTRATE,
25
  MODEL_TYPE_LABELS,
 
26
  SAMPLE_EXTENSIONS,
27
  SAMPLE_THUMBNAIL_LIMIT,
 
 
28
  )
29
  from utils.paths import get_ckp_base, get_ckp_folder, get_sample_folder, list_files_in_folder, model_subfolder
30
  from utils.segmentation import estimate_cell_mask
31
- from utils.substrate_settings import list_substrates
 
32
  from utils.display import apply_display_scale
33
  from ui.components import (
34
  build_original_vals,
@@ -98,7 +107,7 @@ def _get_measure_dialog_fn():
98
 
99
  def _populate_measure_session_state(heatmap, img, pixel_sum, force, key_img, colormap_name,
100
  display_mode, auto_cell_boundary, cell_mask=None,
101
- clip_min=0, clip_max=1, clamp_only=False):
102
  """Populate session state for the measure tool. If cell_mask is None and auto_cell_boundary, computes it."""
103
  if cell_mask is None and auto_cell_boundary:
104
  cell_mask = estimate_cell_mask(heatmap)
@@ -109,10 +118,10 @@ def _populate_measure_session_state(heatmap, img, pixel_sum, force, key_img, col
109
  st.session_state["measure_clamp_only"] = clamp_only
110
  st.session_state["measure_bf_img"] = img.copy()
111
  st.session_state["measure_input_filename"] = key_img or "image"
112
- st.session_state["measure_original_vals"] = build_original_vals(heatmap, pixel_sum, force)
113
  st.session_state["measure_colormap"] = colormap_name
114
  st.session_state["measure_auto_cell_on"] = auto_cell_boundary
115
- st.session_state["measure_cell_vals"] = build_cell_vals(heatmap, cell_mask, pixel_sum, force) if auto_cell_boundary else None
116
  st.session_state["measure_cell_mask"] = cell_mask if auto_cell_boundary else None
117
 
118
 
@@ -131,7 +140,7 @@ if os.path.exists(_css_path):
131
  st.markdown("""
132
  <div class="s2f-header">
133
  <h1>🦠 Shape2Force (S2F)</h1>
134
- <p>Predict traction force maps from bright-field microscopy images of cells or spheroids</p>
135
  </div>
136
  """, unsafe_allow_html=True)
137
 
@@ -155,6 +164,22 @@ def get_cached_sample_thumbnails(model_type, sample_folder, sample_files):
155
  return cache[cache_key]
156
 
157
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
158
  def _render_sample_selector(model_type, batch_mode):
159
  """
160
  Render sample image selector (Example mode). Returns (img, imgs_batch, selected_sample, selected_samples).
@@ -221,19 +246,26 @@ with st.sidebar:
221
  ["single_cell", "spheroid"],
222
  format_func=lambda x: MODEL_TYPE_LABELS[x],
223
  horizontal=False,
224
- help="Single cell: substrate-aware force prediction. Spheroid: spheroid force maps.",
225
  )
226
 
227
  ckp_folder = get_ckp_folder(ckp_base, model_type)
228
  ckp_files = list_files_in_folder(ckp_folder, ".pth")
229
  ckp_subfolder_name = model_subfolder(model_type)
230
 
 
 
 
 
 
 
231
  if ckp_files:
232
  checkpoint = st.selectbox(
233
  "Checkpoint",
234
  ckp_files,
235
  key=f"checkpoint_{model_type}",
236
- help=f"Select a .pth file from ckp/{ckp_subfolder_name}/",
 
237
  )
238
  else:
239
  st.warning(f"No .pth files in ckp/{ckp_subfolder_name}/. Add checkpoints to load.")
@@ -241,38 +273,57 @@ with st.sidebar:
241
 
242
  substrate_config = None
243
  substrate_val = DEFAULT_SUBSTRATE
244
- use_manual = True
245
- if model_type == "single_cell":
 
246
  try:
247
  with st.container(border=False, key="s2f_grp_conditions"):
248
- st.markdown('<p class="s2f-form-label s2f-form-label--section">Conditions</p>', unsafe_allow_html=True)
 
 
 
 
 
249
  conditions_source = st.radio(
250
- "Conditions",
251
- ["From config", "Manually"],
252
- horizontal=True,
253
- label_visibility="collapsed",
254
  )
255
- from_config = conditions_source == "From config"
256
- if from_config:
257
- substrate_config = None
258
  substrates = list_substrates()
 
 
259
  substrate_val = st.selectbox(
260
- "Conditions (from config)",
261
- substrates,
262
- help="Select a preset from config/substrate_settings.json",
263
  label_visibility="collapsed",
264
  )
265
- use_manual = False
266
  else:
267
- manual_pixelsize = st.number_input("Pixel size (µm/px)", min_value=0.1, max_value=50.0,
268
- value=3.0769, step=0.1, format="%.4f")
269
- manual_young = st.number_input("Pascals", min_value=100.0, max_value=100000.0,
270
- value=6000.0, step=100.0, format="%.0f")
 
 
 
 
271
  substrate_config = {"pixelsize": manual_pixelsize, "young": manual_young}
272
  use_manual = True
273
  except FileNotFoundError:
274
  st.error("config/substrate_settings.json not found")
275
 
 
 
 
 
 
 
 
 
 
 
 
276
  batch_mode = st.toggle(
277
  "Batch mode",
278
  value=False,
@@ -280,18 +331,23 @@ with st.sidebar:
280
  )
281
 
282
  auto_cell_boundary = st.toggle(
283
- "Auto boundary",
284
- value=False,
285
- help="When on: estimate cell region from force map and use it for metrics (red contour). When off: use entire map.",
 
 
 
286
  )
287
 
 
288
  with st.container(border=False, key="s2f_grp_force"):
289
  force_scale_mode = st.radio(
290
- "Force scale",
291
  ["Default", "Range"],
292
  horizontal=True,
293
  key="s2f_force_scale",
294
- help="Default: display forces on the full 0–1 scale. Range: set a sub-range; values outside are zeroed and the rest is stretched to the colormap.",
 
295
  )
296
  if force_scale_mode == "Default":
297
  clip_min, clip_max = 0.0, 1.0
@@ -300,29 +356,14 @@ with st.sidebar:
300
  else:
301
  mn_col, mx_col = st.columns(2)
302
  with mn_col:
303
- clip_min = st.number_input(
304
- "Min",
305
- min_value=0.0,
306
- max_value=1.0,
307
- value=0.0,
308
- step=0.01,
309
- format="%.2f",
310
- key="s2f_clip_min",
311
- help="Lower bound of the display range (0–1).",
312
- )
313
  with mx_col:
314
- clip_max = st.number_input(
315
- "Max",
316
- min_value=0.0,
317
- max_value=1.0,
318
- value=1.0,
319
- step=0.01,
320
- format="%.2f",
321
- key="s2f_clip_max",
322
- help="Upper bound of the display range (0–1).",
323
- )
324
  if clip_min >= clip_max:
325
- st.warning("Min must be less than max. Using 0.00–1.00 for display.")
326
  clip_min, clip_max = 0.0, 1.0
327
  display_mode = "Range"
328
  clamp_only = False
@@ -336,7 +377,7 @@ with st.sidebar:
336
  list(COLORMAPS.keys()),
337
  key="s2f_colormap",
338
  label_visibility="collapsed",
339
- help="Color scheme for the force map. Viridis is often preferred for accessibility.",
340
  )
341
 
342
 
@@ -362,6 +403,7 @@ if batch_mode:
362
  uploaded_list = uploaded_list[:BATCH_MAX_IMAGES]
363
  for u in uploaded_list:
364
  bytes_data = u.read()
 
365
  nparr = np.frombuffer(bytes_data, np.uint8)
366
  decoded = cv2.imdecode(nparr, cv2.IMREAD_GRAYSCALE)
367
  if decoded is not None:
@@ -379,6 +421,7 @@ else:
379
  )
380
  if uploaded:
381
  bytes_data = uploaded.read()
 
382
  nparr = np.frombuffer(bytes_data, np.uint8)
383
  img = cv2.imdecode(nparr, cv2.IMREAD_GRAYSCALE)
384
  uploaded.seek(0)
@@ -429,12 +472,40 @@ def _load_predictor(model_type, checkpoint, ckp_folder):
429
  )
430
 
431
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
432
  def _prepare_and_render_cached_result(r, key_img, colormap_name, display_mode, auto_cell_boundary,
433
  clip_min, clip_max, clamp_only,
434
  download_key_suffix="", check_measure_dialog=False,
435
  show_success=False):
436
  """Prepare display from cached result and render. Used by both just_ran and has_cached paths."""
437
  img, heatmap, force, pixel_sum = r["img"], r["heatmap"], r["force"], r["pixel_sum"]
 
 
 
 
438
  display_heatmap = apply_display_scale(
439
  heatmap, display_mode,
440
  clip_min=clip_min,
@@ -445,7 +516,7 @@ def _prepare_and_render_cached_result(r, key_img, colormap_name, display_mode, a
445
  _populate_measure_session_state(
446
  heatmap, img, pixel_sum, force, key_img, colormap_name,
447
  display_mode, auto_cell_boundary, cell_mask=cell_mask,
448
- clip_min=clip_min, clip_max=clip_max, clamp_only=clamp_only,
449
  )
450
  if check_measure_dialog and st.session_state.pop("open_measure_dialog", False):
451
  measure_region_dialog()
@@ -460,9 +531,23 @@ def _prepare_and_render_cached_result(r, key_img, colormap_name, display_mode, a
460
  auto_cell_boundary=auto_cell_boundary,
461
  cell_mask=cell_mask,
462
  clip_min=clip_min, clip_max=clip_max, clamp_only=clamp_only,
 
463
  )
464
 
465
 
 
 
 
 
 
 
 
 
 
 
 
 
 
466
  if just_ran_batch:
467
  st.session_state["prediction_result"] = None
468
  st.session_state["batch_results"] = None
@@ -484,6 +569,7 @@ if just_ran_batch:
484
  pred_results.extend(chunk_results)
485
  progress_bar.progress(min(start + len(chunk), n_images) / n_images,
486
  text=f"Predicting {len(pred_results)} / {n_images} images")
 
487
  batch_results = [
488
  {
489
  "img": img_b.copy(),
@@ -491,11 +577,13 @@ if just_ran_batch:
491
  "force": force,
492
  "pixel_sum": pixel_sum,
493
  "key_img": key_b,
 
494
  "cell_mask": estimate_cell_mask(heatmap) if auto_cell_boundary else None,
495
  }
496
  for (img_b, key_b), (heatmap, force, pixel_sum) in zip(imgs_batch, pred_results)
497
  ]
498
  st.session_state["batch_results"] = batch_results
 
499
  progress_bar.empty()
500
  st.success(f"Prediction complete for {len(batch_results)} image(s)!")
501
  render_batch_results(
@@ -514,6 +602,7 @@ if just_ran_batch:
514
  st.code(traceback.format_exc())
515
 
516
  elif batch_mode and st.session_state.get("batch_results"):
 
517
  render_batch_results(
518
  st.session_state["batch_results"],
519
  colormap_name=colormap_name,
@@ -542,6 +631,7 @@ elif just_ran:
542
  "force": force,
543
  "pixel_sum": pixel_sum,
544
  "cache_key": cache_key,
 
545
  }
546
  st.session_state["prediction_result"] = r
547
  _prepare_and_render_cached_result(
 
1
  """
2
  Shape2Force (S2F) - GUI for force map prediction from bright field microscopy images.
3
  """
4
+ import hashlib
5
  import os
6
  import sys
7
  import traceback
 
18
  if S2F_ROOT not in sys.path:
19
  sys.path.insert(0, S2F_ROOT)
20
 
21
+ from datetime import datetime, timezone
22
+
23
  from config.constants import (
24
+ APP_VERSION,
25
  BATCH_INFERENCE_SIZE,
26
  BATCH_MAX_IMAGES,
27
  COLORMAPS,
28
+ DEFAULT_IMAGE_UM_PER_PX,
29
  DEFAULT_SUBSTRATE,
30
  MODEL_TYPE_LABELS,
31
+ REFERENCE_SUBSTRATE,
32
  SAMPLE_EXTENSIONS,
33
  SAMPLE_THUMBNAIL_LIMIT,
34
+ SPHEROID_DEFAULT_CKP,
35
+ STRESS_MAX_PA,
36
  )
37
  from utils.paths import get_ckp_base, get_ckp_folder, get_sample_folder, list_files_in_folder, model_subfolder
38
  from utils.segmentation import estimate_cell_mask
39
+ from utils.substrate_settings import get_settings_of_category, list_substrates
40
+ from utils.units import make_scale
41
  from utils.display import apply_display_scale
42
  from ui.components import (
43
  build_original_vals,
 
107
 
108
  def _populate_measure_session_state(heatmap, img, pixel_sum, force, key_img, colormap_name,
109
  display_mode, auto_cell_boundary, cell_mask=None,
110
+ clip_min=0, clip_max=1, clamp_only=False, scale=None):
111
  """Populate session state for the measure tool. If cell_mask is None and auto_cell_boundary, computes it."""
112
  if cell_mask is None and auto_cell_boundary:
113
  cell_mask = estimate_cell_mask(heatmap)
 
118
  st.session_state["measure_clamp_only"] = clamp_only
119
  st.session_state["measure_bf_img"] = img.copy()
120
  st.session_state["measure_input_filename"] = key_img or "image"
121
+ st.session_state["measure_original_vals"] = build_original_vals(heatmap, pixel_sum, force, scale)
122
  st.session_state["measure_colormap"] = colormap_name
123
  st.session_state["measure_auto_cell_on"] = auto_cell_boundary
124
+ st.session_state["measure_cell_vals"] = build_cell_vals(heatmap, cell_mask, pixel_sum, force, scale) if auto_cell_boundary else None
125
  st.session_state["measure_cell_mask"] = cell_mask if auto_cell_boundary else None
126
 
127
 
 
140
  st.markdown("""
141
  <div class="s2f-header">
142
  <h1>🦠 Shape2Force (S2F)</h1>
143
+ <p>Predict traction-stress magnitude maps (Pa) from bright-field microscopy images of cells or spheroids</p>
144
  </div>
145
  """, unsafe_allow_html=True)
146
 
 
164
  return cache[cache_key]
165
 
166
 
167
+ def _remember_input_hash(name, data):
168
+ """SHA-256 of the uploaded file bytes, so the report identifies the exact input image."""
169
+ st.session_state.setdefault("input_sha256", {})[name] = hashlib.sha256(data).hexdigest()
170
+
171
+
172
+ def _input_sha256(name):
173
+ h = st.session_state.get("input_sha256", {}).get(name)
174
+ if h is None and name:
175
+ p = os.path.join(get_sample_folder(S2F_ROOT, model_type), name)
176
+ if os.path.isfile(p):
177
+ with open(p, "rb") as f:
178
+ h = hashlib.sha256(f.read()).hexdigest()
179
+ st.session_state.setdefault("input_sha256", {})[name] = h
180
+ return h or "–"
181
+
182
+
183
  def _render_sample_selector(model_type, batch_mode):
184
  """
185
  Render sample image selector (Example mode). Returns (img, imgs_batch, selected_sample, selected_samples).
 
246
  ["single_cell", "spheroid"],
247
  format_func=lambda x: MODEL_TYPE_LABELS[x],
248
  horizontal=False,
249
+ help="Single cell: substrate-aware force prediction. Spheroid: spheroid traction stress maps.",
250
  )
251
 
252
  ckp_folder = get_ckp_folder(ckp_base, model_type)
253
  ckp_files = list_files_in_folder(ckp_folder, ".pth")
254
  ckp_subfolder_name = model_subfolder(model_type)
255
 
256
+ if model_type == "spheroid" and SPHEROID_DEFAULT_CKP in ckp_files:
257
+ ckp_files = [SPHEROID_DEFAULT_CKP] + [f for f in ckp_files if f != SPHEROID_DEFAULT_CKP]
258
+ _ckp_notes = {"ckp_spheroid_FN.pth": "recommended: smoother maps, 11.8 M parameters",
259
+ "ckp_spheroid_GN.pth": "S2F adversarial model, 77 M parameters",
260
+ "ckp_singlecell_GN.pth": "S2F + substrate",
261
+ "ckp_singlecell_GN_image_only.pth": "S2F, image only"}
262
  if ckp_files:
263
  checkpoint = st.selectbox(
264
  "Checkpoint",
265
  ckp_files,
266
  key=f"checkpoint_{model_type}",
267
+ format_func=lambda f: f"{f} ({_ckp_notes[f]})" if f in _ckp_notes else f,
268
+ help=f"Select a .pth file from ckp/{ckp_subfolder_name}/. The architecture is read from the checkpoint.",
269
  )
270
  else:
271
  st.warning(f"No .pth files in ckp/{ckp_subfolder_name}/. Add checkpoints to load.")
 
273
 
274
  substrate_config = None
275
  substrate_val = DEFAULT_SUBSTRATE
276
+ use_manual = False
277
+ substrate_mode_label = "reference"
278
+ if model_type == "single_cell" and not (checkpoint and "image_only" in checkpoint):
279
  try:
280
  with st.container(border=False, key="s2f_grp_conditions"):
281
+ st.markdown(
282
+ '<p class="s2f-form-label s2f-form-label--section">Substrate setting (model input)</p>',
283
+ unsafe_allow_html=True,
284
+ help="Young's modulus of the gel and pixel size of the TFM reconstruction, given to the model "
285
+ "as two input channels. Select a preset (default: 6 kPa) or enter the values manually.",
286
+ )
287
  conditions_source = st.radio(
288
+ "Substrate setting", ["Preset", "Manual"],
289
+ horizontal=True, label_visibility="collapsed",
 
 
290
  )
291
+ if conditions_source == "Preset":
292
+ substrate_mode_label = "preset"
 
293
  substrates = list_substrates()
294
+ if REFERENCE_SUBSTRATE in substrates: # the default preset is listed first
295
+ substrates = [REFERENCE_SUBSTRATE] + [s for s in substrates if s != REFERENCE_SUBSTRATE]
296
  substrate_val = st.selectbox(
297
+ "Preset", substrates, index=0,
298
+ format_func=lambda s: "Default (6 kPa)" if s == REFERENCE_SUBSTRATE
299
+ else get_settings_of_category(s).get("name", s),
300
  label_visibility="collapsed",
301
  )
 
302
  else:
303
+ substrate_mode_label = "manual"
304
+ manual_pixelsize = st.number_input(
305
+ "Pixel size of TFM reconstruction", min_value=0.1, max_value=50.0, value=3.0769, step=0.1,
306
+ format="%.4f",
307
+ help="Model input. The presets use 3.0769 for fibroblasts and 6.1538 for U2OS cells.")
308
+ manual_young = st.number_input(
309
+ "Young's modulus (Pa)", min_value=100.0, max_value=100000.0, value=6000.0, step=100.0,
310
+ format="%.0f", help="Model input. Young's modulus of the gel.")
311
  substrate_config = {"pixelsize": manual_pixelsize, "young": manual_young}
312
  use_manual = True
313
  except FileNotFoundError:
314
  st.error("config/substrate_settings.json not found")
315
 
316
+ with st.container(border=False, key="s2f_grp_pixel"):
317
+ _def_px = DEFAULT_IMAGE_UM_PER_PX.get(model_type) or 0.0
318
+ image_um_per_px = st.number_input(
319
+ "Image pixel size (µm/px)",
320
+ min_value=0.0, max_value=100.0, value=float(_def_px), step=0.005, format="%.4f",
321
+ key=f"s2f_um_per_px_{model_type}",
322
+ help="Pixel size of the uploaded bright-field image, for the scale bar, area (µm²) and total force (nN). "
323
+ "0 = unknown (only traction stress in Pa is reported). The single-cell training images "
324
+ "(2048 x 2048 px) have 0.325 µm/px.",
325
+ ) or None
326
+
327
  batch_mode = st.toggle(
328
  "Batch mode",
329
  value=False,
 
331
  )
332
 
333
  auto_cell_boundary = st.toggle(
334
+ "Measure force region only",
335
+ value=True,
336
+ help="On (recommended): the metrics are computed inside the region where the predicted traction stress is "
337
+ "high (red contour), so the empty background does not dilute the mean stress or the area. The region is "
338
+ "estimated automatically from the predicted map, not from the cell outline in the bright-field image. "
339
+ "Off: the metrics cover the whole image. For your own regions, use the Measure tool.",
340
  )
341
 
342
+ _smax = STRESS_MAX_PA["spheroid" if model_type == "spheroid" else "single_cell"]
343
  with st.container(border=False, key="s2f_grp_force"):
344
  force_scale_mode = st.radio(
345
+ "Display range",
346
  ["Default", "Range"],
347
  horizontal=True,
348
  key="s2f_force_scale",
349
+ help=f"Default: 0–{_smax:.0f} Pa (the full output scale of this model). Range: show a narrower window, "
350
+ "e.g. 0–250 Pa; stresses above the window are shown in the top colour. Display only.",
351
  )
352
  if force_scale_mode == "Default":
353
  clip_min, clip_max = 0.0, 1.0
 
356
  else:
357
  mn_col, mx_col = st.columns(2)
358
  with mn_col:
359
+ lo_pa = st.number_input("Min (Pa)", min_value=0.0, max_value=_smax, value=0.0, step=_smax / 50,
360
+ format="%.0f", key=f"s2f_clip_min_pa_{model_type}")
 
 
 
 
 
 
 
 
361
  with mx_col:
362
+ hi_pa = st.number_input("Max (Pa)", min_value=0.0, max_value=_smax, value=_smax, step=_smax / 50,
363
+ format="%.0f", key=f"s2f_clip_max_pa_{model_type}")
364
+ clip_min, clip_max = lo_pa / _smax, hi_pa / _smax
 
 
 
 
 
 
 
365
  if clip_min >= clip_max:
366
+ st.warning(f"Min must be less than max. Using 0–{_smax:.0f} Pa.")
367
  clip_min, clip_max = 0.0, 1.0
368
  display_mode = "Range"
369
  clamp_only = False
 
377
  list(COLORMAPS.keys()),
378
  key="s2f_colormap",
379
  label_visibility="collapsed",
380
+ help="Color scheme for the traction stress map. Viridis is often preferred for accessibility.",
381
  )
382
 
383
 
 
403
  uploaded_list = uploaded_list[:BATCH_MAX_IMAGES]
404
  for u in uploaded_list:
405
  bytes_data = u.read()
406
+ _remember_input_hash(u.name, bytes_data)
407
  nparr = np.frombuffer(bytes_data, np.uint8)
408
  decoded = cv2.imdecode(nparr, cv2.IMREAD_GRAYSCALE)
409
  if decoded is not None:
 
421
  )
422
  if uploaded:
423
  bytes_data = uploaded.read()
424
+ _remember_input_hash(uploaded.name, bytes_data)
425
  nparr = np.frombuffer(bytes_data, np.uint8)
426
  img = cv2.imdecode(nparr, cv2.IMREAD_GRAYSCALE)
427
  uploaded.seek(0)
 
472
  )
473
 
474
 
475
+ def _build_info(predictor, key_img, img, pred_time, image_um_per_px, display_mode, clip_min, clip_max, colormap_name,
476
+ auto_cell_boundary):
477
+ """Provenance of one prediction (shown in the app and written to CSV/PDF)."""
478
+ smax = STRESS_MAX_PA["spheroid" if predictor.model_type == "spheroid" else "single_cell"]
479
+ sub = None
480
+ if predictor.uses_substrate:
481
+ settings = substrate_config if (use_manual and substrate_config) else get_settings_of_category(sub_val_for_info)
482
+ sub = {"mode": substrate_mode_label if substrate_mode_label != "reference" else "preset",
483
+ "name": None if use_manual else (sub_val_for_info + (" (reference)" if substrate_mode_label == "reference" else "")),
484
+ "pixelsize": float(settings["pixelsize"]), "young": float(settings["young"]),
485
+ **predictor.substrate_channels(sub_val_for_info, substrate_config if use_manual else None)}
486
+ rng = (clip_min * smax, clip_max * smax) if display_mode == "Range" else (0.0, smax)
487
+ return {
488
+ "input_file": key_img or "image", "input_sha256": _input_sha256(key_img), "time": pred_time, "model": predictor.describe(), "substrate": sub,
489
+ "image_shape": tuple(img.shape[:2]), "image_um_per_px": image_um_per_px, "stress_max_pa": smax,
490
+ "display": {"mode": display_mode, "range_pa": rng, "colormap": colormap_name},
491
+ "auto_boundary": bool(auto_cell_boundary), "app_version": APP_VERSION,
492
+ "app_commit": os.environ.get("S2F_APP_COMMIT", ""),
493
+ }
494
+
495
+
496
+ sub_val_for_info = substrate_val if (model_type == "single_cell" and not use_manual) else DEFAULT_SUBSTRATE
497
+
498
+
499
  def _prepare_and_render_cached_result(r, key_img, colormap_name, display_mode, auto_cell_boundary,
500
  clip_min, clip_max, clamp_only,
501
  download_key_suffix="", check_measure_dialog=False,
502
  show_success=False):
503
  """Prepare display from cached result and render. Used by both just_ran and has_cached paths."""
504
  img, heatmap, force, pixel_sum = r["img"], r["heatmap"], r["force"], r["pixel_sum"]
505
+ predictor = _load_predictor(model_type, checkpoint, ckp_folder)
506
+ scale = make_scale(model_type, image_um_per_px, img.shape[:2], heatmap.shape)
507
+ info = _build_info(predictor, key_img, img, r.get("time", "–"), image_um_per_px, display_mode, clip_min, clip_max,
508
+ colormap_name, auto_cell_boundary)
509
  display_heatmap = apply_display_scale(
510
  heatmap, display_mode,
511
  clip_min=clip_min,
 
516
  _populate_measure_session_state(
517
  heatmap, img, pixel_sum, force, key_img, colormap_name,
518
  display_mode, auto_cell_boundary, cell_mask=cell_mask,
519
+ clip_min=clip_min, clip_max=clip_max, clamp_only=clamp_only, scale=scale,
520
  )
521
  if check_measure_dialog and st.session_state.pop("open_measure_dialog", False):
522
  measure_region_dialog()
 
531
  auto_cell_boundary=auto_cell_boundary,
532
  cell_mask=cell_mask,
533
  clip_min=clip_min, clip_max=clip_max, clamp_only=clamp_only,
534
+ scale=scale, info=info,
535
  )
536
 
537
 
538
+ def _attach_batch_info(results):
539
+ """Physical scale and provenance for each batch result (depends on current sidebar settings)."""
540
+ predictor = _load_predictor(model_type, checkpoint, ckp_folder)
541
+ for r in results:
542
+ r["scale"] = make_scale(model_type, image_um_per_px, r["img"].shape[:2], r["heatmap"].shape)
543
+ r["info"] = _build_info(predictor, r["key_img"], r["img"], r.get("time", "–"), image_um_per_px, display_mode,
544
+ clip_min, clip_max, colormap_name, auto_cell_boundary)
545
+
546
+
547
+ def _utc_now():
548
+ return datetime.now(timezone.utc).strftime("%Y-%m-%d %H:%M:%S")
549
+
550
+
551
  if just_ran_batch:
552
  st.session_state["prediction_result"] = None
553
  st.session_state["batch_results"] = None
 
569
  pred_results.extend(chunk_results)
570
  progress_bar.progress(min(start + len(chunk), n_images) / n_images,
571
  text=f"Predicting {len(pred_results)} / {n_images} images")
572
+ pred_time = _utc_now()
573
  batch_results = [
574
  {
575
  "img": img_b.copy(),
 
577
  "force": force,
578
  "pixel_sum": pixel_sum,
579
  "key_img": key_b,
580
+ "time": pred_time,
581
  "cell_mask": estimate_cell_mask(heatmap) if auto_cell_boundary else None,
582
  }
583
  for (img_b, key_b), (heatmap, force, pixel_sum) in zip(imgs_batch, pred_results)
584
  ]
585
  st.session_state["batch_results"] = batch_results
586
+ _attach_batch_info(batch_results)
587
  progress_bar.empty()
588
  st.success(f"Prediction complete for {len(batch_results)} image(s)!")
589
  render_batch_results(
 
602
  st.code(traceback.format_exc())
603
 
604
  elif batch_mode and st.session_state.get("batch_results"):
605
+ _attach_batch_info(st.session_state["batch_results"])
606
  render_batch_results(
607
  st.session_state["batch_results"],
608
  colormap_name=colormap_name,
 
631
  "force": force,
632
  "pixel_sum": pixel_sum,
633
  "cache_key": cache_key,
634
+ "time": _utc_now(),
635
  }
636
  st.session_state["prediction_result"] = r
637
  _prepare_and_render_cached_result(
S2FApp/config/constants.py CHANGED
@@ -6,8 +6,31 @@ import cv2
6
  # Model & paths
7
  MODEL_INPUT_SIZE = 1024
8
 
9
- # Default substrate (used when config lookup fails or manual mode fallback)
 
 
10
  DEFAULT_SUBSTRATE = "Fibroblasts_Fibronectin_6KPa"
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
11
 
12
  # UI
13
  CANVAS_SIZE = 320
 
6
  # Model & paths
7
  MODEL_INPUT_SIZE = 1024
8
 
9
+ APP_VERSION = "1.2.0" # shown in reports; the git commit is added from S2F_APP_COMMIT if set
10
+
11
+ # Default substrate preset (6 kPa)
12
  DEFAULT_SUBSTRATE = "Fibroblasts_Fibronectin_6KPa"
13
+ REFERENCE_SUBSTRATE = DEFAULT_SUBSTRATE
14
+
15
+ # Normalisation of the two substrate channels: the ranges used in training (S2F config/substrate_settings.json).
16
+ # Fixed here so that the model input does not depend on which presets the app lists.
17
+ SETTINGS_NORMALIZATION = {"pixelsize": {"min": 3.0769, "max": 9.8138}, "young": {"min": 1000.0, "max": 10000.0}}
18
+
19
+ # Physical scale of the output: the ground-truth maps were exported on a fixed colour scale,
20
+ # so a normalised value of 1 corresponds to this traction stress.
21
+ STRESS_MAX_PA = {"single_cell": 500.0, "spheroid": 50.0}
22
+
23
+ # Default pixel size of the bright-field image (µm/px); None = entered by the user
24
+ DEFAULT_IMAGE_UM_PER_PX = {"single_cell": 0.325, "spheroid": None}
25
+
26
+ SPHEROID_DEFAULT_CKP = "ckp_spheroid_FN.pth"
27
+ ARCH_LABELS = {
28
+ "s2f": "S2F generator (attention U-Net + PatchGAN training), 77.0 M parameters",
29
+ "s2f_spheroid": "Supervised attention U-Net (no discriminator), 11.8 M parameters",
30
+ }
31
+
32
+ # Auto-boundary parameters (utils/segmentation.estimate_cell_mask defaults), recorded in reports
33
+ AUTO_BOUNDARY_DESCRIPTION = "high-stress region from the predicted map: Otsu threshold x 0.85 after Gaussian smoothing (sigma 2 px), dilated by 4 px"
34
 
35
  # UI
36
  CANVAS_SIZE = 320
S2FApp/download_ckp.py CHANGED
@@ -14,12 +14,6 @@ if not has_any:
14
  repo = os.environ.get("HF_MODEL_REPO", "Angione-Lab/Shape2Force")
15
  files = list_repo_files(repo)
16
  pth_files = [f for f in files if f.startswith("ckp/") and f.endswith(".pth")]
17
- # For spheroid: only download ckp_spheroid_FN.pth (not ckp_spheroid_GN.pth or others)
18
- def should_download(f):
19
- if "spheroid" in f and "ckp_spheroid_FN.pth" not in f:
20
- return False
21
- return True
22
- pth_files = [f for f in pth_files if should_download(f)]
23
  for f in pth_files:
24
  hf_hub_download(repo_id=repo, filename=f, local_dir="/app")
25
  print("Downloaded checkpoints from", repo)
 
14
  repo = os.environ.get("HF_MODEL_REPO", "Angione-Lab/Shape2Force")
15
  files = list_repo_files(repo)
16
  pth_files = [f for f in files if f.startswith("ckp/") and f.endswith(".pth")]
 
 
 
 
 
 
17
  for f in pth_files:
18
  hf_hub_download(repo_id=repo, filename=f, local_dir="/app")
19
  print("Downloaded checkpoints from", repo)
S2FApp/predictor.py CHANGED
@@ -2,6 +2,7 @@
2
  Core inference logic for S2F (Shape2Force).
3
  Predicts force maps from bright field microscopy images.
4
  """
 
5
  import os
6
  import sys
7
  import cv2
@@ -77,9 +78,33 @@ def create_settings_channels_single(substrate_name, device, height, width, confi
77
  return torch.cat([pixelsize_ch, young_ch], dim=1)
78
 
79
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
80
  class S2FPredictor:
81
  """
82
- Shape2Force predictor for single-cell or spheroid force map prediction.
 
83
  """
84
 
85
  def __init__(self, model_type="single_cell", checkpoint_path=None, ckp_folder=None, device=None):
@@ -97,37 +122,60 @@ class S2FPredictor:
97
  ckp_dir = ckp_folder if ckp_folder else os.path.join(ckp_base, subfolder)
98
  if not os.path.isdir(ckp_dir):
99
  ckp_dir = ckp_base # fallback if subfolders not used
100
-
101
- in_channels = 3 if model_type == "single_cell" else 1
102
- s2f_model_type = "s2f" if model_type == "single_cell" else "s2f_spheroid"
103
- generator, _ = create_s2f_model(in_channels=in_channels, model_type=s2f_model_type)
104
- self.generator = generator
105
-
106
- if checkpoint_path:
107
- full_path = checkpoint_path
108
- if not os.path.isabs(checkpoint_path):
109
- full_path = os.path.join(ckp_dir, checkpoint_path)
110
- if not os.path.exists(full_path):
111
- full_path = os.path.join(ckp_base, checkpoint_path) # try base folder
112
- if not os.path.exists(full_path):
113
- raise FileNotFoundError(f"Checkpoint not found: {full_path}")
114
-
115
- if model_type == "single_cell":
116
- self.generator.load_checkpoint_with_expansion(full_path, strict=True)
117
- else:
118
- checkpoint = torch.load(full_path, map_location="cpu", weights_only=False)
119
- state = checkpoint.get("generator_state_dict") or checkpoint.get("model_state_dict") or checkpoint
120
- self.generator.load_state_dict(state, strict=True)
121
- if hasattr(self.generator, "set_output_mode"):
122
- self.generator.set_output_mode(use_tanh=False) # sigmoid [0,1] for inference
123
-
124
- self.generator = self.generator.to(self.device)
125
- self.generator.eval()
126
-
 
 
 
 
127
  self.norm_params = compute_settings_normalization() if model_type == "single_cell" else None
128
- self._use_tanh_output = model_type == "single_cell" # single_cell uses tanh, spheroid uses sigmoid
129
  self.config_path = os.path.join(S2F_ROOT, "config", "substrate_settings.json")
130
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
131
  def predict(self, image_path=None, image_array=None, substrate=None,
132
  substrate_config=None):
133
  """
@@ -171,7 +219,7 @@ class S2FPredictor:
171
 
172
  if self._use_tanh_output:
173
  pred = (pred + 1.0) / 2.0 # Tanh [-1,1] to [0, 1]
174
- # else: spheroid already outputs sigmoid [0, 1]
175
  heatmap = pred[0, 0].cpu().numpy()
176
  force = sum_force_map(pred).item()
177
  pixel_sum = float(np.sum(heatmap))
 
2
  Core inference logic for S2F (Shape2Force).
3
  Predicts force maps from bright field microscopy images.
4
  """
5
+ import hashlib
6
  import os
7
  import sys
8
  import cv2
 
78
  return torch.cat([pixelsize_ch, young_ch], dim=1)
79
 
80
 
81
+ def file_sha256(path, chunk=1 << 20):
82
+ """SHA-256 of a file (recorded in reports so a prediction can be traced to its checkpoint)."""
83
+ h = hashlib.sha256()
84
+ with open(path, "rb") as f:
85
+ for block in iter(lambda: f.read(chunk), b""):
86
+ h.update(block)
87
+ return h.hexdigest()
88
+
89
+
90
+ def detect_architecture(state_dict):
91
+ """
92
+ Generator architecture from the checkpoint keys:
93
+ 's2f' S2FGenerator (multi-scale input 'scale_pyramid.*'); tanh output -> (y + 1) / 2
94
+ 's2f_spheroid' supervised attention U-Net ('encoder1.*'); sigmoid output in [0, 1]
95
+ """
96
+ keys = list(state_dict.keys())
97
+ if any(k.startswith("scale_pyramid.") or k.startswith("initial_conv.") for k in keys):
98
+ return "s2f"
99
+ if any(k.startswith("encoder1.") for k in keys):
100
+ return "s2f_spheroid"
101
+ raise ValueError("Unrecognised checkpoint: neither S2FGenerator nor the supervised spheroid model")
102
+
103
+
104
  class S2FPredictor:
105
  """
106
+ Shape2Force predictor for single-cell or spheroid traction-stress maps.
107
+ The generator architecture is read from the checkpoint.
108
  """
109
 
110
  def __init__(self, model_type="single_cell", checkpoint_path=None, ckp_folder=None, device=None):
 
122
  ckp_dir = ckp_folder if ckp_folder else os.path.join(ckp_base, subfolder)
123
  if not os.path.isdir(ckp_dir):
124
  ckp_dir = ckp_base # fallback if subfolders not used
125
+ if not checkpoint_path:
126
+ raise ValueError("checkpoint_path is required")
127
+
128
+ full_path = checkpoint_path
129
+ if not os.path.isabs(checkpoint_path):
130
+ full_path = os.path.join(ckp_dir, checkpoint_path)
131
+ if not os.path.exists(full_path):
132
+ full_path = os.path.join(ckp_base, checkpoint_path) # try base folder
133
+ if not os.path.exists(full_path):
134
+ raise FileNotFoundError(f"Checkpoint not found: {full_path}")
135
+
136
+ checkpoint = torch.load(full_path, map_location="cpu", weights_only=False)
137
+ state = checkpoint.get("generator_state_dict") or checkpoint.get("model_state_dict") or checkpoint
138
+ self.architecture = detect_architecture(state)
139
+ self.in_channels = 3 if model_type == "single_cell" else 1
140
+ first = state.get("scale_pyramid.0.weight", state.get("initial_conv.weight"))
141
+ self.uses_substrate = model_type == "single_cell" and first is not None and first.shape[1] == 3
142
+ generator, _ = create_s2f_model(in_channels=self.in_channels, model_type=self.architecture)
143
+ if model_type == "single_cell":
144
+ generator.load_checkpoint_with_expansion(full_path, strict=True)
145
+ else:
146
+ generator.load_state_dict(state, strict=True)
147
+ if self.architecture == "s2f_spheroid" and hasattr(generator, "set_output_mode"):
148
+ generator.set_output_mode(use_tanh=False) # trained with sigmoid output in [0, 1]
149
+ self._use_tanh_output = self.architecture == "s2f" # S2FGenerator: tanh in [-1, 1]
150
+
151
+ self.generator = generator.to(self.device).eval()
152
+ self.checkpoint_name = os.path.basename(full_path)
153
+ self.checkpoint_sha256 = file_sha256(full_path)
154
+ self.checkpoint_epoch = checkpoint.get("epoch") if isinstance(checkpoint, dict) else None
155
+ self.n_params = sum(p.numel() for p in self.generator.parameters())
156
  self.norm_params = compute_settings_normalization() if model_type == "single_cell" else None
 
157
  self.config_path = os.path.join(S2F_ROOT, "config", "substrate_settings.json")
158
 
159
+ def describe(self):
160
+ """Model information for reports."""
161
+ return {
162
+ "model_type": self.model_type,
163
+ "architecture": self.architecture,
164
+ "checkpoint": self.checkpoint_name,
165
+ "checkpoint_sha256": self.checkpoint_sha256,
166
+ "checkpoint_epoch": self.checkpoint_epoch,
167
+ "n_params_M": round(self.n_params / 1e6, 1),
168
+ "device": str(self.device),
169
+ }
170
+
171
+ def substrate_channels(self, substrate=None, substrate_config=None):
172
+ """Values of the two substrate input channels (normalised pixel-size and Young's-modulus settings)."""
173
+ if not self.uses_substrate:
174
+ return None
175
+ ch = create_settings_channels_single(substrate if substrate is not None else DEFAULT_SUBSTRATE, "cpu", 1, 1,
176
+ config_path=self.config_path, substrate_config=substrate_config)
177
+ return {"pixelsize_norm": float(ch[0, 0, 0, 0]), "young_norm": float(ch[0, 1, 0, 0])}
178
+
179
  def predict(self, image_path=None, image_array=None, substrate=None,
180
  substrate_config=None):
181
  """
 
219
 
220
  if self._use_tanh_output:
221
  pred = (pred + 1.0) / 2.0 # Tanh [-1,1] to [0, 1]
222
+ # else: the supervised spheroid model already outputs sigmoid [0, 1]
223
  heatmap = pred[0, 0].cpu().numpy()
224
  force = sum_force_map(pred).item()
225
  pixel_sum = float(np.sum(heatmap))
S2FApp/requirements-docker.txt CHANGED
@@ -4,7 +4,7 @@ numpy>=1.20.0,<2.0
4
  opencv-python>=4.5.0
5
  scipy>=1.7.0
6
  scikit-image>=0.19.0,<0.26
7
- streamlit>=1.29.0
8
  streamlit-drawable-canvas-fix>=0.9.8
9
  matplotlib>=3.5.0
10
  Pillow>=9.0.0
 
4
  opencv-python>=4.5.0
5
  scipy>=1.7.0
6
  scikit-image>=0.19.0,<0.26
7
+ streamlit>=1.51.0
8
  streamlit-drawable-canvas-fix>=0.9.8
9
  matplotlib>=3.5.0
10
  Pillow>=9.0.0
S2FApp/requirements.txt CHANGED
@@ -5,7 +5,7 @@ numpy>=1.20.0
5
  opencv-python>=4.5.0
6
  scipy>=1.7.0
7
  scikit-image>=0.19.0
8
- streamlit>=1.29.0
9
  streamlit-drawable-canvas-fix>=0.9.8
10
  matplotlib>=3.5.0
11
  Pillow>=9.0.0
 
5
  opencv-python>=4.5.0
6
  scipy>=1.7.0
7
  scikit-image>=0.19.0
8
+ streamlit>=1.51.0
9
  streamlit-drawable-canvas-fix>=0.9.8
10
  matplotlib>=3.5.0
11
  Pillow>=9.0.0
S2FApp/res/ss.png CHANGED

Git LFS Details

  • SHA256: 419bcb7e13db9de5999cc375a5189f814d5373d86c6f51730b20aee717d27406
  • Pointer size: 131 Bytes
  • Size of remote file: 453 kB

Git LFS Details

  • SHA256: 1f7eff9819f899530556c0ecaca40e8ff8fd984c2ffe48ccdbb2c6ba5db352c2
  • Pointer size: 131 Bytes
  • Size of remote file: 646 kB
S2FApp/static/s2f_styles.css CHANGED
@@ -6,13 +6,43 @@
6
  --s2f-primary-rgb: 13, 148, 136;
7
  /* Space for Streamlit’s fixed top toolbar (Deploy / menu). Set when header exists (see below). */
8
  --s2f-streamlit-header-offset: 0px;
9
- /* Sidebar grouped blocks: faint surface, no heavy chrome */
10
- --s2f-sidebar-panel-bg: rgba(255, 255, 255, 0.42);
11
- --s2f-sidebar-panel-border: rgba(203, 213, 225, 0.34);
12
  /* Match Streamlit’s sidebar horizontal padding so panels can full-bleed the track */
13
  --s2f-sidebar-inline-inset: 1rem;
14
  --s2f-sidebar-width: 360px;
15
  }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
16
  /* Streamlit renders a fixed header; without this offset, the sidebar and first main block sit underneath it. */
17
  .stApp:has(header[data-testid="stHeader"]) {
18
  --s2f-streamlit-header-offset: 2rem;
@@ -42,9 +72,9 @@ html, body {
42
  overflow: hidden !important;
43
  display: flex !important;
44
  flex-direction: column !important;
45
- background-color: #fafbfc !important;
46
  background-image:
47
- radial-gradient(circle at 1px 1px, rgba(148, 163, 184, 0.12) 1px, transparent 0);
48
  background-size: 28px 28px !important;
49
  background-position: 0 0, 0 0 !important;
50
  }
@@ -64,8 +94,8 @@ html, body {
64
  right: 0;
65
  bottom: 0;
66
  background:
67
- radial-gradient(ellipse 80% 50% at 70% -20%, rgba(var(--s2f-primary-rgb), 0.06) 0%, transparent 50%),
68
- radial-gradient(ellipse 60% 40% at 0% 100%, rgba(var(--s2f-primary-rgb), 0.04) 0%, transparent 50%);
69
  pointer-events: none;
70
  z-index: 0;
71
  }
@@ -143,16 +173,16 @@ section[data-testid="stSidebar"] {
143
  overflow-y: auto !important;
144
  scrollbar-gutter: stable !important;
145
  background:
146
- linear-gradient(180deg, #f8fafc 0%, #f1f5f9 100%),
147
  /* Subtle vertical rhythm */
148
  repeating-linear-gradient(
149
  90deg,
150
  transparent,
151
  transparent 89px,
152
- rgba(203, 213, 225, 0.25) 89px,
153
- rgba(203, 213, 225, 0.25) 90px
154
  ) !important;
155
- border-right: 1px solid #e2e8f0 !important;
156
  }
157
  @media (max-width: 768px) {
158
  section[data-testid="stSidebar"] { width: 100% !important; max-width: 100% !important; }
@@ -165,7 +195,7 @@ section[data-testid="stSidebar"] [data-testid="stWidgetLabel"],
165
  section[data-testid="stSidebar"] [data-testid="stWidgetLabel"] p {
166
  font-size: 0.9rem !important;
167
  font-weight: 500 !important;
168
- color: #334155 !important;
169
  }
170
  .sidebar-brand {
171
  display: flex;
@@ -177,7 +207,7 @@ section[data-testid="stSidebar"] [data-testid="stWidgetLabel"] p {
177
  .sidebar-brand .brand-text {
178
  font-size: 1.1rem;
179
  font-weight: 700;
180
- color: var(--s2f-primary-dark);
181
  letter-spacing: -0.01em;
182
  }
183
 
@@ -213,8 +243,8 @@ section[data-testid="stSidebar"] .st-key-s2f_grp_force > div {
213
 
214
  /* === Metric cards === */
215
  [data-testid="stMetric"] {
216
- background: linear-gradient(145deg, #ffffff 0%, #f8fafc 100%);
217
- border: 1px solid #e2e8f0;
218
  border-radius: 12px;
219
  padding: 0.85rem 1rem !important;
220
  box-shadow: 0 1px 4px rgba(0,0,0,0.06);
@@ -227,14 +257,14 @@ section[data-testid="stSidebar"] .st-key-s2f_grp_force > div {
227
  [data-testid="stMetric"] label {
228
  font-size: 0.75rem !important;
229
  font-weight: 600 !important;
230
- color: #64748b !important;
231
  text-transform: uppercase;
232
  letter-spacing: 0.04em;
233
  }
234
  [data-testid="stMetric"] [data-testid="stMetricValue"] {
235
  font-size: 1.25rem !important;
236
  font-weight: 700 !important;
237
- color: var(--s2f-primary-dark) !important;
238
  }
239
 
240
  /* === Buttons === */
@@ -255,7 +285,7 @@ section[data-testid="stSidebar"] .st-key-s2f_grp_force > div {
255
  .stButton > button:not([kind="primary"]) {
256
  border-radius: 10px !important;
257
  font-weight: 500 !important;
258
- border: 1px solid #cbd5e1 !important;
259
  transition: all 0.2s ease !important;
260
  }
261
  .stButton > button:not([kind="primary"]):hover {
@@ -275,8 +305,8 @@ section[data-testid="stSidebar"] .st-key-s2f_grp_force > div {
275
 
276
  /* === Action buttons row (measure + downloads) === */
277
  div[data-testid="stHorizontalBlock"]:has([data-testid="stDownloadButton"]):has([data-testid="stButton"]) {
278
- background: #f8fafc;
279
- border: 1px solid #e2e8f0;
280
  border-radius: 14px;
281
  padding: 0.65rem 0.6rem !important;
282
  margin-top: 0.5rem;
@@ -307,22 +337,22 @@ div[data-testid="stHorizontalBlock"]:has([data-testid="stDownloadButton"]):has([
307
  transform: translateY(-1px) !important;
308
  }
309
  div[data-testid="stHorizontalBlock"]:has([data-testid="stDownloadButton"]):has([data-testid="stButton"]) [data-testid="stDownloadButton"] button {
310
- background: white !important;
311
- border: 1px solid #e2e8f0 !important;
312
- color: #334155 !important;
313
  box-shadow: 0 1px 2px rgba(0,0,0,0.04) !important;
314
  }
315
  div[data-testid="stHorizontalBlock"]:has([data-testid="stDownloadButton"]):has([data-testid="stButton"]) [data-testid="stDownloadButton"] button:hover {
316
  background: rgba(var(--s2f-primary-rgb), 0.06) !important;
317
  border-color: var(--s2f-primary) !important;
318
- color: var(--s2f-primary-dark) !important;
319
  box-shadow: 0 2px 6px rgba(var(--s2f-primary-rgb), 0.12) !important;
320
  transform: translateY(-1px) !important;
321
  }
322
 
323
  /* === Expanders === */
324
  .stExpander {
325
- border: 1px solid #e2e8f0 !important;
326
  border-radius: 12px !important;
327
  overflow: hidden;
328
  box-shadow: 0 1px 3px rgba(0,0,0,0.04);
@@ -330,7 +360,7 @@ div[data-testid="stHorizontalBlock"]:has([data-testid="stDownloadButton"]):has([
330
 
331
  /* === File uploader === */
332
  [data-testid="stFileUploader"] section {
333
- border: 2px dashed #cbd5e1 !important;
334
  border-radius: 12px !important;
335
  transition: border-color 0.2s ease;
336
  }
@@ -345,7 +375,7 @@ div[data-testid="stHorizontalBlock"]:has([data-testid="stDownloadButton"]):has([
345
  gap: 8px;
346
  font-size: 0.92rem;
347
  font-weight: 600;
348
- color: #334155;
349
  padding: 0.4rem 0;
350
  }
351
  .result-badge {
@@ -356,12 +386,12 @@ div[data-testid="stHorizontalBlock"]:has([data-testid="stDownloadButton"]):has([
356
  letter-spacing: 0.06em;
357
  }
358
  .result-badge.input {
359
- background: #e2e8f0;
360
- color: #475569;
361
  }
362
  .result-badge.output {
363
  background: rgba(var(--s2f-primary-rgb), 0.15);
364
- color: var(--s2f-primary-dark);
365
  }
366
 
367
  /* === Run prediction info bar === */
@@ -371,29 +401,30 @@ div[data-testid="stHorizontalBlock"]:has([data-testid="stDownloadButton"]):has([
371
  gap: 10px;
372
  height: 42px;
373
  font-size: 0.85rem;
374
- color: #64748b;
375
  }
376
  .run-info-tag {
377
  background: rgba(var(--s2f-primary-rgb), 0.1);
378
- color: var(--s2f-primary-dark);
379
  font-weight: 600;
380
  font-size: 0.78rem;
381
  padding: 3px 10px;
382
  border-radius: 6px;
383
  }
384
  .run-info code {
385
- background: #f1f5f9;
386
  padding: 2px 8px;
387
  border-radius: 4px;
388
  font-size: 0.8rem;
389
- color: #475569;
390
  }
391
 
392
  /* === Messages === */
393
  .stSuccess {
394
- background: linear-gradient(135deg, #ecfdf5 0%, #d1fae5 100%) !important;
395
  border-left: 4px solid #10b981 !important;
396
  border-radius: 8px !important;
 
397
  }
398
  .stWarning { border-radius: 8px !important; }
399
  .stInfo { border-radius: 8px !important; }
@@ -402,19 +433,19 @@ div[data-testid="stHorizontalBlock"]:has([data-testid="stDownloadButton"]):has([
402
  [data-testid="stSelectbox"] > div > div,
403
  [data-testid="stSelectbox"] input,
404
  [data-testid="stMultiSelect"] > div > div {
405
- color: #1e293b !important;
406
- background-color: #ffffff !important;
407
  }
408
  /* Multiselect input: transparent so it doesn't show as a white block before the tags */
409
  [data-testid="stMultiSelect"] input {
410
  background-color: transparent !important;
411
- color: #1e293b !important;
412
  min-width: 2ch !important;
413
  }
414
  [data-testid="stSelectbox"] > div > div,
415
  [data-testid="stMultiSelect"] > div > div {
416
  border-radius: 8px !important;
417
- border: 1px solid #cbd5e1 !important;
418
  transition: border-color 0.15s ease, box-shadow 0.15s ease !important;
419
  }
420
  section[data-testid="stSidebar"] [data-testid="stSelectbox"] > div > div:focus-within,
@@ -428,7 +459,7 @@ section[data-testid="stSidebar"] [data-testid="stMultiSelect"] > div > div:focus
428
  }
429
  /* Toggle: on state uses --s2f-primary */
430
  [data-testid="stToggle"] [data-baseweb="toggleTrack"] {
431
- background-color: #cbd5e1 !important;
432
  }
433
  [data-testid="stToggle"] [data-baseweb="toggleTrack"][aria-checked="true"] {
434
  background-color: var(--s2f-primary) !important;
@@ -437,27 +468,27 @@ section[data-testid="stSidebar"] [data-testid="stMultiSelect"] > div > div:focus
437
  background-color: var(--s2f-primary) !important;
438
  }
439
  [data-testid="stToggle"] [data-baseweb="toggleTrack"][data-state="unchecked"] {
440
- background-color: #cbd5e1 !important;
441
  }
442
  /* Newer Streamlit may render a switch button instead of Base Web track */
443
  [data-testid="stToggle"] button[role="switch"][aria-checked="true"] {
444
  background-color: var(--s2f-primary) !important;
445
  }
446
  [data-testid="stToggle"] button[role="switch"][aria-checked="false"] {
447
- background-color: #cbd5e1 !important;
448
  }
449
- /* Dropdown options: ensure visible text on light background */
450
  [role="listbox"] [role="option"],
451
  [data-baseweb="menu"] li,
452
  ul[role="listbox"] li {
453
- color: #1e293b !important;
454
- background-color: #ffffff !important;
455
  }
456
  /* Sidebar / form labels (colormap row, section titles) */
457
  .s2f-form-label {
458
  font-size: 0.95rem;
459
  font-weight: 500;
460
- color: #334155;
461
  line-height: 1.2;
462
  margin: 0;
463
  }
@@ -492,7 +523,7 @@ ul[role="listbox"] li {
492
  padding: 0 1px;
493
  font-size: 0.65rem;
494
  font-weight: 600;
495
- color: #64748b;
496
  letter-spacing: 0.03em;
497
  }
498
  .colorbar-ticks .cb-tick {
@@ -508,7 +539,7 @@ ul[role="listbox"] li {
508
  box-shadow: inset 0 1px 1px rgba(0,0,0,0.05);
509
  }
510
  /* === Divider === */
511
- hr { border-color: #cbd5e1 !important; opacity: 0.7; }
512
 
513
  /* === Plotly chart === */
514
  .stPlotlyChart { border-radius: 12px; overflow: hidden; }
@@ -521,10 +552,10 @@ hr { border-color: #cbd5e1 !important; opacity: 0.7; }
521
  right: 0;
522
  z-index: 999;
523
  padding: 0.5rem 1rem 0.55rem;
524
- background: #f1f5f9;
525
- border-top: 1px solid #e2e8f0;
526
  font-size: 0.7rem;
527
- color: #64748b;
528
  text-align: center;
529
  line-height: 1.45;
530
  }
@@ -561,19 +592,33 @@ section[data-testid="stSidebar"] > div:first-child {
561
  /* Measure tool: value panel (replaces inline styles in measure_tool.py) */
562
  .s2f-measure-vals-heading {
563
  font-weight: 400;
564
- color: #334155;
565
  font-size: 0.95rem;
566
  margin: 0 20px 4px 4px;
567
  }
568
  .s2f-measure-vals-panel {
569
  width: 100%;
570
  box-sizing: border-box;
571
- border: 1px solid #e2e8f0;
572
  border-radius: 10px;
573
  padding: 10px 12px;
574
  margin: 0 10px 20px 10px;
575
- background: linear-gradient(145deg, #f8fafc 0%, #f1f5f9 100%);
576
- box-shadow: 0 1px 3px rgba(0, 0, 0, 0.06);
 
 
 
 
 
 
 
 
 
 
 
 
 
 
577
  }
578
  .s2f-measure-vals-grid {
579
  display: flex;
 
6
  --s2f-primary-rgb: 13, 148, 136;
7
  /* Space for Streamlit’s fixed top toolbar (Deploy / menu). Set when header exists (see below). */
8
  --s2f-streamlit-header-offset: 0px;
 
 
 
9
  /* Match Streamlit’s sidebar horizontal padding so panels can full-bleed the track */
10
  --s2f-sidebar-inline-inset: 1rem;
11
  --s2f-sidebar-width: 360px;
12
  }
13
+ /*
14
+ * Surfaces follow the active Streamlit theme. light-dark() uses the color-scheme
15
+ * Streamlit sets from the system setting (or from Settings → Light / Dark).
16
+ */
17
+ .stApp {
18
+ --s2f-page-bg: light-dark(#fafbfc, #0b1220);
19
+ --s2f-page-dot: light-dark(rgba(148, 163, 184, 0.12), rgba(148, 163, 184, 0.18));
20
+ --s2f-glow: light-dark(rgba(13, 148, 136, 0.06), rgba(45, 212, 191, 0.08));
21
+ --s2f-glow-2: light-dark(rgba(13, 148, 136, 0.04), rgba(45, 212, 191, 0.05));
22
+ --s2f-sidebar-start: light-dark(#f8fafc, #111827);
23
+ --s2f-sidebar-end: light-dark(#f1f5f9, #0f172a);
24
+ --s2f-sidebar-rule: light-dark(rgba(203, 213, 225, 0.25), rgba(51, 65, 85, 0.55));
25
+ --s2f-sidebar-panel-bg: light-dark(rgba(255, 255, 255, 0.42), rgba(15, 23, 42, 0.55));
26
+ --s2f-sidebar-panel-border: light-dark(rgba(203, 213, 225, 0.34), rgba(51, 65, 85, 0.75));
27
+ --s2f-text: light-dark(#1e293b, #e2e8f0);
28
+ --s2f-text-secondary: light-dark(#334155, #cbd5e1);
29
+ --s2f-text-muted: light-dark(#64748b, #94a3b8);
30
+ --s2f-text-faint: light-dark(#475569, #94a3b8);
31
+ --s2f-accent-text: light-dark(#0f766e, #5eead4);
32
+ --s2f-surface: light-dark(#ffffff, #111827);
33
+ --s2f-surface-2: light-dark(#f8fafc, #1e293b);
34
+ --s2f-surface-3: light-dark(#f1f5f9, #1e293b);
35
+ --s2f-border: light-dark(#e2e8f0, #334155);
36
+ --s2f-border-strong: light-dark(#cbd5e1, #475569);
37
+ --s2f-badge-bg: light-dark(#e2e8f0, #334155);
38
+ --s2f-code-bg: light-dark(#f1f5f9, #1e293b);
39
+ --s2f-footer-bg: light-dark(#f1f5f9, #0f172a);
40
+ --s2f-success-start: light-dark(#ecfdf5, #064e3b);
41
+ --s2f-success-end: light-dark(#d1fae5, #065f46);
42
+ --s2f-success-text: light-dark(#065f46, #d1fae5);
43
+ --s2f-shadow: light-dark(rgba(0, 0, 0, 0.06), rgba(0, 0, 0, 0.35));
44
+ --s2f-shadow-hover: light-dark(rgba(0, 0, 0, 0.1), rgba(0, 0, 0, 0.45));
45
+ }
46
  /* Streamlit renders a fixed header; without this offset, the sidebar and first main block sit underneath it. */
47
  .stApp:has(header[data-testid="stHeader"]) {
48
  --s2f-streamlit-header-offset: 2rem;
 
72
  overflow: hidden !important;
73
  display: flex !important;
74
  flex-direction: column !important;
75
+ background-color: var(--s2f-page-bg) !important;
76
  background-image:
77
+ radial-gradient(circle at 1px 1px, var(--s2f-page-dot) 1px, transparent 0);
78
  background-size: 28px 28px !important;
79
  background-position: 0 0, 0 0 !important;
80
  }
 
94
  right: 0;
95
  bottom: 0;
96
  background:
97
+ radial-gradient(ellipse 80% 50% at 70% -20%, var(--s2f-glow) 0%, transparent 50%),
98
+ radial-gradient(ellipse 60% 40% at 0% 100%, var(--s2f-glow-2) 0%, transparent 50%);
99
  pointer-events: none;
100
  z-index: 0;
101
  }
 
173
  overflow-y: auto !important;
174
  scrollbar-gutter: stable !important;
175
  background:
176
+ linear-gradient(180deg, var(--s2f-sidebar-start) 0%, var(--s2f-sidebar-end) 100%),
177
  /* Subtle vertical rhythm */
178
  repeating-linear-gradient(
179
  90deg,
180
  transparent,
181
  transparent 89px,
182
+ var(--s2f-sidebar-rule) 89px,
183
+ var(--s2f-sidebar-rule) 90px
184
  ) !important;
185
+ border-right: 1px solid var(--s2f-border) !important;
186
  }
187
  @media (max-width: 768px) {
188
  section[data-testid="stSidebar"] { width: 100% !important; max-width: 100% !important; }
 
195
  section[data-testid="stSidebar"] [data-testid="stWidgetLabel"] p {
196
  font-size: 0.9rem !important;
197
  font-weight: 500 !important;
198
+ color: var(--s2f-text-secondary) !important;
199
  }
200
  .sidebar-brand {
201
  display: flex;
 
207
  .sidebar-brand .brand-text {
208
  font-size: 1.1rem;
209
  font-weight: 700;
210
+ color: var(--s2f-accent-text);
211
  letter-spacing: -0.01em;
212
  }
213
 
 
243
 
244
  /* === Metric cards === */
245
  [data-testid="stMetric"] {
246
+ background: linear-gradient(145deg, var(--s2f-surface) 0%, var(--s2f-surface-2) 100%);
247
+ border: 1px solid var(--s2f-border);
248
  border-radius: 12px;
249
  padding: 0.85rem 1rem !important;
250
  box-shadow: 0 1px 4px rgba(0,0,0,0.06);
 
257
  [data-testid="stMetric"] label {
258
  font-size: 0.75rem !important;
259
  font-weight: 600 !important;
260
+ color: var(--s2f-text-muted) !important;
261
  text-transform: uppercase;
262
  letter-spacing: 0.04em;
263
  }
264
  [data-testid="stMetric"] [data-testid="stMetricValue"] {
265
  font-size: 1.25rem !important;
266
  font-weight: 700 !important;
267
+ color: var(--s2f-accent-text) !important;
268
  }
269
 
270
  /* === Buttons === */
 
285
  .stButton > button:not([kind="primary"]) {
286
  border-radius: 10px !important;
287
  font-weight: 500 !important;
288
+ border: 1px solid var(--s2f-border-strong) !important;
289
  transition: all 0.2s ease !important;
290
  }
291
  .stButton > button:not([kind="primary"]):hover {
 
305
 
306
  /* === Action buttons row (measure + downloads) === */
307
  div[data-testid="stHorizontalBlock"]:has([data-testid="stDownloadButton"]):has([data-testid="stButton"]) {
308
+ background: var(--s2f-surface-2);
309
+ border: 1px solid var(--s2f-border);
310
  border-radius: 14px;
311
  padding: 0.65rem 0.6rem !important;
312
  margin-top: 0.5rem;
 
337
  transform: translateY(-1px) !important;
338
  }
339
  div[data-testid="stHorizontalBlock"]:has([data-testid="stDownloadButton"]):has([data-testid="stButton"]) [data-testid="stDownloadButton"] button {
340
+ background: var(--s2f-surface) !important;
341
+ border: 1px solid var(--s2f-border) !important;
342
+ color: var(--s2f-text-secondary) !important;
343
  box-shadow: 0 1px 2px rgba(0,0,0,0.04) !important;
344
  }
345
  div[data-testid="stHorizontalBlock"]:has([data-testid="stDownloadButton"]):has([data-testid="stButton"]) [data-testid="stDownloadButton"] button:hover {
346
  background: rgba(var(--s2f-primary-rgb), 0.06) !important;
347
  border-color: var(--s2f-primary) !important;
348
+ color: var(--s2f-accent-text) !important;
349
  box-shadow: 0 2px 6px rgba(var(--s2f-primary-rgb), 0.12) !important;
350
  transform: translateY(-1px) !important;
351
  }
352
 
353
  /* === Expanders === */
354
  .stExpander {
355
+ border: 1px solid var(--s2f-border) !important;
356
  border-radius: 12px !important;
357
  overflow: hidden;
358
  box-shadow: 0 1px 3px rgba(0,0,0,0.04);
 
360
 
361
  /* === File uploader === */
362
  [data-testid="stFileUploader"] section {
363
+ border: 2px dashed var(--s2f-border-strong) !important;
364
  border-radius: 12px !important;
365
  transition: border-color 0.2s ease;
366
  }
 
375
  gap: 8px;
376
  font-size: 0.92rem;
377
  font-weight: 600;
378
+ color: var(--s2f-text-secondary);
379
  padding: 0.4rem 0;
380
  }
381
  .result-badge {
 
386
  letter-spacing: 0.06em;
387
  }
388
  .result-badge.input {
389
+ background: var(--s2f-badge-bg);
390
+ color: var(--s2f-text-faint);
391
  }
392
  .result-badge.output {
393
  background: rgba(var(--s2f-primary-rgb), 0.15);
394
+ color: var(--s2f-accent-text);
395
  }
396
 
397
  /* === Run prediction info bar === */
 
401
  gap: 10px;
402
  height: 42px;
403
  font-size: 0.85rem;
404
+ color: var(--s2f-text-muted);
405
  }
406
  .run-info-tag {
407
  background: rgba(var(--s2f-primary-rgb), 0.1);
408
+ color: var(--s2f-accent-text);
409
  font-weight: 600;
410
  font-size: 0.78rem;
411
  padding: 3px 10px;
412
  border-radius: 6px;
413
  }
414
  .run-info code {
415
+ background: var(--s2f-code-bg);
416
  padding: 2px 8px;
417
  border-radius: 4px;
418
  font-size: 0.8rem;
419
+ color: var(--s2f-text-faint);
420
  }
421
 
422
  /* === Messages === */
423
  .stSuccess {
424
+ background: linear-gradient(135deg, var(--s2f-success-start) 0%, var(--s2f-success-end) 100%) !important;
425
  border-left: 4px solid #10b981 !important;
426
  border-radius: 8px !important;
427
+ color: var(--s2f-success-text) !important;
428
  }
429
  .stWarning { border-radius: 8px !important; }
430
  .stInfo { border-radius: 8px !important; }
 
433
  [data-testid="stSelectbox"] > div > div,
434
  [data-testid="stSelectbox"] input,
435
  [data-testid="stMultiSelect"] > div > div {
436
+ color: var(--s2f-text) !important;
437
+ background-color: var(--s2f-surface) !important;
438
  }
439
  /* Multiselect input: transparent so it doesn't show as a white block before the tags */
440
  [data-testid="stMultiSelect"] input {
441
  background-color: transparent !important;
442
+ color: var(--s2f-text) !important;
443
  min-width: 2ch !important;
444
  }
445
  [data-testid="stSelectbox"] > div > div,
446
  [data-testid="stMultiSelect"] > div > div {
447
  border-radius: 8px !important;
448
+ border: 1px solid var(--s2f-border-strong) !important;
449
  transition: border-color 0.15s ease, box-shadow 0.15s ease !important;
450
  }
451
  section[data-testid="stSidebar"] [data-testid="stSelectbox"] > div > div:focus-within,
 
459
  }
460
  /* Toggle: on state uses --s2f-primary */
461
  [data-testid="stToggle"] [data-baseweb="toggleTrack"] {
462
+ background-color: var(--s2f-border-strong) !important;
463
  }
464
  [data-testid="stToggle"] [data-baseweb="toggleTrack"][aria-checked="true"] {
465
  background-color: var(--s2f-primary) !important;
 
468
  background-color: var(--s2f-primary) !important;
469
  }
470
  [data-testid="stToggle"] [data-baseweb="toggleTrack"][data-state="unchecked"] {
471
+ background-color: var(--s2f-border-strong) !important;
472
  }
473
  /* Newer Streamlit may render a switch button instead of Base Web track */
474
  [data-testid="stToggle"] button[role="switch"][aria-checked="true"] {
475
  background-color: var(--s2f-primary) !important;
476
  }
477
  [data-testid="stToggle"] button[role="switch"][aria-checked="false"] {
478
+ background-color: var(--s2f-border-strong) !important;
479
  }
480
+ /* Dropdowns can render outside .stApp, so resolve colors here instead of inherited variables. */
481
  [role="listbox"] [role="option"],
482
  [data-baseweb="menu"] li,
483
  ul[role="listbox"] li {
484
+ color: light-dark(#1e293b, #e2e8f0) !important;
485
+ background-color: light-dark(#ffffff, #111827) !important;
486
  }
487
  /* Sidebar / form labels (colormap row, section titles) */
488
  .s2f-form-label {
489
  font-size: 0.95rem;
490
  font-weight: 500;
491
+ color: var(--s2f-text-secondary);
492
  line-height: 1.2;
493
  margin: 0;
494
  }
 
523
  padding: 0 1px;
524
  font-size: 0.65rem;
525
  font-weight: 600;
526
+ color: var(--s2f-text-muted);
527
  letter-spacing: 0.03em;
528
  }
529
  .colorbar-ticks .cb-tick {
 
539
  box-shadow: inset 0 1px 1px rgba(0,0,0,0.05);
540
  }
541
  /* === Divider === */
542
+ hr { border-color: var(--s2f-border-strong) !important; opacity: 0.7; }
543
 
544
  /* === Plotly chart === */
545
  .stPlotlyChart { border-radius: 12px; overflow: hidden; }
 
552
  right: 0;
553
  z-index: 999;
554
  padding: 0.5rem 1rem 0.55rem;
555
+ background: var(--s2f-footer-bg);
556
+ border-top: 1px solid var(--s2f-border);
557
  font-size: 0.7rem;
558
+ color: var(--s2f-text-muted);
559
  text-align: center;
560
  line-height: 1.45;
561
  }
 
592
  /* Measure tool: value panel (replaces inline styles in measure_tool.py) */
593
  .s2f-measure-vals-heading {
594
  font-weight: 400;
595
+ color: var(--s2f-text-secondary);
596
  font-size: 0.95rem;
597
  margin: 0 20px 4px 4px;
598
  }
599
  .s2f-measure-vals-panel {
600
  width: 100%;
601
  box-sizing: border-box;
602
+ border: 1px solid var(--s2f-border);
603
  border-radius: 10px;
604
  padding: 10px 12px;
605
  margin: 0 10px 20px 10px;
606
+ background: linear-gradient(145deg, var(--s2f-surface-2) 0%, var(--s2f-surface-3) 100%);
607
+ box-shadow: 0 1px 3px var(--s2f-shadow);
608
+ }
609
+ .s2f-region-table {
610
+ border-collapse: collapse;
611
+ width: 100%;
612
+ color: var(--s2f-text);
613
+ }
614
+ .s2f-region-table th,
615
+ .s2f-region-table td {
616
+ border: 1px solid var(--s2f-border);
617
+ padding: 8px;
618
+ text-align: left;
619
+ }
620
+ .s2f-region-table th {
621
+ background: var(--s2f-surface-2);
622
  }
623
  .s2f-measure-vals-grid {
624
  display: flex;
S2FApp/ui/heatmaps.py CHANGED
@@ -44,22 +44,32 @@ def _draw_region_overlay(annotated, mask, color, fill_alpha=0.3, stroke_width=2)
44
  cv2.drawContours(annotated, contours, -1, color, stroke_width)
45
 
46
 
47
- def render_horizontal_colorbar(colormap_name, clip_min=0, clip_max=1, is_rescale=False, caption=None):
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
48
  """
49
- Render a compact horizontal colorbar for batch mode, anchored above the table.
50
-
51
- When ``is_rescale`` is True (Force scale **Range** with a strict sub-interval), tick labels show
52
- model force values in ``[clip_min, clip_max]``. The gradient still spans the full colormap because
53
- the heatmap has already been **rescaled** so the lowest (highest) value in your range maps to
54
- the colormap minimum (maximum)—same convention as the main Plotly view.
55
  """
56
- ticks = [0, 0.25, 0.5, 0.75, 1]
57
- if is_rescale:
58
- rng = clip_max - clip_min
59
- labels = [f"{clip_min + t * rng:.2f}" for t in ticks]
60
- else:
61
- labels = [f"{t:.2f}" for t in ticks]
62
-
63
  data_url = _colormap_gradient_base64(colormap_name)
64
  labels_html = "".join(f'<span class="cb-tick">{l}</span>' for l in labels)
65
  html = f"""
@@ -69,8 +79,7 @@ def render_horizontal_colorbar(colormap_name, clip_min=0, clip_max=1, is_rescale
69
  </div>
70
  """
71
  st.markdown(html, unsafe_allow_html=True)
72
- if caption:
73
- st.caption(caption)
74
 
75
 
76
  def make_annotated_heatmap(heatmap_rgb, mask, fill_alpha=0.3, stroke_color=(0, 188, 212), stroke_width=2):
 
44
  cv2.drawContours(annotated, contours, -1, color, stroke_width)
45
 
46
 
47
+ def colorbar_ticks_pa(clip_min=0.0, clip_max=1.0, stress_max_pa=500.0, n=5):
48
+ """Tick positions (0-1 along the colormap) and labels in Pa at round values for the displayed window."""
49
+ lo, hi = float(clip_min), float(clip_max)
50
+ if not hi > lo:
51
+ lo, hi = 0.0, 1.0
52
+ lo_pa, hi_pa = lo * stress_max_pa, hi * stress_max_pa
53
+ span = hi_pa - lo_pa
54
+ raw = span / max(n - 1, 1)
55
+ k = 10 ** np.floor(np.log10(raw))
56
+ step = min((m * k for m in (1, 2, 2.5, 5, 10)), key=lambda st_: abs(st_ - raw))
57
+ first = np.ceil(lo_pa / step - 1e-9) * step
58
+ vals = np.arange(first, hi_pa + 1e-9, step) + 0.0 # +0.0 turns -0 into 0
59
+ pos = [float((v - lo_pa) / span) for v in vals]
60
+ labels = [f"{v:g}" for v in vals]
61
+ return pos, labels
62
+
63
+
64
+ def render_horizontal_colorbar(colormap_name, clip_min=0, clip_max=1, is_rescale=False, caption=None,
65
+ stress_max_pa=500.0):
66
  """
67
+ Compact horizontal colorbar (batch mode) labelled in Pa. With a display window (Range mode) the gradient
68
+ spans the window [clip_min, clip_max]; values above it are shown in the top colour.
 
 
 
 
69
  """
70
+ ticks, labels = colorbar_ticks_pa(clip_min, clip_max, stress_max_pa)
71
+ if not is_rescale:
72
+ ticks, labels = colorbar_ticks_pa(0.0, 1.0, stress_max_pa)
 
 
 
 
73
  data_url = _colormap_gradient_base64(colormap_name)
74
  labels_html = "".join(f'<span class="cb-tick">{l}</span>' for l in labels)
75
  html = f"""
 
79
  </div>
80
  """
81
  st.markdown(html, unsafe_allow_html=True)
82
+ st.caption(caption or "Traction stress (Pa)")
 
83
 
84
 
85
  def make_annotated_heatmap(heatmap_rgb, mask, fill_alpha=0.3, stroke_color=(0, 188, 212), stroke_width=2):
S2FApp/ui/measure_tool.py CHANGED
@@ -12,6 +12,7 @@ from PIL import Image
12
  from config.constants import CANVAS_SIZE, DRAW_TOOLS, TOOL_LABELS
13
  from utils.report import heatmap_to_rgb_with_contour, create_measure_pdf_report
14
  from ui.heatmaps import make_annotated_heatmap_multi_regions
 
15
 
16
  try:
17
  from streamlit_drawable_canvas import st_canvas
@@ -94,66 +95,32 @@ def parse_canvas_shapes_to_masks(json_data, canvas_h, canvas_w, heatmap_h, heatm
94
  return masks
95
 
96
 
97
- def build_original_vals(raw_heatmap, pixel_sum, force):
98
- """Build original_vals dict for measure tool (full map)."""
99
- return {
100
- "pixel_sum": pixel_sum,
101
- "force": force,
102
- "max": float(np.max(raw_heatmap)),
103
- "mean": float(np.mean(raw_heatmap)),
104
- }
105
 
106
 
107
- def _compute_cell_metrics(raw_heatmap, cell_mask, pixel_sum, force):
108
- """Compute metrics over estimated cell area only."""
109
- area_px = int(np.sum(cell_mask))
110
- if area_px == 0:
111
- return None, None, None
112
- region_values = raw_heatmap * cell_mask
113
- cell_pixel_sum = float(np.sum(region_values))
114
- cell_force = cell_pixel_sum * (force / pixel_sum) if pixel_sum > 0 else cell_pixel_sum
115
- cell_mean = cell_pixel_sum / area_px
116
- return cell_pixel_sum, cell_force, cell_mean
117
 
118
 
119
- def build_cell_vals(raw_heatmap, cell_mask, pixel_sum, force):
120
- """Build cell_vals dict for measure tool (estimated cell area). Returns None if invalid."""
121
- cell_pixel_sum, cell_force, cell_mean = _compute_cell_metrics(raw_heatmap, cell_mask, pixel_sum, force)
122
- if cell_pixel_sum is None:
123
  return None
124
- region_values = raw_heatmap * cell_mask
125
- region_nonzero = region_values[cell_mask > 0]
126
- cell_max = float(np.max(region_nonzero)) if len(region_nonzero) > 0 else 0
127
- return {
128
- "pixel_sum": cell_pixel_sum,
129
- "force": cell_force,
130
- "max": cell_max,
131
- "mean": cell_mean,
132
- }
133
 
134
 
135
  def compute_region_metrics(raw_heatmap, mask, original_vals=None):
136
- """Compute region metrics from mask."""
137
- area_px = int(np.sum(mask))
138
- region_values = raw_heatmap * mask
139
- region_nonzero = region_values[mask > 0]
140
- force_sum = float(np.sum(region_values))
141
- density = force_sum / area_px if area_px > 0 else 0
142
- region_max = float(np.max(region_nonzero)) if len(region_nonzero) > 0 else 0
143
- region_mean = float(np.mean(region_nonzero)) if len(region_nonzero) > 0 else 0
144
- region_force_scaled = (
145
- force_sum * (original_vals["force"] / original_vals["pixel_sum"])
146
- if original_vals and original_vals.get("pixel_sum", 0) > 0
147
- else force_sum
148
- )
149
- return {
150
- "area_px": area_px,
151
- "force_sum": force_sum,
152
- "density": density,
153
- "max": region_max,
154
- "mean": region_mean,
155
- "force_scaled": region_force_scaled,
156
- }
157
 
158
 
159
  def _draw_contour_on_image(img_rgb, mask, stroke_color=(255, 0, 0), stroke_width=3):
@@ -171,48 +138,32 @@ def render_region_metrics_and_downloads(metrics_list, masks, heatmap_rgb, input_
171
  first_region_label=None, bf_img=None, cell_mask=None, colormap_name="Jet"):
172
  """
173
  Render per-shape metrics table and download buttons.
174
- first_region_label: custom label for first row (e.g. 'Auto boundary').
175
  masks: list of region masks (user-drawn only; used for labeled heatmap with R1, R2...).
176
  """
177
  base_name = os.path.splitext(input_filename or "image")[0]
178
  st.markdown("**Regions (each selection = one row)**")
179
- if has_original_vals:
180
- headers = ["Region", "Area", "F.sum", "Force", "Max", "Mean"]
181
- csv_rows = [["image", "region"] + headers[1:]]
182
- else:
183
- headers = ["Region", "Area (px²)", "Force sum", "Mean"]
184
- csv_rows = [["image", "region", "Area", "Force sum", "Mean"]]
185
  table_rows = [headers]
186
  for i, metrics in enumerate(metrics_list, 1):
187
  region_label = first_region_label if (i == 1 and first_region_label) else f"Region {i - (1 if first_region_label else 0)}"
188
- if has_original_vals:
189
- row = [region_label, str(metrics["area_px"]), f"{metrics['force_sum']:.3f}", f"{metrics['force_scaled']:.1f}",
190
- f"{metrics['max']:.3f}", f"{metrics['mean']:.4f}"]
191
- csv_rows.append([base_name, region_label, metrics["area_px"], f"{metrics['force_sum']:.3f}",
192
- f"{metrics['force_scaled']:.1f}", f"{metrics['max']:.3f}", f"{metrics['mean']:.4f}"])
193
- else:
194
- row = [region_label, str(metrics["area_px"]), f"{metrics['force_sum']:.4f}", f"{metrics['mean']:.6f}"]
195
- csv_rows.append([base_name, region_label, metrics["area_px"], f"{metrics['force_sum']:.4f}",
196
- f"{metrics['mean']:.6f}"])
197
  table_rows.append(row)
198
  # Render as HTML table to avoid Streamlit's default row/column indices
199
  header = table_rows[0]
200
  body = table_rows[1:]
201
- th_cells = "".join(
202
- f'<th style="border: 1px solid #ddd; padding: 8px; text-align: left;">{html.escape(str(h))}</th>'
203
- for h in header
204
- )
205
  rows_html = [
206
  "<tr>"
207
- + "".join(
208
- f'<td style="border: 1px solid #ddd; padding: 8px;">{html.escape(str(c))}</td>'
209
- for c in row
210
- )
211
  + "</tr>"
212
  for row in body
213
  ]
214
  table_html = (
215
- f'<table style="border-collapse: collapse; width: 100%;">'
216
  f"<thead><tr>{th_cells}</tr></thead>"
217
  f"<tbody>{''.join(rows_html)}</tbody></table>"
218
  )
@@ -263,7 +214,7 @@ def render_region_canvas(display_heatmap, raw_heatmap=None, bf_img=None, origina
263
  left_col, right_col = st.columns(2, gap=None)
264
  with left_col:
265
  draw_mode = st.selectbox("Tool", DRAW_TOOLS, format_func=lambda x: TOOL_LABELS[x], key=f"draw_mode_region_{key_suffix}")
266
- st.caption("Left-click add, right-click close. \nForce map (draw region)")
267
  canvas_result = st_canvas(
268
  fill_color="rgba(0, 188, 212, 0.25)", stroke_width=2, stroke_color="#00bcd4",
269
  background_image=pil_bg, drawing_mode=draw_mode, update_streamlit=True,
@@ -273,14 +224,14 @@ def render_region_canvas(display_heatmap, raw_heatmap=None, bf_img=None, origina
273
  with right_col:
274
  vals = cell_vals if cell_vals else original_vals
275
  if vals:
276
- label = "Cell area" if cell_vals else "Full map"
277
  st.markdown(
278
  f'<p class="s2f-measure-vals-heading">{html.escape(label)}</p>'
279
  f'<div class="s2f-measure-vals-panel"><div class="s2f-measure-vals-grid">'
280
- f"<span><strong>Sum:</strong> {vals['pixel_sum']:.1f}</span>"
281
- f"<span><strong>Force:</strong> {vals['force']:.1f}</span>"
282
- f"<span><strong>Max:</strong> {vals['max']:.3f}</span>"
283
- f"<span><strong>Mean:</strong> {vals['mean']:.3f}</span>"
284
  f"</div></div>",
285
  unsafe_allow_html=True,
286
  )
@@ -311,6 +262,6 @@ def render_region_canvas(display_heatmap, raw_heatmap=None, bf_img=None, origina
311
  metrics_list = [cell_metrics] + metrics_list
312
  render_region_metrics_and_downloads(
313
  metrics_list, masks, heatmap_rgb, input_filename, key_suffix, original_vals is not None,
314
- first_region_label="Auto boundary" if (cell_mask is not None and np.any(cell_mask > 0)) else None,
315
  bf_img=bf_img, cell_mask=cell_mask, colormap_name=colormap_name,
316
  )
 
12
  from config.constants import CANVAS_SIZE, DRAW_TOOLS, TOOL_LABELS
13
  from utils.report import heatmap_to_rgb_with_contour, create_measure_pdf_report
14
  from ui.heatmaps import make_annotated_heatmap_multi_regions
15
+ from utils.units import fmt, make_scale, region_metrics
16
 
17
  try:
18
  from streamlit_drawable_canvas import st_canvas
 
95
  return masks
96
 
97
 
98
+ def build_original_vals(raw_heatmap, pixel_sum, force, scale=None):
99
+ """Whole-map values for the measure tool (physical units when `scale` is given; see utils/units.py)."""
100
+ scale = scale or make_scale("single_cell")
101
+ m = region_metrics(raw_heatmap, None, scale)
102
+ return {"pixel_sum": pixel_sum, "force": force, "scale": scale, **m}
 
 
 
103
 
104
 
105
+ def _compute_cell_metrics(raw_heatmap, cell_mask, pixel_sum, force, scale=None):
106
+ """Metrics over the estimated cell area: dict from utils.units.region_metrics, or None if the mask is empty."""
107
+ if cell_mask is None or int(np.sum(cell_mask)) == 0:
108
+ return None
109
+ return region_metrics(raw_heatmap, cell_mask, scale or make_scale("single_cell"))
 
 
 
 
 
110
 
111
 
112
+ def build_cell_vals(raw_heatmap, cell_mask, pixel_sum, force, scale=None):
113
+ """Values over the estimated cell area for the measure tool. Returns None if invalid."""
114
+ m = _compute_cell_metrics(raw_heatmap, cell_mask, pixel_sum, force, scale)
115
+ if m is None:
116
  return None
117
+ return {"scale": scale, **m}
 
 
 
 
 
 
 
 
118
 
119
 
120
  def compute_region_metrics(raw_heatmap, mask, original_vals=None):
121
+ """Region metrics in physical units (area µm², total force nN, mean/max traction stress Pa)."""
122
+ scale = (original_vals or {}).get("scale") or make_scale("single_cell")
123
+ return region_metrics(raw_heatmap, mask, scale)
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
124
 
125
 
126
  def _draw_contour_on_image(img_rgb, mask, stroke_color=(255, 0, 0), stroke_width=3):
 
138
  first_region_label=None, bf_img=None, cell_mask=None, colormap_name="Jet"):
139
  """
140
  Render per-shape metrics table and download buttons.
141
+ first_region_label: custom label for first row (e.g. 'Force region').
142
  masks: list of region masks (user-drawn only; used for labeled heatmap with R1, R2...).
143
  """
144
  base_name = os.path.splitext(input_filename or "image")[0]
145
  st.markdown("**Regions (each selection = one row)**")
146
+ headers = ["Region", "Area (µm²)", "Total force (nN)", "Mean stress (Pa)", "Max stress (Pa)"]
147
+ csv_rows = [["image", "region", "area_um2", "total_force_nN", "mean_stress_Pa", "max_stress_Pa", "n_pixels"]]
 
 
 
 
148
  table_rows = [headers]
149
  for i, metrics in enumerate(metrics_list, 1):
150
  region_label = first_region_label if (i == 1 and first_region_label) else f"Region {i - (1 if first_region_label else 0)}"
151
+ row = [region_label, fmt(metrics["area_um2"], nd=0), fmt(metrics["total_force_nN"], nd=2),
152
+ fmt(metrics["mean_pa"], nd=1), fmt(metrics["max_pa"], nd=1)]
153
+ csv_rows.append([base_name, region_label] + row[1:] + [metrics["n_px"]])
 
 
 
 
 
 
154
  table_rows.append(row)
155
  # Render as HTML table to avoid Streamlit's default row/column indices
156
  header = table_rows[0]
157
  body = table_rows[1:]
158
+ th_cells = "".join(f"<th>{html.escape(str(h))}</th>" for h in header)
 
 
 
159
  rows_html = [
160
  "<tr>"
161
+ + "".join(f"<td>{html.escape(str(c))}</td>" for c in row)
 
 
 
162
  + "</tr>"
163
  for row in body
164
  ]
165
  table_html = (
166
+ '<table class="s2f-region-table">'
167
  f"<thead><tr>{th_cells}</tr></thead>"
168
  f"<tbody>{''.join(rows_html)}</tbody></table>"
169
  )
 
214
  left_col, right_col = st.columns(2, gap=None)
215
  with left_col:
216
  draw_mode = st.selectbox("Tool", DRAW_TOOLS, format_func=lambda x: TOOL_LABELS[x], key=f"draw_mode_region_{key_suffix}")
217
+ st.caption("Left-click add, right-click close. \nTraction stress map (draw region)")
218
  canvas_result = st_canvas(
219
  fill_color="rgba(0, 188, 212, 0.25)", stroke_width=2, stroke_color="#00bcd4",
220
  background_image=pil_bg, drawing_mode=draw_mode, update_streamlit=True,
 
224
  with right_col:
225
  vals = cell_vals if cell_vals else original_vals
226
  if vals:
227
+ label = "Force region" if cell_vals else "Full map"
228
  st.markdown(
229
  f'<p class="s2f-measure-vals-heading">{html.escape(label)}</p>'
230
  f'<div class="s2f-measure-vals-panel"><div class="s2f-measure-vals-grid">'
231
+ f"<span><strong>Mean:</strong> {fmt(vals.get('mean_pa'), 'Pa')}</span>"
232
+ f"<span><strong>Max:</strong> {fmt(vals.get('max_pa'), 'Pa')}</span>"
233
+ f"<span><strong>Area:</strong> {fmt(vals.get('area_um2'), 'µm²', 0)}</span>"
234
+ f"<span><strong>Force:</strong> {fmt(vals.get('total_force_nN'), 'nN', 2)}</span>"
235
  f"</div></div>",
236
  unsafe_allow_html=True,
237
  )
 
262
  metrics_list = [cell_metrics] + metrics_list
263
  render_region_metrics_and_downloads(
264
  metrics_list, masks, heatmap_rgb, input_filename, key_suffix, original_vals is not None,
265
+ first_region_label="Force region" if (cell_mask is not None and np.any(cell_mask > 0)) else None,
266
  bf_img=bf_img, cell_mask=cell_mask, colormap_name=colormap_name,
267
  )
S2FApp/ui/result_display.py CHANGED
@@ -1,4 +1,4 @@
1
- """Result display: single and batch prediction views."""
2
  import csv
3
  import io
4
  import os
@@ -11,21 +11,29 @@ import plotly.graph_objects as go
11
  from plotly.subplots import make_subplots
12
 
13
  from utils.display import apply_display_scale, cv_colormap_to_plotly_colorscale, is_display_range_remapped
14
- from utils.report import heatmap_to_rgb_with_contour, heatmap_to_png_bytes, create_pdf_report
 
15
  from utils.segmentation import estimate_cell_mask
16
- from ui.heatmaps import render_horizontal_colorbar, add_cell_contour_to_fig
 
17
  from ui.measure_tool import (
18
  build_original_vals,
19
  build_cell_vals,
20
  render_region_canvas,
21
- _compute_cell_metrics,
22
  HAS_DRAWABLE_CANVAS,
23
  )
24
 
25
  # Histogram bar color (matches static/s2f_styles.css accent)
26
  _HISTOGRAM_ACCENT = "#0d9488"
27
- _RESULT_FIG_HEIGHT = 320
28
  _HISTOGRAM_HEIGHT = 180
 
 
 
 
 
 
 
29
 
30
 
31
  def _result_banner(badge: str, badge_class: str, title: str) -> str:
@@ -35,284 +43,266 @@ def _result_banner(badge: str, badge_class: str, title: str) -> str:
35
  )
36
 
37
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
38
  def render_batch_results(batch_results, colormap_name="Jet", display_mode="Default",
39
- clip_min=0, clip_max=1,
40
- auto_cell_boundary=False, clamp_only=False):
41
  """
42
- Render batch prediction results: summary table, bright-field row, heatmap row, and bulk download.
43
- batch_results: list of dicts with img, heatmap, force, pixel_sum, key_img, cell_mask.
44
- cell_mask is computed on-the-fly when auto_cell_boundary is True and not stored.
45
  """
46
  if not batch_results:
47
  return
48
 
49
- # Resolve cell_mask and precompute display_heatmap for each result
50
  for r in batch_results:
51
  if auto_cell_boundary and (r.get("cell_mask") is None or not np.any(r.get("cell_mask", 0) > 0)):
52
  r["_cell_mask"] = estimate_cell_mask(r["heatmap"])
53
  else:
54
  r["_cell_mask"] = r.get("cell_mask") if auto_cell_boundary else None
55
- r["_display_heatmap"] = apply_display_scale(
56
- r["heatmap"], display_mode,
57
- clip_min=clip_min, clip_max=clip_max, clamp_only=clamp_only,
58
- )
59
- # Build table rows - consistent column names for both modes
60
- headers = ["Image", "Force", "Sum", "Max", "Mean"]
61
  rows = []
62
- csv_rows = [["image"] + headers[1:]]
 
 
63
  for r in batch_results:
64
- heatmap = r["heatmap"]
65
- cell_mask = r.get("_cell_mask")
66
- key = r["key_img"] or "image"
67
- if auto_cell_boundary and cell_mask is not None and np.any(cell_mask > 0):
68
- vals = heatmap[cell_mask > 0]
69
- cell_pixel_sum = float(np.sum(vals))
70
- cell_force = cell_pixel_sum * (r["force"] / r["pixel_sum"]) if r["pixel_sum"] > 0 else cell_pixel_sum
71
- cell_mean = cell_pixel_sum / np.sum(cell_mask) if np.sum(cell_mask) > 0 else 0
72
- row = [key, f"{cell_force:.2f}", f"{cell_pixel_sum:.2f}",
73
- f"{np.max(heatmap):.4f}", f"{cell_mean:.4f}"]
74
- else:
75
- row = [key, f"{r['force']:.2f}", f"{r['pixel_sum']:.2f}",
76
- f"{np.max(heatmap):.4f}", f"{np.mean(heatmap):.4f}"]
77
- rows.append(row)
78
- csv_rows.append([os.path.splitext(key)[0]] + row[1:])
79
  st.markdown(_result_banner("INPUT", "input", "Bright-field images"), unsafe_allow_html=True)
80
  n_cols = min(5, len(batch_results))
81
  bf_cols = st.columns(n_cols)
82
  for i, r in enumerate(batch_results):
83
  img = r["img"]
84
- if img.ndim == 2:
85
- img_rgb = cv2.cvtColor(img, cv2.COLOR_GRAY2RGB)
86
- else:
87
- img_rgb = cv2.cvtColor(img, cv2.COLOR_BGR2RGB)
88
  with bf_cols[i % n_cols]:
89
  st.image(img_rgb, caption=r["key_img"], use_container_width=True)
90
  is_rescale_b = is_display_range_remapped(display_mode, clip_min, clip_max)
91
- st.markdown(_result_banner("OUTPUT", "output", "Predicted force maps"), unsafe_allow_html=True)
92
  hm_cols = st.columns(n_cols)
93
  for i, r in enumerate(batch_results):
94
- hm_rgb = heatmap_to_rgb_with_contour(
95
- r["_display_heatmap"], colormap_name,
96
- r.get("_cell_mask") if auto_cell_boundary else None,
97
- )
98
  with hm_cols[i % n_cols]:
99
  st.image(hm_rgb, caption=r["key_img"], use_container_width=True)
100
- render_horizontal_colorbar(colormap_name, clip_min, clip_max, is_rescale_b)
101
- # Table
102
- st.dataframe(
103
- {h: [r[i] for r in rows] for i, h in enumerate(headers)},
104
- use_container_width=True,
105
- hide_index=True,
106
- )
107
- # Histograms in accordion (one per row for visibility)
108
- with st.expander("Force distribution (histograms)", expanded=False):
109
  for i, r in enumerate(batch_results):
110
- heatmap = r["heatmap"]
111
  cell_mask = r.get("_cell_mask")
112
- vals = heatmap[cell_mask > 0] if (cell_mask is not None and np.any(cell_mask > 0) and auto_cell_boundary) else heatmap.flatten()
 
113
  vals = vals[vals > 0] if np.any(vals > 0) else vals
114
  st.markdown(f"**{r['key_img']}**")
115
  if len(vals) > 0:
116
  fig = go.Figure(data=[go.Histogram(x=vals, nbinsx=50, marker_color=_HISTOGRAM_ACCENT)])
117
- fig.update_layout(
118
- height=_HISTOGRAM_HEIGHT, margin=dict(l=40, r=20, t=10, b=40),
119
- xaxis_title="Force value", yaxis_title="Count",
120
- showlegend=False,
121
- )
122
  st.plotly_chart(fig, use_container_width=True, config={"displayModeBar": False})
123
  else:
124
  st.caption("No data")
125
  if i < len(batch_results) - 1:
126
  st.divider()
127
- # Bulk downloads: CSV and heatmaps (zip)
128
  buf_csv = io.StringIO()
129
  csv.writer(buf_csv).writerows(csv_rows)
 
130
  zip_buf = io.BytesIO()
131
  with zipfile.ZipFile(zip_buf, "w", zipfile.ZIP_DEFLATED) as zf:
132
  for r in batch_results:
133
- hm_bytes = heatmap_to_png_bytes(
134
- r["_display_heatmap"], colormap_name,
135
- r.get("_cell_mask") if auto_cell_boundary else None,
136
- )
137
  base = os.path.splitext(r["key_img"] or "image")[0]
138
- zf.writestr(f"{base}_heatmap.png", hm_bytes.getvalue())
 
 
 
 
139
  zip_buf.seek(0)
140
- dl_col1, dl_col2 = st.columns(2)
 
 
 
 
 
 
 
141
  with dl_col1:
142
- st.download_button(
143
- "Download all as CSV",
144
- data=buf_csv.getvalue(),
145
- file_name="s2f_batch_results.csv",
146
- mime="text/csv",
147
- key="download_batch_csv",
148
- icon=":material/download:",
149
- )
150
  with dl_col2:
151
- st.download_button(
152
- "Download all heatmaps",
153
- data=zip_buf.getvalue(),
154
- file_name="s2f_batch_heatmaps.zip",
155
- mime="application/zip",
156
- key="download_batch_heatmaps",
157
- icon=":material/image:",
158
- )
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
159
 
160
 
161
  def render_result_display(img, raw_heatmap, display_heatmap, pixel_sum, force, key_img, download_key_suffix="",
162
- colormap_name="Jet", display_mode="Default", measure_region_dialog=None, auto_cell_boundary=True,
163
- cell_mask=None, clip_min=0.0, clip_max=1.0, clamp_only=False):
164
  """
165
- Render prediction result: plot, metrics, expander, and download/measure buttons.
166
- measure_region_dialog: callable to open measure dialog (when ST_DIALOG available).
167
- auto_cell_boundary: when True, use estimated cell area for metrics; when False, use entire map.
168
- cell_mask: optional precomputed cell mask; if None and auto_cell_boundary, will be computed.
169
  """
 
 
170
  if cell_mask is None and auto_cell_boundary:
171
  cell_mask = estimate_cell_mask(raw_heatmap)
172
  elif not auto_cell_boundary:
173
  cell_mask = None
174
- cell_pixel_sum, cell_force, cell_mean = _compute_cell_metrics(raw_heatmap, cell_mask, pixel_sum, force) if cell_mask is not None else (None, None, None)
175
- use_cell_metrics = auto_cell_boundary and cell_pixel_sum is not None and cell_force is not None and cell_mean is not None
176
-
177
  base_name = os.path.splitext(key_img or "image")[0]
178
- if use_cell_metrics:
179
- main_csv_rows = [
180
- ["image", "Cell sum", "Cell force (scaled)", "Heatmap max", "Heatmap mean"],
181
- [base_name, f"{cell_pixel_sum:.2f}", f"{cell_force:.2f}",
182
- f"{np.max(raw_heatmap):.4f}", f"{cell_mean:.4f}"],
183
- ]
184
- else:
185
- main_csv_rows = [
186
- ["image", "Sum of all pixels", "Force (scaled)", "Heatmap max", "Heatmap mean"],
187
- [base_name, f"{pixel_sum:.2f}", f"{force:.2f}",
188
- f"{np.max(raw_heatmap):.4f}", f"{np.mean(raw_heatmap):.4f}"],
189
- ]
190
- buf_main_csv = io.StringIO()
191
- csv.writer(buf_main_csv).writerows(main_csv_rows)
192
-
193
- buf_hm = heatmap_to_png_bytes(display_heatmap, colormap_name, cell_mask=cell_mask)
194
-
195
  is_rescale = is_display_range_remapped(display_mode, clip_min, clip_max)
 
196
 
197
  tit1, tit2 = st.columns(2)
198
  with tit1:
199
  st.markdown(_result_banner("INPUT", "input", "Bright-field image"), unsafe_allow_html=True)
200
  with tit2:
201
- st.markdown(_result_banner("OUTPUT", "output", "Predicted force map"), unsafe_allow_html=True)
202
  fig_pl = make_subplots(rows=1, cols=2)
203
- fig_pl.add_trace(go.Heatmap(z=img, colorscale="gray", showscale=False), row=1, col=1)
204
- plotly_colorscale = cv_colormap_to_plotly_colorscale(colormap_name)
205
- colorbar_cfg = dict(len=0.4, thickness=12, tickmode="array")
206
- tick_positions = [0, 0.25, 0.5, 0.75, 1]
207
- if is_rescale:
208
- rng = clip_max - clip_min
209
- colorbar_cfg["tickvals"] = tick_positions
210
- colorbar_cfg["ticktext"] = [f"{clip_min + t * rng:.2f}" for t in tick_positions]
211
- else:
212
- colorbar_cfg["tickvals"] = tick_positions
213
- colorbar_cfg["ticktext"] = [f"{t:.2f}" for t in tick_positions]
214
- fig_pl.add_trace(go.Heatmap(z=display_heatmap, colorscale=plotly_colorscale, zmin=0.0, zmax=1.0, showscale=True,
215
- colorbar=colorbar_cfg), row=1, col=2)
216
  add_cell_contour_to_fig(fig_pl, cell_mask, row=1, col=2)
217
- fig_pl.update_layout(
218
- height=_RESULT_FIG_HEIGHT,
219
- margin=dict(l=10, r=10, t=10, b=10),
220
- xaxis=dict(scaleanchor="y", scaleratio=1),
221
- xaxis2=dict(scaleanchor="y2", scaleratio=1),
222
- )
223
  fig_pl.update_xaxes(showticklabels=False, showgrid=False, zeroline=False)
224
  fig_pl.update_yaxes(showticklabels=False, autorange="reversed", showgrid=False, zeroline=False)
225
  st.plotly_chart(fig_pl, use_container_width=True, config={"displayModeBar": True, "responsive": True})
 
 
 
226
 
227
- col1, col2, col3, col4 = st.columns(4)
228
- if use_cell_metrics:
229
- with col1:
230
- st.metric("Cell sum", f"{cell_pixel_sum:.2f}", help="Sum over estimated cell area (background excluded)")
231
- with col2:
232
- st.metric("Cell force (scaled)", f"{cell_force:.2f}", help="Total traction force in physical units")
233
- with col3:
234
- st.metric("Heatmap max", f"{np.max(raw_heatmap):.4f}", help="Peak force intensity in the map")
235
- with col4:
236
- st.metric("Heatmap mean", f"{cell_mean:.4f}", help="Mean force over estimated cell area")
237
- else:
238
- with col1:
239
- st.metric("Sum of all pixels", f"{pixel_sum:.2f}", help="Raw sum of all pixel values in the force map")
240
- with col2:
241
- st.metric("Force (scaled)", f"{force:.2f}", help="Total traction force in physical units (full field of view)")
242
- with col3:
243
- st.metric("Heatmap max", f"{np.max(raw_heatmap):.4f}", help="Peak force intensity in the map")
244
- with col4:
245
- st.metric("Heatmap mean", f"{np.mean(raw_heatmap):.4f}", help="Average force intensity (full FOV)")
246
 
247
- # Statistics panel (mean, std, percentiles, histogram)
248
  with st.expander("Statistics"):
249
- vals = raw_heatmap[cell_mask > 0] if (cell_mask is not None and np.any(cell_mask > 0) and use_cell_metrics) else raw_heatmap.flatten()
 
250
  if len(vals) > 0:
251
- stat_col1, stat_col2, stat_col3 = st.columns(3)
252
- p25, p50, p75, p90 = (
253
- float(np.percentile(vals, 25)), float(np.percentile(vals, 50)),
254
- float(np.percentile(vals, 75)), float(np.percentile(vals, 90)),
255
- )
256
- with stat_col1:
257
- st.metric("Mean", f"{float(np.mean(vals)):.4f}")
258
- st.metric("Std", f"{float(np.std(vals)):.4f}")
259
- with stat_col2:
260
- st.metric("P25", f"{p25:.4f}")
261
- st.metric("P50 (median)", f"{p50:.4f}")
262
- with stat_col3:
263
- st.metric("P75", f"{p75:.4f}")
264
- st.metric("P90", f"{p90:.4f}")
265
- st.markdown("**Histogram**")
266
  hist_fig = go.Figure(data=[go.Histogram(x=vals, nbinsx=50, marker_color=_HISTOGRAM_ACCENT)])
267
- hist_fig.update_layout(
268
- height=_HISTOGRAM_HEIGHT, margin=dict(l=40, r=20, t=20, b=40),
269
- xaxis_title="Force value", yaxis_title="Count",
270
- showlegend=False,
271
- )
272
  st.plotly_chart(hist_fig, use_container_width=True, config={"displayModeBar": False})
273
  else:
274
- st.caption("No nonzero values to compute statistics.")
275
-
276
- with st.expander("How to read the results"):
277
- if use_cell_metrics:
278
- st.markdown("""
279
- **Input (left):** Bright-field microscopy image of a cell or spheroid on a substrate.
280
- This is the raw image you provided—it shows cell shape but not forces.
281
 
282
- **Output (right):** Predicted traction force map.
283
- - **Color** indicates force magnitude: blue = low, red = high
284
- - **Brighter/warmer colors** = stronger forces exerted by the cell on the substrate
285
- - **Red border = estimated cell area** (background excluded from metrics)
286
- - Values are normalized to [0, 1] for visualization
287
 
288
- **Metrics (auto cell boundary on):**
289
- - **Cell sum:** Sum over estimated cell area (background excluded)
290
- - **Cell force (scaled):** Total traction force in physical units
291
- - **Heatmap max:** Peak force intensity in the map
292
- - **Heatmap mean:** Mean force over the estimated cell area
293
- """)
294
- else:
295
- st.markdown("""
296
- **Input (left):** Bright-field microscopy image of a cell or spheroid on a substrate.
297
- This is the raw image you provided—it shows cell shape but not forces.
298
-
299
- **Output (right):** Predicted traction force map.
300
- - **Color** indicates force magnitude: blue = low, red = high
301
- - **Brighter/warmer colors** = stronger forces exerted by the cell on the substrate
302
- - Values are normalized to [0, 1] for visualization
303
 
304
- **Metrics (auto cell boundary off):**
305
- - **Sum of all pixels:** Raw sum over entire map
306
- - **Force (scaled):** Total traction force in physical units (full field of view)
307
- - **Heatmap max/mean:** Peak and average force intensity (full field of view)
308
- """)
 
 
 
309
 
310
- original_vals = build_original_vals(raw_heatmap, pixel_sum, force)
 
 
311
 
312
- pdf_bytes = create_pdf_report(
313
- img, display_heatmap, raw_heatmap, pixel_sum, force, base_name, colormap_name,
314
- cell_mask=cell_mask, cell_pixel_sum=cell_pixel_sum, cell_force=cell_force, cell_mean=cell_mean
315
- )
 
 
316
 
317
  btn_col1, btn_col2, btn_col3, btn_col4 = st.columns(4)
318
  with btn_col1:
@@ -322,48 +312,20 @@ This is the raw image you provided—it shows cell shape but not forces.
322
  st.rerun()
323
  elif HAS_DRAWABLE_CANVAS:
324
  with st.expander("Measure tool"):
325
- expander_cell_vals = build_cell_vals(raw_heatmap, cell_mask, pixel_sum, force) if (auto_cell_boundary and cell_mask is not None) else None
326
- expander_cell_mask = cell_mask if auto_cell_boundary else None
327
- render_region_canvas(
328
- display_heatmap,
329
- raw_heatmap=raw_heatmap,
330
- bf_img=img,
331
- original_vals=original_vals,
332
- cell_vals=expander_cell_vals,
333
- cell_mask=expander_cell_mask,
334
- key_suffix="expander",
335
- input_filename=key_img,
336
- colormap_name=colormap_name,
337
- )
338
  else:
339
  st.caption("Install `streamlit-drawable-canvas-fix` for region measurement: `pip install streamlit-drawable-canvas-fix`")
340
  with btn_col2:
341
- st.download_button(
342
- "Download heatmap",
343
- width="stretch",
344
- data=buf_hm.getvalue(),
345
- file_name="s2f_heatmap.png",
346
- mime="image/png",
347
- key=f"download_heatmap{download_key_suffix}",
348
- icon=":material/download:",
349
- )
350
  with btn_col3:
351
- st.download_button(
352
- "Download values",
353
- width="stretch",
354
- data=buf_main_csv.getvalue(),
355
- file_name=f"{base_name}_main_values.csv",
356
- mime="text/csv",
357
- key=f"download_main_values{download_key_suffix}",
358
- icon=":material/download:",
359
- )
360
  with btn_col4:
361
- st.download_button(
362
- "Download report",
363
- width="stretch",
364
- data=pdf_bytes,
365
- file_name=f"{base_name}_report.pdf",
366
- mime="application/pdf",
367
- key=f"download_pdf{download_key_suffix}",
368
- icon=":material/picture_as_pdf:",
369
- )
 
1
+ """Result display: single and batch prediction views (traction stress in Pa, areas in µm², forces in nN)."""
2
  import csv
3
  import io
4
  import os
 
11
  from plotly.subplots import make_subplots
12
 
13
  from utils.display import apply_display_scale, cv_colormap_to_plotly_colorscale, is_display_range_remapped
14
+ from utils.report import (create_batch_pdf_report, create_pdf_report, heatmap_figure_png_bytes,
15
+ heatmap_to_rgb_with_contour, info_rows)
16
  from utils.segmentation import estimate_cell_mask
17
+ from utils.units import fmt, make_scale, metric_rows, nice_scale_bar_um, region_metrics, to_pa
18
+ from ui.heatmaps import colorbar_ticks_pa, render_horizontal_colorbar, add_cell_contour_to_fig
19
  from ui.measure_tool import (
20
  build_original_vals,
21
  build_cell_vals,
22
  render_region_canvas,
 
23
  HAS_DRAWABLE_CANVAS,
24
  )
25
 
26
  # Histogram bar color (matches static/s2f_styles.css accent)
27
  _HISTOGRAM_ACCENT = "#0d9488"
28
+ _RESULT_FIG_HEIGHT = 340
29
  _HISTOGRAM_HEIGHT = 180
30
+ _METRIC_HELP = {
31
+ "Mean traction stress": "Mean predicted traction-stress magnitude over the region (Pa)",
32
+ "Max traction stress": "Peak predicted traction-stress magnitude (Pa)",
33
+ "Area": "Region area in µm² (needs the image pixel size)",
34
+ "Total force": "Sum of traction stress × pixel area, in nN (needs the image pixel size). Magnitudes only: "
35
+ "vector cancellation is not taken into account",
36
+ }
37
 
38
 
39
  def _result_banner(badge: str, badge_class: str, title: str) -> str:
 
43
  )
44
 
45
 
46
+ def _metrics_csv(base_name, metrics_full, metrics_cell, info):
47
+ """CSV: one row of metrics with units, then the parameters needed to reproduce the prediction."""
48
+ rows = [["image", "region", "mean_stress_Pa", "max_stress_Pa", "area_um2", "total_force_nN", "n_pixels"]]
49
+ for region, m in [("whole_field", metrics_full), ("force_region", metrics_cell)]:
50
+ if m:
51
+ rows.append([base_name, region, fmt(m["mean_pa"], nd=2), fmt(m["max_pa"], nd=2), fmt(m["area_um2"], nd=1),
52
+ fmt(m["total_force_nN"], nd=3), m["n_px"]])
53
+ rows += [[], ["parameter", "value"]] + [[k.strip(), v] for k, v in info_rows(info)]
54
+ buf = io.StringIO()
55
+ csv.writer(buf).writerows(rows)
56
+ return buf.getvalue()
57
+
58
+
59
+ def _add_scale_bar_to_fig(fig, width_px, height_px, um_per_px, row, col):
60
+ """Draw a µm scale bar (bottom right) on a Plotly image subplot whose axes are in pixels."""
61
+ if not um_per_px:
62
+ return
63
+ length_um = nice_scale_bar_um(width_px * um_per_px)
64
+ if not length_um:
65
+ return
66
+ length_px = length_um / um_per_px
67
+ m = 0.05 * width_px
68
+ x1, y = width_px - m, height_px - m
69
+ xref = "x" if (row, col) == (1, 1) else "x2"
70
+ yref = "y" if (row, col) == (1, 1) else "y2"
71
+ fig.add_shape(type="line", x0=x1 - length_px, x1=x1, y0=y, y1=y, xref=xref, yref=yref,
72
+ line=dict(color="white", width=4))
73
+ fig.add_annotation(x=x1 - length_px / 2, y=y - 0.03 * height_px, xref=xref, yref=yref, text=f"{length_um:g} µm",
74
+ showarrow=False, font=dict(color="white", size=11))
75
+
76
+
77
  def render_batch_results(batch_results, colormap_name="Jet", display_mode="Default",
78
+ clip_min=0, clip_max=1,
79
+ auto_cell_boundary=False, clamp_only=False):
80
  """
81
+ Render batch prediction results: summary table (units), bright-field row, heatmap row and bulk downloads.
82
+ batch_results: list of dicts with img, heatmap, key_img, cell_mask, scale, info.
 
83
  """
84
  if not batch_results:
85
  return
86
 
 
87
  for r in batch_results:
88
  if auto_cell_boundary and (r.get("cell_mask") is None or not np.any(r.get("cell_mask", 0) > 0)):
89
  r["_cell_mask"] = estimate_cell_mask(r["heatmap"])
90
  else:
91
  r["_cell_mask"] = r.get("cell_mask") if auto_cell_boundary else None
92
+ r["_display_heatmap"] = apply_display_scale(r["heatmap"], display_mode, clip_min=clip_min, clip_max=clip_max)
93
+ r["_metrics"] = region_metrics(r["heatmap"], r["_cell_mask"] if auto_cell_boundary else None, r["scale"])
94
+
95
+ region = "force region (red contour)" if auto_cell_boundary else "whole field"
96
+ headers = ["Image", "Mean stress (Pa)", "Max stress (Pa)", "Area (µm²)", "Total force (nN)"]
 
97
  rows = []
98
+ csv_rows = [["image", "region", "mean_stress_Pa", "max_stress_Pa", "area_um2", "total_force_nN", "n_pixels",
99
+ "model", "checkpoint", "checkpoint_sha256", "substrate_setting", "image_um_per_px", "stress_max_Pa",
100
+ "app_version"]]
101
  for r in batch_results:
102
+ m, key, info = r["_metrics"], r["key_img"] or "image", r.get("info", {})
103
+ rows.append([key, fmt(m["mean_pa"], nd=1), fmt(m["max_pa"], nd=1), fmt(m["area_um2"], nd=0),
104
+ fmt(m["total_force_nN"], nd=2)])
105
+ sub = info.get("substrate") or {}
106
+ csv_rows.append([os.path.splitext(key)[0], region, fmt(m["mean_pa"], nd=2), fmt(m["max_pa"], nd=2),
107
+ fmt(m["area_um2"], nd=1), fmt(m["total_force_nN"], nd=3), m["n_px"],
108
+ info.get("model", {}).get("architecture", ""), info.get("model", {}).get("checkpoint", ""),
109
+ info.get("model", {}).get("checkpoint_sha256", ""),
110
+ sub.get("name") or (f"manual {sub.get('pixelsize')}/{sub.get('young')}" if sub else ""),
111
+ info.get("image_um_per_px") or "", info.get("stress_max_pa", ""), info.get("app_version", "")])
 
 
 
 
 
112
  st.markdown(_result_banner("INPUT", "input", "Bright-field images"), unsafe_allow_html=True)
113
  n_cols = min(5, len(batch_results))
114
  bf_cols = st.columns(n_cols)
115
  for i, r in enumerate(batch_results):
116
  img = r["img"]
117
+ img_rgb = cv2.cvtColor(img, cv2.COLOR_GRAY2RGB) if img.ndim == 2 else cv2.cvtColor(img, cv2.COLOR_BGR2RGB)
 
 
 
118
  with bf_cols[i % n_cols]:
119
  st.image(img_rgb, caption=r["key_img"], use_container_width=True)
120
  is_rescale_b = is_display_range_remapped(display_mode, clip_min, clip_max)
121
+ st.markdown(_result_banner("OUTPUT", "output", "Predicted traction-stress maps"), unsafe_allow_html=True)
122
  hm_cols = st.columns(n_cols)
123
  for i, r in enumerate(batch_results):
124
+ hm_rgb = heatmap_to_rgb_with_contour(r["_display_heatmap"], colormap_name,
125
+ r.get("_cell_mask") if auto_cell_boundary else None)
 
 
126
  with hm_cols[i % n_cols]:
127
  st.image(hm_rgb, caption=r["key_img"], use_container_width=True)
128
+ smax = batch_results[0]["scale"]["stress_max_pa"]
129
+ render_horizontal_colorbar(colormap_name, clip_min, clip_max, is_rescale_b, stress_max_pa=smax)
130
+ st.dataframe({h: [row[i] for row in rows] for i, h in enumerate(headers)}, use_container_width=True, hide_index=True)
131
+ st.caption(f"Metrics over the {region}. Area and total force need the image pixel size (sidebar).")
132
+ with st.expander("Traction-stress distribution (histograms)", expanded=False):
 
 
 
 
133
  for i, r in enumerate(batch_results):
 
134
  cell_mask = r.get("_cell_mask")
135
+ vals = to_pa(r["heatmap"], r["scale"])
136
+ vals = vals[cell_mask > 0] if (cell_mask is not None and np.any(cell_mask > 0) and auto_cell_boundary) else vals.ravel()
137
  vals = vals[vals > 0] if np.any(vals > 0) else vals
138
  st.markdown(f"**{r['key_img']}**")
139
  if len(vals) > 0:
140
  fig = go.Figure(data=[go.Histogram(x=vals, nbinsx=50, marker_color=_HISTOGRAM_ACCENT)])
141
+ fig.update_layout(height=_HISTOGRAM_HEIGHT, margin=dict(l=40, r=20, t=10, b=40),
142
+ xaxis_title="Traction stress (Pa)", yaxis_title="Pixels", showlegend=False)
 
 
 
143
  st.plotly_chart(fig, use_container_width=True, config={"displayModeBar": False})
144
  else:
145
  st.caption("No data")
146
  if i < len(batch_results) - 1:
147
  st.divider()
 
148
  buf_csv = io.StringIO()
149
  csv.writer(buf_csv).writerows(csv_rows)
150
+ lo_b, hi_b = (clip_min, clip_max) if is_rescale_b else (0.0, 1.0)
151
  zip_buf = io.BytesIO()
152
  with zipfile.ZipFile(zip_buf, "w", zipfile.ZIP_DEFLATED) as zf:
153
  for r in batch_results:
 
 
 
 
154
  base = os.path.splitext(r["key_img"] or "image")[0]
155
+ png = heatmap_figure_png_bytes(r["_display_heatmap"], colormap_name,
156
+ r.get("_cell_mask") if auto_cell_boundary else None, r["scale"], lo_b, hi_b)
157
+ zf.writestr(f"{base}_traction_stress.png", png.getvalue())
158
+ zf.writestr(f"{base}_traction_stress_Pa.tif", _tiff_pa_bytes(r["heatmap"], r["scale"]))
159
+ zf.writestr("README.txt", _ZIP_README.format(smax=smax))
160
  zip_buf.seek(0)
161
+ pdf_items = [dict(img=r["img"], display_heatmap=r["_display_heatmap"], raw_heatmap=r["heatmap"],
162
+ base_name=os.path.splitext(r["key_img"] or "image")[0],
163
+ cell_mask=r.get("_cell_mask") if auto_cell_boundary else None,
164
+ metrics_full=region_metrics(r["heatmap"], None, r["scale"]),
165
+ metrics_cell=r["_metrics"] if auto_cell_boundary else None,
166
+ info=r.get("info"), scale=r["scale"]) for r in batch_results]
167
+ pdf_bytes = create_batch_pdf_report(pdf_items, colormap_name, lo_b, hi_b, auto_cell_boundary)
168
+ dl_col1, dl_col2, dl_col3 = st.columns(3)
169
  with dl_col1:
170
+ st.download_button("Download report (PDF)", data=pdf_bytes, file_name="s2f_batch_report.pdf",
171
+ mime="application/pdf", key="download_batch_pdf", icon=":material/picture_as_pdf:",
172
+ help="Summary table of all images, then one page per image with maps, metrics and parameters.")
 
 
 
 
 
173
  with dl_col2:
174
+ st.download_button("Download values (CSV)", data=buf_csv.getvalue(), file_name="s2f_batch_results.csv",
175
+ mime="text/csv", key="download_batch_csv", icon=":material/download:",
176
+ help="One row per image: metrics with units and the parameters used.")
177
+ with dl_col3:
178
+ st.download_button("Download maps (ZIP)", data=zip_buf.getvalue(), file_name="s2f_batch_maps.zip",
179
+ mime="application/zip", key="download_batch_heatmaps", icon=":material/image:",
180
+ help="For each image: a PNG to view (colourbar and scale bar) and a TIFF whose pixel "
181
+ "values are traction stress in Pa, for measurements in Fiji/ImageJ.")
182
+
183
+
184
+ _ZIP_README = """Shape2Force (S2F) - predicted traction-stress maps
185
+
186
+ For each image:
187
+ <name>_traction_stress.png picture of the map with colourbar (Pa) and scale bar, for viewing and figures
188
+ <name>_traction_stress_Pa.tif the same map as numbers: each pixel value is the predicted traction stress in Pa
189
+ (32-bit, 1024 x 1024). Open it in Fiji/ImageJ to measure regions yourself
190
+ (e.g. draw an ROI and use Analyze > Measure: Mean = mean traction stress in Pa).
191
+
192
+ Scale: model output 1.0 = {smax:.0f} Pa. S2F predicts the magnitude of the traction stress, not its direction.
193
+ The TIFF covers the whole image resized to 1024 x 1024 pixels; one TIFF pixel = (image width x pixel size / 1024) um.
194
+ """
195
+
196
+
197
+ def _tiff_pa_bytes(heatmap, scale):
198
+ """Traction-stress map in Pa as a 32-bit float TIFF (readable by Fiji/ImageJ)."""
199
+ ok, enc = cv2.imencode(".tif", to_pa(heatmap, scale).astype(np.float32))
200
+ return enc.tobytes() if ok else b""
201
 
202
 
203
  def render_result_display(img, raw_heatmap, display_heatmap, pixel_sum, force, key_img, download_key_suffix="",
204
+ colormap_name="Jet", display_mode="Default", measure_region_dialog=None, auto_cell_boundary=True,
205
+ cell_mask=None, clip_min=0.0, clip_max=1.0, clamp_only=False, scale=None, info=None):
206
  """
207
+ Render one prediction: bright field + traction-stress map (µm scale bars, colourbar in Pa), metrics with
208
+ units, statistics, and downloads (PNG with scale bar and colourbar, CSV and PDF report with all parameters).
209
+ scale: utils.units.make_scale(...); info: provenance dict (see app.py).
 
210
  """
211
+ scale = scale or make_scale("single_cell", image_shape=img.shape[:2])
212
+ smax = scale["stress_max_pa"]
213
  if cell_mask is None and auto_cell_boundary:
214
  cell_mask = estimate_cell_mask(raw_heatmap)
215
  elif not auto_cell_boundary:
216
  cell_mask = None
217
+ metrics_full = region_metrics(raw_heatmap, None, scale)
218
+ metrics_cell = region_metrics(raw_heatmap, cell_mask, scale) if (cell_mask is not None and np.any(cell_mask > 0)) else None
219
+ shown = metrics_cell if (auto_cell_boundary and metrics_cell) else metrics_full
220
  base_name = os.path.splitext(key_img or "image")[0]
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
221
  is_rescale = is_display_range_remapped(display_mode, clip_min, clip_max)
222
+ lo, hi = (clip_min, clip_max) if is_rescale else (0.0, 1.0)
223
 
224
  tit1, tit2 = st.columns(2)
225
  with tit1:
226
  st.markdown(_result_banner("INPUT", "input", "Bright-field image"), unsafe_allow_html=True)
227
  with tit2:
228
+ st.markdown(_result_banner("OUTPUT", "output", "Predicted traction-stress map"), unsafe_allow_html=True)
229
  fig_pl = make_subplots(rows=1, cols=2)
230
+ fig_pl.add_trace(go.Heatmap(z=img, colorscale="gray", showscale=False, hoverinfo="skip"), row=1, col=1)
231
+ ticks, labels = colorbar_ticks_pa(lo, hi, smax)
232
+ colorbar_cfg = dict(len=0.8, thickness=12, tickmode="array", tickvals=ticks, ticktext=labels,
233
+ title=dict(text="Pa", side="top"))
234
+ fig_pl.add_trace(go.Heatmap(z=display_heatmap, colorscale=cv_colormap_to_plotly_colorscale(colormap_name),
235
+ zmin=0.0, zmax=1.0, showscale=True, colorbar=colorbar_cfg,
236
+ customdata=to_pa(raw_heatmap, scale),
237
+ hovertemplate="x %{x}, y %{y}<br>%{customdata:.1f} Pa<extra></extra>"), row=1, col=2)
 
 
 
 
 
238
  add_cell_contour_to_fig(fig_pl, cell_mask, row=1, col=2)
239
+ _add_scale_bar_to_fig(fig_pl, img.shape[1], img.shape[0], scale.get("image_um_per_px"), 1, 1)
240
+ _add_scale_bar_to_fig(fig_pl, display_heatmap.shape[1], display_heatmap.shape[0], scale.get("hm_um_per_px_x"), 1, 2)
241
+ fig_pl.update_layout(height=_RESULT_FIG_HEIGHT, margin=dict(l=10, r=10, t=10, b=10),
242
+ xaxis=dict(scaleanchor="y", scaleratio=1), xaxis2=dict(scaleanchor="y2", scaleratio=1))
 
 
243
  fig_pl.update_xaxes(showticklabels=False, showgrid=False, zeroline=False)
244
  fig_pl.update_yaxes(showticklabels=False, autorange="reversed", showgrid=False, zeroline=False)
245
  st.plotly_chart(fig_pl, use_container_width=True, config={"displayModeBar": True, "responsive": True})
246
+ if is_rescale:
247
+ st.caption(f"Display range {lo * smax:.0f}–{hi * smax:.0f} Pa; stresses above {hi * smax:.0f} Pa are shown "
248
+ "in the top colour. Metrics always use the full prediction.")
249
 
250
+ cols = st.columns(4)
251
+ for col, (label, value) in zip(cols, metric_rows(shown)):
252
+ with col:
253
+ st.metric(label, value, help=_METRIC_HELP[label])
254
+ st.caption(("Metrics inside the force region (red contour), estimated from the predicted map." if shown is metrics_cell else
255
+ "Metrics over the whole field of view.")
256
+ + ("" if scale.get("hm_px_area_um2") else " Enter the image pixel size in the sidebar to get area and total force."))
 
 
 
 
 
 
 
 
 
 
 
 
257
 
 
258
  with st.expander("Statistics"):
259
+ vals = to_pa(raw_heatmap, scale)
260
+ vals = vals[cell_mask > 0] if (shown is metrics_cell and cell_mask is not None) else vals.ravel()
261
  if len(vals) > 0:
262
+ c1, c2, c3 = st.columns(3)
263
+ p25, p50, p75, p90 = (float(np.percentile(vals, q)) for q in (25, 50, 75, 90))
264
+ with c1:
265
+ st.metric("Mean", f"{float(np.mean(vals)):.1f} Pa")
266
+ st.metric("Std", f"{float(np.std(vals)):.1f} Pa")
267
+ with c2:
268
+ st.metric("P25", f"{p25:.1f} Pa")
269
+ st.metric("P50 (median)", f"{p50:.1f} Pa")
270
+ with c3:
271
+ st.metric("P75", f"{p75:.1f} Pa")
272
+ st.metric("P90", f"{p90:.1f} Pa")
 
 
 
 
273
  hist_fig = go.Figure(data=[go.Histogram(x=vals, nbinsx=50, marker_color=_HISTOGRAM_ACCENT)])
274
+ hist_fig.update_layout(height=_HISTOGRAM_HEIGHT, margin=dict(l=40, r=20, t=20, b=40),
275
+ xaxis_title="Traction stress (Pa)", yaxis_title="Pixels", showlegend=False)
 
 
 
276
  st.plotly_chart(hist_fig, use_container_width=True, config={"displayModeBar": False})
277
  else:
278
+ st.caption("No values to compute statistics.")
 
 
 
 
 
 
279
 
280
+ with st.expander("Parameters of this prediction"):
281
+ st.table({"Parameter": [k for k, _ in info_rows(info)], "Value": [str(v) for _, v in info_rows(info)]})
 
 
 
282
 
283
+ with st.expander("How to read the results"):
284
+ st.markdown(f"""
285
+ **Input (left):** the bright-field image you provided (cell shape only, no force information).
 
 
 
 
 
 
 
 
 
 
 
 
286
 
287
+ **Output (right):** predicted **traction-stress magnitude** (Pa).
288
+ - The model output is normalised to 0–1, with 1 = **{smax:.0f} Pa**, the fixed colour limit of the
289
+ {'single-cell' if smax >= 500 else 'spheroid'} ground-truth TFM maps used for training. The colourbar shows Pa.
290
+ - S2F predicts the magnitude only, not the direction, and predictions tend to underestimate the highest stresses.
291
+ - **Range** (sidebar) narrows the displayed window, e.g. 0–250 Pa, to show low-stress patterns; stresses above the
292
+ window saturate. The metrics are always computed from the full prediction.
293
+ - **Red contour** ("Measure force region only", on by default): the region of high predicted stress, estimated from
294
+ the map (not the cell outline); the metrics refer to this region so the background does not dilute them.
295
 
296
+ **Metrics:** mean and maximum traction stress (Pa); area (µm²) and total force (nN = Σ stress × pixel area)
297
+ need the image pixel size. Total force sums magnitudes, so it is not the net force.
298
+ """)
299
 
300
+ original_vals = build_original_vals(raw_heatmap, pixel_sum, force, scale)
301
+ buf_hm = heatmap_figure_png_bytes(display_heatmap, colormap_name, cell_mask, scale, lo, hi)
302
+ csv_text = _metrics_csv(base_name, metrics_full, metrics_cell, info)
303
+ pdf_bytes = create_pdf_report(img, display_heatmap, raw_heatmap, base_name, colormap_name, cell_mask=cell_mask,
304
+ metrics_full=metrics_full, metrics_cell=metrics_cell, info=info, scale=scale,
305
+ clip_min=lo, clip_max=hi)
306
 
307
  btn_col1, btn_col2, btn_col3, btn_col4 = st.columns(4)
308
  with btn_col1:
 
312
  st.rerun()
313
  elif HAS_DRAWABLE_CANVAS:
314
  with st.expander("Measure tool"):
315
+ expander_cell_vals = build_cell_vals(raw_heatmap, cell_mask, pixel_sum, force, scale) if (auto_cell_boundary and cell_mask is not None) else None
316
+ render_region_canvas(display_heatmap, raw_heatmap=raw_heatmap, bf_img=img, original_vals=original_vals,
317
+ cell_vals=expander_cell_vals, cell_mask=cell_mask if auto_cell_boundary else None,
318
+ key_suffix="expander", input_filename=key_img, colormap_name=colormap_name)
 
 
 
 
 
 
 
 
 
319
  else:
320
  st.caption("Install `streamlit-drawable-canvas-fix` for region measurement: `pip install streamlit-drawable-canvas-fix`")
321
  with btn_col2:
322
+ st.download_button("Download map", width="stretch", data=buf_hm.getvalue(),
323
+ file_name=f"{base_name}_traction_stress.png", mime="image/png",
324
+ key=f"download_heatmap{download_key_suffix}", icon=":material/download:")
 
 
 
 
 
 
325
  with btn_col3:
326
+ st.download_button("Download values", width="stretch", data=csv_text, file_name=f"{base_name}_values.csv",
327
+ mime="text/csv", key=f"download_main_values{download_key_suffix}", icon=":material/download:")
 
 
 
 
 
 
 
328
  with btn_col4:
329
+ st.download_button("Download report", width="stretch", data=pdf_bytes, file_name=f"{base_name}_report.pdf",
330
+ mime="application/pdf", key=f"download_pdf{download_key_suffix}",
331
+ icon=":material/picture_as_pdf:")
 
 
 
 
 
 
S2FApp/utils/display.py CHANGED
@@ -32,30 +32,16 @@ def is_display_range_remapped(display_mode, clip_min, clip_max):
32
 
33
  def apply_display_scale(heatmap, mode, clip_min=0, clip_max=1, clamp_only=False):
34
  """
35
- Apply display scaling. Display only—does not change underlying values.
36
 
37
- Supports modes used by the app: ``Default`` (clip to [0, 1]) and ``Range``
38
- (window to [clip_min, clip_max]). Unknown ``mode`` is treated like ``Default``.
39
-
40
- Parameters
41
- ----------
42
- clamp_only : bool
43
- For ``mode == "Range"`` when ``clip_max > clip_min``:
44
-
45
- - **False** (default in the app for Range): pixels outside ``[clip_min, clip_max]`` are set
46
- to 0; values inside are linearly mapped to ``[0, 1]`` for the colormap.
47
- - **True**: values are clamped to ``[clip_min, clip_max]`` without rescaling to ``[0, 1]``.
48
  """
 
49
  if mode != "Range":
50
- return np.clip(heatmap, 0, 1).astype(np.float32)
51
- # Range
52
  vmin, vmax = float(clip_min), float(clip_max)
53
  if vmax > vmin:
54
- h = heatmap.astype(np.float32)
55
- if clamp_only:
56
- return np.clip(h, vmin, vmax).astype(np.float32)
57
- mask = (h >= vmin) & (h <= vmax)
58
- out = np.zeros_like(h)
59
- out[mask] = (h[mask] - vmin) / (vmax - vmin)
60
- return np.clip(out, 0, 1).astype(np.float32)
61
- return np.clip(heatmap, 0, 1).astype(np.float32)
 
32
 
33
  def apply_display_scale(heatmap, mode, clip_min=0, clip_max=1, clamp_only=False):
34
  """
35
+ Map the normalised prediction (0-1) to colormap positions. Display only; values are unchanged.
36
 
37
+ ``Default``: the full scale, 0-1 (= 0-500 Pa single cells, 0-50 Pa spheroids).
38
+ ``Range``: the window [clip_min, clip_max] is stretched over the whole colormap; values below the window
39
+ are shown as the lowest colour and values above it saturate at the highest colour.
 
 
 
 
 
 
 
 
40
  """
41
+ h = np.asarray(heatmap, dtype=np.float32)
42
  if mode != "Range":
43
+ return np.clip(h, 0, 1).astype(np.float32)
 
44
  vmin, vmax = float(clip_min), float(clip_max)
45
  if vmax > vmin:
46
+ return np.clip((h - vmin) / (vmax - vmin), 0, 1).astype(np.float32)
47
+ return np.clip(h, 0, 1).astype(np.float32)
 
 
 
 
 
 
S2FApp/utils/report.py CHANGED
@@ -1,5 +1,6 @@
1
  """Report and heatmap export utilities."""
2
  import io
 
3
  from datetime import datetime
4
 
5
  import cv2
@@ -10,7 +11,7 @@ from reportlab.lib.units import inch
10
  from reportlab.lib.utils import ImageReader
11
  from reportlab.pdfgen import canvas
12
 
13
- from config.constants import COLORMAPS
14
 
15
 
16
  def _draw_pdf_footer(c, margin=72, footer_y=40, include_web_app=False):
@@ -82,73 +83,244 @@ def heatmap_to_png_bytes(scaled_heatmap, colormap_name="Jet", cell_mask=None, zm
82
  return buf
83
 
84
 
85
- def create_pdf_report(img, display_heatmap, raw_heatmap, pixel_sum, force, base_name, colormap_name="Jet",
86
- cell_mask=None, cell_pixel_sum=None, cell_force=None, cell_mean=None, zmin=None, zmax=None):
87
- """Create a PDF report with input image, heatmap, and metrics."""
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
88
  buf = io.BytesIO()
89
- c = canvas.Canvas(buf, pagesize=A4)
90
- c.setTitle("Shape2Force")
91
- c.setAuthor("Angione-Lab")
 
 
 
 
 
 
 
92
  page_w_pt, page_h_pt = A4[0], A4[1]
93
- margin = 72
94
  layout = _pdf_image_layout(page_w_pt, page_h_pt, margin)
95
- img_w = layout["img_w"]
96
- img_h = layout["img_h"]
97
- bf_x = layout["bf_x"]
98
- hm_x = layout["hm_x"]
99
  img_bottom = layout["img_bottom"]
100
- y_top = layout["y_top"]
101
 
102
  _draw_pdf_footer(c, margin=margin, include_web_app=True)
103
- c.setFont("Helvetica-Bold", 16)
104
  c.drawString(margin, y_top, "Shape2Force (S2F) - Prediction Report")
105
  c.setFont("Helvetica", 10)
106
- c.drawString(margin, y_top - 14, f"Image: {base_name}")
107
- y_top -= 35
108
 
109
- img_pil = Image.fromarray(img) if img.ndim == 2 else Image.fromarray(cv2.cvtColor(img, cv2.COLOR_BGR2RGB))
110
- img_buf = io.BytesIO()
111
- img_pil.save(img_buf, format="PNG")
112
- img_buf.seek(0)
113
- c.drawImage(ImageReader(img_buf), bf_x, img_bottom, width=img_w, height=img_h, preserveAspectRatio=True)
 
 
 
 
 
 
114
  c.setFont("Helvetica", 9)
115
- bf_label_w = c.stringWidth("Bright-field", "Helvetica", 9)
116
- c.drawString(bf_x + (img_w - bf_label_w) / 2, img_bottom - 14, "Bright-field")
117
 
118
- heatmap_rgb = heatmap_to_rgb_with_contour(display_heatmap, colormap_name, cell_mask, zmin=zmin, zmax=zmax)
119
- hm_buf = io.BytesIO()
120
- Image.fromarray(heatmap_rgb).save(hm_buf, format="PNG")
121
- hm_buf.seek(0)
122
- c.drawImage(ImageReader(hm_buf), hm_x, img_bottom, width=img_w, height=img_h, preserveAspectRatio=True)
123
- hm_label = "Force map (red = estimated boundary)" if cell_mask is not None and np.any(cell_mask > 0) else "Force map"
124
- hm_label_w = c.stringWidth(hm_label, "Helvetica", 9)
125
- c.drawString(hm_x + (img_w - hm_label_w) / 2, img_bottom - 14, hm_label)
126
 
127
- # Metrics section with spacing
128
- row_height = 14
129
- y = img_bottom - 14 - row_height
130
  c.setFont("Helvetica-Bold", 10)
131
  c.drawString(margin, y, "Metrics")
 
132
  c.setFont("Helvetica", 9)
133
- y -= 18
134
- if cell_pixel_sum is not None and cell_force is not None and cell_mean is not None:
135
- metrics = [
136
- ("Cell sum (estimated boundary)", f"{cell_pixel_sum:.2f}"),
137
- ("Cell force (scaled)", f"{cell_force:.2f}"),
138
- ("Heatmap max", f"{np.max(raw_heatmap):.4f}"),
139
- ("Heatmap mean (estimated boundary)", f"{cell_mean:.4f}"),
140
- ]
141
- else:
142
- metrics = [
143
- ("Sum of all pixels", f"{pixel_sum:.2f}"),
144
- ("Cell force (scaled)", f"{force:.2f}"),
145
- ("Heatmap max", f"{np.max(raw_heatmap):.4f}"),
146
- ("Heatmap mean", f"{np.mean(raw_heatmap):.4f}"),
147
- ]
148
- for label, val in metrics:
149
- c.drawString(margin, y, f"{label}: {val}")
150
- y -= 16
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
151
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
152
  c.save()
153
  buf.seek(0)
154
  return buf.getvalue()
@@ -194,8 +366,8 @@ def create_measure_pdf_report(bf_img, heatmap_labeled_rgb, table_rows, base_name
194
  Image.fromarray(heatmap_labeled_rgb).save(hm_labeled_buf, format="PNG")
195
  hm_labeled_buf.seek(0)
196
  c.drawImage(ImageReader(hm_labeled_buf), hm_x, img_bottom, width=img_w, height=img_h, preserveAspectRatio=True)
197
- hm_label_w = c.stringWidth("Force map", "Helvetica", 9)
198
- c.drawString(hm_x + (img_w - hm_label_w) / 2, img_bottom - 14, "Force map")
199
 
200
  # Spacing: one line between images/labels and measurements section
201
  row_height = 14
 
1
  """Report and heatmap export utilities."""
2
  import io
3
+ import textwrap
4
  from datetime import datetime
5
 
6
  import cv2
 
11
  from reportlab.lib.utils import ImageReader
12
  from reportlab.pdfgen import canvas
13
 
14
+ from config.constants import ARCH_LABELS, AUTO_BOUNDARY_DESCRIPTION, COLORMAPS
15
 
16
 
17
  def _draw_pdf_footer(c, margin=72, footer_y=40, include_web_app=False):
 
83
  return buf
84
 
85
 
86
+ def info_rows(info):
87
+ """Provenance of a prediction as (label, value) rows: everything needed to reproduce it."""
88
+ if not info:
89
+ return []
90
+ m = info.get("model", {})
91
+ rows = [
92
+ ("Input file", info.get("input_file", "–")),
93
+ ("Input file SHA-256", info.get("input_sha256", "–")),
94
+ ("Prediction time (UTC)", info.get("time", "–")),
95
+ ("Model type", {"single_cell": "Single cell", "spheroid": "Spheroid"}.get(m.get("model_type"), "–")),
96
+ ("Architecture", ARCH_LABELS.get(m.get("architecture"), m.get("architecture", "–"))),
97
+ ("Checkpoint", m.get("checkpoint", "–")),
98
+ ("Checkpoint SHA-256", m.get("checkpoint_sha256", "–")),
99
+ ]
100
+ sub = info.get("substrate")
101
+ if sub:
102
+ if sub.get("mode") == "preset":
103
+ rows.append(("Substrate setting (preset)", sub.get("name", "–")))
104
+ else:
105
+ rows.append(("Substrate setting (manual)", "–"))
106
+ rows.append((" pixel-size setting / Young's modulus", f"{sub.get('pixelsize'):.4f} / {sub.get('young'):.0f} Pa"))
107
+ rows.append((" model input channels (normalised)",
108
+ f"{sub.get('pixelsize_norm'):.3f} / {sub.get('young_norm'):.3f}"))
109
+ shp = info.get("image_shape")
110
+ rows += [
111
+ ("Image size (px)", f"{shp[1]} x {shp[0]}" if shp else "–"),
112
+ ("Image pixel size", f"{info['image_um_per_px']:.4f} µm/px (user input)" if info.get("image_um_per_px") else "not set"),
113
+ ("Stress scale", f"normalised output 1.0 = {info.get('stress_max_pa', 0):.0f} Pa"),
114
+ ]
115
+ d = info.get("display", {})
116
+ if d:
117
+ rows.append(("Display", f"{d.get('colormap', '–')}, {d.get('range_pa', ('–', '–'))[0]:.0f}-{d.get('range_pa', ('–', '–'))[1]:.0f} Pa"
118
+ + (" (values above the range shown in the top colour)" if d.get("mode") == "Range" else "")))
119
+ rows.append(("Measure force region only", f"on ({AUTO_BOUNDARY_DESCRIPTION})" if info.get("auto_boundary") else "off (whole field of view)"))
120
+ rows.append(("App version", f"{info.get('app_version', '–')}" + (f" (commit {info['app_commit']})" if info.get("app_commit") else "")))
121
+ return rows
122
+
123
+
124
+ def colorbar_strip_rgb(width, colormap_name, clip_min=0.0, clip_max=1.0, stress_max_pa=500.0, height=70):
125
+ """Horizontal colourbar with tick labels in Pa, as an RGB image (white background)."""
126
+ from ui.heatmaps import colorbar_ticks_pa
127
+ strip = np.full((height, width, 3), 255, np.uint8)
128
+ pad = max(10, width // 30)
129
+ bar_w = width - 2 * pad
130
+ grad = np.linspace(0, 255, bar_w).astype(np.uint8).reshape(1, -1)
131
+ rgb = cv2.cvtColor(cv2.applyColorMap(grad, COLORMAPS.get(colormap_name, cv2.COLORMAP_JET)), cv2.COLOR_BGR2RGB)
132
+ bar_h = height // 4
133
+ strip[6:6 + bar_h, pad:pad + bar_w] = np.repeat(rgb, bar_h, axis=0)
134
+ pos, labels = colorbar_ticks_pa(clip_min, clip_max, stress_max_pa)
135
+ fs = max(0.4, width / 950)
136
+ lw = max(1, int(round(fs * 1.6)))
137
+ for t, lab in zip(pos, labels):
138
+ x = pad + int(t * (bar_w - 1))
139
+ cv2.line(strip, (x, 6 + bar_h), (x, 12 + bar_h), (0, 0, 0), lw)
140
+ (tw, th), _ = cv2.getTextSize(lab, cv2.FONT_HERSHEY_SIMPLEX, fs, lw)
141
+ cv2.putText(strip, lab, (min(max(x - tw // 2, 0), width - tw), 18 + bar_h + th), cv2.FONT_HERSHEY_SIMPLEX, fs,
142
+ (0, 0, 0), lw, cv2.LINE_AA)
143
+ title = "Traction stress (Pa)"
144
+ (tw, th), _ = cv2.getTextSize(title, cv2.FONT_HERSHEY_SIMPLEX, fs, lw)
145
+ cv2.putText(strip, title, ((width - tw) // 2, height - 8), cv2.FONT_HERSHEY_SIMPLEX, fs, (0, 0, 0), lw, cv2.LINE_AA)
146
+ return strip
147
+
148
+
149
+ def heatmap_figure_rgb(display_heatmap, colormap_name="Jet", cell_mask=None, scale=None, clip_min=0.0, clip_max=1.0):
150
+ """Heatmap with optional red boundary, µm scale bar and a Pa colourbar underneath (for PNG/PDF export)."""
151
+ from utils.units import draw_scale_bar
152
+ hm = heatmap_to_rgb_with_contour(display_heatmap, colormap_name, cell_mask)
153
+ if scale is not None and scale.get("hm_um_per_px_x"):
154
+ draw_scale_bar(hm, scale["hm_um_per_px_x"])
155
+ smax = scale["stress_max_pa"] if scale else 1.0
156
+ bar = colorbar_strip_rgb(hm.shape[1], colormap_name, clip_min, clip_max, smax, height=max(80, hm.shape[0] // 6))
157
+ return np.vstack([hm, bar])
158
+
159
+
160
+ def heatmap_figure_png_bytes(display_heatmap, colormap_name="Jet", cell_mask=None, scale=None, clip_min=0.0, clip_max=1.0):
161
  buf = io.BytesIO()
162
+ Image.fromarray(heatmap_figure_rgb(display_heatmap, colormap_name, cell_mask, scale, clip_min, clip_max)).save(buf, format="PNG")
163
+ buf.seek(0)
164
+ return buf
165
+
166
+
167
+ def _draw_prediction_page(c, img, display_heatmap, raw_heatmap, base_name, colormap_name="Jet", cell_mask=None,
168
+ metrics_full=None, metrics_cell=None, info=None, scale=None, clip_min=0.0, clip_max=1.0,
169
+ page_label=None):
170
+ """Draw one prediction (images, metrics, parameters) on the current page of canvas `c`."""
171
+ from utils.units import draw_scale_bar, metric_rows
172
  page_w_pt, page_h_pt = A4[0], A4[1]
173
+ margin = 60
174
  layout = _pdf_image_layout(page_w_pt, page_h_pt, margin)
175
+ img_w, img_h = layout["img_w"], layout["img_h"]
176
+ bf_x, hm_x, y_top = layout["bf_x"], layout["hm_x"], layout["y_top"]
 
 
177
  img_bottom = layout["img_bottom"]
 
178
 
179
  _draw_pdf_footer(c, margin=margin, include_web_app=True)
180
+ c.setFont("Helvetica-Bold", 15)
181
  c.drawString(margin, y_top, "Shape2Force (S2F) - Prediction Report")
182
  c.setFont("Helvetica", 10)
183
+ c.drawString(margin, y_top - 14, f"Image: {base_name}" + (f" ({page_label})" if page_label else ""))
 
184
 
185
+ bf = img if img.ndim == 3 else cv2.cvtColor(img, cv2.COLOR_GRAY2RGB)
186
+ bf_um_per_px = scale.get("image_um_per_px") if scale else None
187
+ if max(bf.shape[:2]) > 1024: # keep the PDF small; the scale bar follows the resampling
188
+ f = 1024 / max(bf.shape[:2])
189
+ bf = cv2.resize(bf, (int(bf.shape[1] * f), int(bf.shape[0] * f)), interpolation=cv2.INTER_AREA)
190
+ bf_um_per_px = bf_um_per_px / f if bf_um_per_px else None
191
+ bf = np.ascontiguousarray(bf.copy())
192
+ if bf_um_per_px:
193
+ draw_scale_bar(bf, bf_um_per_px)
194
+ bf_buf = io.BytesIO(); Image.fromarray(bf).save(bf_buf, format="PNG"); bf_buf.seek(0)
195
+ c.drawImage(ImageReader(bf_buf), bf_x, img_bottom, width=img_w, height=img_h, preserveAspectRatio=True)
196
  c.setFont("Helvetica", 9)
197
+ c.drawCentredString(bf_x + img_w / 2, img_bottom - 12, "Bright field")
 
198
 
199
+ fig = heatmap_figure_rgb(display_heatmap, colormap_name, cell_mask, scale, clip_min, clip_max)
200
+ fig_h = img_h * fig.shape[0] / fig.shape[1]
201
+ hm_buf = io.BytesIO(); Image.fromarray(fig).save(hm_buf, format="PNG", optimize=True); hm_buf.seek(0)
202
+ c.drawImage(ImageReader(hm_buf), hm_x, img_bottom + img_h - fig_h, width=img_w, height=fig_h, preserveAspectRatio=True)
203
+ hm_label = "Predicted traction stress (red = force region)" if cell_mask is not None and np.any(cell_mask > 0) \
204
+ else "Predicted traction stress"
205
+ c.drawCentredString(hm_x + img_w / 2, img_bottom + img_h - fig_h - 12, hm_label)
 
206
 
207
+ y = img_bottom + img_h - fig_h - 40
 
 
208
  c.setFont("Helvetica-Bold", 10)
209
  c.drawString(margin, y, "Metrics")
210
+ y -= 15
211
  c.setFont("Helvetica", 9)
212
+ cols = [("Whole field of view", metrics_full)] + ([("Force region (red)", metrics_cell)] if metrics_cell else [])
213
+ x_cols = [margin + 170 + i * 150 for i in range(len(cols))]
214
+ for xc, (title, _) in zip(x_cols, cols):
215
+ c.setFont("Helvetica-Bold", 9); c.drawString(xc, y, title)
216
+ c.setFont("Helvetica", 9)
217
+ y -= 13
218
+ labels = [r[0] for r in metric_rows(metrics_full or {})]
219
+ for li, lab in enumerate(labels):
220
+ c.drawString(margin, y, lab)
221
+ for xc, (_, m) in zip(x_cols, cols):
222
+ c.drawString(xc, y, metric_rows(m or {})[li][1])
223
+ y -= 13
224
+ if scale is None or not scale.get("hm_px_area_um2"):
225
+ c.setFont("Helvetica-Oblique", 8)
226
+ c.drawString(margin, y, "Area and total force need the image pixel size (sidebar).")
227
+ y -= 12
228
+ c.setFont("Helvetica-Oblique", 8)
229
+ c.drawString(margin, y, "Total force = sum of traction stress x pixel area. S2F predicts magnitude only (no direction).")
230
+ y -= 20
231
+
232
+ c.setFont("Helvetica-Bold", 10)
233
+ c.drawString(margin, y, "Parameters (for reproducibility)")
234
+ y -= 14
235
+ c.setFont("Helvetica", 8)
236
+ for lab, val in info_rows(info):
237
+ c.drawString(margin, y, f"{lab}:")
238
+ for line in textwrap.wrap(str(val), 82) or ["–"]:
239
+ c.drawString(margin + 175, y, line)
240
+ y -= 11
241
+ if y < 70:
242
+ c.showPage(); _draw_pdf_footer(c, margin=margin, include_web_app=True); y = page_h_pt - 60; c.setFont("Helvetica", 8)
243
+
244
+
245
+ def create_pdf_report(img, display_heatmap, raw_heatmap, base_name, colormap_name="Jet", cell_mask=None,
246
+ metrics_full=None, metrics_cell=None, info=None, scale=None, clip_min=0.0, clip_max=1.0):
247
+ """
248
+ PDF report: bright field and predicted traction-stress map (with µm scale bar and Pa colourbar),
249
+ metrics with units, and every parameter needed to reproduce the prediction.
250
+ """
251
+ buf = io.BytesIO()
252
+ c = canvas.Canvas(buf, pagesize=A4)
253
+ c.setTitle("Shape2Force prediction report")
254
+ c.setAuthor("Angione-Lab")
255
+ _draw_prediction_page(c, img, display_heatmap, raw_heatmap, base_name, colormap_name, cell_mask,
256
+ metrics_full, metrics_cell, info, scale, clip_min, clip_max)
257
+ c.save()
258
+ buf.seek(0)
259
+ return buf.getvalue()
260
+
261
+
262
+ _SHARED_KEYS = ("Model type", "Architecture", "Checkpoint", "Checkpoint SHA-256", "Substrate setting (preset)",
263
+ "Substrate setting (manual)", " pixel-size setting / Young's modulus",
264
+ " model input channels (normalised)", "Image pixel size", "Stress scale", "Display", "Measure force region only",
265
+ "App version")
266
 
267
+
268
+ def create_batch_pdf_report(items, colormap_name="Jet", clip_min=0.0, clip_max=1.0, auto_cell_boundary=False):
269
+ """
270
+ Batch PDF: page 1 = summary table of all images (metrics with units) and the shared parameters;
271
+ then one page per image with the same layout as the single-image report.
272
+ items: list of dicts with img, display_heatmap, raw_heatmap, base_name, cell_mask, metrics_full,
273
+ metrics_cell, info, scale.
274
+ """
275
+ from utils.units import fmt
276
+ buf = io.BytesIO()
277
+ c = canvas.Canvas(buf, pagesize=A4)
278
+ c.setTitle("Shape2Force batch report")
279
+ c.setAuthor("Angione-Lab")
280
+ page_w_pt, page_h_pt = A4
281
+ margin = 60
282
+ _draw_pdf_footer(c, margin=margin, include_web_app=True)
283
+ y = page_h_pt - 50
284
+ c.setFont("Helvetica-Bold", 15)
285
+ c.drawString(margin, y, "Shape2Force (S2F) - Batch Report")
286
+ y -= 16
287
+ c.setFont("Helvetica", 10)
288
+ region = "force region (red contour)" if auto_cell_boundary else "whole field of view"
289
+ c.drawString(margin, y, f"{len(items)} images; metrics over the {region}. One page per image follows.")
290
+ y -= 26
291
+ headers = ["#", "Image", "Mean stress (Pa)", "Max stress (Pa)", "Area (µm²)", "Total force (nN)"]
292
+ xs = [margin, margin + 22, margin + 210, margin + 290, margin + 370, margin + 440]
293
+ c.setFont("Helvetica-Bold", 9)
294
+ for x, h in zip(xs, headers):
295
+ c.drawString(x, y, h)
296
+ y -= 4
297
+ c.line(margin, y, page_w_pt - margin, y)
298
+ y -= 12
299
+ c.setFont("Helvetica", 9)
300
+ for i, it in enumerate(items, 1):
301
+ m = (it["metrics_cell"] if (auto_cell_boundary and it.get("metrics_cell")) else it["metrics_full"]) or {}
302
+ vals = [str(i), it["base_name"][:34], fmt(m.get("mean_pa"), nd=1), fmt(m.get("max_pa"), nd=1),
303
+ fmt(m.get("area_um2"), nd=0), fmt(m.get("total_force_nN"), nd=2)]
304
+ for x, v in zip(xs, vals):
305
+ c.drawString(x, y, v)
306
+ y -= 13
307
+ y -= 18
308
+ c.setFont("Helvetica-Bold", 10)
309
+ c.drawString(margin, y, "Parameters (shared by all images)")
310
+ y -= 14
311
+ c.setFont("Helvetica", 8)
312
+ for lab, val in info_rows(items[0]["info"] if items else None):
313
+ if lab in _SHARED_KEYS:
314
+ c.drawString(margin, y, f"{lab}:")
315
+ for line in textwrap.wrap(str(val), 82) or ["–"]:
316
+ c.drawString(margin + 175, y, line)
317
+ y -= 11
318
+ c.showPage()
319
+ for i, it in enumerate(items, 1):
320
+ _draw_prediction_page(c, it["img"], it["display_heatmap"], it["raw_heatmap"], it["base_name"], colormap_name,
321
+ it.get("cell_mask"), it["metrics_full"], it.get("metrics_cell"), it["info"], it["scale"],
322
+ clip_min, clip_max, page_label=f"image {i} of {len(items)}")
323
+ c.showPage()
324
  c.save()
325
  buf.seek(0)
326
  return buf.getvalue()
 
366
  Image.fromarray(heatmap_labeled_rgb).save(hm_labeled_buf, format="PNG")
367
  hm_labeled_buf.seek(0)
368
  c.drawImage(ImageReader(hm_labeled_buf), hm_x, img_bottom, width=img_w, height=img_h, preserveAspectRatio=True)
369
+ hm_label_w = c.stringWidth("Traction stress map", "Helvetica", 9)
370
+ c.drawString(hm_x + (img_w - hm_label_w) / 2, img_bottom - 14, "Traction stress map")
371
 
372
  # Spacing: one line between images/labels and measurements section
373
  row_height = 14
S2FApp/utils/substrate_settings.py CHANGED
@@ -114,21 +114,6 @@ def compute_settings_normalization(config=None, config_path=None):
114
  Returns:
115
  dict: {'pixelsize': {'min', 'max'}, 'young': {'min', 'max'}}
116
  """
117
- if config is None:
118
- config = load_substrate_config(config_path)
119
-
120
- substrates = config.get('substrates', {})
121
- all_pixelsizes = [s['pixelsize'] for s in substrates.values()]
122
- all_youngs = [s['young'] for s in substrates.values()]
123
-
124
- if not all_pixelsizes or not all_youngs:
125
- pixelsize_min, pixelsize_max = 3.0769, 9.8138
126
- young_min, young_max = 1000.0, 10000.0
127
- else:
128
- pixelsize_min, pixelsize_max = min(all_pixelsizes), max(all_pixelsizes)
129
- young_min, young_max = min(all_youngs), max(all_youngs)
130
-
131
- return {
132
- 'pixelsize': {'min': pixelsize_min, 'max': pixelsize_max},
133
- 'young': {'min': young_min, 'max': young_max}
134
- }
 
114
  Returns:
115
  dict: {'pixelsize': {'min', 'max'}, 'young': {'min', 'max'}}
116
  """
117
+ # Ranges used in training, independent of the presets listed by the app
118
+ from config.constants import SETTINGS_NORMALIZATION
119
+ return {k: dict(v) for k, v in SETTINGS_NORMALIZATION.items()}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
S2FApp/utils/units.py ADDED
@@ -0,0 +1,125 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ """
2
+ Physical units for S2F predictions.
3
+
4
+ The network output is a normalised map y_hat in [0, 1]. The ground-truth traction-stress maps used for
5
+ training were exported by the TFM software on a fixed colour scale, so
6
+
7
+ traction stress T [Pa] = y_hat * STRESS_MAX_PA[model_type] (500 Pa single cells, 50 Pa spheroids).
8
+
9
+ Areas and forces additionally need the pixel size of the bright-field image (µm per pixel, entered by the
10
+ user). The prediction is made on a MODEL_INPUT_SIZE x MODEL_INPUT_SIZE grid, so one heatmap pixel covers
11
+ (image width * pixel size / MODEL_INPUT_SIZE) µm in x, and likewise in y.
12
+
13
+ area [µm²] = number of pixels * heatmap pixel area
14
+ force [nN] = sum(T [Pa] * heatmap pixel area [µm²]) * 1e-3 (1 Pa · µm² = 1e-12 N = 1e-3 nN)
15
+ """
16
+ import numpy as np
17
+
18
+ from config.constants import MODEL_INPUT_SIZE, STRESS_MAX_PA
19
+
20
+
21
+ def stress_max_pa(model_type):
22
+ return STRESS_MAX_PA["spheroid" if model_type == "spheroid" else "single_cell"]
23
+
24
+
25
+ def make_scale(model_type, image_um_per_px=None, image_shape=None, heatmap_shape=(MODEL_INPUT_SIZE, MODEL_INPUT_SIZE)):
26
+ """
27
+ Physical scale of one prediction.
28
+
29
+ image_um_per_px: pixel size of the uploaded bright-field image (µm/px); None or <= 0 if unknown.
30
+ image_shape: (height, width) of the uploaded image, before resizing to the model input.
31
+ Returns a dict used by the display, report and measurement code.
32
+ """
33
+ smax = stress_max_pa(model_type)
34
+ s = {"stress_max_pa": smax, "image_um_per_px": None, "image_shape": None,
35
+ "hm_um_per_px_x": None, "hm_um_per_px_y": None, "hm_px_area_um2": None}
36
+ if image_shape is not None:
37
+ s["image_shape"] = (int(image_shape[0]), int(image_shape[1]))
38
+ if image_um_per_px and image_um_per_px > 0 and image_shape is not None:
39
+ h, w = image_shape[:2]
40
+ hh, hw = heatmap_shape[:2]
41
+ sx = image_um_per_px * w / hw
42
+ sy = image_um_per_px * h / hh
43
+ s.update(image_um_per_px=float(image_um_per_px), hm_um_per_px_x=sx, hm_um_per_px_y=sy, hm_px_area_um2=sx * sy)
44
+ return s
45
+
46
+
47
+ def has_physical_size(scale):
48
+ return scale is not None and scale.get("hm_px_area_um2") is not None
49
+
50
+
51
+ def to_pa(heatmap, scale):
52
+ """Normalised map -> traction stress in Pa."""
53
+ return np.clip(np.asarray(heatmap, dtype=np.float64), 0, 1) * scale["stress_max_pa"]
54
+
55
+
56
+ def region_metrics(heatmap, mask, scale):
57
+ """
58
+ Metrics over a region (mask = 1) or the whole map (mask = None).
59
+ Keys: n_px, area_um2, mean_pa, max_pa, total_force_nN (area and force are None without a pixel size).
60
+ """
61
+ t = to_pa(heatmap, scale)
62
+ m = np.ones(t.shape, dtype=bool) if mask is None else (np.asarray(mask) > 0)
63
+ n = int(m.sum())
64
+ if n == 0:
65
+ return {"n_px": 0, "area_um2": None, "mean_pa": None, "max_pa": None, "total_force_nN": None}
66
+ vals = t[m]
67
+ out = {"n_px": n, "mean_pa": float(vals.mean()), "max_pa": float(vals.max()), "area_um2": None, "total_force_nN": None}
68
+ if has_physical_size(scale):
69
+ a = scale["hm_px_area_um2"]
70
+ out["area_um2"] = n * a
71
+ out["total_force_nN"] = float(vals.sum()) * a * 1e-3
72
+ return out
73
+
74
+
75
+ def fmt(value, unit="", nd=1):
76
+ """Format a metric value; '–' when not available."""
77
+ if value is None:
78
+ return "–"
79
+ return f"{value:.{nd}f}{(' ' + unit) if unit else ''}"
80
+
81
+
82
+ def metric_rows(metrics):
83
+ """(label, formatted value) pairs, in the order used everywhere in the app."""
84
+ return [
85
+ ("Mean traction stress", fmt(metrics.get("mean_pa"), "Pa")),
86
+ ("Max traction stress", fmt(metrics.get("max_pa"), "Pa")),
87
+ ("Area", fmt(metrics.get("area_um2"), "µm²", 0)),
88
+ ("Total force", fmt(metrics.get("total_force_nN"), "nN", 2)),
89
+ ]
90
+
91
+
92
+ def nice_scale_bar_um(field_width_um, fraction=0.2):
93
+ """Scale-bar length (µm) from {1, 2, 5} x 10^k closest to `fraction` of the field width."""
94
+ target = field_width_um * fraction
95
+ if target <= 0:
96
+ return None
97
+ k = np.floor(np.log10(target))
98
+ candidates = [m * 10 ** k for m in (1, 2, 5, 10)]
99
+ return float(min(candidates, key=lambda c: abs(c - target)))
100
+
101
+
102
+ def draw_scale_bar(rgb, um_per_px, color=(255, 255, 255), margin_frac=0.04):
103
+ """Draw a µm scale bar (bottom right) on an RGB uint8 image in place. Returns (rgb, length_um)."""
104
+ import cv2
105
+
106
+ if not um_per_px or um_per_px <= 0:
107
+ return rgb, None
108
+ h, w = rgb.shape[:2]
109
+ length_um = nice_scale_bar_um(w * um_per_px)
110
+ if length_um is None:
111
+ return rgb, None
112
+ length_px = int(round(length_um / um_per_px))
113
+ thick = max(2, h // 120)
114
+ m = int(margin_frac * w)
115
+ x1, y = w - m, h - m
116
+ x0 = x1 - length_px
117
+ cv2.rectangle(rgb, (x0 - 1, y - thick - 1), (x1 + 1, y + 1), (0, 0, 0), -1)
118
+ cv2.rectangle(rgb, (x0, y - thick), (x1, y), color, -1)
119
+ label = f"{length_um:g} um" # OpenCV fonts have no µ glyph
120
+ font_scale = max(0.4, w / 1100)
121
+ (tw, th), _ = cv2.getTextSize(label, cv2.FONT_HERSHEY_SIMPLEX, font_scale, max(1, thick // 2))
122
+ tx, ty = x0 + (length_px - tw) // 2, y - thick - 6
123
+ cv2.putText(rgb, label, (tx, ty), cv2.FONT_HERSHEY_SIMPLEX, font_scale, (0, 0, 0), max(2, thick), cv2.LINE_AA)
124
+ cv2.putText(rgb, label, (tx, ty), cv2.FONT_HERSHEY_SIMPLEX, font_scale, color, max(1, thick // 2), cv2.LINE_AA)
125
+ return rgb, length_um
ckp/single_cell/ckp_singlecell_GN_image_only.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b6296a99184ca50b2cb7f91bf2e5c06f11af4cd50eb0f32650ec4d28635380be
3
+ size 959483713
experiments/README.md ADDED
@@ -0,0 +1,74 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ # Baselines and ablations
2
+
3
+ Code for the evaluation of the released checkpoints and for the baseline and ablation models.
4
+ Run every command from the repository root; a GPU is used when available.
5
+
6
+ ```
7
+ experiments/
8
+ layout.py paths and split-manifest helpers
9
+ manifest_data.py data loader driven by a split manifest
10
+ ablation_models.py U-Net and S2F generator variants
11
+ losses.py reconstruction losses
12
+ configs.py training protocol and variants
13
+ train.py train one variant
14
+ evaluate.py evaluate checkpoints and trained runs on all manifests
15
+ run_all.py run the steps in order
16
+ splits/ split manifests
17
+ results/eval/ evaluation tables
18
+ ```
19
+
20
+ ## Data
21
+
22
+ The image pairs are available on Zenodo (doi: 10.5281/zenodo.18457879). Place them in `dataset/` or set
23
+ `S2F_DATASET_ROOT`. Each manifest in `splits/` lists one sample per row (folder relative to the dataset root,
24
+ condition, Young's modulus, pixel-size setting, colour-scale limit and substrate setting):
25
+
26
+ - `alltune_train` (280) and `alltune_val` (81): single-cell training and validation sets;
27
+ - `test_fibro_*`: independent single-cell test sets;
28
+ - `spheroid_train` (129) and `spheroid_val` (28).
29
+
30
+ ## Usage
31
+
32
+ ```bash
33
+ python -m experiments.run_all --steps eval_released
34
+ python -m experiments.run_all --steps train,eval_runs --variants s2f_no_substrate,unet_no_substrate --seeds 0,1
35
+ python -m experiments.train --variant unet --seed 0
36
+ ```
37
+
38
+ Runs are written to `experiments/runs/<variant>_seed<seed>/` and resume when restarted. Add
39
+ `--epochs 1 --max-batches 2` for a quick test.
40
+
41
+ ## Training protocol
42
+
43
+ All variants use the training and validation sets above, batch size 2, 1024 × 1024 px, the augmentations of
44
+ `data/augmentations.py` and Adam (β1 = 0.5, β2 = 0.999) with a cosine schedule and 10 % warm-up per phase.
45
+
46
+ | phase | epochs | reconstruction loss | other terms | lr |
47
+ |---|---|---|---|---|
48
+ | 1 | 100 | 100 × weighted MSE + soft Dice | 1 × adversarial | 1e-4 |
49
+ | 2 | 40 | 10 × RME | 1 × adversarial, 100 × traction-stress consistency | 1e-5 |
50
+
51
+ Phase 2 starts from the best phase-1 generator. In each phase the checkpoint with the lowest validation loss is
52
+ kept; the final model is the best phase-2 checkpoint.
53
+
54
+ ## Variants reported in the paper
55
+
56
+ | model | variant |
57
+ |---|---|
58
+ | U-Net | `unet_no_substrate` |
59
+ | pix2pix | `unet_gan_no_substrate` |
60
+ | S2F | `s2f_no_substrate` |
61
+ | S2F (+ substrate) | `s2f_staged` |
62
+ | without multi-scale input module | `s2f_no_substrate_no_multiscale` |
63
+ | without bottleneck context and attention modules | `s2f_no_substrate_bridge_plain` |
64
+ | without attention gates | `s2f_no_substrate_no_attention_gates` |
65
+ | without discriminator | `s2f_no_substrate_no_gan` |
66
+ | without traction-stress consistency loss | `s2f_staged_no_force` |
67
+
68
+ The input-free baseline (average training map) is evaluated with `python -m experiments.evaluate --meanmap`.
69
+ Other variants are listed in `configs.py`.
70
+
71
+ ## Outputs
72
+
73
+ `evaluate.py` computes per-image MSE, MS-SSIM, pixel-wise Pearson r, RME and mean traction stress (Pa), and writes
74
+ `results/eval/per_image.csv`, `summary.csv` and `model_params.csv`.
experiments/__init__.py ADDED
@@ -0,0 +1,5 @@
 
 
 
 
 
 
1
+ import os
2
+
3
+ # The bright-field TIFFs carry ImageJ/Fiji metadata tags (50838/50839) that OpenCV does not know and
4
+ # reports as warnings on every read. They are harmless; silence them before cv2 is imported anywhere.
5
+ os.environ.setdefault("OPENCV_LOG_LEVEL", "ERROR")
experiments/ablation_models.py ADDED
@@ -0,0 +1,73 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ """
2
+ Generators for the baselines and ablations (tanh output in [-1, 1]).
3
+
4
+ arch='s2f' S2FGenerator (models/s2f_model.py) with optional switches:
5
+ use_multi_scale_input False -> single 3x3 input conv
6
+ bridge 'cbam' (default) | 'cnn' (no CBAM) | 'plain' (no CBAM, Global Context
7
+ Module or hierarchical attention)
8
+ attention_gates False -> skip connections pass encoder features unchanged
9
+ arch='unet' U-Net (Ronneberger et al., 2015): 4 levels, 64-1024 channels, double 3x3 conv + BN + ReLU,
10
+ transposed-conv upsampling, concatenation skips.
11
+ """
12
+ import torch
13
+ import torch.nn as nn
14
+
15
+ from models.blocks import ResidualBlock
16
+ from models.s2f_model import PatchGANDiscriminator, S2FGenerator
17
+
18
+
19
+ class _PassSkip(nn.Module):
20
+ """Replaces an attention gate: returns the encoder skip feature unchanged."""
21
+ def forward(self, g, x):
22
+ return x
23
+
24
+
25
+ def _double_conv(i, o):
26
+ return nn.Sequential(nn.Conv2d(i, o, 3, padding=1, bias=False), nn.BatchNorm2d(o), nn.ReLU(inplace=True),
27
+ nn.Conv2d(o, o, 3, padding=1, bias=False), nn.BatchNorm2d(o), nn.ReLU(inplace=True))
28
+
29
+
30
+ class UNet(nn.Module):
31
+ def __init__(self, in_channels=1, out_channels=1, base=64):
32
+ super().__init__()
33
+ c = [base, base * 2, base * 4, base * 8, base * 16]
34
+ self.downs = nn.ModuleList([_double_conv(in_channels, c[0])] + [_double_conv(c[i], c[i + 1]) for i in range(3)])
35
+ self.pool = nn.MaxPool2d(2)
36
+ self.bottleneck = _double_conv(c[3], c[4])
37
+ self.ups = nn.ModuleList([nn.ConvTranspose2d(c[i + 1], c[i], 2, stride=2) for i in reversed(range(4))])
38
+ self.decs = nn.ModuleList([_double_conv(c[i] * 2, c[i]) for i in reversed(range(4))])
39
+ self.out = nn.Sequential(nn.Conv2d(c[0], out_channels, 1), nn.Tanh())
40
+
41
+ def forward(self, x):
42
+ skips = []
43
+ for d in self.downs:
44
+ x = d(x); skips.append(x); x = self.pool(x)
45
+ x = self.bottleneck(x)
46
+ for up, dec, s in zip(self.ups, self.decs, reversed(skips)):
47
+ x = dec(torch.cat([up(x), s], dim=1))
48
+ return self.out(x)
49
+
50
+
51
+ def build_generator(arch="s2f", in_channels=3, use_multi_scale_input=True, bridge="cbam",
52
+ attention_gates=True, **_):
53
+ if arch == "unet":
54
+ return UNet(in_channels=in_channels)
55
+ if arch != "s2f":
56
+ raise ValueError(f"unknown arch {arch}")
57
+ g = S2FGenerator(in_channels=in_channels, out_channels=1, img_size=1024,
58
+ bridge_type="cnn" if bridge in ("cnn", "plain") else "cbam",
59
+ use_multi_scale_input=use_multi_scale_input)
60
+ if bridge == "plain":
61
+ g.bridge = nn.Sequential(nn.Conv2d(512, 1024, 3, padding=2, dilation=2), nn.BatchNorm2d(1024),
62
+ nn.ReLU(inplace=True), ResidualBlock(1024, 1024))
63
+ if not attention_gates:
64
+ g.att4, g.att3, g.att2, g.att1 = _PassSkip(), _PassSkip(), _PassSkip(), _PassSkip()
65
+ return g
66
+
67
+
68
+ def build_discriminator(in_channels=3):
69
+ return PatchGANDiscriminator(in_channels=in_channels + 1, ndf=64, n_layers=3)
70
+
71
+
72
+ def n_params(module):
73
+ return sum(p.numel() for p in module.parameters())
experiments/configs.py ADDED
@@ -0,0 +1,85 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ """
2
+ Training protocol shared by the baseline and ablation runs, and the variants.
3
+
4
+ phase 1: weighted MSE + soft Dice (lambda_rec 100), lr 1e-4
5
+ phase 2: RME (lambda_rec 10) + traction-stress consistency (lambda_force 100), lr 1e-5,
6
+ starting from the best phase-1 generator
7
+ """
8
+ import copy
9
+
10
+ PROTOCOL = dict(
11
+ train_manifest="alltune_train",
12
+ val_manifest="alltune_val",
13
+ phases=[
14
+ dict(name="phase1", epochs=100, rec_loss="wmd", lambda_rec=100.0, lambda_force=0.0, g_lr=1e-4, d_lr=1e-4),
15
+ dict(name="phase2", epochs=40, rec_loss="rme", lambda_rec=10.0, lambda_force="from_variant", g_lr=1e-5, d_lr=1e-5),
16
+ ],
17
+ batch_size=2,
18
+ img_size=1024,
19
+ augment=True,
20
+ beta1=0.5, beta2=0.999,
21
+ warmup_frac=0.1,
22
+ lambda_gan=1.0,
23
+ lambda_force=100.0,
24
+ arch="s2f", in_channels=3, use_multi_scale_input=True, bridge="cbam", attention_gates=True,
25
+ substrate_mode="legacy",
26
+ input_mode="bf",
27
+ seed=0,
28
+ )
29
+
30
+ VARIANTS = {
31
+ # reference
32
+ "s2f_full": dict(),
33
+ # baselines
34
+ "unet": dict(arch="unet", lambda_gan=0.0),
35
+ "unet_gan": dict(arch="unet"),
36
+ "mask_only": dict(input_mode="mask"),
37
+ # loss ablations
38
+ "s2f_no_gan": dict(lambda_gan=0.0),
39
+ "s2f_no_force": dict(lambda_force=0.0, share_phase1_with="s2f_full"),
40
+ "s2f_gan_0.1": dict(lambda_gan=0.1),
41
+ "s2f_gan_5": dict(lambda_gan=5.0),
42
+ # input ablations
43
+ "s2f_no_substrate": dict(in_channels=1, substrate_mode="none"),
44
+ "s2f_nominal_substrate": dict(substrate_mode="nominal"),
45
+ # architecture ablations
46
+ "s2f_no_multiscale": dict(use_multi_scale_input=False),
47
+ "s2f_bridge_no_cbam": dict(bridge="cnn"),
48
+ "s2f_bridge_plain": dict(bridge="plain"),
49
+ "s2f_no_attention_gates": dict(attention_gates=False),
50
+ # bright-field only
51
+ "unet_no_substrate": dict(arch="unet", lambda_gan=0.0, in_channels=1, substrate_mode="none"),
52
+ "unet_gan_no_substrate": dict(arch="unet", in_channels=1, substrate_mode="none"),
53
+ "s2f_no_substrate_no_gan": dict(in_channels=1, substrate_mode="none", lambda_gan=0.0),
54
+ "s2f_no_substrate_no_multiscale": dict(in_channels=1, substrate_mode="none", use_multi_scale_input=False),
55
+ "s2f_no_substrate_bridge_plain": dict(in_channels=1, substrate_mode="none", bridge="plain"),
56
+ "s2f_no_substrate_no_attention_gates": dict(in_channels=1, substrate_mode="none", attention_gates=False),
57
+ # substrate channels added in phase 2 (phase 1 shared with s2f_no_substrate)
58
+ "s2f_staged": dict(share_phase1_with="s2f_no_substrate", expand_from_image_only=True),
59
+ "s2f_staged_no_force": dict(share_phase1_with="s2f_no_substrate", expand_from_image_only=True,
60
+ lambda_force=0.0),
61
+ }
62
+
63
+ PRIORITY = ["s2f_full", "unet", "unet_gan", "s2f_no_gan", "s2f_no_substrate", "s2f_no_force",
64
+ "s2f_no_attention_gates", "s2f_no_multiscale", "s2f_bridge_plain",
65
+ "s2f_bridge_no_cbam", "s2f_nominal_substrate", "s2f_gan_0.1", "s2f_gan_5"]
66
+
67
+
68
+ def get_config(variant, epochs=None, g_lr=None, d_lr=None, **overrides):
69
+ """epochs / g_lr / d_lr override every phase (smoke tests); other overrides are top-level keys."""
70
+ if variant not in VARIANTS:
71
+ raise KeyError(f"unknown variant '{variant}'. Options: {', '.join(VARIANTS)}")
72
+ cfg = copy.deepcopy(PROTOCOL)
73
+ cfg.update(VARIANTS[variant])
74
+ cfg.update({k: v for k, v in overrides.items() if v is not None})
75
+ cfg["variant"] = variant
76
+ if cfg["substrate_mode"] == "none":
77
+ cfg["in_channels"] = 1
78
+ for ph in cfg["phases"]:
79
+ if ph["lambda_force"] == "from_variant":
80
+ ph["lambda_force"] = cfg["lambda_force"]
81
+ for k, v in (("epochs", epochs), ("g_lr", g_lr), ("d_lr", d_lr)):
82
+ if v is not None:
83
+ ph[k] = v
84
+ cfg["epochs"] = sum(ph["epochs"] for ph in cfg["phases"]) # total, used to detect finished runs
85
+ return cfg
experiments/evaluate.py ADDED
@@ -0,0 +1,197 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ """
2
+ Evaluate checkpoints, baselines and trained runs on every split manifest.
3
+
4
+ python -m experiments.evaluate --released --meanmap # released checkpoints and input-free baseline
5
+ python -m experiments.evaluate --runs # experiments/runs/*/best_checkpoint.pth
6
+
7
+ Per-image metrics: MSE, MS-SSIM, pixel-wise Pearson r, RME, mean traction stress (Pa) and inference time.
8
+ Outputs: experiments/results/eval/per_image.csv and summary.csv.
9
+ """
10
+ import argparse
11
+ import glob
12
+ import json
13
+ import os
14
+ import time
15
+
16
+ import numpy as np
17
+ import pandas as pd
18
+ import torch
19
+
20
+ from experiments.ablation_models import build_generator, n_params
21
+ from experiments.layout import DEFAULT_DATASET_ROOT, RESULTS_DIR, RUNS_DIR, S2F_ROOT, list_manifests
22
+ from experiments.losses import PerImageWFMRMELoss
23
+ from experiments.manifest_data import make_loader
24
+ from models.s2f_model import create_s2f_model, create_settings_channels
25
+ from utils.metrics import TorchMetricsWrapper
26
+ from utils.substrate_settings import compute_settings_normalization
27
+
28
+ CONFIG_PATH = os.path.join(S2F_ROOT, "config", "substrate_settings.json")
29
+ SWEEP_KEYS = ["PDMS_1kPa_3um", "fibroblasts_PDMS", "PDMS_10kPa_3um"]
30
+
31
+
32
+ def released_models(device):
33
+ out = {}
34
+ g, _ = create_s2f_model(in_channels=3, model_type="s2f")
35
+ g.load_state_dict(torch.load(os.path.join(S2F_ROOT, "ckp/single_cell/ckp_singlecell_GN.pth"), map_location="cpu",
36
+ weights_only=False)["generator_state_dict"], strict=True)
37
+ out["released_singlecell"] = dict(model=g.to(device).eval(), kind="singlecell", in_channels=3, tanh=True)
38
+ g, _ = create_s2f_model(in_channels=1, model_type="s2f")
39
+ g.load_state_dict(torch.load(os.path.join(S2F_ROOT, "ckp/spheroid/ckp_spheroid_GN.pth"), map_location="cpu",
40
+ weights_only=False)["generator_state_dict"], strict=True)
41
+ out["released_spheroid_GN"] = dict(model=g.to(device).eval(), kind="spheroid", in_channels=1, tanh=True)
42
+ fn = os.path.join(S2F_ROOT, "ckp/spheroid/ckp_spheroid_FN.pth")
43
+ if os.path.exists(fn):
44
+ g, _ = create_s2f_model(in_channels=1, model_type="s2f_spheroid")
45
+ g.load_state_dict(torch.load(fn, map_location="cpu", weights_only=False)["model_state_dict"], strict=True)
46
+ g.set_output_mode(use_tanh=False)
47
+ out["supervised_spheroid_FN"] = dict(model=g.to(device).eval(), kind="spheroid", in_channels=1, tanh=False)
48
+ return out
49
+
50
+
51
+ def run_models(device, pattern):
52
+ out = {}
53
+ for p in sorted(glob.glob(pattern)):
54
+ h = os.path.join(os.path.dirname(p), "history.json")
55
+ ck = torch.load(p, map_location="cpu", weights_only=False)
56
+ cfg = ck["config"]
57
+ done = os.path.exists(h) and len(json.load(open(h))) >= cfg.get("epochs", 0)
58
+ if not done and not os.environ.get("S2F_EVAL_UNFINISHED"):
59
+ print(f" skipping unfinished run {os.path.basename(os.path.dirname(p))} (set S2F_EVAL_UNFINISHED=1 to include)")
60
+ continue
61
+ g = build_generator(**cfg); g.load_state_dict(ck["generator_state_dict"], strict=True)
62
+ name = os.path.basename(os.path.dirname(p))
63
+ out[name] = dict(model=g.to(device).eval(), kind="singlecell", in_channels=cfg["in_channels"], tanh=True,
64
+ substrate_mode=cfg["substrate_mode"], input_mode=cfg["input_mode"],
65
+ epoch=ck.get("epoch"), val_loss=ck.get("val_loss"))
66
+ return out
67
+
68
+
69
+ def mean_map(manifest, dataset_root):
70
+ acc, n = None, 0
71
+ for b in make_loader(manifest, dataset_root, batch_size=8, substrate_mode="none"):
72
+ acc = b[1].sum(0, keepdim=True) if acc is None else acc + b[1].sum(0, keepdim=True); n += b[1].size(0)
73
+ return acc / n
74
+
75
+
76
+ def evaluate_one(name, spec, manifest, dataset_root, device, mw, norm, substrate_mode, batch, mean_pred=None):
77
+ input_mode = spec.get("input_mode", "bf")
78
+ use_settings = spec.get("in_channels", 1) == 3
79
+ sm = substrate_mode if use_settings else "none"
80
+ forced = None
81
+ if sm and sm.startswith("force:"):
82
+ forced, sm = sm.split(":", 1)[1], "reference"
83
+ try:
84
+ loader = make_loader(manifest, dataset_root, batch_size=batch, substrate_mode=sm, input_mode=input_mode)
85
+ except FileNotFoundError as e:
86
+ print(f" [skip] {name} on {manifest}: {e}"); return []
87
+ rows_meta, rec, out, k = loader.dataset.rows, PerImageWFMRMELoss(), [], 0
88
+ with torch.no_grad():
89
+ for b in loader:
90
+ x, y = b[0].to(device), b[1].to(device)
91
+ t0 = time.time()
92
+ if mean_pred is not None:
93
+ p = mean_pred.to(device).expand_as(y)
94
+ else:
95
+ if use_settings:
96
+ meta = b[4]
97
+ if forced:
98
+ meta = dict(meta, substrate=[forced] * x.size(0))
99
+ x = torch.cat([x, create_settings_channels(meta, norm, device, x.shape, config_path=CONFIG_PATH)], 1)
100
+ p = spec["model"](x)
101
+ p = (p + 1) / 2 if spec.get("tanh", True) else p
102
+ dt = (time.time() - t0) / x.size(0)
103
+ for i in range(y.size(0)):
104
+ r = rows_meta[k]; k += 1
105
+ t, q = y[i:i + 1], p[i:i + 1]
106
+ yt = float(r.get("ythreshold_Pa") or (50 if "spheroid" in manifest else 500))
107
+ out.append({"model": name, "manifest": manifest, "substrate_mode": substrate_mode if use_settings else "n/a",
108
+ "sample_dir": r["sample_dir"], "set": r.get("set", ""), "condition": r.get("condition", ""),
109
+ "mse": mw.compute_mse(t, q), "ms_ssim": mw.compute_ms_ssim(t, q),
110
+ "pixel_r": float(np.corrcoef(t.flatten().cpu().numpy(), q.flatten().cpu().numpy())[0, 1]),
111
+ "rme": float(rec(q, t)), "mean_gt": float(t.mean()), "mean_pred": float(q.mean()),
112
+ "mean_gt_Pa": float(t.mean()) * yt, "mean_pred_Pa": float(q.mean()) * yt,
113
+ "gt_max": float(t.max()), "gt_frac_saturated": float((t >= 0.98).float().mean()),
114
+ "seconds_per_image": dt})
115
+ return out
116
+
117
+
118
+ def summarise(df):
119
+ df = df.assign(substrate_mode=df["substrate_mode"].fillna("none")) # "n/a" is read back from CSV as NaN
120
+ g = df.groupby(["model", "manifest", "substrate_mode"], dropna=False)
121
+ s = g.agg(n=("mse", "size"), **{f"{m}_{f}": (m, f) for m in ["mse", "ms_ssim", "pixel_r", "rme", "mean_gt_Pa",
122
+ "mean_pred_Pa", "gt_frac_saturated"] for f in ["mean", "std"]},
123
+ seconds_per_image=("seconds_per_image", "mean")).reset_index()
124
+ s["pred_over_gt"] = s["mean_pred_Pa_mean"] / s["mean_gt_Pa_mean"]
125
+ return s
126
+
127
+
128
+ def main():
129
+ ap = argparse.ArgumentParser(description=__doc__, formatter_class=argparse.RawDescriptionHelpFormatter)
130
+ ap.add_argument("--released", action="store_true", help="released single-cell + spheroid checkpoints")
131
+ ap.add_argument("--sweep", action="store_true", help="released single-cell model with 1 / 6 / 10 kPa settings")
132
+ ap.add_argument("--meanmap", action="store_true", help="input-free baseline (mean training map)")
133
+ ap.add_argument("--runs", nargs="?", const=os.path.join(RUNS_DIR, "*", "best_checkpoint.pth"), default=None,
134
+ help="glob of trained run checkpoints (default experiments/runs/*/best_checkpoint.pth)")
135
+ ap.add_argument("--manifests", default="", help="comma-separated manifest names (default: all in experiments/splits)")
136
+ ap.add_argument("--dataset-root", default=DEFAULT_DATASET_ROOT)
137
+ ap.add_argument("--out", default=os.path.join(RESULTS_DIR, "eval"))
138
+ ap.add_argument("--batch", type=int, default=2)
139
+ ap.add_argument("--device", default=None)
140
+ ap.add_argument("--run-modes", default=None,
141
+ help="substrate modes for trained runs with substrate channels, e.g. legacy,nominal (default: run config)")
142
+ a = ap.parse_args()
143
+ device = torch.device(a.device or ("cuda" if torch.cuda.is_available() else "cpu"))
144
+ mans = [m for m in (a.manifests.split(",") if a.manifests else list_manifests()) if m]
145
+ sc_mans = [m for m in mans if not m.startswith("spheroid") and m != "alltune_train" and m != "zenodo_v1_train"]
146
+ sph_mans = [m for m in mans if m.startswith("spheroid") and m != "spheroid_train"]
147
+ print(f"device {device}; single-cell manifests {sc_mans}; spheroid manifests {sph_mans}")
148
+ mw, norm = TorchMetricsWrapper(device=device), compute_settings_normalization(config_path=CONFIG_PATH)
149
+
150
+ models = {}
151
+ if a.released:
152
+ models.update(released_models(device))
153
+ if a.runs:
154
+ models.update(run_models(device, a.runs))
155
+ rows, params = [], []
156
+ for name, spec in models.items():
157
+ params.append({"model": name, "n_params_M": n_params(spec["model"]) / 1e6, "epoch": spec.get("epoch"),
158
+ "val_loss": spec.get("val_loss")})
159
+ targets = sc_mans if spec["kind"] == "singlecell" else sph_mans
160
+ modes = [spec.get("substrate_mode", "legacy")]
161
+ if a.run_modes and spec.get("in_channels", 1) == 3 and name not in ("released_singlecell",):
162
+ modes = [m for m in a.run_modes.split(",") if m]
163
+ if name == "released_singlecell":
164
+ modes = ["legacy", "nominal"] + ([f"force:{k}" for k in SWEEP_KEYS] if a.sweep else [])
165
+ for m in targets:
166
+ for sm in modes:
167
+ print(f" {name:28s} {m:28s} {sm}", flush=True)
168
+ rows += evaluate_one(name, spec, m, a.dataset_root, device, mw, norm, sm, a.batch)
169
+ if a.meanmap:
170
+ for train_m, targets, name in [("alltune_train", sc_mans, "baseline_mean_map_singlecell"),
171
+ ("spheroid_train", sph_mans, "baseline_mean_map_spheroid")]:
172
+ if train_m not in list_manifests():
173
+ continue
174
+ M = mean_map(train_m, a.dataset_root)
175
+ for m in targets:
176
+ print(f" {name:28s} {m}", flush=True)
177
+ rows += evaluate_one(name, {"in_channels": 1}, m, a.dataset_root, device, mw, norm, "n/a", a.batch, mean_pred=M)
178
+ os.makedirs(a.out, exist_ok=True)
179
+ new = pd.DataFrame(rows)
180
+ pi = os.path.join(a.out, "per_image.csv")
181
+ if os.path.exists(pi) and len(new): # keep rows of models not re-evaluated now
182
+ old = pd.read_csv(pi)
183
+ new = pd.concat([old[~old.model.isin(new.model.unique())], new], ignore_index=True)
184
+ if len(new):
185
+ new.to_csv(pi, index=False)
186
+ summarise(new).to_csv(os.path.join(a.out, "summary.csv"), index=False)
187
+ pp = os.path.join(a.out, "model_params.csv")
188
+ if params:
189
+ P = pd.DataFrame(params)
190
+ if os.path.exists(pp):
191
+ old = pd.read_csv(pp); P = pd.concat([old[~old.model.isin(P.model)], P], ignore_index=True)
192
+ P.to_csv(pp, index=False)
193
+ print(f"wrote {pi}, summary.csv, model_params.csv in {a.out}")
194
+
195
+
196
+ if __name__ == "__main__":
197
+ main()
experiments/layout.py ADDED
@@ -0,0 +1,26 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ """Paths and split-manifest helpers. Each manifest in experiments/splits/ lists one sample per row."""
2
+ import csv
3
+ import os
4
+
5
+ S2F_ROOT = os.path.dirname(os.path.dirname(os.path.abspath(__file__)))
6
+ DEFAULT_DATASET_ROOT = os.environ.get("S2F_DATASET_ROOT", os.path.join(S2F_ROOT, "dataset"))
7
+ SPLITS_DIR = os.environ.get("S2F_SPLITS_DIR", os.path.join(S2F_ROOT, "experiments", "splits"))
8
+ RUNS_DIR = os.environ.get("S2F_RUNS_DIR", os.path.join(S2F_ROOT, "experiments", "runs"))
9
+ RESULTS_DIR = os.environ.get("S2F_RESULTS_DIR", os.path.join(S2F_ROOT, "experiments", "results"))
10
+
11
+ MASK_NAMES = ("cell_mask.tif", "cell_mask.png", "mask.tif", "mask.png")
12
+
13
+
14
+ def read_manifest(path):
15
+ with open(path, newline="") as f:
16
+ return list(csv.DictReader(f))
17
+
18
+
19
+ def manifest_path(name):
20
+ return os.path.join(SPLITS_DIR, f"{name}.csv")
21
+
22
+
23
+ def list_manifests():
24
+ if not os.path.isdir(SPLITS_DIR):
25
+ return []
26
+ return sorted(os.path.splitext(f)[0] for f in os.listdir(SPLITS_DIR) if f.endswith(".csv"))
experiments/losses.py ADDED
@@ -0,0 +1,37 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ """
2
+ Reconstruction losses.
3
+
4
+ PerImageWFMRMELoss: relative magnitude error, each pixel weighted by its ground-truth magnitude divided by
5
+ the mean ground-truth magnitude of the same image.
6
+ WeightedMSEPlusDiceLoss: MSE with pixels above `threshold` weighted by 1 + pos_weight, plus a soft-Dice term.
7
+ """
8
+ import torch
9
+ import torch.nn as nn
10
+
11
+
12
+ class PerImageWFMRMELoss(nn.Module):
13
+ def __init__(self, eps=1e-6):
14
+ super().__init__()
15
+ self.eps = eps
16
+
17
+ def forward(self, pred, target):
18
+ t, p = target[:, 0], pred[:, 0]
19
+ rel = (p - t).abs() / (t + self.eps)
20
+ w = t / (t.mean(dim=(1, 2), keepdim=True) + self.eps)
21
+ return (rel * w).mean()
22
+
23
+
24
+ class WeightedMSEPlusDiceLoss(nn.Module):
25
+ def __init__(self, pos_weight=3.0, threshold=0.2, dice_weight=0.5):
26
+ super().__init__()
27
+ self.pos_weight, self.threshold, self.dice_weight = pos_weight, threshold, dice_weight
28
+
29
+ def forward(self, pred, target):
30
+ w = 1.0 + self.pos_weight * (target > self.threshold).float()
31
+ mse = (w * (pred - target) ** 2).mean()
32
+ p, t = pred.flatten(1), target.flatten(1)
33
+ dice = (2 * (p * t).sum(1) + 1e-6) / (p.sum(1) + t.sum(1) + 1e-6)
34
+ return mse + self.dice_weight * (1 - dice.mean())
35
+
36
+
37
+ REC_LOSSES = {"rme": PerImageWFMRMELoss, "wmd": WeightedMSEPlusDiceLoss}
experiments/manifest_data.py ADDED
@@ -0,0 +1,84 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ """
2
+ Manifest-based data loading with the preprocessing of data/cell_dataset.py.
3
+
4
+ substrate_mode (single-cell): 'legacy' (substrate setting used in training, default), 'nominal' (Young's modulus
5
+ and pixel size of each sample), 'reference' (6 kPa setting for every sample), 'none' (no substrate channels).
6
+ input_mode: 'bf' (bright-field image, default) or 'mask' (binary cell mask, cell_mask.tif/png in the sample folder).
7
+ """
8
+ import os
9
+
10
+ import numpy as np
11
+ import torch
12
+ from torch.utils.data import DataLoader
13
+
14
+ from data.cell_dataset import ImageDataset, load_image
15
+ from experiments.layout import DEFAULT_DATASET_ROOT, MASK_NAMES, manifest_path, read_manifest
16
+
17
+
18
+ def _find(folder, suffix=None, names=None):
19
+ for f in sorted(os.listdir(folder)):
20
+ if (suffix and f.endswith(suffix)) or (names and f in names):
21
+ return os.path.join(folder, f)
22
+ return None
23
+
24
+
25
+ def load_manifest_pairs(manifest, dataset_root=DEFAULT_DATASET_ROOT, img_size=1024,
26
+ substrate_mode="legacy", input_mode="bf"):
27
+ rows = read_manifest(manifest if os.path.isfile(manifest) else manifest_path(manifest))
28
+ pairs = []
29
+ for r in rows:
30
+ d = os.path.join(dataset_root, r["sample_dir"])
31
+ bf = _find(d, suffix="BF_001.tif")
32
+ hm = _find(d, suffix="_gray.jpg")
33
+ if bf is None or hm is None:
34
+ raise FileNotFoundError(f"missing BF/heatmap in {d}")
35
+ if input_mode == "mask":
36
+ mp = _find(d, names=MASK_NAMES)
37
+ if mp is None:
38
+ raise FileNotFoundError(f"input_mode='mask' but no {MASK_NAMES} in {d}")
39
+ x = (load_image(mp, (img_size, img_size)) > 0.5).astype(np.float32)
40
+ else:
41
+ x = load_image(bf, (img_size, img_size))
42
+ y = load_image(hm, (img_size, img_size))
43
+ if substrate_mode == "none":
44
+ pairs.append((x, y, (0, 0)))
45
+ continue
46
+ sub = {"legacy": r.get("substrate_legacy"), "nominal": r.get("substrate_nominal"),
47
+ "reference": "fibroblasts_PDMS"}[substrate_mode] or "fibroblasts_PDMS"
48
+ pairs.append((x, y, (0, 0), {"folder_name": os.path.basename(d), "substrate": sub,
49
+ "root_folder": os.path.dirname(r["sample_dir"]), "set": r.get("set", "")}))
50
+ return pairs, rows
51
+
52
+
53
+ def _worker_init(worker_id):
54
+ """Distinct, reproducible numpy seed per worker (augmentations use np.random). Module-level for Windows spawn."""
55
+ np.random.seed(torch.initial_seed() % 2 ** 32)
56
+
57
+
58
+ class _MaskDataset(ImageDataset):
59
+ """Re-binarise the input after augmentation (intensity augmentations are meaningless for masks)."""
60
+ def __getitem__(self, idx):
61
+ out = list(super().__getitem__(idx))
62
+ out[0] = (out[0] > 0.5).float()
63
+ return tuple(out)
64
+
65
+
66
+ def make_loader(manifest, dataset_root=DEFAULT_DATASET_ROOT, batch_size=2, img_size=1024, augment=False,
67
+ shuffle=False, substrate_mode="legacy", input_mode="bf", seed=None, num_workers=0):
68
+ pairs, rows = load_manifest_pairs(manifest, dataset_root, img_size, substrate_mode, input_mode)
69
+ transform = None
70
+ if augment:
71
+ from data.augmentations import AdvancedAugmentations
72
+ transform = AdvancedAugmentations((img_size, img_size))
73
+ cls = _MaskDataset if input_mode == "mask" else ImageDataset
74
+ ds = cls(pairs, transform=transform, channel_first=True, threshold=0.0,
75
+ return_metadata=substrate_mode != "none")
76
+ ds.rows = rows
77
+ g = None
78
+ if seed is not None:
79
+ g = torch.Generator(); g.manual_seed(seed)
80
+ if num_workers > 0: # workers run the augmentations so the GPU is not left waiting
81
+ return DataLoader(ds, batch_size=batch_size, shuffle=shuffle, generator=g, num_workers=num_workers,
82
+ persistent_workers=True, pin_memory=torch.cuda.is_available(),
83
+ worker_init_fn=_worker_init)
84
+ return DataLoader(ds, batch_size=batch_size, shuffle=shuffle, generator=g, num_workers=0)
experiments/results/eval/model_params.csv ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ model,n_params_M,epoch,val_loss
2
+ released_singlecell,77.002341,,
3
+ released_spheroid_GN,77.000613,,
4
+ supervised_spheroid_FN,11.783428,,
5
+ stage1_image_only,77.000613,,
6
+ s2f_full_seed0,77.002341,22.0,0.6845365777248289
7
+ s2f_full_seed1,77.002341,32.0,0.7641608729595091
8
+ s2f_no_force_seed0,77.002341,36.0,0.6944503726028814
9
+ s2f_no_force_seed1,77.002341,31.0,0.7536247052797457
10
+ s2f_no_gan_seed0,77.002341,21.0,0.721968437113413
11
+ s2f_no_gan_seed1,77.002341,34.0,0.7040372549033747
12
+ s2f_no_substrate_bridge_plain_seed0,51.928322,14.0,0.649271821103445
13
+ s2f_no_substrate_no_attention_gates_seed0,76.213165,23.0,0.63600116241269
14
+ s2f_no_substrate_no_gan_seed0,77.000613,25.0,0.598808929687593
15
+ s2f_no_substrate_no_gan_seed1,77.000613,38.0,0.6280873359703436
16
+ s2f_no_substrate_no_multiscale_seed0,76.994085,17.0,0.670633654768874
17
+ s2f_no_substrate_seed0,77.000613,23.0,0.6303678663765512
18
+ s2f_no_substrate_seed1,77.000613,17.0,0.6032634014036597
19
+ s2f_staged_no_force_seed0,77.002341,14.0,0.6439362328226973
20
+ s2f_staged_no_force_seed1,77.002341,19.0,0.6032002917150172
21
+ s2f_staged_seed0,77.002341,14.0,0.6465322782353657
22
+ s2f_staged_seed1,77.002341,19.0,0.6014741949918794
23
+ unet_gan_no_substrate_seed0,31.036481,21.0,0.6770522376386131
24
+ unet_gan_no_substrate_seed1,31.036481,1.0,0.6818016338639143
25
+ unet_gan_seed0,31.037633,18.0,0.7331220245942837
26
+ unet_gan_seed1,31.037633,24.0,0.8099774224002186
27
+ unet_no_substrate_seed0,31.036481,12.0,0.646111976809618
28
+ unet_no_substrate_seed1,31.036481,29.0,0.6637544072255855
29
+ unet_seed0,31.037633,21.0,0.7371067419284727
30
+ unet_seed1,31.037633,31.0,0.7615440138956395
experiments/results/eval/per_image.csv ADDED
The diff for this file is too large to render. See raw diff
 
experiments/results/eval/summary.csv ADDED
The diff for this file is too large to render. See raw diff
 
experiments/run_all.py ADDED
@@ -0,0 +1,93 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ """
2
+ Train and evaluate the baselines and ablations (run from the repository root).
3
+
4
+ python -m experiments.run_all --steps eval_released
5
+ python -m experiments.run_all --steps train,eval_runs --variants s2f_full,unet,unet_gan
6
+
7
+ steps:
8
+ eval_released released checkpoints and input-free baseline -> experiments/results/eval/
9
+ train train the listed variants, one job per GPU (--gpus); finished runs are skipped
10
+ eval_runs evaluate every experiments/runs/*/best_checkpoint.pth
11
+ """
12
+ import argparse
13
+ import json
14
+ import os
15
+ import subprocess
16
+ import sys
17
+ import time
18
+
19
+ from experiments.configs import PRIORITY, get_config
20
+ from experiments.layout import RUNS_DIR, S2F_ROOT
21
+
22
+
23
+ def sh(args):
24
+ print("\n$ " + " ".join(args), flush=True)
25
+ r = subprocess.run([sys.executable, "-m"] + args, cwd=S2F_ROOT)
26
+ if r.returncode:
27
+ sys.exit(r.returncode)
28
+
29
+
30
+ def finished(variant, seed):
31
+ h = os.path.join(RUNS_DIR, f"{variant}_seed{seed}", "history.json")
32
+ if not os.path.exists(h):
33
+ return False
34
+ return len(json.load(open(h))) >= get_config(variant)["epochs"]
35
+
36
+
37
+ def gpu_queue(queue, gpus, num_workers, extra=(), max_retries=2):
38
+ """Run training jobs in parallel, one per GPU. A failed job is re-queued and resumes from its last checkpoint."""
39
+ running, failed, tries = {}, [], {}
40
+ queue = list(queue)
41
+ while queue or running:
42
+ for gpu in gpus:
43
+ if gpu not in running and queue:
44
+ v, seed = queue.pop(0)
45
+ run_dir = os.path.join(RUNS_DIR, f"{v}_seed{seed}")
46
+ os.makedirs(run_dir, exist_ok=True)
47
+ log = open(os.path.join(run_dir, "train.log"), "a")
48
+ env = dict(os.environ, CUDA_DEVICE_ORDER="PCI_BUS_ID", CUDA_VISIBLE_DEVICES=gpu, PYTHONUNBUFFERED="1")
49
+ cmd = [sys.executable, "-X", "faulthandler", "-m", "experiments.train", "--variant", v, "--seed", seed,
50
+ "--resume", "--num-workers", num_workers] + list(extra)
51
+ running[gpu] = (subprocess.Popen(cmd, cwd=S2F_ROOT, env=env, stdout=log, stderr=subprocess.STDOUT), v, seed, log)
52
+ print(f"[{time.strftime('%H:%M')}] GPU {gpu}: started {v} seed {seed} (log {run_dir}/train.log)", flush=True)
53
+ time.sleep(10 if extra else 30)
54
+ for gpu, (proc, v, seed, log) in list(running.items()):
55
+ if proc.poll() is not None:
56
+ log.close(); del running[gpu]
57
+ if proc.returncode == 0:
58
+ print(f"[{time.strftime('%H:%M')}] GPU {gpu}: {v} seed {seed} finished", flush=True)
59
+ continue
60
+ tries[(v, seed)] = tries.get((v, seed), 0) + 1
61
+ if tries[(v, seed)] <= max_retries:
62
+ queue.insert(0, (v, seed))
63
+ print(f"[{time.strftime('%H:%M')}] GPU {gpu}: {v} seed {seed} failed (exit {proc.returncode}); "
64
+ f"resuming (retry {tries[(v, seed)]}/{max_retries})", flush=True)
65
+ else:
66
+ failed.append((v, seed))
67
+ print(f"[{time.strftime('%H:%M')}] GPU {gpu}: {v} seed {seed} failed (exit {proc.returncode}, see train.log)", flush=True)
68
+ if failed:
69
+ print(f"failed jobs: {failed}")
70
+
71
+
72
+ def main():
73
+ ap = argparse.ArgumentParser(description=__doc__, formatter_class=argparse.RawDescriptionHelpFormatter)
74
+ ap.add_argument("--steps", default="eval_released")
75
+ ap.add_argument("--variants", default=",".join(PRIORITY))
76
+ ap.add_argument("--seeds", default="0")
77
+ ap.add_argument("--gpus", default="0,1")
78
+ ap.add_argument("--num-workers", default="2")
79
+ ap.add_argument("--extra-train-args", default="", help="passed to experiments.train, e.g. '--epochs 1 --max-batches 2'")
80
+ a = ap.parse_args()
81
+ steps = a.steps.split(",")
82
+ if "eval_released" in steps:
83
+ sh(["experiments.evaluate", "--released", "--meanmap"])
84
+ if "train" in steps:
85
+ queue = [(v, s) for v in a.variants.split(",") for s in a.seeds.split(",") if not finished(v, int(s))]
86
+ print(f"{len(queue)} training jobs on GPUs {a.gpus}: {queue}")
87
+ gpu_queue(queue, a.gpus.split(","), a.num_workers, a.extra_train_args.split())
88
+ if "eval_runs" in steps:
89
+ sh(["experiments.evaluate", "--runs"])
90
+
91
+
92
+ if __name__ == "__main__":
93
+ main()
experiments/splits/.gitkeep ADDED
File without changes
experiments/splits/alltune_train.csv ADDED
@@ -0,0 +1,281 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ sample_dir,split,set,condition,cell_type,coating,young_Pa,tfm_pixelsize,ythreshold_Pa,legacy_folder,legacy_substrate_code,substrate_legacy,substrate_nominal,bf_md5
2
+ singlecell/train/Position_01_Fibros_SET_III_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_01_Fibros_SET_III_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,907943a24fccb1766d677a3ac2ca67fd
3
+ singlecell/train/Position_01_Fibros_SET_II_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_01_Fibros_SET_II_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,18fe8363f5d3319c62565051d9f1ac1d
4
+ singlecell/train/Position_01_Fibros_SET_IV_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_01_Fibros_SET_IV_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,edccb9abff5751736cda3cefff359695
5
+ singlecell/train/Position_01_Fibros_SET_V_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_01_Fibros_SET_V_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,b463c7b5c414d7c256d86795f1da15ec
6
+ singlecell/train/Position_02_Fibros_SET_III_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_02_Fibros_SET_III_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,428890b057f33cf2ab5b274925fd8758
7
+ singlecell/train/Position_02_Fibros_SET_II_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_02_Fibros_SET_II_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,173a5248d0bb9b4f0260b377078e710f
8
+ singlecell/train/Position_02_Fibros_SET_IV_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_02_Fibros_SET_IV_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,d51b239ff3bb09feb046381eb4c3e3fc
9
+ singlecell/train/Position_02_Fibros_SET_I_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_02_Fibros_SET_I_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,f25b4cb1efbbbc4432a0b15d2c43c61e
10
+ singlecell/train/Position_02_Fibros_SET_V_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_02_Fibros_SET_V_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,1241e9390202e14b3ba55872e093d060
11
+ singlecell/train/Position_03_Fibros_SET_II_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_03_Fibros_SET_II_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,6b5a9dccf76a0fc66e0fc7e13023471e
12
+ singlecell/train/Position_03_Fibros_SET_IV_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_03_Fibros_SET_IV_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,a9080d4bcfb4f29d058d4e165da11b62
13
+ singlecell/train/Position_03_Fibros_SET_I_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_03_Fibros_SET_I_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,43586564bd7e3ce6b9ef1d8c10ecaa24
14
+ singlecell/train/Position_03_Fibros_SET_V_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_03_Fibros_SET_V_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,abf9693c591e99de352a7a10200b8f5b
15
+ singlecell/train/Position_04_Fibros_SET_III_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_04_Fibros_SET_III_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,12028e118c60f672bba180cc301ad82c
16
+ singlecell/train/Position_04_Fibros_SET_II_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_04_Fibros_SET_II_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,c910c52daee16bd3a0707219b5abf085
17
+ singlecell/train/Position_04_Fibros_SET_IV_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_04_Fibros_SET_IV_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,a4e57a5f97f09ca08df5945559478acf
18
+ singlecell/train/Position_04_Fibros_SET_I_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_04_Fibros_SET_I_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,49d8f0f32b53fb1230e6c8fc7011ea10
19
+ singlecell/train/Position_04_Fibros_SET_V_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_04_Fibros_SET_V_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,f03f0058d3214e08c448babbbf6ba50e
20
+ singlecell/train/Position_05_Fibros_SET_II_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_05_Fibros_SET_II_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,38db8db89312b0c697fd4c3a29fd795b
21
+ singlecell/train/Position_05_Fibros_SET_IV_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_05_Fibros_SET_IV_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,8100e8dbe2353b41e2f5e5a37c4352be
22
+ singlecell/train/Position_05_Fibros_SET_I_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_05_Fibros_SET_I_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,2fb133cf9618c205bc14f785304cf6db
23
+ singlecell/train/Position_05_Fibros_SET_V_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_05_Fibros_SET_V_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,1f31ccdce8f928cf0e3a74e928c37a3b
24
+ singlecell/train/Position_06_Fibros_SET_III_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_06_Fibros_SET_III_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,7dc877a4829945a5ba3e4d0b65c597e4
25
+ singlecell/train/Position_06_Fibros_SET_II_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_06_Fibros_SET_II_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,edd237e4605db602813270f50cd70115
26
+ singlecell/train/Position_06_Fibros_SET_IV_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_06_Fibros_SET_IV_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,e66b998b2eca065394053bba989a6a47
27
+ singlecell/train/Position_06_Fibros_SET_I_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_06_Fibros_SET_I_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,a2a2ee01fac3ce8577314d79cb98bb7e
28
+ singlecell/train/Position_06_Fibros_SET_V_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_06_Fibros_SET_V_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,0111bb42f91fba4bb720ca9130f0c4d8
29
+ singlecell/train/Position_07_Fibros_SET_III_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_07_Fibros_SET_III_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,4c3869327bc98172ae17f1f1e12fe7ae
30
+ singlecell/train/Position_07_Fibros_SET_II_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_07_Fibros_SET_II_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,6e3e607da1f1b6743b2dcd699c5d594d
31
+ singlecell/train/Position_07_Fibros_SET_IV_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_07_Fibros_SET_IV_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,fcdd08a71c772b74acc9896e73e675ec
32
+ singlecell/train/Position_07_Fibros_SET_I_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_07_Fibros_SET_I_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,d84d1dc035292e1e843cf831a733705e
33
+ singlecell/train/Position_08_Fibros_SET_II_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_08_Fibros_SET_II_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,5942ec331106ee047166890f6f8e6d3f
34
+ singlecell/train/Position_08_Fibros_SET_IV_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_08_Fibros_SET_IV_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,f689b5b599e7823e0f94ed1818332d02
35
+ singlecell/train/Position_08_Fibros_SET_I_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_08_Fibros_SET_I_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,c959d59ea15b4077347712223e37a8a7
36
+ singlecell/train/Position_08_Fibros_SET_V_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_08_Fibros_SET_V_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,37c034cf0a243fbf4a80d9ee7ea3d92f
37
+ singlecell/train/Position_09_Fibros_SET_III_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_09_Fibros_SET_III_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,501d43cac495e43425132ecf80400d4e
38
+ singlecell/train/Position_09_Fibros_SET_II_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_09_Fibros_SET_II_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,749441f65be3652227477b621f7ab816
39
+ singlecell/train/Position_09_Fibros_SET_IV_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_09_Fibros_SET_IV_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,254f665021b7045a08c0ee16373cff73
40
+ singlecell/train/Position_09_Fibros_SET_I_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_09_Fibros_SET_I_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,e0b2d115867aa95c5cee7543d99e04af
41
+ singlecell/train/Position_09_Fibros_SET_V_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_09_Fibros_SET_V_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,956df9995c5a6fa67b5c14a1796a3b06
42
+ singlecell/train/Position_10_Fibros_SET_II_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_10_Fibros_SET_II_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,d98d25db8a2940d44e05e1784c982815
43
+ singlecell/train/Position_10_Fibros_SET_IV_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_10_Fibros_SET_IV_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,925cec4d0230e900c8d506b0fcd46e4c
44
+ singlecell/train/Position_10_Fibros_SET_I_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_10_Fibros_SET_I_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,28f7d2a33093283c365ef31249987adb
45
+ singlecell/train/Position_10_Fibros_SET_V_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_10_Fibros_SET_V_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,e8a8870dc47cca520bc132b1d38ca1d7
46
+ singlecell/train/Position_11_Fibros_SET_III_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_11_Fibros_SET_III_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,521be6524f516dcff355137b77688b8d
47
+ singlecell/train/Position_11_Fibros_SET_II_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_11_Fibros_SET_II_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,5d16540b8323501fc44f1a12ea1659e9
48
+ singlecell/train/Position_11_Fibros_SET_IV_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_11_Fibros_SET_IV_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,c4b484904a8f3986ae534202e8c1ef74
49
+ singlecell/train/Position_11_Fibros_SET_I_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_11_Fibros_SET_I_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,61f453c167ae62a7ae228cd3dac6fca5
50
+ singlecell/train/Position_11_Fibros_SET_V_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_11_Fibros_SET_V_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,cb2a80b347889b58c815fb00866aed72
51
+ singlecell/train/Position_12_Fibros_SET_II_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_12_Fibros_SET_II_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,d3d259a3727120f47e3bac955b2efa3d
52
+ singlecell/train/Position_12_Fibros_SET_IV_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_12_Fibros_SET_IV_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,77412ee9980f25ce6f9ffea78237fb3c
53
+ singlecell/train/Position_12_Fibros_SET_I_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_12_Fibros_SET_I_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,359d1d86355e162105bd2f0a6d01829e
54
+ singlecell/train/Position_12_Fibros_SET_V_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_12_Fibros_SET_V_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,c0a6e48229a9e0c7a4e69a92087a4670
55
+ singlecell/train/Position_13_Fibros_SET_III_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_13_Fibros_SET_III_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,88fc451773febe6945c3a642530eace1
56
+ singlecell/train/Position_13_Fibros_SET_II_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_13_Fibros_SET_II_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,9bcb3411b1cd1a634ea0e2f5d9be3ce8
57
+ singlecell/train/Position_13_Fibros_SET_IV_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_13_Fibros_SET_IV_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,4ea5567c7a28390a4f98426c000c0325
58
+ singlecell/train/Position_13_Fibros_SET_I_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_13_Fibros_SET_I_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,766a6b35ed896bfede13d256befa0bda
59
+ singlecell/train/Position_13_Fibros_SET_V_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_13_Fibros_SET_V_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,b557021d45a7bd2f9761b74014e48ece
60
+ singlecell/train/Position_14_Fibros_SET_III_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_14_Fibros_SET_III_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,3239fae9f42d6de790ef5aead2d5a0aa
61
+ singlecell/train/Position_14_Fibros_SET_II_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_14_Fibros_SET_II_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,41c522cc0b46dd655f836f7122ebab27
62
+ singlecell/train/Position_14_Fibros_SET_IV_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_14_Fibros_SET_IV_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,3fea8f256d39c166156a93ff98e9e870
63
+ singlecell/train/Position_14_Fibros_SET_V_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_14_Fibros_SET_V_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,95ca8945e9cafbe080281e56ef54f989
64
+ singlecell/train/Position_15_Fibros_SET_III_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_15_Fibros_SET_III_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,699e4a3c0629a7cd76390f45f3a7227d
65
+ singlecell/train/Position_15_Fibros_SET_II_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_15_Fibros_SET_II_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,ffbaf88fa23d6b9fe76e827d3f472d46
66
+ singlecell/train/Position_15_Fibros_SET_IV_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_15_Fibros_SET_IV_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,8d74378fdb124bf3e9bf8e84ab74b36f
67
+ singlecell/train/Position_15_Fibros_SET_I_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_15_Fibros_SET_I_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,a943fa9724f19d47d45cbeedd00f3690
68
+ singlecell/train/Position_15_Fibros_SET_V_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_15_Fibros_SET_V_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,db744d39b013e22e44f85194d719aaaf
69
+ singlecell/train/Position_16_Fibros_SET_II_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_16_Fibros_SET_II_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,0ac3a76d7413c16a63d5661146efc2d6
70
+ singlecell/train/Position_16_Fibros_SET_IV_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_16_Fibros_SET_IV_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,f8ce2e3a7fb23f54574e70953b14eaf7
71
+ singlecell/train/Position_16_Fibros_SET_V_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_16_Fibros_SET_V_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,76f26bbc9a893e521250b69e4321317d
72
+ singlecell/train/Position_17_Fibros_SET_III_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_17_Fibros_SET_III_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,35c37de14dd46c50a83a84d067c3fc66
73
+ singlecell/train/Position_17_Fibros_SET_II_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_17_Fibros_SET_II_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,93b40ac00d3a3fe0b311b97bab6f14de
74
+ singlecell/train/Position_17_Fibros_SET_IV_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_17_Fibros_SET_IV_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,c19b52c747cd203312acbd358a58ce2c
75
+ singlecell/train/Position_17_Fibros_SET_I_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_17_Fibros_SET_I_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,3e13a958536f4fcb0fadb40e7ce1fa80
76
+ singlecell/train/Position_17_Fibros_SET_V_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_17_Fibros_SET_V_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,92268e5891a97662c06b4dfac8207f86
77
+ singlecell/train/Position_18_Fibros_SET_III_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_18_Fibros_SET_III_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,2c69ee8ca32f208262ec9cace5da24b9
78
+ singlecell/train/Position_18_Fibros_SET_II_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_18_Fibros_SET_II_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,fbc32a9af174431444f1990276f3da7a
79
+ singlecell/train/Position_18_Fibros_SET_IV_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_18_Fibros_SET_IV_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,f6ed1b4421792e801f06f0ddd6938363
80
+ singlecell/train/Position_18_Fibros_SET_I_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_18_Fibros_SET_I_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,4b1f67971e024f1f5a9b9a3942a2b048
81
+ singlecell/train/Position_18_Fibros_SET_V_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_18_Fibros_SET_V_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,17c949f42623275447396440dacc7663
82
+ singlecell/train/Position_19_Fibros_SET_III_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_19_Fibros_SET_III_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,ef5ae47211c78bfc90b409dfb2364f2c
83
+ singlecell/train/Position_19_Fibros_SET_II_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_19_Fibros_SET_II_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,bc4e6174ad59b68a29c9afd11d54cf74
84
+ singlecell/train/Position_19_Fibros_SET_IV_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_19_Fibros_SET_IV_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,54cf3b60b9458b37b049b2b55110c4c4
85
+ singlecell/train/Position_19_Fibros_SET_I_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_19_Fibros_SET_I_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,e850f79c83798113d3c0ccbaf16333fb
86
+ singlecell/train/Position_19_Fibros_SET_V_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_19_Fibros_SET_V_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,c6d7ff4721172ea3b40a356a8bdc68a0
87
+ singlecell/train/Position_20_Fibros_SET_III_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_20_Fibros_SET_III_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,cd1e97675b5786c98e2e80aa35b5720a
88
+ singlecell/train/Position_20_Fibros_SET_II_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_20_Fibros_SET_II_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,f2e687370044da85deb4fcc594f8b817
89
+ singlecell/train/Position_20_Fibros_SET_IV_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_20_Fibros_SET_IV_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,829aa02bd2a3562c463b4b73116e1ea8
90
+ singlecell/train/Position_20_Fibros_SET_I_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_20_Fibros_SET_I_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,94b097dea0e2d35128c551027c8aa349
91
+ singlecell/train/Position_20_Fibros_SET_V_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_20_Fibros_SET_V_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,b71109d768845c8721e578befa03e7ab
92
+ singlecell/train/Position_21_Fibros_SET_III_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_21_Fibros_SET_III_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,5ac5f25f551e83fb635571c14c787dbe
93
+ singlecell/train/Position_21_Fibros_SET_II_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_21_Fibros_SET_II_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,62bb2ba31a2995dea84c70d11057cd38
94
+ singlecell/train/Position_21_Fibros_SET_IV_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_21_Fibros_SET_IV_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,ced60105efb44f700d01660cf87b8280
95
+ singlecell/train/Position_21_Fibros_SET_I_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_21_Fibros_SET_I_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,2a6cd457df6c67764aee46c8a81989c8
96
+ singlecell/train/Position_21_Fibros_SET_V_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_21_Fibros_SET_V_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,6da902805a70e8e3612d2b37e0f9fee4
97
+ singlecell/train/Position_22_Fibros_SET_II_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_22_Fibros_SET_II_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,a0311f390aa0cefb7e759cac064067d0
98
+ singlecell/train/Position_22_Fibros_SET_IV_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_22_Fibros_SET_IV_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,5fb1e844e16338c47a4c5d44193b813e
99
+ singlecell/train/Position_22_Fibros_SET_V_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_22_Fibros_SET_V_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,f410176deaab3a82f4d7323dae2aef52
100
+ singlecell/train/Position_23_Fibros_SET_III_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_23_Fibros_SET_III_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,4c45c900810ca9232da21293f6943e32
101
+ singlecell/train/Position_23_Fibros_SET_II_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_23_Fibros_SET_II_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,e5f2fc6fd472f12e89be76a70ac42694
102
+ singlecell/train/Position_23_Fibros_SET_IV_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_23_Fibros_SET_IV_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,910d22961cc5657adfb437bde05dad45
103
+ singlecell/train/Position_23_Fibros_SET_I_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_23_Fibros_SET_I_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,bf1555e5887bd12fa4b405242e44815a
104
+ singlecell/train/Position_23_Fibros_SET_V_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_23_Fibros_SET_V_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,e0189cbbb3671a4fa238a6006101e74e
105
+ singlecell/train/Position_24_Fibros_SET_III_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_24_Fibros_SET_III_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,f64aa3bae2dd242171cb9a999d0ede4a
106
+ singlecell/train/Position_24_Fibros_SET_II_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_24_Fibros_SET_II_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,8018a2a5fb0142eb1adfab91b0f60e80
107
+ singlecell/train/Position_24_Fibros_SET_IV_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_24_Fibros_SET_IV_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,dd65336a4c1471bc1db009a6fd195c00
108
+ singlecell/train/Position_24_Fibros_SET_V_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_24_Fibros_SET_V_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,39139c164c3dea2f8587e59271341ba7
109
+ singlecell/train/Position_25_Fibros_SET_III_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_25_Fibros_SET_III_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,6ae7bf05e64b0ccfc0e0c9c97f3d51ba
110
+ singlecell/train/Position_25_Fibros_SET_II_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_25_Fibros_SET_II_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,b35ef55641a560f0434d08feeae20bdf
111
+ singlecell/train/Position_25_Fibros_SET_IV_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_25_Fibros_SET_IV_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,32236fcd5f14d0cfd07a0b38b74fcc7f
112
+ singlecell/train/Position_25_Fibros_SET_I_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_25_Fibros_SET_I_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,740957b643467b8e2780eefa54a41ad9
113
+ singlecell/train/Position_25_Fibros_SET_V_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_25_Fibros_SET_V_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,032e400dacb6923e7744d1df7f085fcf
114
+ singlecell/train/Position_26_Fibros_SET_III_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_26_Fibros_SET_III_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,61e0f12bc3405209b7fb44c5e4680d06
115
+ singlecell/train/Position_26_Fibros_SET_II_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_26_Fibros_SET_II_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,94141c9b1b5298f954863951f32880d0
116
+ singlecell/train/Position_26_Fibros_SET_IV_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_26_Fibros_SET_IV_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,45450e1fc3e9882f11d4428241b930ec
117
+ singlecell/train/Position_26_Fibros_SET_V_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_26_Fibros_SET_V_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,227e83ef232c91a5225876b4ef9439f6
118
+ singlecell/train/Position_27_Fibros_SET_II_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_27_Fibros_SET_II_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,65330592991a965194525856b08385f5
119
+ singlecell/train/Position_27_Fibros_SET_IV_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_27_Fibros_SET_IV_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,740a81d38f1208e6fcefd00f9edc9018
120
+ singlecell/train/Position_27_Fibros_SET_V_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_27_Fibros_SET_V_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,bf81536c63f480fd68114b4b4ffbea0f
121
+ singlecell/train/Position_28_Fibros_SET_II_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_28_Fibros_SET_II_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,eefc4086ed1d8f0df14f07f350a81772
122
+ singlecell/train/Position_28_Fibros_SET_IV_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_28_Fibros_SET_IV_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,02a328c339ac8004b6ea341c7066f10d
123
+ singlecell/train/Position_28_Fibros_SET_I_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_28_Fibros_SET_I_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,e37e6d8a5fb2908a20e15743eb185b80
124
+ singlecell/train/Position_28_Fibros_SET_V_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_28_Fibros_SET_V_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,b87cf42217d259665182fdf06fc74e79
125
+ singlecell/train/Position_29_Fibros_SET_III_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_29_Fibros_SET_III_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,85025c3e095d82d35bde2b6c9c7211c8
126
+ singlecell/train/Position_29_Fibros_SET_II_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_29_Fibros_SET_II_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,2d2867a8d21786b79f511e0ca2412d53
127
+ singlecell/train/Position_29_Fibros_SET_IV_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_29_Fibros_SET_IV_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,c758f80c5629b61bba6776e4100130ef
128
+ singlecell/train/Position_29_Fibros_SET_I_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_29_Fibros_SET_I_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,bb007c2e11a937db5825b4c2eb53e5be
129
+ singlecell/train/Position_29_Fibros_SET_V_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_29_Fibros_SET_V_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,0784871001ec4d32ab334aa1d5197bc1
130
+ singlecell/train/Position_30_Fibros_SET_III_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_30_Fibros_SET_III_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,dbdd58554ebbba82f9ea34fc6a815933
131
+ singlecell/train/Position_30_Fibros_SET_II_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_30_Fibros_SET_II_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,684c63918ed7a5b74fdfd4766ac1b542
132
+ singlecell/train/Position_30_Fibros_SET_IV_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_30_Fibros_SET_IV_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,20c4cef1cae9ba1494d976e479b0df17
133
+ singlecell/train/Position_30_Fibros_SET_I_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_30_Fibros_SET_I_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,549b7c558429ccf07a7baf582ca06a6f
134
+ singlecell/train/Position_30_Fibros_SET_V_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_30_Fibros_SET_V_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,c590c7106786c354cd4c0094bb5d452e
135
+ singlecell/train/Position_31_Fibros_SET_III_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_31_Fibros_SET_III_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,84f4f90fa00610b7022ab5aa35b38f4a
136
+ singlecell/train/Position_31_Fibros_SET_II_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_31_Fibros_SET_II_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,f79625662c6c9ed5c514f3074b72990c
137
+ singlecell/train/Position_31_Fibros_SET_IV_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_31_Fibros_SET_IV_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,b7ba4d59931279e8128a306b22fb9add
138
+ singlecell/train/Position_31_Fibros_SET_V_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_31_Fibros_SET_V_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,cfd3a58c50f71cd5c7c3a04ae405fe85
139
+ singlecell/train/Position_32_Fibros_SET_III_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_32_Fibros_SET_III_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,5dad2ad325c5a7ece0f9c8589e5ffd89
140
+ singlecell/train/Position_32_Fibros_SET_II_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_32_Fibros_SET_II_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,68d298a4a9569850a4e4463475cc3d50
141
+ singlecell/train/Position_32_Fibros_SET_IV_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_32_Fibros_SET_IV_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,6269dbd518112aea594098095546666a
142
+ singlecell/train/Position_32_Fibros_SET_I_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_32_Fibros_SET_I_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,98c337a537308fa4296898241ec0e043
143
+ singlecell/train/Position_32_Fibros_SET_V_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_32_Fibros_SET_V_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,b19d096efd988816dd9f6cf9391cf0f1
144
+ singlecell/train/Position_33_Fibros_SET_III_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_33_Fibros_SET_III_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,9173bd6adbf24be2ce564170ac7c4630
145
+ singlecell/train/Position_33_Fibros_SET_II_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_33_Fibros_SET_II_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,35332c468d553ca67557bc015ef9226c
146
+ singlecell/train/Position_33_Fibros_SET_IV_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_33_Fibros_SET_IV_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,e3ffa27e2017e8a1aadb7b39289d5ba7
147
+ singlecell/train/Position_33_Fibros_SET_I_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_33_Fibros_SET_I_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,e335f8f756b4eb6a0412b5f047820f1f
148
+ singlecell/train/Position_33_Fibros_SET_V_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_33_Fibros_SET_V_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,e51dbe4e2297bb67db120a1c2889e0ed
149
+ singlecell/train/Position_34_Fibros_SET_III_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_34_Fibros_SET_III_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,c29020f3dc4b7c3c32f8e1c198f0c3f9
150
+ singlecell/train/Position_34_Fibros_SET_II_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_34_Fibros_SET_II_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,8231b6bb048a6e0629de2785e72594ec
151
+ singlecell/train/Position_34_Fibros_SET_IV_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_34_Fibros_SET_IV_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,8c9bb48eb733e5436ae3f9ddfbe03e38
152
+ singlecell/train/Position_34_Fibros_SET_I_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_34_Fibros_SET_I_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,53cc8285500436e31940e817f6a9bb1c
153
+ singlecell/train/Position_34_Fibros_SET_V_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_34_Fibros_SET_V_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,f04b37e29e73c66a2e6ff85748eb5644
154
+ singlecell/train/Position_35_Fibros_SET_III_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_35_Fibros_SET_III_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,0b755a22cb26e0e5577b67cd05fdca86
155
+ singlecell/train/Position_35_Fibros_SET_II_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_35_Fibros_SET_II_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,81d246d36e24dfae342aaffff16c20e0
156
+ singlecell/train/Position_35_Fibros_SET_IV_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_35_Fibros_SET_IV_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,0e706ce14275d6aaa7ee06044f22c999
157
+ singlecell/train/Position_35_Fibros_SET_I_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_35_Fibros_SET_I_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,79d75d349432b2b76c163aa840b99a29
158
+ singlecell/train/Position_35_Fibros_SET_V_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_35_Fibros_SET_V_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,d8295b2c1b3883c683ee7731a99cf4af
159
+ singlecell/train/Position_36_Fibros_SET_III_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_36_Fibros_SET_III_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,3402fdec3e5dfea3dd8d9a01e376454c
160
+ singlecell/train/Position_36_Fibros_SET_IV_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_36_Fibros_SET_IV_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,f784b8506bcd0638d2d87d190cc1eaad
161
+ singlecell/train/Position_36_Fibros_SET_I_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_36_Fibros_SET_I_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,4a684ddddce254006aecb1b6794c6827
162
+ singlecell/train/Position_36_Fibros_SET_V_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_36_Fibros_SET_V_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,5a707f8bf7b1cd274791c113a5d57e4d
163
+ singlecell/train/Position_37_Fibros_SET_III_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_37_Fibros_SET_III_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,7e3724a85418a92cae55495ec5c199be
164
+ singlecell/train/Position_37_Fibros_SET_II_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_37_Fibros_SET_II_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,d34eca1f300278894d33404c55ed607d
165
+ singlecell/train/Position_37_Fibros_SET_IV_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_37_Fibros_SET_IV_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,a687c531e35f6d09374c5ae16bab6aa7
166
+ singlecell/train/Position_37_Fibros_SET_I_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_37_Fibros_SET_I_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,44a25bd354e4ff1d305f64d91e1f5af2
167
+ singlecell/train/Position_37_Fibros_SET_V_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_37_Fibros_SET_V_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,7d2aab8d540405410cec2abd66aa4bd4
168
+ singlecell/train/Position_38_Fibros_SET_II_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_38_Fibros_SET_II_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,a6b8820d9251148a46e7ca7b089cdb12
169
+ singlecell/train/Position_38_Fibros_SET_IV_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_38_Fibros_SET_IV_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,27aea07350351f49c2da412ebc3a8fac
170
+ singlecell/train/Position_38_Fibros_SET_I_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_38_Fibros_SET_I_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,16fa90069bd63da214c3dd70d8e3144e
171
+ singlecell/train/Position_38_Fibros_SET_V_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_38_Fibros_SET_V_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,aebe9a4bb4bea574e410d95496da1564
172
+ singlecell/train/Position_39_Fibros_SET_III_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_39_Fibros_SET_III_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,dfc72ee2dd7b9e8b26a96c58a9b72d7a
173
+ singlecell/train/Position_39_Fibros_SET_II_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_39_Fibros_SET_II_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,a661425f19d6de4d5a9b8d58b222b2f7
174
+ singlecell/train/Position_39_Fibros_SET_IV_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_39_Fibros_SET_IV_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,6d53b26a88c6437be16a993523031484
175
+ singlecell/train/Position_39_Fibros_SET_I_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_39_Fibros_SET_I_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,071550e1ae296492b93bea6f0d08cb46
176
+ singlecell/train/Position_39_Fibros_SET_V_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_39_Fibros_SET_V_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,cb4319c4c4dc983b5066a9ba07a20587
177
+ singlecell/train/Position_40_Fibros_SET_III_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_40_Fibros_SET_III_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,ea1e6e7efeec098c3c5a02db6f6ba331
178
+ singlecell/train/Position_40_Fibros_SET_II_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_40_Fibros_SET_II_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,c975ea6fff75bcb82fe60356967e00b8
179
+ singlecell/train/Position_40_Fibros_SET_IV_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_40_Fibros_SET_IV_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,0a5c1cc6b25b63bd2c6b66645991ef3d
180
+ singlecell/train/Position_40_Fibros_SET_I_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_40_Fibros_SET_I_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,4bfdd7a273eff050bf4985d761f990e6
181
+ singlecell/train/Position_40_Fibros_SET_V_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_40_Fibros_SET_V_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,99b91378a531dbe58833113fbc01ff7f
182
+ singlecell/train/Position_41_Fibros_SET_III_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_41_Fibros_SET_III_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,b32e88d200845e8f150ab86078430437
183
+ singlecell/train/Position_41_Fibros_SET_II_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_41_Fibros_SET_II_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,d0c077505d05cf702ceaac21e64c0c42
184
+ singlecell/train/Position_41_Fibros_SET_IV_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_41_Fibros_SET_IV_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,9829d54c8a39a7c432fbd7e317cc2089
185
+ singlecell/train/Position_41_Fibros_SET_I_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_41_Fibros_SET_I_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,21de635ae01b66763ba6dba3e07d7b55
186
+ singlecell/train/Position_41_Fibros_SET_V_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_41_Fibros_SET_V_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,501db3aad6dc5d068f3237e3dcc26bf5
187
+ singlecell/train/Position_42_Fibros_SET_II_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_42_Fibros_SET_II_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,7c3bc9a254783887428533d2bddd3b61
188
+ singlecell/train/Position_42_Fibros_SET_IV_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_42_Fibros_SET_IV_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,727940eccfe7262526317950ecaffe0a
189
+ singlecell/train/Position_42_Fibros_SET_I_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_42_Fibros_SET_I_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,f5eb042a3df1c1f7082b261a5c81ff4f
190
+ singlecell/train/Position_42_Fibros_SET_V_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_42_Fibros_SET_V_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,4142a8c2568404426b1ff054e1ac9dfd
191
+ singlecell/train/Position_43_Fibros_SET_II_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_43_Fibros_SET_II_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,34c58c313e8a07ac10124415dc2f565e
192
+ singlecell/train/Position_43_Fibros_SET_IV_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_43_Fibros_SET_IV_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,1b24e744f08aee358d2b93f0fe373348
193
+ singlecell/train/Position_43_Fibros_SET_I_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_43_Fibros_SET_I_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,a927bbf35e8680d8324166aefd40f476
194
+ singlecell/train/Position_43_Fibros_SET_V_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_43_Fibros_SET_V_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,e172341cbe15de2d16b9149db36fd300
195
+ singlecell/train/Position_44_Fibros_SET_II_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_44_Fibros_SET_II_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,06a1a7f0b61967643ee4a9d5c45d1d48
196
+ singlecell/train/Position_44_Fibros_SET_IV_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_44_Fibros_SET_IV_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,cf6bebb668ac1aef788c4fe93c1bd73a
197
+ singlecell/train/Position_44_Fibros_SET_I_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_44_Fibros_SET_I_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,9c73c1f6246690ffd1f9410c7df9470f
198
+ singlecell/train/Position_44_Fibros_SET_V_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_44_Fibros_SET_V_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,aade2788ae6ad3d83999833d76f0abae
199
+ singlecell/train/Position_45_Fibros_SET_II_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_45_Fibros_SET_II_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,e7fba4934bd8c6e43629804ffacf16a9
200
+ singlecell/train/Position_45_Fibros_SET_I_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_45_Fibros_SET_I_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,f7a2e887cd705fe5c7a4035026bc63e7
201
+ singlecell/train/Position_45_Fibros_SET_V_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_45_Fibros_SET_V_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,5e3283f423b591bfd6b1e1ae6f14f593
202
+ singlecell/train/Position_46_Fibros_SET_II_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_46_Fibros_SET_II_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,40c7167b5c18d34ebe41de327d386ffe
203
+ singlecell/train/Position_46_Fibros_SET_I_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_46_Fibros_SET_I_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,e217a88172193395a688b8281ba1d634
204
+ singlecell/train/Position_46_Fibros_SET_V_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_46_Fibros_SET_V_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,7746be74f5a3c4933cd699f2e50337f6
205
+ singlecell/train/Position_47_Fibros_SET_II_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_47_Fibros_SET_II_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,c80d3ba162c5d20391df345c332a7965
206
+ singlecell/train/Position_47_Fibros_SET_I_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_47_Fibros_SET_I_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,8b21d6c339c213f59b3bc2ac05e23cb9
207
+ singlecell/train/Position_47_Fibros_SET_V_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_47_Fibros_SET_V_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,eb5e7340661fba1a16c19ab6601bab8d
208
+ singlecell/train/Position_48_Fibros_SET_II_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_48_Fibros_SET_II_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,a1ed82b53c6868830cc54f82619de882
209
+ singlecell/train/Position_48_Fibros_SET_I_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_48_Fibros_SET_I_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,619c69c6e8e97a3c1ffe76f670543104
210
+ singlecell/train/Position_48_Fibros_SET_V_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_48_Fibros_SET_V_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,a83b184eb0b2ed66bf3ebb317976740d
211
+ singlecell/train/Position_49_Fibros_SET_II_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_49_Fibros_SET_II_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,b59024bb2ea72244bd460650d7e19a2b
212
+ singlecell/train/Position_49_Fibros_SET_V_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_49_Fibros_SET_V_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,f7fa6f715b0510ca224325f6427de183
213
+ singlecell/train/Position_50_Fibros_SET_II_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_50_Fibros_SET_II_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,12dd15fa10362e5dc4a6ffbe145c90d3
214
+ singlecell/train/Position_50_Fibros_SET_I_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_50_Fibros_SET_I_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,cd637f41b52a579f34dac00c2e791015
215
+ singlecell/train/Position_50_Fibros_SET_V_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_50_Fibros_SET_V_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,10bd06e993988f7700a6c6d5195488fa
216
+ singlecell/train/Position_51_Fibros_SET_II_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_51_Fibros_SET_II_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,5bb6c0a3a623e0502f97e3831f3ecf8c
217
+ singlecell/train/Position_51_Fibros_SET_V_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_51_Fibros_SET_V_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,8c04b4b0ee3dd805ccdf0465b51bbb7c
218
+ singlecell/train/Position_52_Fibros_SET_II_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_52_Fibros_SET_II_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,5418f0066f886d3fa310a91d4ef5067d
219
+ singlecell/train/Position_52_Fibros_SET_V_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_52_Fibros_SET_V_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,7a8250df51a482d53bbed02405e4e048
220
+ singlecell/train/Position_53_Fibros_SET_II_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_53_Fibros_SET_II_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,151c402acbf619fd7a9c22d1d8bdc247
221
+ singlecell/train/Position_53_Fibros_SET_V_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_53_Fibros_SET_V_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,859d14e95b8283b8cfb641b7aa514384
222
+ singlecell/train/Position_54_Fibros_SET_II_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_54_Fibros_SET_II_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,e55ac86bc98ff779c32741fa22dd3304
223
+ singlecell/train/Position_54_Fibros_SET_V_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_54_Fibros_SET_V_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,673af811a279c8cdf329006974374a52
224
+ singlecell/train/Position_55_Fibros_SET_II_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_55_Fibros_SET_II_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,c46fc425aa0659d18c753a3e807ef380
225
+ singlecell/train/Position_55_Fibros_SET_V_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_55_Fibros_SET_V_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,eae3eabfb16a02979db68907ce3e49f0
226
+ singlecell/train/Position_56_Fibros_SET_II_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_56_Fibros_SET_II_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,4da38a60ab75e23d1c2c17143fc0059d
227
+ singlecell/train/Position_56_Fibros_SET_V_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_56_Fibros_SET_V_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,d7fcca8b7a88a9f67fda9382ad277bd6
228
+ singlecell/train/Position_57_Fibros_SET_II_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_57_Fibros_SET_II_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,69d0c6669646fe7cb755f567815740e0
229
+ singlecell/train/Position_57_Fibros_SET_V_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_57_Fibros_SET_V_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,2aefe3c353cd8750d3b4f31890fca54f
230
+ singlecell/train/Position_58_Fibros_SET_II_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_58_Fibros_SET_II_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,3c8987d9ef4e437b2f29a72412232f56
231
+ singlecell/train/Position_58_Fibros_SET_V_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_58_Fibros_SET_V_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,71e6d9e15ee1b79c2a906f8c41fce1b4
232
+ singlecell/train/Position_59_Fibros_SET_II_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_59_Fibros_SET_II_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,9abecc2cb74d9fa467cd5568cffcd61a
233
+ singlecell/train/Position_59_Fibros_SET_V_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_59_Fibros_SET_V_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,573d844c323bbe3c24f8db6457933aae
234
+ singlecell/train/Position_60_Fibros_SET_II_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_60_Fibros_SET_II_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,afe8609409b635dd974cb0b11051b607
235
+ singlecell/train/Position_60_Fibros_SET_V_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_60_Fibros_SET_V_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,fb553028892f3354a3d269e4e142065b
236
+ singlecell/train/Position_61_Fibros_SET_II_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_61_Fibros_SET_II_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,a1f49042aa8d3de8802052eef927612f
237
+ singlecell/train/Position_62_Fibros_SET_II_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_62_Fibros_SET_II_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,b595c7cce48eb3f64447568315a92581
238
+ singlecell_extra/fibro_1kPa_train/kpan0,train,1kpa_new/train,1 kPa collagen,HFF,collagen I,1000,3.0769,500,kpan0,kpan0,PDMS_1kPa_3um,PDMS_1kPa_3um,cd2323e9de92298a73f915c0454a47d0
239
+ singlecell_extra/fibro_1kPa_train/kpan0 (10),train,1kpa_new/train,1 kPa collagen,HFF,collagen I,1000,3.0769,500,kpan0 (10),kpan0,PDMS_1kPa_3um,PDMS_1kPa_3um,f99e0e6af31272428e8c9dd09dcec264
240
+ singlecell_extra/fibro_1kPa_train/kpan0 (11),train,1kpa_new/train,1 kPa collagen,HFF,collagen I,1000,3.0769,500,kpan0 (11),kpan0,PDMS_1kPa_3um,PDMS_1kPa_3um,9cac462026e18d981e3b235045c932af
241
+ singlecell_extra/fibro_1kPa_train/kpan0 (12),train,1kpa_new/train,1 kPa collagen,HFF,collagen I,1000,3.0769,500,kpan0 (12),kpan0,PDMS_1kPa_3um,PDMS_1kPa_3um,187aa0c36a34c17bda352bc57e947937
242
+ singlecell_extra/fibro_1kPa_train/kpan0 (13),train,1kpa_new/train,1 kPa collagen,HFF,collagen I,1000,3.0769,500,kpan0 (13),kpan0,PDMS_1kPa_3um,PDMS_1kPa_3um,a9d0f02c1d665b49dc7691569d16c30d
243
+ singlecell_extra/fibro_1kPa_train/kpan0 (14),train,1kpa_new/train,1 kPa collagen,HFF,collagen I,1000,3.0769,500,kpan0 (14),kpan0,PDMS_1kPa_3um,PDMS_1kPa_3um,31745c2a1c83a754ebca0bc70882a627
244
+ singlecell_extra/fibro_1kPa_train/kpan0 (15),train,1kpa_new/train,1 kPa collagen,HFF,collagen I,1000,3.0769,500,kpan0 (15),kpan0,PDMS_1kPa_3um,PDMS_1kPa_3um,1b964f423a6f9c25bda8b3e5e7a29481
245
+ singlecell_extra/fibro_1kPa_train/kpan0 (16),train,1kpa_new/train,1 kPa collagen,HFF,collagen I,1000,3.0769,500,kpan0 (16),kpan0,PDMS_1kPa_3um,PDMS_1kPa_3um,c4174f9be098d4f62d173a7aa8982f57
246
+ singlecell_extra/fibro_1kPa_train/kpan0 (2),train,1kpa_new/train,1 kPa collagen,HFF,collagen I,1000,3.0769,500,kpan0 (2),kpan0,PDMS_1kPa_3um,PDMS_1kPa_3um,ab4081d248a08473ec8880fab0abcae8
247
+ singlecell_extra/fibro_1kPa_train/kpan0 (3),train,1kpa_new/train,1 kPa collagen,HFF,collagen I,1000,3.0769,500,kpan0 (3),kpan0,PDMS_1kPa_3um,PDMS_1kPa_3um,3bad6b8d7230147b5907fe3c2da698d0
248
+ singlecell_extra/fibro_1kPa_train/kpan0 (4),train,1kpa_new/train,1 kPa collagen,HFF,collagen I,1000,3.0769,500,kpan0 (4),kpan0,PDMS_1kPa_3um,PDMS_1kPa_3um,a5219fcbb3ae5b1f80f1d863ec71760e
249
+ singlecell_extra/fibro_1kPa_train/kpan0 (5),train,1kpa_new/train,1 kPa collagen,HFF,collagen I,1000,3.0769,500,kpan0 (5),kpan0,PDMS_1kPa_3um,PDMS_1kPa_3um,1c67f8f3963d95aed1a39ed9967094d6
250
+ singlecell_extra/fibro_1kPa_train/kpan0 (6),train,1kpa_new/train,1 kPa collagen,HFF,collagen I,1000,3.0769,500,kpan0 (6),kpan0,PDMS_1kPa_3um,PDMS_1kPa_3um,12e1456fbc64b25fff784a52b5664fab
251
+ singlecell_extra/fibro_1kPa_train/kpan0 (7),train,1kpa_new/train,1 kPa collagen,HFF,collagen I,1000,3.0769,500,kpan0 (7),kpan0,PDMS_1kPa_3um,PDMS_1kPa_3um,c283c0d7d00c66b5b1d889dabf11b11b
252
+ singlecell_extra/fibro_1kPa_train/kpan0 (8),train,1kpa_new/train,1 kPa collagen,HFF,collagen I,1000,3.0769,500,kpan0 (8),kpan0,PDMS_1kPa_3um,PDMS_1kPa_3um,8655be9184e86ee00c5974c2255ee27a
253
+ singlecell_extra/fibro_1kPa_train/kpan0 (9),train,1kpa_new/train,1 kPa collagen,HFF,collagen I,1000,3.0769,500,kpan0 (9),kpan0,PDMS_1kPa_3um,PDMS_1kPa_3um,c9a9e1374054ac833e3171673058a3bc
254
+ singlecell_extra/fibro_10kPa_train/kpan1,train,10kpa_new/train,10 kPa collagen,HFF,collagen I,10000,3.0769,500,kpan1,kpan1,PDMS_10kPa_3um,PDMS_10kPa_3um,678bcfc493693851d0e415475a963851
255
+ singlecell_extra/fibro_10kPa_train/kpan1 (10),train,10kpa_new/train,10 kPa collagen,HFF,collagen I,10000,3.0769,500,kpan1 (10),kpan1,PDMS_10kPa_3um,PDMS_10kPa_3um,844b41c7163063f2a417671d7de7b8e1
256
+ singlecell_extra/fibro_10kPa_train/kpan1 (11),train,10kpa_new/train,10 kPa collagen,HFF,collagen I,10000,3.0769,500,kpan1 (11),kpan1,PDMS_10kPa_3um,PDMS_10kPa_3um,d002d081de4526e937aef05bd7ec6228
257
+ singlecell_extra/fibro_10kPa_train/kpan1 (12),train,10kpa_new/train,10 kPa collagen,HFF,collagen I,10000,3.0769,500,kpan1 (12),kpan1,PDMS_10kPa_3um,PDMS_10kPa_3um,4218fa7b000a795897165e0eeb884ee5
258
+ singlecell_extra/fibro_10kPa_train/kpan1 (13),train,10kpa_new/train,10 kPa collagen,HFF,collagen I,10000,3.0769,500,kpan1 (13),kpan1,PDMS_10kPa_3um,PDMS_10kPa_3um,3c815ee4b929edbf8ba0f8ab00e07690
259
+ singlecell_extra/fibro_10kPa_train/kpan1 (14),train,10kpa_new/train,10 kPa collagen,HFF,collagen I,10000,3.0769,500,kpan1 (14),kpan1,PDMS_10kPa_3um,PDMS_10kPa_3um,f6cc34cf8e2da7469c69c6c26f2f90de
260
+ singlecell_extra/fibro_10kPa_train/kpan1 (15),train,10kpa_new/train,10 kPa collagen,HFF,collagen I,10000,3.0769,500,kpan1 (15),kpan1,PDMS_10kPa_3um,PDMS_10kPa_3um,37292b0ef7e7d5af5faf5048b4f124da
261
+ singlecell_extra/fibro_10kPa_train/kpan1 (16),train,10kpa_new/train,10 kPa collagen,HFF,collagen I,10000,3.0769,500,kpan1 (16),kpan1,PDMS_10kPa_3um,PDMS_10kPa_3um,bc2cb9d4adfc7e6f162b67ca248ff019
262
+ singlecell_extra/fibro_10kPa_train/kpan1 (17),train,10kpa_new/train,10 kPa collagen,HFF,collagen I,10000,3.0769,500,kpan1 (17),kpan1,PDMS_10kPa_3um,PDMS_10kPa_3um,c38a5b83b010e69263426cd0288baaac
263
+ singlecell_extra/fibro_10kPa_train/kpan1 (18),train,10kpa_new/train,10 kPa collagen,HFF,collagen I,10000,3.0769,500,kpan1 (18),kpan1,PDMS_10kPa_3um,PDMS_10kPa_3um,26ec3fe6a4a0c1bdc8fc9f6aeb49a7d5
264
+ singlecell_extra/fibro_10kPa_train/kpan1 (19),train,10kpa_new/train,10 kPa collagen,HFF,collagen I,10000,3.0769,500,kpan1 (19),kpan1,PDMS_10kPa_3um,PDMS_10kPa_3um,96aa6f76b44ad527cf4723f70de3a8c7
265
+ singlecell_extra/fibro_10kPa_train/kpan1 (2),train,10kpa_new/train,10 kPa collagen,HFF,collagen I,10000,3.0769,500,kpan1 (2),kpan1,PDMS_10kPa_3um,PDMS_10kPa_3um,a4364dc23aead54d31e81c35aa0521f0
266
+ singlecell_extra/fibro_10kPa_train/kpan1 (20),train,10kpa_new/train,10 kPa collagen,HFF,collagen I,10000,3.0769,500,kpan1 (20),kpan1,PDMS_10kPa_3um,PDMS_10kPa_3um,29f3e5a2b33c4aea8ed28f2fafbbb7cd
267
+ singlecell_extra/fibro_10kPa_train/kpan1 (21),train,10kpa_new/train,10 kPa collagen,HFF,collagen I,10000,3.0769,500,kpan1 (21),kpan1,PDMS_10kPa_3um,PDMS_10kPa_3um,0d015cf3c311278d53ce0494d8b1fe54
268
+ singlecell_extra/fibro_10kPa_train/kpan1 (22),train,10kpa_new/train,10 kPa collagen,HFF,collagen I,10000,3.0769,500,kpan1 (22),kpan1,PDMS_10kPa_3um,PDMS_10kPa_3um,d05de3094d446dd02ac12322c978f8ef
269
+ singlecell_extra/fibro_10kPa_train/kpan1 (23),train,10kpa_new/train,10 kPa collagen,HFF,collagen I,10000,3.0769,500,kpan1 (23),kpan1,PDMS_10kPa_3um,PDMS_10kPa_3um,d3d65d9e734b3782a641067d09dd8e6c
270
+ singlecell_extra/fibro_10kPa_train/kpan1 (24),train,10kpa_new/train,10 kPa collagen,HFF,collagen I,10000,3.0769,500,kpan1 (24),kpan1,PDMS_10kPa_3um,PDMS_10kPa_3um,816a8be4bba1b64b0577f54bfb4b048d
271
+ singlecell_extra/fibro_10kPa_train/kpan1 (25),train,10kpa_new/train,10 kPa collagen,HFF,collagen I,10000,3.0769,500,kpan1 (25),kpan1,PDMS_10kPa_3um,PDMS_10kPa_3um,ea228238405ed7585137548920908df8
272
+ singlecell_extra/fibro_10kPa_train/kpan1 (26),train,10kpa_new/train,10 kPa collagen,HFF,collagen I,10000,3.0769,500,kpan1 (26),kpan1,PDMS_10kPa_3um,PDMS_10kPa_3um,6e779deb108bd16e51e4c5d3ab5576d8
273
+ singlecell_extra/fibro_10kPa_train/kpan1 (27),train,10kpa_new/train,10 kPa collagen,HFF,collagen I,10000,3.0769,500,kpan1 (27),kpan1,PDMS_10kPa_3um,PDMS_10kPa_3um,31bc5a726b1b1e63158827a5409f4090
274
+ singlecell_extra/fibro_10kPa_train/kpan1 (28),train,10kpa_new/train,10 kPa collagen,HFF,collagen I,10000,3.0769,500,kpan1 (28),kpan1,PDMS_10kPa_3um,PDMS_10kPa_3um,d4edd9b164f592c7fab6a3b67570a1de
275
+ singlecell_extra/fibro_10kPa_train/kpan1 (3),train,10kpa_new/train,10 kPa collagen,HFF,collagen I,10000,3.0769,500,kpan1 (3),kpan1,PDMS_10kPa_3um,PDMS_10kPa_3um,b88145dc70dd43778bba2096f45f6574
276
+ singlecell_extra/fibro_10kPa_train/kpan1 (4),train,10kpa_new/train,10 kPa collagen,HFF,collagen I,10000,3.0769,500,kpan1 (4),kpan1,PDMS_10kPa_3um,PDMS_10kPa_3um,718e96cf9306cf3f6fb999bc333103bd
277
+ singlecell_extra/fibro_10kPa_train/kpan1 (5),train,10kpa_new/train,10 kPa collagen,HFF,collagen I,10000,3.0769,500,kpan1 (5),kpan1,PDMS_10kPa_3um,PDMS_10kPa_3um,6b55f416b0efd6ad53b6dd7a2850c751
278
+ singlecell_extra/fibro_10kPa_train/kpan1 (6),train,10kpa_new/train,10 kPa collagen,HFF,collagen I,10000,3.0769,500,kpan1 (6),kpan1,PDMS_10kPa_3um,PDMS_10kPa_3um,e3d17a07b8cb90adfabd4f9db98d3de0
279
+ singlecell_extra/fibro_10kPa_train/kpan1 (7),train,10kpa_new/train,10 kPa collagen,HFF,collagen I,10000,3.0769,500,kpan1 (7),kpan1,PDMS_10kPa_3um,PDMS_10kPa_3um,b19c63e31371a68a11cd72d19c71c5eb
280
+ singlecell_extra/fibro_10kPa_train/kpan1 (8),train,10kpa_new/train,10 kPa collagen,HFF,collagen I,10000,3.0769,500,kpan1 (8),kpan1,PDMS_10kPa_3um,PDMS_10kPa_3um,cf0213c6ecf807df01de0d05a69428ec
281
+ singlecell_extra/fibro_10kPa_train/kpan1 (9),train,10kpa_new/train,10 kPa collagen,HFF,collagen I,10000,3.0769,500,kpan1 (9),kpan1,PDMS_10kPa_3um,PDMS_10kPa_3um,65176fe59f0b6e6228a7cfc9e532903e
experiments/splits/alltune_val.csv ADDED
@@ -0,0 +1,82 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ sample_dir,split,set,condition,cell_type,coating,young_Pa,tfm_pixelsize,ythreshold_Pa,legacy_folder,legacy_substrate_code,substrate_legacy,substrate_nominal,bf_md5
2
+ singlecell/test/Position_01_Fibros_SET_VI_for_Kaveh,val,fibro_split/test,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_01_Fibros_SET_VI_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,16d1e356f6811f66ee811a5db51d7ab1
3
+ singlecell/test/Position_02_Fibros_SET_VI_for_Kaveh,val,fibro_split/test,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_02_Fibros_SET_VI_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,cf14eccf4d4ad3db9f7207b905577397
4
+ singlecell/test/Position_03_Fibros_SET_VI_for_Kaveh,val,fibro_split/test,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_03_Fibros_SET_VI_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,9595462e4ec4107f30d16f5d4babc88c
5
+ singlecell/test/Position_04_Fibros_SET_VI_for_Kaveh,val,fibro_split/test,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_04_Fibros_SET_VI_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,e562d1d7876ff49b25bb167863804588
6
+ singlecell/test/Position_05_Fibros_SET_VI_for_Kaveh,val,fibro_split/test,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_05_Fibros_SET_VI_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,4338359255835bb02ef7aa966f236fc1
7
+ singlecell/test/Position_06_Fibros_SET_VI_for_Kaveh,val,fibro_split/test,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_06_Fibros_SET_VI_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,f68f65bcb182c09cb77bb2fb9bbe560f
8
+ singlecell/test/Position_07_Fibros_SET_VI_for_Kaveh,val,fibro_split/test,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_07_Fibros_SET_VI_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,2c5b638e494822c473c79601424106ad
9
+ singlecell/test/Position_08_Fibros_SET_VI_for_Kaveh,val,fibro_split/test,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_08_Fibros_SET_VI_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,191fe407db3249e029480307da88261c
10
+ singlecell/test/Position_09_Fibros_SET_VI_for_Kaveh,val,fibro_split/test,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_09_Fibros_SET_VI_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,7c91e95d0b1ddae4a50a1c4889e049c1
11
+ singlecell/test/Position_10_Fibros_SET_VI_for_Kaveh,val,fibro_split/test,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_10_Fibros_SET_VI_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,2b2784691cc84acb7a59d109517d8fd4
12
+ singlecell/test/Position_11_Fibros_SET_VI_for_Kaveh,val,fibro_split/test,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_11_Fibros_SET_VI_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,6be82222835f2f1d86522d37132f5f50
13
+ singlecell/test/Position_12_Fibros_SET_VI_for_Kaveh,val,fibro_split/test,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_12_Fibros_SET_VI_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,9aba966a4e385658445733b6f2c5f129
14
+ singlecell/test/Position_13_Fibros_SET_VI_for_Kaveh,val,fibro_split/test,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_13_Fibros_SET_VI_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,68f4edd892dbd27270e4ad2318cb3907
15
+ singlecell/test/Position_14_Fibros_SET_VI_for_Kaveh,val,fibro_split/test,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_14_Fibros_SET_VI_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,fd7af4e97dccd05295fcaad9e7561433
16
+ singlecell/test/Position_15_Fibros_SET_VI_for_Kaveh,val,fibro_split/test,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_15_Fibros_SET_VI_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,b54693e84a955e42b025235794108f6e
17
+ singlecell/test/Position_16_Fibros_SET_VI_for_Kaveh,val,fibro_split/test,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_16_Fibros_SET_VI_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,f4ad9bdb24bb0a6f1f60eab8d164d650
18
+ singlecell/test/Position_17_Fibros_SET_VI_for_Kaveh,val,fibro_split/test,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_17_Fibros_SET_VI_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,66e07499eff1b63ae8321eebe1828d38
19
+ singlecell/test/Position_18_Fibros_SET_VI_for_Kaveh,val,fibro_split/test,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_18_Fibros_SET_VI_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,03d8fd302362e352e6f15f0ede2e1611
20
+ singlecell/test/Position_19_Fibros_SET_VI_for_Kaveh,val,fibro_split/test,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_19_Fibros_SET_VI_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,f2477f80a8b077e6fd91f94a4130aefa
21
+ singlecell/test/Position_20_Fibros_SET_VI_for_Kaveh,val,fibro_split/test,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_20_Fibros_SET_VI_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,761fcd26e15b290c25b4475eae65f0a4
22
+ singlecell/test/Position_21_Fibros_SET_VI_for_Kaveh,val,fibro_split/test,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_21_Fibros_SET_VI_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,f775897638d8fc864bbd85a2984cc175
23
+ singlecell/test/Position_22_Fibros_SET_VI_for_Kaveh,val,fibro_split/test,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_22_Fibros_SET_VI_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,957a5d1022f1f2cd40167e6aa96dd04a
24
+ singlecell/test/Position_23_Fibros_SET_VI_for_Kaveh,val,fibro_split/test,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_23_Fibros_SET_VI_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,2782f9551709788685ab2fea4a5069bd
25
+ singlecell/test/Position_24_Fibros_SET_VI_for_Kaveh,val,fibro_split/test,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_24_Fibros_SET_VI_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,96e6a141799644462463632548b8e5a3
26
+ singlecell/test/Position_25_Fibros_SET_VI_for_Kaveh,val,fibro_split/test,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_25_Fibros_SET_VI_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,d6d3fec2c386aee0bbb8565bb8f13566
27
+ singlecell/test/Position_26_Fibros_SET_VI_for_Kaveh,val,fibro_split/test,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_26_Fibros_SET_VI_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,334466591565cf8f5d1877deef0422bb
28
+ singlecell/test/Position_27_Fibros_SET_VI_for_Kaveh,val,fibro_split/test,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_27_Fibros_SET_VI_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,212bdc83c0511b2930f3853dcd75c2cf
29
+ singlecell/test/Position_28_Fibros_SET_VI_for_Kaveh,val,fibro_split/test,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_28_Fibros_SET_VI_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,1a6483921f18e1bfbfb87128d837f59e
30
+ singlecell/test/Position_29_Fibros_SET_VI_for_Kaveh,val,fibro_split/test,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_29_Fibros_SET_VI_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,5c6c94cce47b04fae0fb3b3c6f7f74b5
31
+ singlecell/test/Position_30_Fibros_SET_VI_for_Kaveh,val,fibro_split/test,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_30_Fibros_SET_VI_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,9d333c7109fef9d7f39643e66a0cf0c0
32
+ singlecell/test/Position_31_Fibros_SET_VI_for_Kaveh,val,fibro_split/test,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_31_Fibros_SET_VI_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,21d7a2cd0c99937623b70b0afff28725
33
+ singlecell/test/Position_32_Fibros_SET_VI_for_Kaveh,val,fibro_split/test,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_32_Fibros_SET_VI_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,2da0965a500504c29362bb9466c34070
34
+ singlecell/test/Position_33_Fibros_SET_VI_for_Kaveh,val,fibro_split/test,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_33_Fibros_SET_VI_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,259a088a128c0d9978d47351b643bf03
35
+ singlecell/test/Position_34_Fibros_SET_VI_for_Kaveh,val,fibro_split/test,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_34_Fibros_SET_VI_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,1231efc0731bda43d78b1c7d10bd7fa8
36
+ singlecell/test/Position_35_Fibros_SET_VI_for_Kaveh,val,fibro_split/test,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_35_Fibros_SET_VI_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,6a932918e87a78633bca6bd136dd2bd5
37
+ singlecell/test/Position_36_Fibros_SET_VI_for_Kaveh,val,fibro_split/test,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_36_Fibros_SET_VI_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,a92a206c8daa4b5c99a87e3f69c81760
38
+ singlecell/test/Position_37_Fibros_SET_VI_for_Kaveh,val,fibro_split/test,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_37_Fibros_SET_VI_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,903d2e994ab7b7381c033c1e59ec4f32
39
+ singlecell/test/Position_38_Fibros_SET_VI_for_Kaveh,val,fibro_split/test,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_38_Fibros_SET_VI_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,6662b23db66b15a3f7657cff990e2dbc
40
+ singlecell/test/Position_39_Fibros_SET_VI_for_Kaveh,val,fibro_split/test,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_39_Fibros_SET_VI_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,489473be18dd682f4e0f9c7367c776e8
41
+ singlecell/test/Position_40_Fibros_SET_VI_for_Kaveh,val,fibro_split/test,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_40_Fibros_SET_VI_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,d0f01dcf05574003e2c40f28e6329566
42
+ singlecell/test/Position_41_Fibros_SET_VI_for_Kaveh,val,fibro_split/test,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_41_Fibros_SET_VI_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,e46a858089a335059e3ef36b60e2a931
43
+ singlecell/test/Position_43_Fibros_SET_VI_for_Kaveh,val,fibro_split/test,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_43_Fibros_SET_VI_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,3c293ef5de04f7e66fd0b225b6fc731b
44
+ singlecell/test/Position_44_Fibros_SET_VI_for_Kaveh,val,fibro_split/test,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_44_Fibros_SET_VI_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,47547bfbc09f9211fc7c57969c611167
45
+ singlecell/test/Position_45_Fibros_SET_VI_for_Kaveh,val,fibro_split/test,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_45_Fibros_SET_VI_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,7daf73af3c78d738f3c8cf8a0c6f4a53
46
+ singlecell/test/Position_46_Fibros_SET_VI_for_Kaveh,val,fibro_split/test,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_46_Fibros_SET_VI_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,eaa81a5d43baf70639861a4205aba4fd
47
+ singlecell/test/Position_48_Fibros_SET_VI_for_Kaveh,val,fibro_split/test,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_48_Fibros_SET_VI_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,b66eed556b24db2623f752adc566a7e1
48
+ singlecell_extra/fibro_1kPa_setI/kpan0,val,1kpa_new/test,1 kPa collagen,HFF,collagen I,1000,3.0769,500,kpan0,kpan0,PDMS_1kPa_3um,PDMS_1kPa_3um,8eb9b80be7e5481c37b2af7d70ced605
49
+ singlecell_extra/fibro_1kPa_setI/kpan0 (10),val,1kpa_new/test,1 kPa collagen,HFF,collagen I,1000,3.0769,500,kpan0 (10),kpan0,PDMS_1kPa_3um,PDMS_1kPa_3um,66f93503e902ae6a8ac3f87edc5f7470
50
+ singlecell_extra/fibro_1kPa_setI/kpan0 (11),val,1kpa_new/test,1 kPa collagen,HFF,collagen I,1000,3.0769,500,kpan0 (11),kpan0,PDMS_1kPa_3um,PDMS_1kPa_3um,d339b48eb65cb36057012c44742e6afc
51
+ singlecell_extra/fibro_1kPa_setI/kpan0 (12),val,1kpa_new/test,1 kPa collagen,HFF,collagen I,1000,3.0769,500,kpan0 (12),kpan0,PDMS_1kPa_3um,PDMS_1kPa_3um,666bb236d4c0125a59d26e320c7f1fce
52
+ singlecell_extra/fibro_1kPa_setI/kpan0 (13),val,1kpa_new/test,1 kPa collagen,HFF,collagen I,1000,3.0769,500,kpan0 (13),kpan0,PDMS_1kPa_3um,PDMS_1kPa_3um,913b2644bb65061891b5136b9bcf9c47
53
+ singlecell_extra/fibro_1kPa_setI/kpan0 (14),val,1kpa_new/test,1 kPa collagen,HFF,collagen I,1000,3.0769,500,kpan0 (14),kpan0,PDMS_1kPa_3um,PDMS_1kPa_3um,b068c8cbc256bcc150bf1134d6972741
54
+ singlecell_extra/fibro_1kPa_setI/kpan0 (15),val,1kpa_new/test,1 kPa collagen,HFF,collagen I,1000,3.0769,500,kpan0 (15),kpan0,PDMS_1kPa_3um,PDMS_1kPa_3um,7294fd45c8197f4ef410927b18fd2527
55
+ singlecell_extra/fibro_1kPa_setI/kpan0 (2),val,1kpa_new/test,1 kPa collagen,HFF,collagen I,1000,3.0769,500,kpan0 (2),kpan0,PDMS_1kPa_3um,PDMS_1kPa_3um,a0f4ad55f07c91f39cd27b697b0da63d
56
+ singlecell_extra/fibro_1kPa_setI/kpan0 (3),val,1kpa_new/test,1 kPa collagen,HFF,collagen I,1000,3.0769,500,kpan0 (3),kpan0,PDMS_1kPa_3um,PDMS_1kPa_3um,370f778725868a156cac77e64a7c8943
57
+ singlecell_extra/fibro_1kPa_setI/kpan0 (4),val,1kpa_new/test,1 kPa collagen,HFF,collagen I,1000,3.0769,500,kpan0 (4),kpan0,PDMS_1kPa_3um,PDMS_1kPa_3um,3814f25b0ef49064f469e5222dd67191
58
+ singlecell_extra/fibro_1kPa_setI/kpan0 (5),val,1kpa_new/test,1 kPa collagen,HFF,collagen I,1000,3.0769,500,kpan0 (5),kpan0,PDMS_1kPa_3um,PDMS_1kPa_3um,ceba1f49d4dee878f2e9154928330d59
59
+ singlecell_extra/fibro_1kPa_setI/kpan0 (6),val,1kpa_new/test,1 kPa collagen,HFF,collagen I,1000,3.0769,500,kpan0 (6),kpan0,PDMS_1kPa_3um,PDMS_1kPa_3um,7b1fec51a13f9a8e7fce68895ba92b0b
60
+ singlecell_extra/fibro_1kPa_setI/kpan0 (7),val,1kpa_new/test,1 kPa collagen,HFF,collagen I,1000,3.0769,500,kpan0 (7),kpan0,PDMS_1kPa_3um,PDMS_1kPa_3um,bba9ba679aa53ab520d707b8899eb822
61
+ singlecell_extra/fibro_1kPa_setI/kpan0 (8),val,1kpa_new/test,1 kPa collagen,HFF,collagen I,1000,3.0769,500,kpan0 (8),kpan0,PDMS_1kPa_3um,PDMS_1kPa_3um,6893cdf5ae1dc5f01b9f3b205150c70f
62
+ singlecell_extra/fibro_1kPa_setI/kpan0 (9),val,1kpa_new/test,1 kPa collagen,HFF,collagen I,1000,3.0769,500,kpan0 (9),kpan0,PDMS_1kPa_3um,PDMS_1kPa_3um,d8f73c310041fbc616b004175a99b409
63
+ singlecell_extra/fibro_10kPa_setI/kpan1,val,10kpa_new/test,10 kPa collagen,HFF,collagen I,10000,3.0769,500,kpan1,kpan1,PDMS_10kPa_3um,PDMS_10kPa_3um,1085b37839c421b896cf7a5d55d59c14
64
+ singlecell_extra/fibro_10kPa_setI/kpan1 (10),val,10kpa_new/test,10 kPa collagen,HFF,collagen I,10000,3.0769,500,kpan1 (10),kpan1,PDMS_10kPa_3um,PDMS_10kPa_3um,558818e5c7cdf4bb2cb3a7de72bf08a9
65
+ singlecell_extra/fibro_10kPa_setI/kpan1 (11),val,10kpa_new/test,10 kPa collagen,HFF,collagen I,10000,3.0769,500,kpan1 (11),kpan1,PDMS_10kPa_3um,PDMS_10kPa_3um,4cb988f5986bc08e992570568b885af3
66
+ singlecell_extra/fibro_10kPa_setI/kpan1 (12),val,10kpa_new/test,10 kPa collagen,HFF,collagen I,10000,3.0769,500,kpan1 (12),kpan1,PDMS_10kPa_3um,PDMS_10kPa_3um,28210da8897664b77d9dbc39744d7ea8
67
+ singlecell_extra/fibro_10kPa_setI/kpan1 (13),val,10kpa_new/test,10 kPa collagen,HFF,collagen I,10000,3.0769,500,kpan1 (13),kpan1,PDMS_10kPa_3um,PDMS_10kPa_3um,cdd5b2375d84773eb4e4428f6daaa5db
68
+ singlecell_extra/fibro_10kPa_setI/kpan1 (14),val,10kpa_new/test,10 kPa collagen,HFF,collagen I,10000,3.0769,500,kpan1 (14),kpan1,PDMS_10kPa_3um,PDMS_10kPa_3um,d4f43ff1b526fa9118153b08d8c3bec8
69
+ singlecell_extra/fibro_10kPa_setI/kpan1 (15),val,10kpa_new/test,10 kPa collagen,HFF,collagen I,10000,3.0769,500,kpan1 (15),kpan1,PDMS_10kPa_3um,PDMS_10kPa_3um,289c69ed79d05ec543272f832eff4fa8
70
+ singlecell_extra/fibro_10kPa_setI/kpan1 (16),val,10kpa_new/test,10 kPa collagen,HFF,collagen I,10000,3.0769,500,kpan1 (16),kpan1,PDMS_10kPa_3um,PDMS_10kPa_3um,a4581d8e2d5efcc59310aad77d545667
71
+ singlecell_extra/fibro_10kPa_setI/kpan1 (17),val,10kpa_new/test,10 kPa collagen,HFF,collagen I,10000,3.0769,500,kpan1 (17),kpan1,PDMS_10kPa_3um,PDMS_10kPa_3um,6150fa627a03f4e29713e2322f7d5d12
72
+ singlecell_extra/fibro_10kPa_setI/kpan1 (18),val,10kpa_new/test,10 kPa collagen,HFF,collagen I,10000,3.0769,500,kpan1 (18),kpan1,PDMS_10kPa_3um,PDMS_10kPa_3um,ddc4284ecdd7d17f8ee473fbf8c5e83e
73
+ singlecell_extra/fibro_10kPa_setI/kpan1 (19),val,10kpa_new/test,10 kPa collagen,HFF,collagen I,10000,3.0769,500,kpan1 (19),kpan1,PDMS_10kPa_3um,PDMS_10kPa_3um,e4cbe16291554b068c0532230ec98799
74
+ singlecell_extra/fibro_10kPa_setI/kpan1 (2),val,10kpa_new/test,10 kPa collagen,HFF,collagen I,10000,3.0769,500,kpan1 (2),kpan1,PDMS_10kPa_3um,PDMS_10kPa_3um,d30ff78756f6b0e70063bc7a59ddac86
75
+ singlecell_extra/fibro_10kPa_setI/kpan1 (20),val,10kpa_new/test,10 kPa collagen,HFF,collagen I,10000,3.0769,500,kpan1 (20),kpan1,PDMS_10kPa_3um,PDMS_10kPa_3um,f1d498ddf12a822082fba788ee5f140e
76
+ singlecell_extra/fibro_10kPa_setI/kpan1 (3),val,10kpa_new/test,10 kPa collagen,HFF,collagen I,10000,3.0769,500,kpan1 (3),kpan1,PDMS_10kPa_3um,PDMS_10kPa_3um,f7af8c6c810772297481283f3c35cbf3
77
+ singlecell_extra/fibro_10kPa_setI/kpan1 (4),val,10kpa_new/test,10 kPa collagen,HFF,collagen I,10000,3.0769,500,kpan1 (4),kpan1,PDMS_10kPa_3um,PDMS_10kPa_3um,e3bd809ba2848dc8708061f1098c6d0d
78
+ singlecell_extra/fibro_10kPa_setI/kpan1 (5),val,10kpa_new/test,10 kPa collagen,HFF,collagen I,10000,3.0769,500,kpan1 (5),kpan1,PDMS_10kPa_3um,PDMS_10kPa_3um,7ebb55a312c4cbb45f5a221646f6c865
79
+ singlecell_extra/fibro_10kPa_setI/kpan1 (6),val,10kpa_new/test,10 kPa collagen,HFF,collagen I,10000,3.0769,500,kpan1 (6),kpan1,PDMS_10kPa_3um,PDMS_10kPa_3um,e0726b51175d3cf12b4fc0a64c3652c5
80
+ singlecell_extra/fibro_10kPa_setI/kpan1 (7),val,10kpa_new/test,10 kPa collagen,HFF,collagen I,10000,3.0769,500,kpan1 (7),kpan1,PDMS_10kPa_3um,PDMS_10kPa_3um,105c3864f193a11b72550eeb495f31fe
81
+ singlecell_extra/fibro_10kPa_setI/kpan1 (8),val,10kpa_new/test,10 kPa collagen,HFF,collagen I,10000,3.0769,500,kpan1 (8),kpan1,PDMS_10kPa_3um,PDMS_10kPa_3um,691ae63cb550fc20ca9b67f8ce2c7a0c
82
+ singlecell_extra/fibro_10kPa_setI/kpan1 (9),val,10kpa_new/test,10 kPa collagen,HFF,collagen I,10000,3.0769,500,kpan1 (9),kpan1,PDMS_10kPa_3um,PDMS_10kPa_3um,555b202832587bc325272279ef796ed4
experiments/splits/spheroid_train.csv ADDED
@@ -0,0 +1,130 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ sample_dir,split,set,condition,cell_type,coating,young_Pa,tfm_pixelsize,ythreshold_Pa,legacy_folder,legacy_substrate_code,substrate_legacy,substrate_nominal,bf_md5
2
+ spheroid/train/01,train,spheroid/train,spheroid,LS174T spheroid,collagen I,,,50,01,01,,,c699004cc17c8ac555042e4c0d9bf192
3
+ spheroid/train/02,train,spheroid/train,spheroid,LS174T spheroid,collagen I,,,50,02,02,,,8ee92b7d32698b1ee627fdd393460757
4
+ spheroid/train/03,train,spheroid/train,spheroid,LS174T spheroid,collagen I,,,50,03,03,,,5df176b3398b1884f9095362de187401
5
+ spheroid/train/04,train,spheroid/train,spheroid,LS174T spheroid,collagen I,,,50,04,04,,,9f376bc46814b997bc735a76fe702305
6
+ spheroid/train/06,train,spheroid/train,spheroid,LS174T spheroid,collagen I,,,50,06,06,,,059ea10495a9f1bfe7263004340715ba
7
+ spheroid/train/07,train,spheroid/train,spheroid,LS174T spheroid,collagen I,,,50,07,07,,,9fbe6fdb7d3c85ef620c8b585a08c329
8
+ spheroid/train/08,train,spheroid/train,spheroid,LS174T spheroid,collagen I,,,50,08,08,,,39ffe78fd1385d2a40aade3262bf5a2f
9
+ spheroid/train/09,train,spheroid/train,spheroid,LS174T spheroid,collagen I,,,50,09,09,,,b47dc557d1ccf18e370b55d90bf06168
10
+ spheroid/train/10,train,spheroid/train,spheroid,LS174T spheroid,collagen I,,,50,10,10,,,ffb90f1b0802f2f78ec932ee26293c52
11
+ spheroid/train/11,train,spheroid/train,spheroid,LS174T spheroid,collagen I,,,50,11,11,,,aed7afe58ed837013a6a5c9ec1117752
12
+ spheroid/train/110,train,spheroid/train,spheroid,LS174T spheroid,collagen I,,,50,110,110,,,f550f22b0539b84429b143bae81ad31c
13
+ spheroid/train/111,train,spheroid/train,spheroid,LS174T spheroid,collagen I,,,50,111,111,,,a5be8b672428dba820037707d32db4aa
14
+ spheroid/train/112,train,spheroid/train,spheroid,LS174T spheroid,collagen I,,,50,112,112,,,14acb40b8019f68209f640bd255db413
15
+ spheroid/train/113,train,spheroid/train,spheroid,LS174T spheroid,collagen I,,,50,113,113,,,cfc91b9ed49b16a8a342ad027e539890
16
+ spheroid/train/114,train,spheroid/train,spheroid,LS174T spheroid,collagen I,,,50,114,114,,,eb42631b65946c6623b6335fec49585f
17
+ spheroid/train/115,train,spheroid/train,spheroid,LS174T spheroid,collagen I,,,50,115,115,,,badb9ba0f978cd0e8b9c825a1215c40d
18
+ spheroid/train/116,train,spheroid/train,spheroid,LS174T spheroid,collagen I,,,50,116,116,,,ffef05d7d3fb7939a4a77fea87c559bf
19
+ spheroid/train/117,train,spheroid/train,spheroid,LS174T spheroid,collagen I,,,50,117,117,,,108a7f48f58b7ab9672d8999bb129783
20
+ spheroid/train/118,train,spheroid/train,spheroid,LS174T spheroid,collagen I,,,50,118,118,,,7a3833f16c18dfead08cf2f9751af463
21
+ spheroid/train/119,train,spheroid/train,spheroid,LS174T spheroid,collagen I,,,50,119,119,,,e032e365a2b1c536ca7a9b23dbb24c66
22
+ spheroid/train/12,train,spheroid/train,spheroid,LS174T spheroid,collagen I,,,50,12,12,,,9b486e1b77160747bf978979c5a8af6a
23
+ spheroid/train/120,train,spheroid/train,spheroid,LS174T spheroid,collagen I,,,50,120,120,,,338e15cb5824ccdb136efc34f3f79dc7
24
+ spheroid/train/121,train,spheroid/train,spheroid,LS174T spheroid,collagen I,,,50,121,121,,,cc38a705592cce5d730ba376d09ddd9f
25
+ spheroid/train/122,train,spheroid/train,spheroid,LS174T spheroid,collagen I,,,50,122,122,,,c53b614954c073b3059ce270914af4ab
26
+ spheroid/train/123,train,spheroid/train,spheroid,LS174T spheroid,collagen I,,,50,123,123,,,c1c43a3299b5d3371a07a4cf3150bfdc
27
+ spheroid/train/124,train,spheroid/train,spheroid,LS174T spheroid,collagen I,,,50,124,124,,,452bb9f8ab2156d6c072540664a60dca
28
+ spheroid/train/126,train,spheroid/train,spheroid,LS174T spheroid,collagen I,,,50,126,126,,,116cc4f7129e2e52f3397ecac8cddbbd
29
+ spheroid/train/127,train,spheroid/train,spheroid,LS174T spheroid,collagen I,,,50,127,127,,,f1d3a9544a4a19dc54c1aeee06d87ef2
30
+ spheroid/train/128,train,spheroid/train,spheroid,LS174T spheroid,collagen I,,,50,128,128,,,0a6f8fb704fb42396e9cbcc0073f0fa5
31
+ spheroid/train/129,train,spheroid/train,spheroid,LS174T spheroid,collagen I,,,50,129,129,,,698180e844636f5f6330530c815962f8
32
+ spheroid/train/13,train,spheroid/train,spheroid,LS174T spheroid,collagen I,,,50,13,13,,,0a878cc41f960d1082f2649f88f7f48d
33
+ spheroid/train/130,train,spheroid/train,spheroid,LS174T spheroid,collagen I,,,50,130,130,,,cf80ad553e7a8d06f8391576f69e7a45
34
+ spheroid/train/132,train,spheroid/train,spheroid,LS174T spheroid,collagen I,,,50,132,132,,,d2523c0118b256c1ece1ef20441aa0b9
35
+ spheroid/train/133,train,spheroid/train,spheroid,LS174T spheroid,collagen I,,,50,133,133,,,a547fac7eee79ebea7cf89532b11e3d0
36
+ spheroid/train/134,train,spheroid/train,spheroid,LS174T spheroid,collagen I,,,50,134,134,,,c39cb91ce74c9d13539f2ecd23a87858
37
+ spheroid/train/136,train,spheroid/train,spheroid,LS174T spheroid,collagen I,,,50,136,136,,,46a2f8283c0fcf7446b37a822c40b805
38
+ spheroid/train/137,train,spheroid/train,spheroid,LS174T spheroid,collagen I,,,50,137,137,,,708c124911d7be99979705ad349143a0
39
+ spheroid/train/138,train,spheroid/train,spheroid,LS174T spheroid,collagen I,,,50,138,138,,,e4b6a811f8bfdd7fc406cca66898cf9a
40
+ spheroid/train/139,train,spheroid/train,spheroid,LS174T spheroid,collagen I,,,50,139,139,,,e4b6a811f8bfdd7fc406cca66898cf9a
41
+ spheroid/train/14,train,spheroid/train,spheroid,LS174T spheroid,collagen I,,,50,14,14,,,400ab913d86b54443baf7c6da4b2e0fb
42
+ spheroid/train/140,train,spheroid/train,spheroid,LS174T spheroid,collagen I,,,50,140,140,,,3de10d1f36b6f4b7017b3761de730adb
43
+ spheroid/train/141,train,spheroid/train,spheroid,LS174T spheroid,collagen I,,,50,141,141,,,39cb71bb6ad29d4a5c90aa0d9d643495
44
+ spheroid/train/142,train,spheroid/train,spheroid,LS174T spheroid,collagen I,,,50,142,142,,,117d3879ad45649848916a793da5ea9c
45
+ spheroid/train/143,train,spheroid/train,spheroid,LS174T spheroid,collagen I,,,50,143,143,,,7c0dcea786b50c397b70e65bd1a71bf2
46
+ spheroid/train/144,train,spheroid/train,spheroid,LS174T spheroid,collagen I,,,50,144,144,,,22502653236ac81039597213541121af
47
+ spheroid/train/145,train,spheroid/train,spheroid,LS174T spheroid,collagen I,,,50,145,145,,,76349419e1f98f142fe9e253243c1724
48
+ spheroid/train/146,train,spheroid/train,spheroid,LS174T spheroid,collagen I,,,50,146,146,,,d37bfa2af49c3e81f50db6e656ab78e1
49
+ spheroid/train/147,train,spheroid/train,spheroid,LS174T spheroid,collagen I,,,50,147,147,,,ec1f26d1a501753db02b0c1d019d61e5
50
+ spheroid/train/148,train,spheroid/train,spheroid,LS174T spheroid,collagen I,,,50,148,148,,,d7e3ba1b5b9a8e227e210fdd3de43047
51
+ spheroid/train/149,train,spheroid/train,spheroid,LS174T spheroid,collagen I,,,50,149,149,,,5d31feff688c085fcf12f1ac44029106
52
+ spheroid/train/15,train,spheroid/train,spheroid,LS174T spheroid,collagen I,,,50,15,15,,,61c75429569f46e65bd9a10a2edf6c21
53
+ spheroid/train/150,train,spheroid/train,spheroid,LS174T spheroid,collagen I,,,50,150,150,,,59301cd6c5b828b1e9d8027a15c43e24
54
+ spheroid/train/152,train,spheroid/train,spheroid,LS174T spheroid,collagen I,,,50,152,152,,,34bb54ed1d1cb883e726ee2162d8bb5d
55
+ spheroid/train/153,train,spheroid/train,spheroid,LS174T spheroid,collagen I,,,50,153,153,,,50c8e6f3ed6407c0609d84d8ba7c9e7d
56
+ spheroid/train/154,train,spheroid/train,spheroid,LS174T spheroid,collagen I,,,50,154,154,,,4f92d91a3d4719a7acf4561dbe77835c
57
+ spheroid/train/155,train,spheroid/train,spheroid,LS174T spheroid,collagen I,,,50,155,155,,,2d30cd939470faf2bbbacca7b3533a57
58
+ spheroid/train/156,train,spheroid/train,spheroid,LS174T spheroid,collagen I,,,50,156,156,,,47aaaf09a0ea35bd781ee21eacab5d7a
59
+ spheroid/train/157,train,spheroid/train,spheroid,LS174T spheroid,collagen I,,,50,157,157,,,b4a434cbdf81e0970d44356e5099c667
60
+ spheroid/train/158,train,spheroid/train,spheroid,LS174T spheroid,collagen I,,,50,158,158,,,5f9bbdce877b194a4d6f54fd3154b51a
61
+ spheroid/train/159,train,spheroid/train,spheroid,LS174T spheroid,collagen I,,,50,159,159,,,f2ea4c7fa7d76bfe6e6b33621a7df5f6
62
+ spheroid/train/16,train,spheroid/train,spheroid,LS174T spheroid,collagen I,,,50,16,16,,,4ac2a4436e7854a41a1e0b3f77aa2335
63
+ spheroid/train/160,train,spheroid/train,spheroid,LS174T spheroid,collagen I,,,50,160,160,,,a53800cccb3f37e5aca14723453b40fe
64
+ spheroid/train/161,train,spheroid/train,spheroid,LS174T spheroid,collagen I,,,50,161,161,,,14fa1d37e5da592aff5f63fa5745c4c9
65
+ spheroid/train/162,train,spheroid/train,spheroid,LS174T spheroid,collagen I,,,50,162,162,,,74c2148335f2e37dbcde9d1c6229e554
66
+ spheroid/train/163,train,spheroid/train,spheroid,LS174T spheroid,collagen I,,,50,163,163,,,159dc7b0ad3e127fb6bba9f6d049f139
67
+ spheroid/train/17,train,spheroid/train,spheroid,LS174T spheroid,collagen I,,,50,17,17,,,a8c809931acbac746078a3d8f06260cc
68
+ spheroid/train/18,train,spheroid/train,spheroid,LS174T spheroid,collagen I,,,50,18,18,,,94b60ccc7ca6bcc5cfe653f7cf9502a7
69
+ spheroid/train/19,train,spheroid/train,spheroid,LS174T spheroid,collagen I,,,50,19,19,,,063550fe881610f4b08e80fe8aa06b8a
70
+ spheroid/train/20,train,spheroid/train,spheroid,LS174T spheroid,collagen I,,,50,20,20,,,3cd8d939d276add8230c8d23701d9321
71
+ spheroid/train/21,train,spheroid/train,spheroid,LS174T spheroid,collagen I,,,50,21,21,,,7108751797e4d6fb5736be9b38daa6a0
72
+ spheroid/train/22,train,spheroid/train,spheroid,LS174T spheroid,collagen I,,,50,22,22,,,dcb172d5f6965b5af597bd72906a1b01
73
+ spheroid/train/23,train,spheroid/train,spheroid,LS174T spheroid,collagen I,,,50,23,23,,,d1d1c1d362e838ec35044d2e72850f0a
74
+ spheroid/train/24,train,spheroid/train,spheroid,LS174T spheroid,collagen I,,,50,24,24,,,363917270812c64127041d82d726b6db
75
+ spheroid/train/25,train,spheroid/train,spheroid,LS174T spheroid,collagen I,,,50,25,25,,,9145e291bec602a03a402035dc5687f0
76
+ spheroid/train/26,train,spheroid/train,spheroid,LS174T spheroid,collagen I,,,50,26,26,,,0c1dbcb22ae835c2b98da91b22c3dab3
77
+ spheroid/train/27,train,spheroid/train,spheroid,LS174T spheroid,collagen I,,,50,27,27,,,ee2f93fc38b634470b9a36a7d6fce3e0
78
+ spheroid/train/28,train,spheroid/train,spheroid,LS174T spheroid,collagen I,,,50,28,28,,,9d8925b7c297a7b9941fe983082464b7
79
+ spheroid/train/29,train,spheroid/train,spheroid,LS174T spheroid,collagen I,,,50,29,29,,,171a821d3efbc993cdac97337fcdbf79
80
+ spheroid/train/30,train,spheroid/train,spheroid,LS174T spheroid,collagen I,,,50,30,30,,,c2c317b3cb5f7afe5f41e3f6a62b723c
81
+ spheroid/train/31,train,spheroid/train,spheroid,LS174T spheroid,collagen I,,,50,31,31,,,8aa66124e3b15821cd618bc098599310
82
+ spheroid/train/33,train,spheroid/train,spheroid,LS174T spheroid,collagen I,,,50,33,33,,,0644c077af597b9eb65759aeaac887a6
83
+ spheroid/train/34,train,spheroid/train,spheroid,LS174T spheroid,collagen I,,,50,34,34,,,417b6599662ccc75b5c42ec3b6516e63
84
+ spheroid/train/35,train,spheroid/train,spheroid,LS174T spheroid,collagen I,,,50,35,35,,,1996a1babfe6a5032d40692c13d831e6
85
+ spheroid/train/36,train,spheroid/train,spheroid,LS174T spheroid,collagen I,,,50,36,36,,,ca7a2969ba5ed6969abe352149dfffbb
86
+ spheroid/train/37,train,spheroid/train,spheroid,LS174T spheroid,collagen I,,,50,37,37,,,bb98b6ea6595c8a0a2fed7157b3abb0b
87
+ spheroid/train/38,train,spheroid/train,spheroid,LS174T spheroid,collagen I,,,50,38,38,,,e7aa295ab004fdc959a6eab5c97a006e
88
+ spheroid/train/39,train,spheroid/train,spheroid,LS174T spheroid,collagen I,,,50,39,39,,,40b271773dd0727d7f9f89961cb85456
89
+ spheroid/train/40,train,spheroid/train,spheroid,LS174T spheroid,collagen I,,,50,40,40,,,08f9fb5751d662442106730827a39fc0
90
+ spheroid/train/41,train,spheroid/train,spheroid,LS174T spheroid,collagen I,,,50,41,41,,,b2960c42003dd8bc7b7d0b981de7eeb5
91
+ spheroid/train/42,train,spheroid/train,spheroid,LS174T spheroid,collagen I,,,50,42,42,,,e18ec9846f697cef37a4d990aa554660
92
+ spheroid/train/43,train,spheroid/train,spheroid,LS174T spheroid,collagen I,,,50,43,43,,,716ec99dd06154acac15b72abbdddc18
93
+ spheroid/train/44,train,spheroid/train,spheroid,LS174T spheroid,collagen I,,,50,44,44,,,66cde15118f9094cfe3143b9d1927988
94
+ spheroid/train/45,train,spheroid/train,spheroid,LS174T spheroid,collagen I,,,50,45,45,,,7566da7d6cf96e9d22853747384be01e
95
+ spheroid/train/46,train,spheroid/train,spheroid,LS174T spheroid,collagen I,,,50,46,46,,,055035f09c6631ce04b4826909a73b2e
96
+ spheroid/train/47,train,spheroid/train,spheroid,LS174T spheroid,collagen I,,,50,47,47,,,8a235366344f1ffd67bd063b9bad040d
97
+ spheroid/train/48,train,spheroid/train,spheroid,LS174T spheroid,collagen I,,,50,48,48,,,db3418cdf37fdf89f2a501512a836f66
98
+ spheroid/train/49,train,spheroid/train,spheroid,LS174T spheroid,collagen I,,,50,49,49,,,7a722b38c0720adbded4c9931a8406e1
99
+ spheroid/train/50,train,spheroid/train,spheroid,LS174T spheroid,collagen I,,,50,50,50,,,abf87eb871df4904e0dc24f6a350cd01
100
+ spheroid/train/51,train,spheroid/train,spheroid,LS174T spheroid,collagen I,,,50,51,51,,,c096840efaf6c3143bcb623f245a7afa
101
+ spheroid/train/52,train,spheroid/train,spheroid,LS174T spheroid,collagen I,,,50,52,52,,,11dcc3cec0e46f2795ec63ae7194def1
102
+ spheroid/train/53,train,spheroid/train,spheroid,LS174T spheroid,collagen I,,,50,53,53,,,6e14c5aa05eddf9a44785c5d10bfaaa4
103
+ spheroid/train/54,train,spheroid/train,spheroid,LS174T spheroid,collagen I,,,50,54,54,,,a0a922af0acb4a403e3ffb46c052b221
104
+ spheroid/train/55,train,spheroid/train,spheroid,LS174T spheroid,collagen I,,,50,55,55,,,e6284bfcd5390d4d5ce20693a52cf776
105
+ spheroid/train/56,train,spheroid/train,spheroid,LS174T spheroid,collagen I,,,50,56,56,,,3ab6538beb15d9b15d1ced432eb3a3fa
106
+ spheroid/train/57,train,spheroid/train,spheroid,LS174T spheroid,collagen I,,,50,57,57,,,41da80ed485c05dc9850a08ea6166921
107
+ spheroid/train/58,train,spheroid/train,spheroid,LS174T spheroid,collagen I,,,50,58,58,,,900ab4bcb5adbcbe70c6f2ac2a2a5797
108
+ spheroid/train/59,train,spheroid/train,spheroid,LS174T spheroid,collagen I,,,50,59,59,,,b221efa3f1bd112b36540279db744894
109
+ spheroid/train/60,train,spheroid/train,spheroid,LS174T spheroid,collagen I,,,50,60,60,,,1a66e46f611794ed717aefafa03d5a2b
110
+ spheroid/train/61,train,spheroid/train,spheroid,LS174T spheroid,collagen I,,,50,61,61,,,64abcfe6e37858cc8a2d774fcd15f14b
111
+ spheroid/train/62,train,spheroid/train,spheroid,LS174T spheroid,collagen I,,,50,62,62,,,1d684e3bc1873d7cc72b78e366d56494
112
+ spheroid/train/63,train,spheroid/train,spheroid,LS174T spheroid,collagen I,,,50,63,63,,,7f6a9f73984e2bdc83098579a524f563
113
+ spheroid/train/64,train,spheroid/train,spheroid,LS174T spheroid,collagen I,,,50,64,64,,,18aee8ebd2b59237af2067ee5bb7476f
114
+ spheroid/train/65,train,spheroid/train,spheroid,LS174T spheroid,collagen I,,,50,65,65,,,49108e7aa022cd786e78310624d40600
115
+ spheroid/train/66,train,spheroid/train,spheroid,LS174T spheroid,collagen I,,,50,66,66,,,2c535336117689659050b3b372877a83
116
+ spheroid/train/67,train,spheroid/train,spheroid,LS174T spheroid,collagen I,,,50,67,67,,,fcd811a1958626f18cff02577e9aa685
117
+ spheroid/train/68,train,spheroid/train,spheroid,LS174T spheroid,collagen I,,,50,68,68,,,55e057cb99c91400726c95b2b9d4969a
118
+ spheroid/train/69,train,spheroid/train,spheroid,LS174T spheroid,collagen I,,,50,69,69,,,3beccdc74a6a68d5b42c87c567d03fd6
119
+ spheroid/train/70,train,spheroid/train,spheroid,LS174T spheroid,collagen I,,,50,70,70,,,a03412395ca8ca80dafad81815d376c5
120
+ spheroid/train/71,train,spheroid/train,spheroid,LS174T spheroid,collagen I,,,50,71,71,,,b3b8ab0bf548513a0be70091218716db
121
+ spheroid/train/72,train,spheroid/train,spheroid,LS174T spheroid,collagen I,,,50,72,72,,,6270c8b1838c7bda16a8b866bb724689
122
+ spheroid/train/73,train,spheroid/train,spheroid,LS174T spheroid,collagen I,,,50,73,73,,,338c0f2926311cf200f55c5d5da05379
123
+ spheroid/train/74,train,spheroid/train,spheroid,LS174T spheroid,collagen I,,,50,74,74,,,574c88c030a7eedf32ab1c47bc0fc2b0
124
+ spheroid/train/75,train,spheroid/train,spheroid,LS174T spheroid,collagen I,,,50,75,75,,,b046c3c514a6deacc01111875f290add
125
+ spheroid/train/76,train,spheroid/train,spheroid,LS174T spheroid,collagen I,,,50,76,76,,,54a0c2751836ccd85bf7e73fe23529a8
126
+ spheroid/train/77,train,spheroid/train,spheroid,LS174T spheroid,collagen I,,,50,77,77,,,ad642cb99a8561ed18952bcc256fb4da
127
+ spheroid/train/78,train,spheroid/train,spheroid,LS174T spheroid,collagen I,,,50,78,78,,,6c336d5cb68ae6ba2b4c3e3eab54eeb4
128
+ spheroid/train/79,train,spheroid/train,spheroid,LS174T spheroid,collagen I,,,50,79,79,,,68ffe613da898a076ca04afb6fe67379
129
+ spheroid/train/80,train,spheroid/train,spheroid,LS174T spheroid,collagen I,,,50,80,80,,,dec72a2729950f790960007d568866eb
130
+ spheroid/train/81,train,spheroid/train,spheroid,LS174T spheroid,collagen I,,,50,81,81,,,533717c3a412b52bc59b92edd471bd78
experiments/splits/spheroid_val.csv ADDED
@@ -0,0 +1,29 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ sample_dir,split,set,condition,cell_type,coating,young_Pa,tfm_pixelsize,ythreshold_Pa,legacy_folder,legacy_substrate_code,substrate_legacy,substrate_nominal,bf_md5
2
+ spheroid/test/100,val,spheroid/test,spheroid,LS174T spheroid,collagen I,,,50,100,100,,,bac2e7ffd0dfdeb0b4dcef7e61d21158
3
+ spheroid/test/101,val,spheroid/test,spheroid,LS174T spheroid,collagen I,,,50,101,101,,,bb0334af0da2b07fe903c778317cca96
4
+ spheroid/test/102,val,spheroid/test,spheroid,LS174T spheroid,collagen I,,,50,102,102,,,af27c594f1cce2a1a37be97963f16329
5
+ spheroid/test/103,val,spheroid/test,spheroid,LS174T spheroid,collagen I,,,50,103,103,,,8c0aad5f7120da888f29e93376858e6e
6
+ spheroid/test/104,val,spheroid/test,spheroid,LS174T spheroid,collagen I,,,50,104,104,,,78f4633d0e073c543c1a0a27364822fc
7
+ spheroid/test/105,val,spheroid/test,spheroid,LS174T spheroid,collagen I,,,50,105,105,,,00c65c42c2975be77573145dfddaff21
8
+ spheroid/test/106,val,spheroid/test,spheroid,LS174T spheroid,collagen I,,,50,106,106,,,dd4a683772ad8def9e81b2c7f3de7c1f
9
+ spheroid/test/107,val,spheroid/test,spheroid,LS174T spheroid,collagen I,,,50,107,107,,,007c58caae5e1131392612b4f37351e6
10
+ spheroid/test/108,val,spheroid/test,spheroid,LS174T spheroid,collagen I,,,50,108,108,,,89fa7d0f134e20dc8715ffeb3c6e18f0
11
+ spheroid/test/109,val,spheroid/test,spheroid,LS174T spheroid,collagen I,,,50,109,109,,,27756e72516436ff0f95a599e4dee220
12
+ spheroid/test/82,val,spheroid/test,spheroid,LS174T spheroid,collagen I,,,50,82,82,,,5098cd2ec1a6e107a761d0746ae9c321
13
+ spheroid/test/83,val,spheroid/test,spheroid,LS174T spheroid,collagen I,,,50,83,83,,,759be59a5b7e5fd9460e176703e5a383
14
+ spheroid/test/84,val,spheroid/test,spheroid,LS174T spheroid,collagen I,,,50,84,84,,,8d8aded9cd7165b7312b8e32064d50f0
15
+ spheroid/test/85,val,spheroid/test,spheroid,LS174T spheroid,collagen I,,,50,85,85,,,c2d042295145dfef4813f0d4d8022130
16
+ spheroid/test/86,val,spheroid/test,spheroid,LS174T spheroid,collagen I,,,50,86,86,,,2c520df579d0822aa83402fe978a67d1
17
+ spheroid/test/87,val,spheroid/test,spheroid,LS174T spheroid,collagen I,,,50,87,87,,,e3b070f2aaf68dad267d8eb0939f52f2
18
+ spheroid/test/88,val,spheroid/test,spheroid,LS174T spheroid,collagen I,,,50,88,88,,,571853d0e551930cf245f4c01989c67c
19
+ spheroid/test/89,val,spheroid/test,spheroid,LS174T spheroid,collagen I,,,50,89,89,,,e2a681a9fc785ab25f892629fb5686a7
20
+ spheroid/test/90,val,spheroid/test,spheroid,LS174T spheroid,collagen I,,,50,90,90,,,429534d23010e9937ca4d928c310a524
21
+ spheroid/test/91,val,spheroid/test,spheroid,LS174T spheroid,collagen I,,,50,91,91,,,d73290323d14e73983bbce995ee06821
22
+ spheroid/test/92,val,spheroid/test,spheroid,LS174T spheroid,collagen I,,,50,92,92,,,58ca6e1b5cf2fce74fd177357f1cfae6
23
+ spheroid/test/93,val,spheroid/test,spheroid,LS174T spheroid,collagen I,,,50,93,93,,,9339c4e8f3011783948fb897bcdd42ce
24
+ spheroid/test/94,val,spheroid/test,spheroid,LS174T spheroid,collagen I,,,50,94,94,,,a286e2ea828a376f8106fd0f1a2ec190
25
+ spheroid/test/95,val,spheroid/test,spheroid,LS174T spheroid,collagen I,,,50,95,95,,,fd7dc5fb5c720ffca0f76024b4b8256f
26
+ spheroid/test/96,val,spheroid/test,spheroid,LS174T spheroid,collagen I,,,50,96,96,,,d4052d51172c20158b5c2c1203e4b9a1
27
+ spheroid/test/97,val,spheroid/test,spheroid,LS174T spheroid,collagen I,,,50,97,97,,,3d125833aa63515212276d508936547e
28
+ spheroid/test/98,val,spheroid/test,spheroid,LS174T spheroid,collagen I,,,50,98,98,,,24ac6aa716d0a01b8bdf59fadfa884d9
29
+ spheroid/test/99,val,spheroid/test,spheroid,LS174T spheroid,collagen I,,,50,99,99,,,b1fee6ec7d20f429c8c56c650f21cfe6
experiments/splits/test_fibro_1kPa_setIII.csv ADDED
@@ -0,0 +1,18 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ sample_dir,split,set,condition,cell_type,coating,young_Pa,tfm_pixelsize,ythreshold_Pa,legacy_folder,legacy_substrate_code,substrate_legacy,substrate_nominal,bf_md5
2
+ singlecell_external/fibro_1kPa_setIII/Position_04,test,1kPa_SET_III,1 kPa collagen,HFF,collagen I,1000,3.0769,500,Position_04,Posi,fibroblasts_PDMS,PDMS_1kPa_3um,24d12e05f66757e311fddbff3fffccda
3
+ singlecell_external/fibro_1kPa_setIII/Position_06,test,1kPa_SET_III,1 kPa collagen,HFF,collagen I,1000,3.0769,500,Position_06,Posi,fibroblasts_PDMS,PDMS_1kPa_3um,c7e3028810245044cd2b1be59048894d
4
+ singlecell_external/fibro_1kPa_setIII/Position_10,test,1kPa_SET_III,1 kPa collagen,HFF,collagen I,1000,3.0769,500,Position_10,Posi,fibroblasts_PDMS,PDMS_1kPa_3um,af932dddbcfcf96456e801ed8d670831
5
+ singlecell_external/fibro_1kPa_setIII/Position_11,test,1kPa_SET_III,1 kPa collagen,HFF,collagen I,1000,3.0769,500,Position_11,Posi,fibroblasts_PDMS,PDMS_1kPa_3um,112705c19ea55ce32740f0a8d708ee67
6
+ singlecell_external/fibro_1kPa_setIII/Position_12,test,1kPa_SET_III,1 kPa collagen,HFF,collagen I,1000,3.0769,500,Position_12,Posi,fibroblasts_PDMS,PDMS_1kPa_3um,0ed6ad89352c0fd179d8b50da0face5f
7
+ singlecell_external/fibro_1kPa_setIII/Position_14,test,1kPa_SET_III,1 kPa collagen,HFF,collagen I,1000,3.0769,500,Position_14,Posi,fibroblasts_PDMS,PDMS_1kPa_3um,9f6a39f93b17f042159741e2057d5bd7
8
+ singlecell_external/fibro_1kPa_setIII/Position_17,test,1kPa_SET_III,1 kPa collagen,HFF,collagen I,1000,3.0769,500,Position_17,Posi,fibroblasts_PDMS,PDMS_1kPa_3um,7eda149aa142b24151ec2343920c143a
9
+ singlecell_external/fibro_1kPa_setIII/Position_18,test,1kPa_SET_III,1 kPa collagen,HFF,collagen I,1000,3.0769,500,Position_18,Posi,fibroblasts_PDMS,PDMS_1kPa_3um,99235aa5adf25f3a3235a2f1a1176309
10
+ singlecell_external/fibro_1kPa_setIII/Position_20,test,1kPa_SET_III,1 kPa collagen,HFF,collagen I,1000,3.0769,500,Position_20,Posi,fibroblasts_PDMS,PDMS_1kPa_3um,6e0a0df7c119a21a58834fe01aa08558
11
+ singlecell_external/fibro_1kPa_setIII/Position_21,test,1kPa_SET_III,1 kPa collagen,HFF,collagen I,1000,3.0769,500,Position_21,Posi,fibroblasts_PDMS,PDMS_1kPa_3um,e3b56dfcfcc96c62b596856d37c0bb55
12
+ singlecell_external/fibro_1kPa_setIII/Position_22,test,1kPa_SET_III,1 kPa collagen,HFF,collagen I,1000,3.0769,500,Position_22,Posi,fibroblasts_PDMS,PDMS_1kPa_3um,6c6544d2f4eed4c4d8739362ebedde71
13
+ singlecell_external/fibro_1kPa_setIII/Position_23,test,1kPa_SET_III,1 kPa collagen,HFF,collagen I,1000,3.0769,500,Position_23,Posi,fibroblasts_PDMS,PDMS_1kPa_3um,c89579bacd82038f600d714c3c501168
14
+ singlecell_external/fibro_1kPa_setIII/Position_26,test,1kPa_SET_III,1 kPa collagen,HFF,collagen I,1000,3.0769,500,Position_26,Posi,fibroblasts_PDMS,PDMS_1kPa_3um,fe3e78b2ab41ebf2f8e421b584747682
15
+ singlecell_external/fibro_1kPa_setIII/Position_27,test,1kPa_SET_III,1 kPa collagen,HFF,collagen I,1000,3.0769,500,Position_27,Posi,fibroblasts_PDMS,PDMS_1kPa_3um,4410e53536f9cf03c2b6992c5e162876
16
+ singlecell_external/fibro_1kPa_setIII/Position_28,test,1kPa_SET_III,1 kPa collagen,HFF,collagen I,1000,3.0769,500,Position_28,Posi,fibroblasts_PDMS,PDMS_1kPa_3um,6092d76dba0f000def4a6738afd45823
17
+ singlecell_external/fibro_1kPa_setIII/Position_29,test,1kPa_SET_III,1 kPa collagen,HFF,collagen I,1000,3.0769,500,Position_29,Posi,fibroblasts_PDMS,PDMS_1kPa_3um,75006160b6ce20fe3911e51ef8b89dac
18
+ singlecell_external/fibro_1kPa_setIII/Position_30,test,1kPa_SET_III,1 kPa collagen,HFF,collagen I,1000,3.0769,500,Position_30,Posi,fibroblasts_PDMS,PDMS_1kPa_3um,d1dd191f91fe5048fc62d9f2d0d33e55
experiments/splits/test_fibro_DMSO_setI.csv ADDED
@@ -0,0 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ sample_dir,split,set,condition,cell_type,coating,young_Pa,tfm_pixelsize,ythreshold_Pa,legacy_folder,legacy_substrate_code,substrate_legacy,substrate_nominal,bf_md5
2
+ singlecell_external/fibro_DMSO_setI/Position_01,test,Control_SET_I,DMSO,HFF,collagen I,6000,3.0769,500,Position_01,Posi,fibroblasts_PDMS,fibroblasts_PDMS,56c8ae4cd898cd84a24286e1843558ce
3
+ singlecell_external/fibro_DMSO_setI/Position_02,test,Control_SET_I,DMSO,HFF,collagen I,6000,3.0769,500,Position_02,Posi,fibroblasts_PDMS,fibroblasts_PDMS,d8316322f010a05b4d6594a2c9dcbad0
4
+ singlecell_external/fibro_DMSO_setI/Position_06,test,Control_SET_I,DMSO,HFF,collagen I,6000,3.0769,500,Position_06,Posi,fibroblasts_PDMS,fibroblasts_PDMS,adc6789deb2551c84f305c020a603ab4
5
+ singlecell_external/fibro_DMSO_setI/Position_07,test,Control_SET_I,DMSO,HFF,collagen I,6000,3.0769,500,Position_07,Posi,fibroblasts_PDMS,fibroblasts_PDMS,9770e009a9b6fda39f4eb7c6810746c4
6
+ singlecell_external/fibro_DMSO_setI/Position_08,test,Control_SET_I,DMSO,HFF,collagen I,6000,3.0769,500,Position_08,Posi,fibroblasts_PDMS,fibroblasts_PDMS,032450e3aee4a2cef787d30b133a0b2e
7
+ singlecell_external/fibro_DMSO_setI/Position_10,test,Control_SET_I,DMSO,HFF,collagen I,6000,3.0769,500,Position_10,Posi,fibroblasts_PDMS,fibroblasts_PDMS,862b8bd322057f0feff8c6fe2878ef84
8
+ singlecell_external/fibro_DMSO_setI/Position_11,test,Control_SET_I,DMSO,HFF,collagen I,6000,3.0769,500,Position_11,Posi,fibroblasts_PDMS,fibroblasts_PDMS,dfe73f6bbe53d1206442553834912197
9
+ singlecell_external/fibro_DMSO_setI/Position_12,test,Control_SET_I,DMSO,HFF,collagen I,6000,3.0769,500,Position_12,Posi,fibroblasts_PDMS,fibroblasts_PDMS,d136e0defa028a5e94b33f0886fa0536
10
+ singlecell_external/fibro_DMSO_setI/Position_13,test,Control_SET_I,DMSO,HFF,collagen I,6000,3.0769,500,Position_13,Posi,fibroblasts_PDMS,fibroblasts_PDMS,7a8ccfe4a90ba9cca483416c0b0b89b2
11
+ singlecell_external/fibro_DMSO_setI/Position_14,test,Control_SET_I,DMSO,HFF,collagen I,6000,3.0769,500,Position_14,Posi,fibroblasts_PDMS,fibroblasts_PDMS,02f89fe55b895856c1ffd3f0e985174e
12
+ singlecell_external/fibro_DMSO_setI/Position_15,test,Control_SET_I,DMSO,HFF,collagen I,6000,3.0769,500,Position_15,Posi,fibroblasts_PDMS,fibroblasts_PDMS,2af53b6829b669d3603f40101c706247
13
+ singlecell_external/fibro_DMSO_setI/Position_16,test,Control_SET_I,DMSO,HFF,collagen I,6000,3.0769,500,Position_16,Posi,fibroblasts_PDMS,fibroblasts_PDMS,b55207a305ebb64138d4519acedce3fc
14
+ singlecell_external/fibro_DMSO_setI/Position_17,test,Control_SET_I,DMSO,HFF,collagen I,6000,3.0769,500,Position_17,Posi,fibroblasts_PDMS,fibroblasts_PDMS,2a89c66f04956fecd64c80e1fa7c721b
15
+ singlecell_external/fibro_DMSO_setI/Position_18,test,Control_SET_I,DMSO,HFF,collagen I,6000,3.0769,500,Position_18,Posi,fibroblasts_PDMS,fibroblasts_PDMS,3ce3b4406cab0f8ad627b3002e2dca51
16
+ singlecell_external/fibro_DMSO_setI/Position_19,test,Control_SET_I,DMSO,HFF,collagen I,6000,3.0769,500,Position_19,Posi,fibroblasts_PDMS,fibroblasts_PDMS,0130c7aac91ad1748db8950cde2229e0
17
+ singlecell_external/fibro_DMSO_setI/Position_20,test,Control_SET_I,DMSO,HFF,collagen I,6000,3.0769,500,Position_20,Posi,fibroblasts_PDMS,fibroblasts_PDMS,116cce653cb6b6c2f1c3f8ff73d0852d
18
+ singlecell_external/fibro_DMSO_setI/Position_21,test,Control_SET_I,DMSO,HFF,collagen I,6000,3.0769,500,Position_21,Posi,fibroblasts_PDMS,fibroblasts_PDMS,ad19e3ada002d644b6f87f84c2842431
19
+ singlecell_external/fibro_DMSO_setI/Position_22,test,Control_SET_I,DMSO,HFF,collagen I,6000,3.0769,500,Position_22,Posi,fibroblasts_PDMS,fibroblasts_PDMS,65b361f7b39a7a81ed149a3baeb6d7c3
20
+ singlecell_external/fibro_DMSO_setI/Position_25,test,Control_SET_I,DMSO,HFF,collagen I,6000,3.0769,500,Position_25,Posi,fibroblasts_PDMS,fibroblasts_PDMS,e72f67045702a35f14bc7dc525091db2
21
+ singlecell_external/fibro_DMSO_setI/Position_26,test,Control_SET_I,DMSO,HFF,collagen I,6000,3.0769,500,Position_26,Posi,fibroblasts_PDMS,fibroblasts_PDMS,5e05f82da909fd5abc635f82aaf5901c
22
+ singlecell_external/fibro_DMSO_setI/Position_27,test,Control_SET_I,DMSO,HFF,collagen I,6000,3.0769,500,Position_27,Posi,fibroblasts_PDMS,fibroblasts_PDMS,6d2e523c3f7e4aa880b3fd180a383894
23
+ singlecell_external/fibro_DMSO_setI/Position_28,test,Control_SET_I,DMSO,HFF,collagen I,6000,3.0769,500,Position_28,Posi,fibroblasts_PDMS,fibroblasts_PDMS,0c6cf7ec3b14e48316795c7817f1b3c3
24
+ singlecell_external/fibro_DMSO_setI/Position_29,test,Control_SET_I,DMSO,HFF,collagen I,6000,3.0769,500,Position_29,Posi,fibroblasts_PDMS,fibroblasts_PDMS,312d78f27816a9d6d54c0a953a1bb1b8
25
+ singlecell_external/fibro_DMSO_setI/Position_31,test,Control_SET_I,DMSO,HFF,collagen I,6000,3.0769,500,Position_31,Posi,fibroblasts_PDMS,fibroblasts_PDMS,0a1314b13279b671457eac685a97e534
26
+ singlecell_external/fibro_DMSO_setI/Position_32,test,Control_SET_I,DMSO,HFF,collagen I,6000,3.0769,500,Position_32,Posi,fibroblasts_PDMS,fibroblasts_PDMS,1c9f5f1e87acbd7c10e4215d45ad3375
27
+ singlecell_external/fibro_DMSO_setI/Position_33,test,Control_SET_I,DMSO,HFF,collagen I,6000,3.0769,500,Position_33,Posi,fibroblasts_PDMS,fibroblasts_PDMS,3f1202c6084a0028b61be3d563491f31
28
+ singlecell_external/fibro_DMSO_setI/Position_34,test,Control_SET_I,DMSO,HFF,collagen I,6000,3.0769,500,Position_34,Posi,fibroblasts_PDMS,fibroblasts_PDMS,7e5325112678dfe6b05729068211a1bf
experiments/splits/test_fibro_DMSO_setII.csv ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ sample_dir,split,set,condition,cell_type,coating,young_Pa,tfm_pixelsize,ythreshold_Pa,legacy_folder,legacy_substrate_code,substrate_legacy,substrate_nominal,bf_md5
2
+ singlecell_external/fibro_DMSO_setII/Position_01,test,DMSO_SET_II,DMSO,HFF,collagen I,6000,3.0769,500,Position_01,Posi,fibroblasts_PDMS,fibroblasts_PDMS,370644cf9014c6ce1f8ef3c67fa2363c
3
+ singlecell_external/fibro_DMSO_setII/Position_02,test,DMSO_SET_II,DMSO,HFF,collagen I,6000,3.0769,500,Position_02,Posi,fibroblasts_PDMS,fibroblasts_PDMS,cc19a37f5c028a9845356fe6c337cda9
4
+ singlecell_external/fibro_DMSO_setII/Position_02b,test,DMSO_SET_II,DMSO,HFF,collagen I,6000,3.0769,500,Position_02b,Posi,fibroblasts_PDMS,fibroblasts_PDMS,0c3ec7b819a9c758dba6d540e6d97075
5
+ singlecell_external/fibro_DMSO_setII/Position_05,test,DMSO_SET_II,DMSO,HFF,collagen I,6000,3.0769,500,Position_05,Posi,fibroblasts_PDMS,fibroblasts_PDMS,f64b80f4a18724db16ef3742efe6d654
6
+ singlecell_external/fibro_DMSO_setII/Position_06,test,DMSO_SET_II,DMSO,HFF,collagen I,6000,3.0769,500,Position_06,Posi,fibroblasts_PDMS,fibroblasts_PDMS,83039fa40e9b5cbd4dc920620c14ce6e
7
+ singlecell_external/fibro_DMSO_setII/Position_08,test,DMSO_SET_II,DMSO,HFF,collagen I,6000,3.0769,500,Position_08,Posi,fibroblasts_PDMS,fibroblasts_PDMS,07a6bdcc040ec225e5f18aa6bf90c47c
8
+ singlecell_external/fibro_DMSO_setII/Position_11,test,DMSO_SET_II,DMSO,HFF,collagen I,6000,3.0769,500,Position_11,Posi,fibroblasts_PDMS,fibroblasts_PDMS,96dded3f8ea2a30648a5df10231b8dca
9
+ singlecell_external/fibro_DMSO_setII/Position_12,test,DMSO_SET_II,DMSO,HFF,collagen I,6000,3.0769,500,Position_12,Posi,fibroblasts_PDMS,fibroblasts_PDMS,21b99930e0667fbef1a802d3ae931f2e
10
+ singlecell_external/fibro_DMSO_setII/Position_14,test,DMSO_SET_II,DMSO,HFF,collagen I,6000,3.0769,500,Position_14,Posi,fibroblasts_PDMS,fibroblasts_PDMS,3cd48997199749dc08d45520523fa9fa
11
+ singlecell_external/fibro_DMSO_setII/Position_35,test,DMSO_SET_II,DMSO,HFF,collagen I,6000,3.0769,500,Position_35,Posi,fibroblasts_PDMS,fibroblasts_PDMS,4bcf896ae0a6893742b13ba3b948d4cb
12
+ singlecell_external/fibro_DMSO_setII/Position_47,test,DMSO_SET_II,DMSO,HFF,collagen I,6000,3.0769,500,Position_47,Posi,fibroblasts_PDMS,fibroblasts_PDMS,d8aef4a461b5dc1f56bfa54bf286dfe4
experiments/splits/test_fibro_TGFb_setI.csv ADDED
@@ -0,0 +1,16 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ sample_dir,split,set,condition,cell_type,coating,young_Pa,tfm_pixelsize,ythreshold_Pa,legacy_folder,legacy_substrate_code,substrate_legacy,substrate_nominal,bf_md5
2
+ singlecell_external/fibro_TGFb_setI/Position_01,test,TGFB_SET_I,TGF-beta,HFF,collagen I,6000,3.0769,500,Position_01,Posi,fibroblasts_PDMS,fibroblasts_PDMS,e93f67bb6c8d1fe4460d5fd92273ee5c
3
+ singlecell_external/fibro_TGFb_setI/Position_05,test,TGFB_SET_I,TGF-beta,HFF,collagen I,6000,3.0769,500,Position_05,Posi,fibroblasts_PDMS,fibroblasts_PDMS,32c9706ba58acdea1bff4096635bc66d
4
+ singlecell_external/fibro_TGFb_setI/Position_10,test,TGFB_SET_I,TGF-beta,HFF,collagen I,6000,3.0769,500,Position_10,Posi,fibroblasts_PDMS,fibroblasts_PDMS,80cbd18d6864eb79b857c31a46a6f625
5
+ singlecell_external/fibro_TGFb_setI/Position_11,test,TGFB_SET_I,TGF-beta,HFF,collagen I,6000,3.0769,500,Position_11,Posi,fibroblasts_PDMS,fibroblasts_PDMS,beb1bf26c07536ce984c45a2b48c1d49
6
+ singlecell_external/fibro_TGFb_setI/Position_12,test,TGFB_SET_I,TGF-beta,HFF,collagen I,6000,3.0769,500,Position_12,Posi,fibroblasts_PDMS,fibroblasts_PDMS,6b9dc506ec18c0811baa2a411464f4dc
7
+ singlecell_external/fibro_TGFb_setI/Position_13,test,TGFB_SET_I,TGF-beta,HFF,collagen I,6000,3.0769,500,Position_13,Posi,fibroblasts_PDMS,fibroblasts_PDMS,20fdaa1df36d3045f4bc5977b74d973e
8
+ singlecell_external/fibro_TGFb_setI/Position_14,test,TGFB_SET_I,TGF-beta,HFF,collagen I,6000,3.0769,500,Position_14,Posi,fibroblasts_PDMS,fibroblasts_PDMS,ab167b264fe8c14eaba587dabe5054fa
9
+ singlecell_external/fibro_TGFb_setI/Position_15,test,TGFB_SET_I,TGF-beta,HFF,collagen I,6000,3.0769,500,Position_15,Posi,fibroblasts_PDMS,fibroblasts_PDMS,49b260dd06fe973f6880ffda5e6a0612
10
+ singlecell_external/fibro_TGFb_setI/Position_16,test,TGFB_SET_I,TGF-beta,HFF,collagen I,6000,3.0769,500,Position_16,Posi,fibroblasts_PDMS,fibroblasts_PDMS,a859cdad607d0b150363935e2d434c38
11
+ singlecell_external/fibro_TGFb_setI/Position_17,test,TGFB_SET_I,TGF-beta,HFF,collagen I,6000,3.0769,500,Position_17,Posi,fibroblasts_PDMS,fibroblasts_PDMS,8e91409a9753bd905fbab33fe5bf7a07
12
+ singlecell_external/fibro_TGFb_setI/Position_18,test,TGFB_SET_I,TGF-beta,HFF,collagen I,6000,3.0769,500,Position_18,Posi,fibroblasts_PDMS,fibroblasts_PDMS,1ff53d61f5244ac3cd2994ea8fec1a31
13
+ singlecell_external/fibro_TGFb_setI/Position_19,test,TGFB_SET_I,TGF-beta,HFF,collagen I,6000,3.0769,500,Position_19,Posi,fibroblasts_PDMS,fibroblasts_PDMS,8988ac7854293bfe80453c7721e006d6
14
+ singlecell_external/fibro_TGFb_setI/Position_20,test,TGFB_SET_I,TGF-beta,HFF,collagen I,6000,3.0769,500,Position_20,Posi,fibroblasts_PDMS,fibroblasts_PDMS,cbd3afe61a16a1cabbe802da4829b0c6
15
+ singlecell_external/fibro_TGFb_setI/Position_22,test,TGFB_SET_I,TGF-beta,HFF,collagen I,6000,3.0769,500,Position_22,Posi,fibroblasts_PDMS,fibroblasts_PDMS,50ffe37d215ea802975f63c34dd7c18b
16
+ singlecell_external/fibro_TGFb_setI/Position_23,test,TGFB_SET_I,TGF-beta,HFF,collagen I,6000,3.0769,500,Position_23,Posi,fibroblasts_PDMS,fibroblasts_PDMS,122e5e6fae2611c16ade255b8a891c27
experiments/splits/test_fibro_Y27632_setI.csv ADDED
@@ -0,0 +1,17 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ sample_dir,split,set,condition,cell_type,coating,young_Pa,tfm_pixelsize,ythreshold_Pa,legacy_folder,legacy_substrate_code,substrate_legacy,substrate_nominal,bf_md5
2
+ singlecell_external/fibro_Y27632_setI/Position_02,test,Y27632_SET_I,Y-27632,HFF,collagen I,6000,3.0769,500,Position_02,Posi,fibroblasts_PDMS,fibroblasts_PDMS,309140990a7a858bb3c6a9760b4dbda5
3
+ singlecell_external/fibro_Y27632_setI/Position_03,test,Y27632_SET_I,Y-27632,HFF,collagen I,6000,3.0769,500,Position_03,Posi,fibroblasts_PDMS,fibroblasts_PDMS,0be7a62d7b656e9505cd422118932372
4
+ singlecell_external/fibro_Y27632_setI/Position_08,test,Y27632_SET_I,Y-27632,HFF,collagen I,6000,3.0769,500,Position_08,Posi,fibroblasts_PDMS,fibroblasts_PDMS,c5df3db9d09bee83ed61b15445ef6ef2
5
+ singlecell_external/fibro_Y27632_setI/Position_10,test,Y27632_SET_I,Y-27632,HFF,collagen I,6000,3.0769,500,Position_10,Posi,fibroblasts_PDMS,fibroblasts_PDMS,fa7ee5e0cd24b6faf98cb0a34e6fa5a6
6
+ singlecell_external/fibro_Y27632_setI/Position_11,test,Y27632_SET_I,Y-27632,HFF,collagen I,6000,3.0769,500,Position_11,Posi,fibroblasts_PDMS,fibroblasts_PDMS,93db5b92e10e79ca14bef923fae3be58
7
+ singlecell_external/fibro_Y27632_setI/Position_12,test,Y27632_SET_I,Y-27632,HFF,collagen I,6000,3.0769,500,Position_12,Posi,fibroblasts_PDMS,fibroblasts_PDMS,5bc4b4f3f44ab7be3e433d3ebc0631ee
8
+ singlecell_external/fibro_Y27632_setI/Position_13,test,Y27632_SET_I,Y-27632,HFF,collagen I,6000,3.0769,500,Position_13,Posi,fibroblasts_PDMS,fibroblasts_PDMS,25823af4b2899ae79f2f28dcfeba7a1c
9
+ singlecell_external/fibro_Y27632_setI/Position_15,test,Y27632_SET_I,Y-27632,HFF,collagen I,6000,3.0769,500,Position_15,Posi,fibroblasts_PDMS,fibroblasts_PDMS,6b63a1212736fd03ea97eeed24cde95e
10
+ singlecell_external/fibro_Y27632_setI/Position_16,test,Y27632_SET_I,Y-27632,HFF,collagen I,6000,3.0769,500,Position_16,Posi,fibroblasts_PDMS,fibroblasts_PDMS,7ab414ccc1313f0c7ab4a8e9be3a95ed
11
+ singlecell_external/fibro_Y27632_setI/Position_17,test,Y27632_SET_I,Y-27632,HFF,collagen I,6000,3.0769,500,Position_17,Posi,fibroblasts_PDMS,fibroblasts_PDMS,4ff0daa0c270f9ffd5939b9c303a9e90
12
+ singlecell_external/fibro_Y27632_setI/Position_19,test,Y27632_SET_I,Y-27632,HFF,collagen I,6000,3.0769,500,Position_19,Posi,fibroblasts_PDMS,fibroblasts_PDMS,81dcf0ad13b4bd4540f0433fdd850053
13
+ singlecell_external/fibro_Y27632_setI/Position_22,test,Y27632_SET_I,Y-27632,HFF,collagen I,6000,3.0769,500,Position_22,Posi,fibroblasts_PDMS,fibroblasts_PDMS,e0c9c395501c737cb690aaca14f4c2de
14
+ singlecell_external/fibro_Y27632_setI/Position_23,test,Y27632_SET_I,Y-27632,HFF,collagen I,6000,3.0769,500,Position_23,Posi,fibroblasts_PDMS,fibroblasts_PDMS,4ff8de5325e9c8e0aab6ec49f52fce07
15
+ singlecell_external/fibro_Y27632_setI/Position_25,test,Y27632_SET_I,Y-27632,HFF,collagen I,6000,3.0769,500,Position_25,Posi,fibroblasts_PDMS,fibroblasts_PDMS,440703a4e7b38872f21d8c2e4b57a0a4
16
+ singlecell_external/fibro_Y27632_setI/Position_26,test,Y27632_SET_I,Y-27632,HFF,collagen I,6000,3.0769,500,Position_26,Posi,fibroblasts_PDMS,fibroblasts_PDMS,a72f4c30759906b5eb3c741f8fb44c28
17
+ singlecell_external/fibro_Y27632_setI/Position_27,test,Y27632_SET_I,Y-27632,HFF,collagen I,6000,3.0769,500,Position_27,Posi,fibroblasts_PDMS,fibroblasts_PDMS,4a5882946fb29af2a4a37b605075d759
experiments/splits/test_fibro_Y27632_setII.csv ADDED
@@ -0,0 +1,21 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ sample_dir,split,set,condition,cell_type,coating,young_Pa,tfm_pixelsize,ythreshold_Pa,legacy_folder,legacy_substrate_code,substrate_legacy,substrate_nominal,bf_md5
2
+ singlecell_external/fibro_Y27632_setII/Position_03,test,Y27632_SET_II,Y-27632,HFF,collagen I,6000,3.0769,500,Position_03,Posi,fibroblasts_PDMS,fibroblasts_PDMS,411a614897d157be68353b945fb0a043
3
+ singlecell_external/fibro_Y27632_setII/Position_04,test,Y27632_SET_II,Y-27632,HFF,collagen I,6000,3.0769,500,Position_04,Posi,fibroblasts_PDMS,fibroblasts_PDMS,ad8a064e0d0fe16aa1a5c5f5f6e526de
4
+ singlecell_external/fibro_Y27632_setII/Position_04b,test,Y27632_SET_II,Y-27632,HFF,collagen I,6000,3.0769,500,Position_04b,Posi,fibroblasts_PDMS,fibroblasts_PDMS,6b7be438b84e036547dd7616bc17548d
5
+ singlecell_external/fibro_Y27632_setII/Position_08,test,Y27632_SET_II,Y-27632,HFF,collagen I,6000,3.0769,500,Position_08,Posi,fibroblasts_PDMS,fibroblasts_PDMS,07a6bdcc040ec225e5f18aa6bf90c47c
6
+ singlecell_external/fibro_Y27632_setII/Position_13,test,Y27632_SET_II,Y-27632,HFF,collagen I,6000,3.0769,500,Position_13,Posi,fibroblasts_PDMS,fibroblasts_PDMS,8d27833f86aae7b8ef7e74d8256d7dd5
7
+ singlecell_external/fibro_Y27632_setII/Position_14,test,Y27632_SET_II,Y-27632,HFF,collagen I,6000,3.0769,500,Position_14,Posi,fibroblasts_PDMS,fibroblasts_PDMS,c8e568a1f9825f2cba60bb9e3e7474d7
8
+ singlecell_external/fibro_Y27632_setII/Position_18,test,Y27632_SET_II,Y-27632,HFF,collagen I,6000,3.0769,500,Position_18,Posi,fibroblasts_PDMS,fibroblasts_PDMS,f9ec5709204eff113280af0dc9410a59
9
+ singlecell_external/fibro_Y27632_setII/Position_20,test,Y27632_SET_II,Y-27632,HFF,collagen I,6000,3.0769,500,Position_20,Posi,fibroblasts_PDMS,fibroblasts_PDMS,164b7bb2ee7875fd2c5e70136174b8c6
10
+ singlecell_external/fibro_Y27632_setII/Position_21,test,Y27632_SET_II,Y-27632,HFF,collagen I,6000,3.0769,500,Position_21,Posi,fibroblasts_PDMS,fibroblasts_PDMS,bcc0e3f8d0fbd275101add3ecd5f8b2d
11
+ singlecell_external/fibro_Y27632_setII/Position_22,test,Y27632_SET_II,Y-27632,HFF,collagen I,6000,3.0769,500,Position_22,Posi,fibroblasts_PDMS,fibroblasts_PDMS,334974cc07973fbfe233cdf0cbc0b91e
12
+ singlecell_external/fibro_Y27632_setII/Position_27,test,Y27632_SET_II,Y-27632,HFF,collagen I,6000,3.0769,500,Position_27,Posi,fibroblasts_PDMS,fibroblasts_PDMS,059bbd3ce5cf2ae380bf07f12388d264
13
+ singlecell_external/fibro_Y27632_setII/Position_28,test,Y27632_SET_II,Y-27632,HFF,collagen I,6000,3.0769,500,Position_28,Posi,fibroblasts_PDMS,fibroblasts_PDMS,02190d24b8832d6ce51956fb619e9b0a
14
+ singlecell_external/fibro_Y27632_setII/Position_29,test,Y27632_SET_II,Y-27632,HFF,collagen I,6000,3.0769,500,Position_29,Posi,fibroblasts_PDMS,fibroblasts_PDMS,ecb33d7eb1fb8f79a92ce5aa1ff9c13e
15
+ singlecell_external/fibro_Y27632_setII/Position_30,test,Y27632_SET_II,Y-27632,HFF,collagen I,6000,3.0769,500,Position_30,Posi,fibroblasts_PDMS,fibroblasts_PDMS,c15dc91409179d33ca0665e6c7fd227f
16
+ singlecell_external/fibro_Y27632_setII/Position_34,test,Y27632_SET_II,Y-27632,HFF,collagen I,6000,3.0769,500,Position_34,Posi,fibroblasts_PDMS,fibroblasts_PDMS,fb1f3a034bd884efc85a4408e3f70634
17
+ singlecell_external/fibro_Y27632_setII/Position_37,test,Y27632_SET_II,Y-27632,HFF,collagen I,6000,3.0769,500,Position_37,Posi,fibroblasts_PDMS,fibroblasts_PDMS,d6ef8df2c1dd20fad9f847250c8f9fa0
18
+ singlecell_external/fibro_Y27632_setII/Position_40,test,Y27632_SET_II,Y-27632,HFF,collagen I,6000,3.0769,500,Position_40,Posi,fibroblasts_PDMS,fibroblasts_PDMS,632dfa31052b125fc1f30303adb5c29a
19
+ singlecell_external/fibro_Y27632_setII/Position_41,test,Y27632_SET_II,Y-27632,HFF,collagen I,6000,3.0769,500,Position_41,Posi,fibroblasts_PDMS,fibroblasts_PDMS,8c253f8c8b79371310cf267fd4e1cb0c
20
+ singlecell_external/fibro_Y27632_setII/Position_42,test,Y27632_SET_II,Y-27632,HFF,collagen I,6000,3.0769,500,Position_42,Posi,fibroblasts_PDMS,fibroblasts_PDMS,b02dd8de5a1478feed44a25a2af35498
21
+ singlecell_external/fibro_Y27632_setII/Position_48,test,Y27632_SET_II,Y-27632,HFF,collagen I,6000,3.0769,500,Position_48,Posi,fibroblasts_PDMS,fibroblasts_PDMS,6b5330dfa38da545bed011ad63343e6e
experiments/splits/test_fibro_fibronectin_setI.csv ADDED
@@ -0,0 +1,41 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ sample_dir,split,set,condition,cell_type,coating,young_Pa,tfm_pixelsize,ythreshold_Pa,legacy_folder,legacy_substrate_code,substrate_legacy,substrate_nominal,bf_md5
2
+ singlecell_external/fibro_fibronectin_setI/Position_01,test,Fibronectin_SET_I,fibronectin,HFF,fibronectin,6000,3.0769,500,Position_01,Posi,fibroblasts_PDMS,fibroblasts_PDMS,158a108e2caceade32369aafe950cf4c
3
+ singlecell_external/fibro_fibronectin_setI/Position_02,test,Fibronectin_SET_I,fibronectin,HFF,fibronectin,6000,3.0769,500,Position_02,Posi,fibroblasts_PDMS,fibroblasts_PDMS,ed6e08b8abf58c5dcf7e545ac842dd5c
4
+ singlecell_external/fibro_fibronectin_setI/Position_03,test,Fibronectin_SET_I,fibronectin,HFF,fibronectin,6000,3.0769,500,Position_03,Posi,fibroblasts_PDMS,fibroblasts_PDMS,51e36f16891c9509da0c56c467a3d50b
5
+ singlecell_external/fibro_fibronectin_setI/Position_04,test,Fibronectin_SET_I,fibronectin,HFF,fibronectin,6000,3.0769,500,Position_04,Posi,fibroblasts_PDMS,fibroblasts_PDMS,4706b91b1dc232e1b410fcf82619a8ea
6
+ singlecell_external/fibro_fibronectin_setI/Position_05,test,Fibronectin_SET_I,fibronectin,HFF,fibronectin,6000,3.0769,500,Position_05,Posi,fibroblasts_PDMS,fibroblasts_PDMS,6889b9156546bd5cdb81262d4060a6cf
7
+ singlecell_external/fibro_fibronectin_setI/Position_06,test,Fibronectin_SET_I,fibronectin,HFF,fibronectin,6000,3.0769,500,Position_06,Posi,fibroblasts_PDMS,fibroblasts_PDMS,ca0d60cfcf0ccfea0f6c3054d0370590
8
+ singlecell_external/fibro_fibronectin_setI/Position_07,test,Fibronectin_SET_I,fibronectin,HFF,fibronectin,6000,3.0769,500,Position_07,Posi,fibroblasts_PDMS,fibroblasts_PDMS,a6dc21744b6fb22b2a5cb726f107a305
9
+ singlecell_external/fibro_fibronectin_setI/Position_09,test,Fibronectin_SET_I,fibronectin,HFF,fibronectin,6000,3.0769,500,Position_09,Posi,fibroblasts_PDMS,fibroblasts_PDMS,f1cbfcf4cd4071d268d63278fdeefc56
10
+ singlecell_external/fibro_fibronectin_setI/Position_10,test,Fibronectin_SET_I,fibronectin,HFF,fibronectin,6000,3.0769,500,Position_10,Posi,fibroblasts_PDMS,fibroblasts_PDMS,1e1c172e07946d874cb9b4f557ee8395
11
+ singlecell_external/fibro_fibronectin_setI/Position_11,test,Fibronectin_SET_I,fibronectin,HFF,fibronectin,6000,3.0769,500,Position_11,Posi,fibroblasts_PDMS,fibroblasts_PDMS,0f41a445b607b58b959129d7fbc6488d
12
+ singlecell_external/fibro_fibronectin_setI/Position_12,test,Fibronectin_SET_I,fibronectin,HFF,fibronectin,6000,3.0769,500,Position_12,Posi,fibroblasts_PDMS,fibroblasts_PDMS,d742118fce159e7af2b9f6646315cef9
13
+ singlecell_external/fibro_fibronectin_setI/Position_13,test,Fibronectin_SET_I,fibronectin,HFF,fibronectin,6000,3.0769,500,Position_13,Posi,fibroblasts_PDMS,fibroblasts_PDMS,288a3a8047ae150cd59a635fa4be13ad
14
+ singlecell_external/fibro_fibronectin_setI/Position_14,test,Fibronectin_SET_I,fibronectin,HFF,fibronectin,6000,3.0769,500,Position_14,Posi,fibroblasts_PDMS,fibroblasts_PDMS,54d54feb41f3bdb7dbb6190d22a95241
15
+ singlecell_external/fibro_fibronectin_setI/Position_15,test,Fibronectin_SET_I,fibronectin,HFF,fibronectin,6000,3.0769,500,Position_15,Posi,fibroblasts_PDMS,fibroblasts_PDMS,99b2e132363806c51dd2d85255917721
16
+ singlecell_external/fibro_fibronectin_setI/Position_16,test,Fibronectin_SET_I,fibronectin,HFF,fibronectin,6000,3.0769,500,Position_16,Posi,fibroblasts_PDMS,fibroblasts_PDMS,3481a941a9fef0474060f14b267f7eb9
17
+ singlecell_external/fibro_fibronectin_setI/Position_17,test,Fibronectin_SET_I,fibronectin,HFF,fibronectin,6000,3.0769,500,Position_17,Posi,fibroblasts_PDMS,fibroblasts_PDMS,b7a2027bda852de532ddc04356bbe0b4
18
+ singlecell_external/fibro_fibronectin_setI/Position_18,test,Fibronectin_SET_I,fibronectin,HFF,fibronectin,6000,3.0769,500,Position_18,Posi,fibroblasts_PDMS,fibroblasts_PDMS,53ae5323bde7a9acbd7cb73b14164304
19
+ singlecell_external/fibro_fibronectin_setI/Position_19,test,Fibronectin_SET_I,fibronectin,HFF,fibronectin,6000,3.0769,500,Position_19,Posi,fibroblasts_PDMS,fibroblasts_PDMS,93d8b81a4cedbcca23f860c9dc391560
20
+ singlecell_external/fibro_fibronectin_setI/Position_20,test,Fibronectin_SET_I,fibronectin,HFF,fibronectin,6000,3.0769,500,Position_20,Posi,fibroblasts_PDMS,fibroblasts_PDMS,cf16aac274588dfadebb6ee70b09f5a2
21
+ singlecell_external/fibro_fibronectin_setI/Position_22,test,Fibronectin_SET_I,fibronectin,HFF,fibronectin,6000,3.0769,500,Position_22,Posi,fibroblasts_PDMS,fibroblasts_PDMS,d7507d1152d3cfd56faee005e98b2091
22
+ singlecell_external/fibro_fibronectin_setI/Position_23,test,Fibronectin_SET_I,fibronectin,HFF,fibronectin,6000,3.0769,500,Position_23,Posi,fibroblasts_PDMS,fibroblasts_PDMS,648c916a64704d23b8c39b3d4d74158d
23
+ singlecell_external/fibro_fibronectin_setI/Position_25,test,Fibronectin_SET_I,fibronectin,HFF,fibronectin,6000,3.0769,500,Position_25,Posi,fibroblasts_PDMS,fibroblasts_PDMS,2d777eff9d60fe4980f10f8883e03c2f
24
+ singlecell_external/fibro_fibronectin_setI/Position_26,test,Fibronectin_SET_I,fibronectin,HFF,fibronectin,6000,3.0769,500,Position_26,Posi,fibroblasts_PDMS,fibroblasts_PDMS,b0a0c117709a0d946b9a4f20ea46e505
25
+ singlecell_external/fibro_fibronectin_setI/Position_28,test,Fibronectin_SET_I,fibronectin,HFF,fibronectin,6000,3.0769,500,Position_28,Posi,fibroblasts_PDMS,fibroblasts_PDMS,3df19520c54fd222bd4dad14e0157a7f
26
+ singlecell_external/fibro_fibronectin_setI/Position_29,test,Fibronectin_SET_I,fibronectin,HFF,fibronectin,6000,3.0769,500,Position_29,Posi,fibroblasts_PDMS,fibroblasts_PDMS,0e00a0c7254d0a1f79bff8f3c849ae3d
27
+ singlecell_external/fibro_fibronectin_setI/Position_30,test,Fibronectin_SET_I,fibronectin,HFF,fibronectin,6000,3.0769,500,Position_30,Posi,fibroblasts_PDMS,fibroblasts_PDMS,c5d97ed97f8f03cbce96c1f54ded3d38
28
+ singlecell_external/fibro_fibronectin_setI/Position_31,test,Fibronectin_SET_I,fibronectin,HFF,fibronectin,6000,3.0769,500,Position_31,Posi,fibroblasts_PDMS,fibroblasts_PDMS,439f299d99a2f2f50a660c496b0163ff
29
+ singlecell_external/fibro_fibronectin_setI/Position_32,test,Fibronectin_SET_I,fibronectin,HFF,fibronectin,6000,3.0769,500,Position_32,Posi,fibroblasts_PDMS,fibroblasts_PDMS,8edbeec4ede4cf51f691e32c78f37936
30
+ singlecell_external/fibro_fibronectin_setI/Position_33,test,Fibronectin_SET_I,fibronectin,HFF,fibronectin,6000,3.0769,500,Position_33,Posi,fibroblasts_PDMS,fibroblasts_PDMS,51434a5af6bca9835bc8378975ad8160
31
+ singlecell_external/fibro_fibronectin_setI/Position_34,test,Fibronectin_SET_I,fibronectin,HFF,fibronectin,6000,3.0769,500,Position_34,Posi,fibroblasts_PDMS,fibroblasts_PDMS,4f199b43b01b5cb049d65b6b5d189aa3
32
+ singlecell_external/fibro_fibronectin_setI/Position_35,test,Fibronectin_SET_I,fibronectin,HFF,fibronectin,6000,3.0769,500,Position_35,Posi,fibroblasts_PDMS,fibroblasts_PDMS,f7ff24827a34739370e952622a19b150
33
+ singlecell_external/fibro_fibronectin_setI/Position_37,test,Fibronectin_SET_I,fibronectin,HFF,fibronectin,6000,3.0769,500,Position_37,Posi,fibroblasts_PDMS,fibroblasts_PDMS,700a973dc13b2a59bb21b72c3ff68f5f
34
+ singlecell_external/fibro_fibronectin_setI/Position_38,test,Fibronectin_SET_I,fibronectin,HFF,fibronectin,6000,3.0769,500,Position_38,Posi,fibroblasts_PDMS,fibroblasts_PDMS,38c06f13d241fb136a5681801baae216
35
+ singlecell_external/fibro_fibronectin_setI/Position_39,test,Fibronectin_SET_I,fibronectin,HFF,fibronectin,6000,3.0769,500,Position_39,Posi,fibroblasts_PDMS,fibroblasts_PDMS,16019034b38e27e8390024c3f305c06d
36
+ singlecell_external/fibro_fibronectin_setI/Position_42,test,Fibronectin_SET_I,fibronectin,HFF,fibronectin,6000,3.0769,500,Position_42,Posi,fibroblasts_PDMS,fibroblasts_PDMS,f5cdb6b3017b482d6a97b13984ba8ade
37
+ singlecell_external/fibro_fibronectin_setI/Position_43,test,Fibronectin_SET_I,fibronectin,HFF,fibronectin,6000,3.0769,500,Position_43,Posi,fibroblasts_PDMS,fibroblasts_PDMS,e6b297f778b3410f9804ebe5d02b6e1d
38
+ singlecell_external/fibro_fibronectin_setI/Position_44,test,Fibronectin_SET_I,fibronectin,HFF,fibronectin,6000,3.0769,500,Position_44,Posi,fibroblasts_PDMS,fibroblasts_PDMS,e8b11d34974ad624a5fe281712aea4b6
39
+ singlecell_external/fibro_fibronectin_setI/Position_45,test,Fibronectin_SET_I,fibronectin,HFF,fibronectin,6000,3.0769,500,Position_45,Posi,fibroblasts_PDMS,fibroblasts_PDMS,1dfe4577771ea2c0bd6dc51653d5be8c
40
+ singlecell_external/fibro_fibronectin_setI/Position_46,test,Fibronectin_SET_I,fibronectin,HFF,fibronectin,6000,3.0769,500,Position_46,Posi,fibroblasts_PDMS,fibroblasts_PDMS,521837fd329929e59cab8132b2cb2133
41
+ singlecell_external/fibro_fibronectin_setI/Position_47,test,Fibronectin_SET_I,fibronectin,HFF,fibronectin,6000,3.0769,500,Position_47,Posi,fibroblasts_PDMS,fibroblasts_PDMS,d3237e434423b9eb56a8c5cef8857ca6
experiments/splits/test_u2os_6kPa.csv ADDED
@@ -0,0 +1,40 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ sample_dir,split,set,condition,cell_type,coating,young_Pa,tfm_pixelsize,ythreshold_Pa,legacy_folder,legacy_substrate_code,substrate_legacy,substrate_nominal,bf_md5
2
+ singlecell_external/u2os_6kPa/Position_01,test,U2OS/test,U2OS,U2OS,collagen I,6000,6.1538,500,Position_01,Posi,fibroblasts_PDMS,U2OS_PDMS,ac947def3468a8bda41ab124fd8804e0
3
+ singlecell_external/u2os_6kPa/Position_02,test,U2OS/test,U2OS,U2OS,collagen I,6000,6.1538,500,Position_02,Posi,fibroblasts_PDMS,U2OS_PDMS,2496f97879c4a4cc640dbe4bd6c3f95d
4
+ singlecell_external/u2os_6kPa/Position_03,test,U2OS/test,U2OS,U2OS,collagen I,6000,6.1538,500,Position_03,Posi,fibroblasts_PDMS,U2OS_PDMS,aa9521c58731cc7bf4bb50649e8ec015
5
+ singlecell_external/u2os_6kPa/Position_04,test,U2OS/test,U2OS,U2OS,collagen I,6000,6.1538,500,Position_04,Posi,fibroblasts_PDMS,U2OS_PDMS,d0ecbc06303df3b5f8548a6b8580fb24
6
+ singlecell_external/u2os_6kPa/Position_05,test,U2OS/test,U2OS,U2OS,collagen I,6000,6.1538,500,Position_05,Posi,fibroblasts_PDMS,U2OS_PDMS,013b5170d5e43074d0e07579c7984a0f
7
+ singlecell_external/u2os_6kPa/Position_06,test,U2OS/test,U2OS,U2OS,collagen I,6000,6.1538,500,Position_06,Posi,fibroblasts_PDMS,U2OS_PDMS,66d58d536d567fad26cc5d54393ad2fd
8
+ singlecell_external/u2os_6kPa/Position_07,test,U2OS/test,U2OS,U2OS,collagen I,6000,6.1538,500,Position_07,Posi,fibroblasts_PDMS,U2OS_PDMS,51c9ef812316c01ce168adc18e857f54
9
+ singlecell_external/u2os_6kPa/Position_08,test,U2OS/test,U2OS,U2OS,collagen I,6000,6.1538,500,Position_08,Posi,fibroblasts_PDMS,U2OS_PDMS,09a67cfa6de1f5b0e757075830629c6a
10
+ singlecell_external/u2os_6kPa/Position_09,test,U2OS/test,U2OS,U2OS,collagen I,6000,6.1538,500,Position_09,Posi,fibroblasts_PDMS,U2OS_PDMS,6683ef0626f4435879094d5a884535d1
11
+ singlecell_external/u2os_6kPa/Position_10,test,U2OS/test,U2OS,U2OS,collagen I,6000,6.1538,500,Position_10,Posi,fibroblasts_PDMS,U2OS_PDMS,2448d1a73a33c2051628ed2ae9b22fa5
12
+ singlecell_external/u2os_6kPa/Position_11,test,U2OS/test,U2OS,U2OS,collagen I,6000,6.1538,500,Position_11,Posi,fibroblasts_PDMS,U2OS_PDMS,1120b96e4dccf7a788ecd1a092791d1a
13
+ singlecell_external/u2os_6kPa/Position_12,test,U2OS/test,U2OS,U2OS,collagen I,6000,6.1538,500,Position_12,Posi,fibroblasts_PDMS,U2OS_PDMS,91c776f05ee97460efa62ba59a973df3
14
+ singlecell_external/u2os_6kPa/Position_13,test,U2OS/test,U2OS,U2OS,collagen I,6000,6.1538,500,Position_13,Posi,fibroblasts_PDMS,U2OS_PDMS,39711de9b7e535a163948fe1ec9c167e
15
+ singlecell_external/u2os_6kPa/Position_14,test,U2OS/test,U2OS,U2OS,collagen I,6000,6.1538,500,Position_14,Posi,fibroblasts_PDMS,U2OS_PDMS,4e3640286b86306e09bdc6c10f2fe113
16
+ singlecell_external/u2os_6kPa/Position_15,test,U2OS/test,U2OS,U2OS,collagen I,6000,6.1538,500,Position_15,Posi,fibroblasts_PDMS,U2OS_PDMS,60503b7e423126a289261d507b6070cd
17
+ singlecell_external/u2os_6kPa/Position_16,test,U2OS/test,U2OS,U2OS,collagen I,6000,6.1538,500,Position_16,Posi,fibroblasts_PDMS,U2OS_PDMS,a66762e6ed1856f6421b2a45ac998755
18
+ singlecell_external/u2os_6kPa/Position_17,test,U2OS/test,U2OS,U2OS,collagen I,6000,6.1538,500,Position_17,Posi,fibroblasts_PDMS,U2OS_PDMS,5b8192f2d0e8bc5a1b11c66d3c7c247d
19
+ singlecell_external/u2os_6kPa/Position_18,test,U2OS/test,U2OS,U2OS,collagen I,6000,6.1538,500,Position_18,Posi,fibroblasts_PDMS,U2OS_PDMS,15ffbc911e369941e9c3882053b30964
20
+ singlecell_external/u2os_6kPa/Position_19,test,U2OS/test,U2OS,U2OS,collagen I,6000,6.1538,500,Position_19,Posi,fibroblasts_PDMS,U2OS_PDMS,ad938107c1c1a78c877367a82d7aae05
21
+ singlecell_external/u2os_6kPa/Position_22,test,U2OS/test,U2OS,U2OS,collagen I,6000,6.1538,500,Position_22,Posi,fibroblasts_PDMS,U2OS_PDMS,98acc1e4a81ce78c35c882360a1f0a28
22
+ singlecell_external/u2os_6kPa/Position_23,test,U2OS/test,U2OS,U2OS,collagen I,6000,6.1538,500,Position_23,Posi,fibroblasts_PDMS,U2OS_PDMS,4a1149e79898e5666610476175c2a626
23
+ singlecell_external/u2os_6kPa/Position_24,test,U2OS/test,U2OS,U2OS,collagen I,6000,6.1538,500,Position_24,Posi,fibroblasts_PDMS,U2OS_PDMS,692892019c37fa6bda9419db885e09b4
24
+ singlecell_external/u2os_6kPa/Position_25,test,U2OS/test,U2OS,U2OS,collagen I,6000,6.1538,500,Position_25,Posi,fibroblasts_PDMS,U2OS_PDMS,9d657ae0ecb2354d3b78c434d57a1894
25
+ singlecell_external/u2os_6kPa/Position_26,test,U2OS/test,U2OS,U2OS,collagen I,6000,6.1538,500,Position_26,Posi,fibroblasts_PDMS,U2OS_PDMS,de8e1b69819dabc631a75e273e29633f
26
+ singlecell_external/u2os_6kPa/Position_27,test,U2OS/test,U2OS,U2OS,collagen I,6000,6.1538,500,Position_27,Posi,fibroblasts_PDMS,U2OS_PDMS,c123bc73d867592428981adec0e5a19c
27
+ singlecell_external/u2os_6kPa/Position_28,test,U2OS/test,U2OS,U2OS,collagen I,6000,6.1538,500,Position_28,Posi,fibroblasts_PDMS,U2OS_PDMS,c051d4381a58866f54bd0d0c97a37ee3
28
+ singlecell_external/u2os_6kPa/Position_29,test,U2OS/test,U2OS,U2OS,collagen I,6000,6.1538,500,Position_29,Posi,fibroblasts_PDMS,U2OS_PDMS,0b08d6a24a52af664178ea830edcda8e
29
+ singlecell_external/u2os_6kPa/Position_32,test,U2OS/test,U2OS,U2OS,collagen I,6000,6.1538,500,Position_32,Posi,fibroblasts_PDMS,U2OS_PDMS,cbd27db6ed7e064edf124b99ef476c79
30
+ singlecell_external/u2os_6kPa/Position_33,test,U2OS/test,U2OS,U2OS,collagen I,6000,6.1538,500,Position_33,Posi,fibroblasts_PDMS,U2OS_PDMS,30ee3fb4099c1e7644f942569f6c9ab8
31
+ singlecell_external/u2os_6kPa/Position_35,test,U2OS/test,U2OS,U2OS,collagen I,6000,6.1538,500,Position_35,Posi,fibroblasts_PDMS,U2OS_PDMS,86c49c6e8903e4b42e74faec8204b1d2
32
+ singlecell_external/u2os_6kPa/Position_36,test,U2OS/test,U2OS,U2OS,collagen I,6000,6.1538,500,Position_36,Posi,fibroblasts_PDMS,U2OS_PDMS,1d53ac071adc6453c6946e7bbea89b0e
33
+ singlecell_external/u2os_6kPa/Position_37,test,U2OS/test,U2OS,U2OS,collagen I,6000,6.1538,500,Position_37,Posi,fibroblasts_PDMS,U2OS_PDMS,c9e9f849ef0677414c7287bd9985e066
34
+ singlecell_external/u2os_6kPa/Position_38,test,U2OS/test,U2OS,U2OS,collagen I,6000,6.1538,500,Position_38,Posi,fibroblasts_PDMS,U2OS_PDMS,305acaed2d26df95b15131f89ed04212
35
+ singlecell_external/u2os_6kPa/Position_39,test,U2OS/test,U2OS,U2OS,collagen I,6000,6.1538,500,Position_39,Posi,fibroblasts_PDMS,U2OS_PDMS,c236507d7f9ac8485df3694262e71751
36
+ singlecell_external/u2os_6kPa/Position_40,test,U2OS/test,U2OS,U2OS,collagen I,6000,6.1538,500,Position_40,Posi,fibroblasts_PDMS,U2OS_PDMS,83bd11798eebd2dc4091d5cc1b9ecacc
37
+ singlecell_external/u2os_6kPa/Position_41,test,U2OS/test,U2OS,U2OS,collagen I,6000,6.1538,500,Position_41,Posi,fibroblasts_PDMS,U2OS_PDMS,7d49197321ffa4ab8853fb729e331ce7
38
+ singlecell_external/u2os_6kPa/Position_42,test,U2OS/test,U2OS,U2OS,collagen I,6000,6.1538,500,Position_42,Posi,fibroblasts_PDMS,U2OS_PDMS,516e631b1ed84d11b1e386d4e60aae1e
39
+ singlecell_external/u2os_6kPa/Position_43,test,U2OS/test,U2OS,U2OS,collagen I,6000,6.1538,500,Position_43,Posi,fibroblasts_PDMS,U2OS_PDMS,ce40417f9b6234f8a5f647c27702f430
40
+ singlecell_external/u2os_6kPa/Position_44,test,U2OS/test,U2OS,U2OS,collagen I,6000,6.1538,500,Position_44,Posi,fibroblasts_PDMS,U2OS_PDMS,b9b8c73b9adfd00e1f8472d579e14824
experiments/splits/zenodo_v1_test.csv ADDED
@@ -0,0 +1,47 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ sample_dir,split,set,condition,cell_type,coating,young_Pa,tfm_pixelsize,ythreshold_Pa,legacy_folder,legacy_substrate_code,substrate_legacy,substrate_nominal,bf_md5
2
+ singlecell/test/Position_01_Fibros_SET_VI_for_Kaveh,test,fibro_split/test,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_01_Fibros_SET_VI_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,16d1e356f6811f66ee811a5db51d7ab1
3
+ singlecell/test/Position_02_Fibros_SET_VI_for_Kaveh,test,fibro_split/test,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_02_Fibros_SET_VI_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,cf14eccf4d4ad3db9f7207b905577397
4
+ singlecell/test/Position_03_Fibros_SET_VI_for_Kaveh,test,fibro_split/test,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_03_Fibros_SET_VI_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,9595462e4ec4107f30d16f5d4babc88c
5
+ singlecell/test/Position_04_Fibros_SET_VI_for_Kaveh,test,fibro_split/test,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_04_Fibros_SET_VI_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,e562d1d7876ff49b25bb167863804588
6
+ singlecell/test/Position_05_Fibros_SET_VI_for_Kaveh,test,fibro_split/test,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_05_Fibros_SET_VI_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,4338359255835bb02ef7aa966f236fc1
7
+ singlecell/test/Position_06_Fibros_SET_VI_for_Kaveh,test,fibro_split/test,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_06_Fibros_SET_VI_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,f68f65bcb182c09cb77bb2fb9bbe560f
8
+ singlecell/test/Position_07_Fibros_SET_VI_for_Kaveh,test,fibro_split/test,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_07_Fibros_SET_VI_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,2c5b638e494822c473c79601424106ad
9
+ singlecell/test/Position_08_Fibros_SET_VI_for_Kaveh,test,fibro_split/test,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_08_Fibros_SET_VI_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,191fe407db3249e029480307da88261c
10
+ singlecell/test/Position_09_Fibros_SET_VI_for_Kaveh,test,fibro_split/test,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_09_Fibros_SET_VI_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,7c91e95d0b1ddae4a50a1c4889e049c1
11
+ singlecell/test/Position_10_Fibros_SET_VI_for_Kaveh,test,fibro_split/test,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_10_Fibros_SET_VI_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,2b2784691cc84acb7a59d109517d8fd4
12
+ singlecell/test/Position_11_Fibros_SET_VI_for_Kaveh,test,fibro_split/test,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_11_Fibros_SET_VI_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,6be82222835f2f1d86522d37132f5f50
13
+ singlecell/test/Position_12_Fibros_SET_VI_for_Kaveh,test,fibro_split/test,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_12_Fibros_SET_VI_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,9aba966a4e385658445733b6f2c5f129
14
+ singlecell/test/Position_13_Fibros_SET_VI_for_Kaveh,test,fibro_split/test,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_13_Fibros_SET_VI_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,68f4edd892dbd27270e4ad2318cb3907
15
+ singlecell/test/Position_14_Fibros_SET_VI_for_Kaveh,test,fibro_split/test,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_14_Fibros_SET_VI_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,fd7af4e97dccd05295fcaad9e7561433
16
+ singlecell/test/Position_15_Fibros_SET_VI_for_Kaveh,test,fibro_split/test,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_15_Fibros_SET_VI_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,b54693e84a955e42b025235794108f6e
17
+ singlecell/test/Position_16_Fibros_SET_VI_for_Kaveh,test,fibro_split/test,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_16_Fibros_SET_VI_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,f4ad9bdb24bb0a6f1f60eab8d164d650
18
+ singlecell/test/Position_17_Fibros_SET_VI_for_Kaveh,test,fibro_split/test,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_17_Fibros_SET_VI_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,66e07499eff1b63ae8321eebe1828d38
19
+ singlecell/test/Position_18_Fibros_SET_VI_for_Kaveh,test,fibro_split/test,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_18_Fibros_SET_VI_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,03d8fd302362e352e6f15f0ede2e1611
20
+ singlecell/test/Position_19_Fibros_SET_VI_for_Kaveh,test,fibro_split/test,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_19_Fibros_SET_VI_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,f2477f80a8b077e6fd91f94a4130aefa
21
+ singlecell/test/Position_20_Fibros_SET_VI_for_Kaveh,test,fibro_split/test,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_20_Fibros_SET_VI_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,761fcd26e15b290c25b4475eae65f0a4
22
+ singlecell/test/Position_21_Fibros_SET_VI_for_Kaveh,test,fibro_split/test,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_21_Fibros_SET_VI_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,f775897638d8fc864bbd85a2984cc175
23
+ singlecell/test/Position_22_Fibros_SET_VI_for_Kaveh,test,fibro_split/test,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_22_Fibros_SET_VI_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,957a5d1022f1f2cd40167e6aa96dd04a
24
+ singlecell/test/Position_23_Fibros_SET_VI_for_Kaveh,test,fibro_split/test,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_23_Fibros_SET_VI_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,2782f9551709788685ab2fea4a5069bd
25
+ singlecell/test/Position_24_Fibros_SET_VI_for_Kaveh,test,fibro_split/test,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_24_Fibros_SET_VI_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,96e6a141799644462463632548b8e5a3
26
+ singlecell/test/Position_25_Fibros_SET_VI_for_Kaveh,test,fibro_split/test,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_25_Fibros_SET_VI_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,d6d3fec2c386aee0bbb8565bb8f13566
27
+ singlecell/test/Position_26_Fibros_SET_VI_for_Kaveh,test,fibro_split/test,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_26_Fibros_SET_VI_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,334466591565cf8f5d1877deef0422bb
28
+ singlecell/test/Position_27_Fibros_SET_VI_for_Kaveh,test,fibro_split/test,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_27_Fibros_SET_VI_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,212bdc83c0511b2930f3853dcd75c2cf
29
+ singlecell/test/Position_28_Fibros_SET_VI_for_Kaveh,test,fibro_split/test,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_28_Fibros_SET_VI_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,1a6483921f18e1bfbfb87128d837f59e
30
+ singlecell/test/Position_29_Fibros_SET_VI_for_Kaveh,test,fibro_split/test,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_29_Fibros_SET_VI_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,5c6c94cce47b04fae0fb3b3c6f7f74b5
31
+ singlecell/test/Position_30_Fibros_SET_VI_for_Kaveh,test,fibro_split/test,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_30_Fibros_SET_VI_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,9d333c7109fef9d7f39643e66a0cf0c0
32
+ singlecell/test/Position_31_Fibros_SET_VI_for_Kaveh,test,fibro_split/test,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_31_Fibros_SET_VI_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,21d7a2cd0c99937623b70b0afff28725
33
+ singlecell/test/Position_32_Fibros_SET_VI_for_Kaveh,test,fibro_split/test,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_32_Fibros_SET_VI_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,2da0965a500504c29362bb9466c34070
34
+ singlecell/test/Position_33_Fibros_SET_VI_for_Kaveh,test,fibro_split/test,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_33_Fibros_SET_VI_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,259a088a128c0d9978d47351b643bf03
35
+ singlecell/test/Position_34_Fibros_SET_VI_for_Kaveh,test,fibro_split/test,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_34_Fibros_SET_VI_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,1231efc0731bda43d78b1c7d10bd7fa8
36
+ singlecell/test/Position_35_Fibros_SET_VI_for_Kaveh,test,fibro_split/test,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_35_Fibros_SET_VI_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,6a932918e87a78633bca6bd136dd2bd5
37
+ singlecell/test/Position_36_Fibros_SET_VI_for_Kaveh,test,fibro_split/test,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_36_Fibros_SET_VI_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,a92a206c8daa4b5c99a87e3f69c81760
38
+ singlecell/test/Position_37_Fibros_SET_VI_for_Kaveh,test,fibro_split/test,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_37_Fibros_SET_VI_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,903d2e994ab7b7381c033c1e59ec4f32
39
+ singlecell/test/Position_38_Fibros_SET_VI_for_Kaveh,test,fibro_split/test,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_38_Fibros_SET_VI_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,6662b23db66b15a3f7657cff990e2dbc
40
+ singlecell/test/Position_39_Fibros_SET_VI_for_Kaveh,test,fibro_split/test,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_39_Fibros_SET_VI_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,489473be18dd682f4e0f9c7367c776e8
41
+ singlecell/test/Position_40_Fibros_SET_VI_for_Kaveh,test,fibro_split/test,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_40_Fibros_SET_VI_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,d0f01dcf05574003e2c40f28e6329566
42
+ singlecell/test/Position_41_Fibros_SET_VI_for_Kaveh,test,fibro_split/test,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_41_Fibros_SET_VI_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,e46a858089a335059e3ef36b60e2a931
43
+ singlecell/test/Position_43_Fibros_SET_VI_for_Kaveh,test,fibro_split/test,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_43_Fibros_SET_VI_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,3c293ef5de04f7e66fd0b225b6fc731b
44
+ singlecell/test/Position_44_Fibros_SET_VI_for_Kaveh,test,fibro_split/test,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_44_Fibros_SET_VI_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,47547bfbc09f9211fc7c57969c611167
45
+ singlecell/test/Position_45_Fibros_SET_VI_for_Kaveh,test,fibro_split/test,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_45_Fibros_SET_VI_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,7daf73af3c78d738f3c8cf8a0c6f4a53
46
+ singlecell/test/Position_46_Fibros_SET_VI_for_Kaveh,test,fibro_split/test,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_46_Fibros_SET_VI_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,eaa81a5d43baf70639861a4205aba4fd
47
+ singlecell/test/Position_48_Fibros_SET_VI_for_Kaveh,test,fibro_split/test,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_48_Fibros_SET_VI_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,b66eed556b24db2623f752adc566a7e1
experiments/splits/zenodo_v1_train.csv ADDED
@@ -0,0 +1,237 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ sample_dir,split,set,condition,cell_type,coating,young_Pa,tfm_pixelsize,ythreshold_Pa,legacy_folder,legacy_substrate_code,substrate_legacy,substrate_nominal,bf_md5
2
+ singlecell/train/Position_01_Fibros_SET_III_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_01_Fibros_SET_III_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,907943a24fccb1766d677a3ac2ca67fd
3
+ singlecell/train/Position_01_Fibros_SET_II_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_01_Fibros_SET_II_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,18fe8363f5d3319c62565051d9f1ac1d
4
+ singlecell/train/Position_01_Fibros_SET_IV_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_01_Fibros_SET_IV_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,edccb9abff5751736cda3cefff359695
5
+ singlecell/train/Position_01_Fibros_SET_V_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_01_Fibros_SET_V_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,b463c7b5c414d7c256d86795f1da15ec
6
+ singlecell/train/Position_02_Fibros_SET_III_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_02_Fibros_SET_III_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,428890b057f33cf2ab5b274925fd8758
7
+ singlecell/train/Position_02_Fibros_SET_II_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_02_Fibros_SET_II_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,173a5248d0bb9b4f0260b377078e710f
8
+ singlecell/train/Position_02_Fibros_SET_IV_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_02_Fibros_SET_IV_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,d51b239ff3bb09feb046381eb4c3e3fc
9
+ singlecell/train/Position_02_Fibros_SET_I_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_02_Fibros_SET_I_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,f25b4cb1efbbbc4432a0b15d2c43c61e
10
+ singlecell/train/Position_02_Fibros_SET_V_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_02_Fibros_SET_V_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,1241e9390202e14b3ba55872e093d060
11
+ singlecell/train/Position_03_Fibros_SET_II_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_03_Fibros_SET_II_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,6b5a9dccf76a0fc66e0fc7e13023471e
12
+ singlecell/train/Position_03_Fibros_SET_IV_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_03_Fibros_SET_IV_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,a9080d4bcfb4f29d058d4e165da11b62
13
+ singlecell/train/Position_03_Fibros_SET_I_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_03_Fibros_SET_I_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,43586564bd7e3ce6b9ef1d8c10ecaa24
14
+ singlecell/train/Position_03_Fibros_SET_V_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_03_Fibros_SET_V_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,abf9693c591e99de352a7a10200b8f5b
15
+ singlecell/train/Position_04_Fibros_SET_III_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_04_Fibros_SET_III_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,12028e118c60f672bba180cc301ad82c
16
+ singlecell/train/Position_04_Fibros_SET_II_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_04_Fibros_SET_II_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,c910c52daee16bd3a0707219b5abf085
17
+ singlecell/train/Position_04_Fibros_SET_IV_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_04_Fibros_SET_IV_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,a4e57a5f97f09ca08df5945559478acf
18
+ singlecell/train/Position_04_Fibros_SET_I_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_04_Fibros_SET_I_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,49d8f0f32b53fb1230e6c8fc7011ea10
19
+ singlecell/train/Position_04_Fibros_SET_V_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_04_Fibros_SET_V_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,f03f0058d3214e08c448babbbf6ba50e
20
+ singlecell/train/Position_05_Fibros_SET_II_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_05_Fibros_SET_II_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,38db8db89312b0c697fd4c3a29fd795b
21
+ singlecell/train/Position_05_Fibros_SET_IV_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_05_Fibros_SET_IV_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,8100e8dbe2353b41e2f5e5a37c4352be
22
+ singlecell/train/Position_05_Fibros_SET_I_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_05_Fibros_SET_I_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,2fb133cf9618c205bc14f785304cf6db
23
+ singlecell/train/Position_05_Fibros_SET_V_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_05_Fibros_SET_V_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,1f31ccdce8f928cf0e3a74e928c37a3b
24
+ singlecell/train/Position_06_Fibros_SET_III_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_06_Fibros_SET_III_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,7dc877a4829945a5ba3e4d0b65c597e4
25
+ singlecell/train/Position_06_Fibros_SET_II_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_06_Fibros_SET_II_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,edd237e4605db602813270f50cd70115
26
+ singlecell/train/Position_06_Fibros_SET_IV_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_06_Fibros_SET_IV_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,e66b998b2eca065394053bba989a6a47
27
+ singlecell/train/Position_06_Fibros_SET_I_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_06_Fibros_SET_I_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,a2a2ee01fac3ce8577314d79cb98bb7e
28
+ singlecell/train/Position_06_Fibros_SET_V_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_06_Fibros_SET_V_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,0111bb42f91fba4bb720ca9130f0c4d8
29
+ singlecell/train/Position_07_Fibros_SET_III_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_07_Fibros_SET_III_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,4c3869327bc98172ae17f1f1e12fe7ae
30
+ singlecell/train/Position_07_Fibros_SET_II_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_07_Fibros_SET_II_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,6e3e607da1f1b6743b2dcd699c5d594d
31
+ singlecell/train/Position_07_Fibros_SET_IV_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_07_Fibros_SET_IV_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,fcdd08a71c772b74acc9896e73e675ec
32
+ singlecell/train/Position_07_Fibros_SET_I_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_07_Fibros_SET_I_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,d84d1dc035292e1e843cf831a733705e
33
+ singlecell/train/Position_08_Fibros_SET_II_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_08_Fibros_SET_II_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,5942ec331106ee047166890f6f8e6d3f
34
+ singlecell/train/Position_08_Fibros_SET_IV_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_08_Fibros_SET_IV_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,f689b5b599e7823e0f94ed1818332d02
35
+ singlecell/train/Position_08_Fibros_SET_I_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_08_Fibros_SET_I_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,c959d59ea15b4077347712223e37a8a7
36
+ singlecell/train/Position_08_Fibros_SET_V_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_08_Fibros_SET_V_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,37c034cf0a243fbf4a80d9ee7ea3d92f
37
+ singlecell/train/Position_09_Fibros_SET_III_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_09_Fibros_SET_III_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,501d43cac495e43425132ecf80400d4e
38
+ singlecell/train/Position_09_Fibros_SET_II_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_09_Fibros_SET_II_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,749441f65be3652227477b621f7ab816
39
+ singlecell/train/Position_09_Fibros_SET_IV_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_09_Fibros_SET_IV_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,254f665021b7045a08c0ee16373cff73
40
+ singlecell/train/Position_09_Fibros_SET_I_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_09_Fibros_SET_I_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,e0b2d115867aa95c5cee7543d99e04af
41
+ singlecell/train/Position_09_Fibros_SET_V_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_09_Fibros_SET_V_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,956df9995c5a6fa67b5c14a1796a3b06
42
+ singlecell/train/Position_10_Fibros_SET_II_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_10_Fibros_SET_II_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,d98d25db8a2940d44e05e1784c982815
43
+ singlecell/train/Position_10_Fibros_SET_IV_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_10_Fibros_SET_IV_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,925cec4d0230e900c8d506b0fcd46e4c
44
+ singlecell/train/Position_10_Fibros_SET_I_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_10_Fibros_SET_I_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,28f7d2a33093283c365ef31249987adb
45
+ singlecell/train/Position_10_Fibros_SET_V_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_10_Fibros_SET_V_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,e8a8870dc47cca520bc132b1d38ca1d7
46
+ singlecell/train/Position_11_Fibros_SET_III_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_11_Fibros_SET_III_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,521be6524f516dcff355137b77688b8d
47
+ singlecell/train/Position_11_Fibros_SET_II_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_11_Fibros_SET_II_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,5d16540b8323501fc44f1a12ea1659e9
48
+ singlecell/train/Position_11_Fibros_SET_IV_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_11_Fibros_SET_IV_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,c4b484904a8f3986ae534202e8c1ef74
49
+ singlecell/train/Position_11_Fibros_SET_I_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_11_Fibros_SET_I_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,61f453c167ae62a7ae228cd3dac6fca5
50
+ singlecell/train/Position_11_Fibros_SET_V_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_11_Fibros_SET_V_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,cb2a80b347889b58c815fb00866aed72
51
+ singlecell/train/Position_12_Fibros_SET_II_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_12_Fibros_SET_II_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,d3d259a3727120f47e3bac955b2efa3d
52
+ singlecell/train/Position_12_Fibros_SET_IV_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_12_Fibros_SET_IV_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,77412ee9980f25ce6f9ffea78237fb3c
53
+ singlecell/train/Position_12_Fibros_SET_I_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_12_Fibros_SET_I_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,359d1d86355e162105bd2f0a6d01829e
54
+ singlecell/train/Position_12_Fibros_SET_V_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_12_Fibros_SET_V_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,c0a6e48229a9e0c7a4e69a92087a4670
55
+ singlecell/train/Position_13_Fibros_SET_III_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_13_Fibros_SET_III_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,88fc451773febe6945c3a642530eace1
56
+ singlecell/train/Position_13_Fibros_SET_II_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_13_Fibros_SET_II_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,9bcb3411b1cd1a634ea0e2f5d9be3ce8
57
+ singlecell/train/Position_13_Fibros_SET_IV_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_13_Fibros_SET_IV_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,4ea5567c7a28390a4f98426c000c0325
58
+ singlecell/train/Position_13_Fibros_SET_I_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_13_Fibros_SET_I_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,766a6b35ed896bfede13d256befa0bda
59
+ singlecell/train/Position_13_Fibros_SET_V_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_13_Fibros_SET_V_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,b557021d45a7bd2f9761b74014e48ece
60
+ singlecell/train/Position_14_Fibros_SET_III_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_14_Fibros_SET_III_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,3239fae9f42d6de790ef5aead2d5a0aa
61
+ singlecell/train/Position_14_Fibros_SET_II_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_14_Fibros_SET_II_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,41c522cc0b46dd655f836f7122ebab27
62
+ singlecell/train/Position_14_Fibros_SET_IV_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_14_Fibros_SET_IV_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,3fea8f256d39c166156a93ff98e9e870
63
+ singlecell/train/Position_14_Fibros_SET_V_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_14_Fibros_SET_V_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,95ca8945e9cafbe080281e56ef54f989
64
+ singlecell/train/Position_15_Fibros_SET_III_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_15_Fibros_SET_III_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,699e4a3c0629a7cd76390f45f3a7227d
65
+ singlecell/train/Position_15_Fibros_SET_II_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_15_Fibros_SET_II_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,ffbaf88fa23d6b9fe76e827d3f472d46
66
+ singlecell/train/Position_15_Fibros_SET_IV_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_15_Fibros_SET_IV_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,8d74378fdb124bf3e9bf8e84ab74b36f
67
+ singlecell/train/Position_15_Fibros_SET_I_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_15_Fibros_SET_I_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,a943fa9724f19d47d45cbeedd00f3690
68
+ singlecell/train/Position_15_Fibros_SET_V_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_15_Fibros_SET_V_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,db744d39b013e22e44f85194d719aaaf
69
+ singlecell/train/Position_16_Fibros_SET_II_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_16_Fibros_SET_II_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,0ac3a76d7413c16a63d5661146efc2d6
70
+ singlecell/train/Position_16_Fibros_SET_IV_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_16_Fibros_SET_IV_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,f8ce2e3a7fb23f54574e70953b14eaf7
71
+ singlecell/train/Position_16_Fibros_SET_V_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_16_Fibros_SET_V_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,76f26bbc9a893e521250b69e4321317d
72
+ singlecell/train/Position_17_Fibros_SET_III_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_17_Fibros_SET_III_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,35c37de14dd46c50a83a84d067c3fc66
73
+ singlecell/train/Position_17_Fibros_SET_II_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_17_Fibros_SET_II_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,93b40ac00d3a3fe0b311b97bab6f14de
74
+ singlecell/train/Position_17_Fibros_SET_IV_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_17_Fibros_SET_IV_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,c19b52c747cd203312acbd358a58ce2c
75
+ singlecell/train/Position_17_Fibros_SET_I_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_17_Fibros_SET_I_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,3e13a958536f4fcb0fadb40e7ce1fa80
76
+ singlecell/train/Position_17_Fibros_SET_V_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_17_Fibros_SET_V_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,92268e5891a97662c06b4dfac8207f86
77
+ singlecell/train/Position_18_Fibros_SET_III_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_18_Fibros_SET_III_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,2c69ee8ca32f208262ec9cace5da24b9
78
+ singlecell/train/Position_18_Fibros_SET_II_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_18_Fibros_SET_II_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,fbc32a9af174431444f1990276f3da7a
79
+ singlecell/train/Position_18_Fibros_SET_IV_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_18_Fibros_SET_IV_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,f6ed1b4421792e801f06f0ddd6938363
80
+ singlecell/train/Position_18_Fibros_SET_I_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_18_Fibros_SET_I_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,4b1f67971e024f1f5a9b9a3942a2b048
81
+ singlecell/train/Position_18_Fibros_SET_V_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_18_Fibros_SET_V_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,17c949f42623275447396440dacc7663
82
+ singlecell/train/Position_19_Fibros_SET_III_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_19_Fibros_SET_III_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,ef5ae47211c78bfc90b409dfb2364f2c
83
+ singlecell/train/Position_19_Fibros_SET_II_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_19_Fibros_SET_II_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,bc4e6174ad59b68a29c9afd11d54cf74
84
+ singlecell/train/Position_19_Fibros_SET_IV_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_19_Fibros_SET_IV_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,54cf3b60b9458b37b049b2b55110c4c4
85
+ singlecell/train/Position_19_Fibros_SET_I_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_19_Fibros_SET_I_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,e850f79c83798113d3c0ccbaf16333fb
86
+ singlecell/train/Position_19_Fibros_SET_V_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_19_Fibros_SET_V_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,c6d7ff4721172ea3b40a356a8bdc68a0
87
+ singlecell/train/Position_20_Fibros_SET_III_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_20_Fibros_SET_III_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,cd1e97675b5786c98e2e80aa35b5720a
88
+ singlecell/train/Position_20_Fibros_SET_II_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_20_Fibros_SET_II_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,f2e687370044da85deb4fcc594f8b817
89
+ singlecell/train/Position_20_Fibros_SET_IV_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_20_Fibros_SET_IV_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,829aa02bd2a3562c463b4b73116e1ea8
90
+ singlecell/train/Position_20_Fibros_SET_I_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_20_Fibros_SET_I_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,94b097dea0e2d35128c551027c8aa349
91
+ singlecell/train/Position_20_Fibros_SET_V_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_20_Fibros_SET_V_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,b71109d768845c8721e578befa03e7ab
92
+ singlecell/train/Position_21_Fibros_SET_III_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_21_Fibros_SET_III_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,5ac5f25f551e83fb635571c14c787dbe
93
+ singlecell/train/Position_21_Fibros_SET_II_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_21_Fibros_SET_II_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,62bb2ba31a2995dea84c70d11057cd38
94
+ singlecell/train/Position_21_Fibros_SET_IV_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_21_Fibros_SET_IV_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,ced60105efb44f700d01660cf87b8280
95
+ singlecell/train/Position_21_Fibros_SET_I_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_21_Fibros_SET_I_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,2a6cd457df6c67764aee46c8a81989c8
96
+ singlecell/train/Position_21_Fibros_SET_V_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_21_Fibros_SET_V_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,6da902805a70e8e3612d2b37e0f9fee4
97
+ singlecell/train/Position_22_Fibros_SET_II_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_22_Fibros_SET_II_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,a0311f390aa0cefb7e759cac064067d0
98
+ singlecell/train/Position_22_Fibros_SET_IV_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_22_Fibros_SET_IV_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,5fb1e844e16338c47a4c5d44193b813e
99
+ singlecell/train/Position_22_Fibros_SET_V_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_22_Fibros_SET_V_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,f410176deaab3a82f4d7323dae2aef52
100
+ singlecell/train/Position_23_Fibros_SET_III_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_23_Fibros_SET_III_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,4c45c900810ca9232da21293f6943e32
101
+ singlecell/train/Position_23_Fibros_SET_II_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_23_Fibros_SET_II_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,e5f2fc6fd472f12e89be76a70ac42694
102
+ singlecell/train/Position_23_Fibros_SET_IV_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_23_Fibros_SET_IV_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,910d22961cc5657adfb437bde05dad45
103
+ singlecell/train/Position_23_Fibros_SET_I_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_23_Fibros_SET_I_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,bf1555e5887bd12fa4b405242e44815a
104
+ singlecell/train/Position_23_Fibros_SET_V_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_23_Fibros_SET_V_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,e0189cbbb3671a4fa238a6006101e74e
105
+ singlecell/train/Position_24_Fibros_SET_III_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_24_Fibros_SET_III_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,f64aa3bae2dd242171cb9a999d0ede4a
106
+ singlecell/train/Position_24_Fibros_SET_II_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_24_Fibros_SET_II_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,8018a2a5fb0142eb1adfab91b0f60e80
107
+ singlecell/train/Position_24_Fibros_SET_IV_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_24_Fibros_SET_IV_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,dd65336a4c1471bc1db009a6fd195c00
108
+ singlecell/train/Position_24_Fibros_SET_V_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_24_Fibros_SET_V_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,39139c164c3dea2f8587e59271341ba7
109
+ singlecell/train/Position_25_Fibros_SET_III_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_25_Fibros_SET_III_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,6ae7bf05e64b0ccfc0e0c9c97f3d51ba
110
+ singlecell/train/Position_25_Fibros_SET_II_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_25_Fibros_SET_II_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,b35ef55641a560f0434d08feeae20bdf
111
+ singlecell/train/Position_25_Fibros_SET_IV_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_25_Fibros_SET_IV_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,32236fcd5f14d0cfd07a0b38b74fcc7f
112
+ singlecell/train/Position_25_Fibros_SET_I_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_25_Fibros_SET_I_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,740957b643467b8e2780eefa54a41ad9
113
+ singlecell/train/Position_25_Fibros_SET_V_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_25_Fibros_SET_V_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,032e400dacb6923e7744d1df7f085fcf
114
+ singlecell/train/Position_26_Fibros_SET_III_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_26_Fibros_SET_III_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,61e0f12bc3405209b7fb44c5e4680d06
115
+ singlecell/train/Position_26_Fibros_SET_II_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_26_Fibros_SET_II_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,94141c9b1b5298f954863951f32880d0
116
+ singlecell/train/Position_26_Fibros_SET_IV_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_26_Fibros_SET_IV_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,45450e1fc3e9882f11d4428241b930ec
117
+ singlecell/train/Position_26_Fibros_SET_V_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_26_Fibros_SET_V_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,227e83ef232c91a5225876b4ef9439f6
118
+ singlecell/train/Position_27_Fibros_SET_II_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_27_Fibros_SET_II_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,65330592991a965194525856b08385f5
119
+ singlecell/train/Position_27_Fibros_SET_IV_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_27_Fibros_SET_IV_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,740a81d38f1208e6fcefd00f9edc9018
120
+ singlecell/train/Position_27_Fibros_SET_V_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_27_Fibros_SET_V_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,bf81536c63f480fd68114b4b4ffbea0f
121
+ singlecell/train/Position_28_Fibros_SET_II_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_28_Fibros_SET_II_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,eefc4086ed1d8f0df14f07f350a81772
122
+ singlecell/train/Position_28_Fibros_SET_IV_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_28_Fibros_SET_IV_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,02a328c339ac8004b6ea341c7066f10d
123
+ singlecell/train/Position_28_Fibros_SET_I_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_28_Fibros_SET_I_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,e37e6d8a5fb2908a20e15743eb185b80
124
+ singlecell/train/Position_28_Fibros_SET_V_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_28_Fibros_SET_V_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,b87cf42217d259665182fdf06fc74e79
125
+ singlecell/train/Position_29_Fibros_SET_III_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_29_Fibros_SET_III_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,85025c3e095d82d35bde2b6c9c7211c8
126
+ singlecell/train/Position_29_Fibros_SET_II_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_29_Fibros_SET_II_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,2d2867a8d21786b79f511e0ca2412d53
127
+ singlecell/train/Position_29_Fibros_SET_IV_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_29_Fibros_SET_IV_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,c758f80c5629b61bba6776e4100130ef
128
+ singlecell/train/Position_29_Fibros_SET_I_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_29_Fibros_SET_I_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,bb007c2e11a937db5825b4c2eb53e5be
129
+ singlecell/train/Position_29_Fibros_SET_V_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_29_Fibros_SET_V_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,0784871001ec4d32ab334aa1d5197bc1
130
+ singlecell/train/Position_30_Fibros_SET_III_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_30_Fibros_SET_III_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,dbdd58554ebbba82f9ea34fc6a815933
131
+ singlecell/train/Position_30_Fibros_SET_II_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_30_Fibros_SET_II_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,684c63918ed7a5b74fdfd4766ac1b542
132
+ singlecell/train/Position_30_Fibros_SET_IV_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_30_Fibros_SET_IV_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,20c4cef1cae9ba1494d976e479b0df17
133
+ singlecell/train/Position_30_Fibros_SET_I_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_30_Fibros_SET_I_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,549b7c558429ccf07a7baf582ca06a6f
134
+ singlecell/train/Position_30_Fibros_SET_V_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_30_Fibros_SET_V_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,c590c7106786c354cd4c0094bb5d452e
135
+ singlecell/train/Position_31_Fibros_SET_III_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_31_Fibros_SET_III_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,84f4f90fa00610b7022ab5aa35b38f4a
136
+ singlecell/train/Position_31_Fibros_SET_II_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_31_Fibros_SET_II_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,f79625662c6c9ed5c514f3074b72990c
137
+ singlecell/train/Position_31_Fibros_SET_IV_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_31_Fibros_SET_IV_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,b7ba4d59931279e8128a306b22fb9add
138
+ singlecell/train/Position_31_Fibros_SET_V_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_31_Fibros_SET_V_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,cfd3a58c50f71cd5c7c3a04ae405fe85
139
+ singlecell/train/Position_32_Fibros_SET_III_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_32_Fibros_SET_III_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,5dad2ad325c5a7ece0f9c8589e5ffd89
140
+ singlecell/train/Position_32_Fibros_SET_II_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_32_Fibros_SET_II_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,68d298a4a9569850a4e4463475cc3d50
141
+ singlecell/train/Position_32_Fibros_SET_IV_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_32_Fibros_SET_IV_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,6269dbd518112aea594098095546666a
142
+ singlecell/train/Position_32_Fibros_SET_I_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_32_Fibros_SET_I_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,98c337a537308fa4296898241ec0e043
143
+ singlecell/train/Position_32_Fibros_SET_V_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_32_Fibros_SET_V_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,b19d096efd988816dd9f6cf9391cf0f1
144
+ singlecell/train/Position_33_Fibros_SET_III_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_33_Fibros_SET_III_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,9173bd6adbf24be2ce564170ac7c4630
145
+ singlecell/train/Position_33_Fibros_SET_II_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_33_Fibros_SET_II_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,35332c468d553ca67557bc015ef9226c
146
+ singlecell/train/Position_33_Fibros_SET_IV_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_33_Fibros_SET_IV_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,e3ffa27e2017e8a1aadb7b39289d5ba7
147
+ singlecell/train/Position_33_Fibros_SET_I_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_33_Fibros_SET_I_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,e335f8f756b4eb6a0412b5f047820f1f
148
+ singlecell/train/Position_33_Fibros_SET_V_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_33_Fibros_SET_V_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,e51dbe4e2297bb67db120a1c2889e0ed
149
+ singlecell/train/Position_34_Fibros_SET_III_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_34_Fibros_SET_III_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,c29020f3dc4b7c3c32f8e1c198f0c3f9
150
+ singlecell/train/Position_34_Fibros_SET_II_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_34_Fibros_SET_II_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,8231b6bb048a6e0629de2785e72594ec
151
+ singlecell/train/Position_34_Fibros_SET_IV_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_34_Fibros_SET_IV_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,8c9bb48eb733e5436ae3f9ddfbe03e38
152
+ singlecell/train/Position_34_Fibros_SET_I_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_34_Fibros_SET_I_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,53cc8285500436e31940e817f6a9bb1c
153
+ singlecell/train/Position_34_Fibros_SET_V_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_34_Fibros_SET_V_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,f04b37e29e73c66a2e6ff85748eb5644
154
+ singlecell/train/Position_35_Fibros_SET_III_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_35_Fibros_SET_III_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,0b755a22cb26e0e5577b67cd05fdca86
155
+ singlecell/train/Position_35_Fibros_SET_II_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_35_Fibros_SET_II_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,81d246d36e24dfae342aaffff16c20e0
156
+ singlecell/train/Position_35_Fibros_SET_IV_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_35_Fibros_SET_IV_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,0e706ce14275d6aaa7ee06044f22c999
157
+ singlecell/train/Position_35_Fibros_SET_I_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_35_Fibros_SET_I_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,79d75d349432b2b76c163aa840b99a29
158
+ singlecell/train/Position_35_Fibros_SET_V_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_35_Fibros_SET_V_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,d8295b2c1b3883c683ee7731a99cf4af
159
+ singlecell/train/Position_36_Fibros_SET_III_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_36_Fibros_SET_III_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,3402fdec3e5dfea3dd8d9a01e376454c
160
+ singlecell/train/Position_36_Fibros_SET_IV_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_36_Fibros_SET_IV_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,f784b8506bcd0638d2d87d190cc1eaad
161
+ singlecell/train/Position_36_Fibros_SET_I_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_36_Fibros_SET_I_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,4a684ddddce254006aecb1b6794c6827
162
+ singlecell/train/Position_36_Fibros_SET_V_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_36_Fibros_SET_V_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,5a707f8bf7b1cd274791c113a5d57e4d
163
+ singlecell/train/Position_37_Fibros_SET_III_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_37_Fibros_SET_III_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,7e3724a85418a92cae55495ec5c199be
164
+ singlecell/train/Position_37_Fibros_SET_II_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_37_Fibros_SET_II_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,d34eca1f300278894d33404c55ed607d
165
+ singlecell/train/Position_37_Fibros_SET_IV_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_37_Fibros_SET_IV_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,a687c531e35f6d09374c5ae16bab6aa7
166
+ singlecell/train/Position_37_Fibros_SET_I_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_37_Fibros_SET_I_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,44a25bd354e4ff1d305f64d91e1f5af2
167
+ singlecell/train/Position_37_Fibros_SET_V_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_37_Fibros_SET_V_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,7d2aab8d540405410cec2abd66aa4bd4
168
+ singlecell/train/Position_38_Fibros_SET_II_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_38_Fibros_SET_II_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,a6b8820d9251148a46e7ca7b089cdb12
169
+ singlecell/train/Position_38_Fibros_SET_IV_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_38_Fibros_SET_IV_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,27aea07350351f49c2da412ebc3a8fac
170
+ singlecell/train/Position_38_Fibros_SET_I_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_38_Fibros_SET_I_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,16fa90069bd63da214c3dd70d8e3144e
171
+ singlecell/train/Position_38_Fibros_SET_V_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_38_Fibros_SET_V_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,aebe9a4bb4bea574e410d95496da1564
172
+ singlecell/train/Position_39_Fibros_SET_III_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_39_Fibros_SET_III_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,dfc72ee2dd7b9e8b26a96c58a9b72d7a
173
+ singlecell/train/Position_39_Fibros_SET_II_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_39_Fibros_SET_II_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,a661425f19d6de4d5a9b8d58b222b2f7
174
+ singlecell/train/Position_39_Fibros_SET_IV_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_39_Fibros_SET_IV_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,6d53b26a88c6437be16a993523031484
175
+ singlecell/train/Position_39_Fibros_SET_I_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_39_Fibros_SET_I_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,071550e1ae296492b93bea6f0d08cb46
176
+ singlecell/train/Position_39_Fibros_SET_V_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_39_Fibros_SET_V_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,cb4319c4c4dc983b5066a9ba07a20587
177
+ singlecell/train/Position_40_Fibros_SET_III_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_40_Fibros_SET_III_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,ea1e6e7efeec098c3c5a02db6f6ba331
178
+ singlecell/train/Position_40_Fibros_SET_II_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_40_Fibros_SET_II_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,c975ea6fff75bcb82fe60356967e00b8
179
+ singlecell/train/Position_40_Fibros_SET_IV_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_40_Fibros_SET_IV_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,0a5c1cc6b25b63bd2c6b66645991ef3d
180
+ singlecell/train/Position_40_Fibros_SET_I_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_40_Fibros_SET_I_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,4bfdd7a273eff050bf4985d761f990e6
181
+ singlecell/train/Position_40_Fibros_SET_V_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_40_Fibros_SET_V_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,99b91378a531dbe58833113fbc01ff7f
182
+ singlecell/train/Position_41_Fibros_SET_III_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_41_Fibros_SET_III_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,b32e88d200845e8f150ab86078430437
183
+ singlecell/train/Position_41_Fibros_SET_II_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_41_Fibros_SET_II_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,d0c077505d05cf702ceaac21e64c0c42
184
+ singlecell/train/Position_41_Fibros_SET_IV_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_41_Fibros_SET_IV_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,9829d54c8a39a7c432fbd7e317cc2089
185
+ singlecell/train/Position_41_Fibros_SET_I_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_41_Fibros_SET_I_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,21de635ae01b66763ba6dba3e07d7b55
186
+ singlecell/train/Position_41_Fibros_SET_V_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_41_Fibros_SET_V_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,501db3aad6dc5d068f3237e3dcc26bf5
187
+ singlecell/train/Position_42_Fibros_SET_II_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_42_Fibros_SET_II_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,7c3bc9a254783887428533d2bddd3b61
188
+ singlecell/train/Position_42_Fibros_SET_IV_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_42_Fibros_SET_IV_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,727940eccfe7262526317950ecaffe0a
189
+ singlecell/train/Position_42_Fibros_SET_I_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_42_Fibros_SET_I_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,f5eb042a3df1c1f7082b261a5c81ff4f
190
+ singlecell/train/Position_42_Fibros_SET_V_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_42_Fibros_SET_V_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,4142a8c2568404426b1ff054e1ac9dfd
191
+ singlecell/train/Position_43_Fibros_SET_II_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_43_Fibros_SET_II_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,34c58c313e8a07ac10124415dc2f565e
192
+ singlecell/train/Position_43_Fibros_SET_IV_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_43_Fibros_SET_IV_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,1b24e744f08aee358d2b93f0fe373348
193
+ singlecell/train/Position_43_Fibros_SET_I_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_43_Fibros_SET_I_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,a927bbf35e8680d8324166aefd40f476
194
+ singlecell/train/Position_43_Fibros_SET_V_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_43_Fibros_SET_V_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,e172341cbe15de2d16b9149db36fd300
195
+ singlecell/train/Position_44_Fibros_SET_II_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_44_Fibros_SET_II_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,06a1a7f0b61967643ee4a9d5c45d1d48
196
+ singlecell/train/Position_44_Fibros_SET_IV_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_44_Fibros_SET_IV_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,cf6bebb668ac1aef788c4fe93c1bd73a
197
+ singlecell/train/Position_44_Fibros_SET_I_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_44_Fibros_SET_I_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,9c73c1f6246690ffd1f9410c7df9470f
198
+ singlecell/train/Position_44_Fibros_SET_V_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_44_Fibros_SET_V_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,aade2788ae6ad3d83999833d76f0abae
199
+ singlecell/train/Position_45_Fibros_SET_II_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_45_Fibros_SET_II_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,e7fba4934bd8c6e43629804ffacf16a9
200
+ singlecell/train/Position_45_Fibros_SET_I_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_45_Fibros_SET_I_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,f7a2e887cd705fe5c7a4035026bc63e7
201
+ singlecell/train/Position_45_Fibros_SET_V_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_45_Fibros_SET_V_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,5e3283f423b591bfd6b1e1ae6f14f593
202
+ singlecell/train/Position_46_Fibros_SET_II_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_46_Fibros_SET_II_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,40c7167b5c18d34ebe41de327d386ffe
203
+ singlecell/train/Position_46_Fibros_SET_I_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_46_Fibros_SET_I_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,e217a88172193395a688b8281ba1d634
204
+ singlecell/train/Position_46_Fibros_SET_V_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_46_Fibros_SET_V_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,7746be74f5a3c4933cd699f2e50337f6
205
+ singlecell/train/Position_47_Fibros_SET_II_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_47_Fibros_SET_II_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,c80d3ba162c5d20391df345c332a7965
206
+ singlecell/train/Position_47_Fibros_SET_I_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_47_Fibros_SET_I_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,8b21d6c339c213f59b3bc2ac05e23cb9
207
+ singlecell/train/Position_47_Fibros_SET_V_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_47_Fibros_SET_V_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,eb5e7340661fba1a16c19ab6601bab8d
208
+ singlecell/train/Position_48_Fibros_SET_II_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_48_Fibros_SET_II_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,a1ed82b53c6868830cc54f82619de882
209
+ singlecell/train/Position_48_Fibros_SET_I_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_48_Fibros_SET_I_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,619c69c6e8e97a3c1ffe76f670543104
210
+ singlecell/train/Position_48_Fibros_SET_V_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_48_Fibros_SET_V_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,a83b184eb0b2ed66bf3ebb317976740d
211
+ singlecell/train/Position_49_Fibros_SET_II_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_49_Fibros_SET_II_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,b59024bb2ea72244bd460650d7e19a2b
212
+ singlecell/train/Position_49_Fibros_SET_V_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_49_Fibros_SET_V_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,f7fa6f715b0510ca224325f6427de183
213
+ singlecell/train/Position_50_Fibros_SET_II_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_50_Fibros_SET_II_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,12dd15fa10362e5dc4a6ffbe145c90d3
214
+ singlecell/train/Position_50_Fibros_SET_I_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_50_Fibros_SET_I_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,cd637f41b52a579f34dac00c2e791015
215
+ singlecell/train/Position_50_Fibros_SET_V_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_50_Fibros_SET_V_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,10bd06e993988f7700a6c6d5195488fa
216
+ singlecell/train/Position_51_Fibros_SET_II_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_51_Fibros_SET_II_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,5bb6c0a3a623e0502f97e3831f3ecf8c
217
+ singlecell/train/Position_51_Fibros_SET_V_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_51_Fibros_SET_V_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,8c04b4b0ee3dd805ccdf0465b51bbb7c
218
+ singlecell/train/Position_52_Fibros_SET_II_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_52_Fibros_SET_II_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,5418f0066f886d3fa310a91d4ef5067d
219
+ singlecell/train/Position_52_Fibros_SET_V_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_52_Fibros_SET_V_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,7a8250df51a482d53bbed02405e4e048
220
+ singlecell/train/Position_53_Fibros_SET_II_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_53_Fibros_SET_II_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,151c402acbf619fd7a9c22d1d8bdc247
221
+ singlecell/train/Position_53_Fibros_SET_V_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_53_Fibros_SET_V_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,859d14e95b8283b8cfb641b7aa514384
222
+ singlecell/train/Position_54_Fibros_SET_II_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_54_Fibros_SET_II_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,e55ac86bc98ff779c32741fa22dd3304
223
+ singlecell/train/Position_54_Fibros_SET_V_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_54_Fibros_SET_V_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,673af811a279c8cdf329006974374a52
224
+ singlecell/train/Position_55_Fibros_SET_II_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_55_Fibros_SET_II_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,c46fc425aa0659d18c753a3e807ef380
225
+ singlecell/train/Position_55_Fibros_SET_V_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_55_Fibros_SET_V_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,eae3eabfb16a02979db68907ce3e49f0
226
+ singlecell/train/Position_56_Fibros_SET_II_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_56_Fibros_SET_II_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,4da38a60ab75e23d1c2c17143fc0059d
227
+ singlecell/train/Position_56_Fibros_SET_V_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_56_Fibros_SET_V_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,d7fcca8b7a88a9f67fda9382ad277bd6
228
+ singlecell/train/Position_57_Fibros_SET_II_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_57_Fibros_SET_II_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,69d0c6669646fe7cb755f567815740e0
229
+ singlecell/train/Position_57_Fibros_SET_V_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_57_Fibros_SET_V_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,2aefe3c353cd8750d3b4f31890fca54f
230
+ singlecell/train/Position_58_Fibros_SET_II_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_58_Fibros_SET_II_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,3c8987d9ef4e437b2f29a72412232f56
231
+ singlecell/train/Position_58_Fibros_SET_V_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_58_Fibros_SET_V_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,71e6d9e15ee1b79c2a906f8c41fce1b4
232
+ singlecell/train/Position_59_Fibros_SET_II_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_59_Fibros_SET_II_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,9abecc2cb74d9fa467cd5568cffcd61a
233
+ singlecell/train/Position_59_Fibros_SET_V_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_59_Fibros_SET_V_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,573d844c323bbe3c24f8db6457933aae
234
+ singlecell/train/Position_60_Fibros_SET_II_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_60_Fibros_SET_II_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,afe8609409b635dd974cb0b11051b607
235
+ singlecell/train/Position_60_Fibros_SET_V_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_60_Fibros_SET_V_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,fb553028892f3354a3d269e4e142065b
236
+ singlecell/train/Position_61_Fibros_SET_II_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_61_Fibros_SET_II_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,a1f49042aa8d3de8802052eef927612f
237
+ singlecell/train/Position_62_Fibros_SET_II_for_Kaveh,train,fibro_split/train,6 kPa collagen,HFF,collagen I,6000,3.0769,500,Position_62_Fibros_SET_II_for_Kaveh,Posi,fibroblasts_PDMS,fibroblasts_PDMS,b595c7cce48eb3f64447568315a92581
experiments/train.py ADDED
@@ -0,0 +1,279 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ """
2
+ Train one baseline / ablation variant with the shared protocol (experiments/configs.py).
3
+
4
+ python -m experiments.train --variant s2f_full
5
+ python -m experiments.train --variant unet --seed 1
6
+ python -m experiments.train --variant s2f_no_gan --resume # continue an interrupted run
7
+ python -m experiments.train --variant unet --epochs 1 --max-batches 5 # smoke test (1 epoch per phase)
8
+
9
+ Two phases (see experiments/configs.py). Outputs in experiments/runs/<variant>_seed<seed>/:
10
+ config.json exact configuration used
11
+ phase1/, phase2/ per phase: history.json (every loss term, val loss / WFM-RME / pixel r, lr, time),
12
+ best_checkpoint.pth (lowest validation loss of that phase), last_checkpoint.pth
13
+ (full state for --resume), visualizations/ (first validation batch every 10 epochs)
14
+ best_checkpoint.pth final model = best phase-2 generator (written when the run is complete)
15
+ history.json both phases concatenated (written when the run is complete)
16
+ """
17
+ import argparse
18
+ import json
19
+ import math
20
+ import os
21
+ import random
22
+ import shutil
23
+ import time
24
+
25
+ import numpy as np
26
+ import torch
27
+ import torch.nn as nn
28
+ import torch.nn.functional as F
29
+
30
+ from experiments.ablation_models import build_discriminator, build_generator, n_params
31
+ from experiments.configs import get_config
32
+ from experiments.layout import DEFAULT_DATASET_ROOT, RUNS_DIR, S2F_ROOT
33
+ from experiments.losses import REC_LOSSES, PerImageWFMRMELoss
34
+ from experiments.manifest_data import make_loader
35
+ from models.s2f_model import create_settings_channels
36
+ from utils.substrate_settings import compute_settings_normalization
37
+
38
+ CONFIG_PATH = os.path.join(S2F_ROOT, "config", "substrate_settings.json")
39
+
40
+
41
+ def seed_everything(seed):
42
+ random.seed(seed); np.random.seed(seed); torch.manual_seed(seed); torch.cuda.manual_seed_all(seed)
43
+
44
+
45
+ def cosine_with_warmup(optimizer, warmup_steps, total_steps):
46
+ """Same schedule as diffusers.optimization.get_cosine_schedule_with_warmup (num_cycles=0.5)."""
47
+ def f(step):
48
+ if step < warmup_steps:
49
+ return step / max(1, warmup_steps)
50
+ progress = (step - warmup_steps) / max(1, total_steps - warmup_steps)
51
+ return max(0.0, 0.5 * (1.0 + math.cos(math.pi * progress)))
52
+ return torch.optim.lr_scheduler.LambdaLR(optimizer, f)
53
+
54
+
55
+ def add_settings(x, batch, cfg, norm, device):
56
+ if cfg["substrate_mode"] == "none":
57
+ return x
58
+ meta = batch[4]
59
+ return torch.cat([x, create_settings_channels(meta, norm, device, x.shape, config_path=CONFIG_PATH)], dim=1)
60
+
61
+
62
+ def save_vis(G, val_loader, cfg, norm, device, path):
63
+ import matplotlib
64
+ matplotlib.use("Agg")
65
+ import matplotlib.pyplot as plt
66
+ batch = next(iter(val_loader))
67
+ x = add_settings(batch[0].to(device), batch, cfg, norm, device)
68
+ with torch.no_grad():
69
+ p = (G(x) + 1) / 2
70
+ n = min(2, x.size(0))
71
+ fig, ax = plt.subplots(3, n, figsize=(4 * n, 12), squeeze=False)
72
+ for i in range(n):
73
+ ax[0, i].imshow(x[i, 0].cpu(), cmap="gray"); ax[1, i].imshow(p[i, 0].cpu(), cmap="jet", vmin=0, vmax=1)
74
+ ax[2, i].imshow(batch[1][i, 0], cmap="jet", vmin=0, vmax=1)
75
+ for r in range(3):
76
+ ax[r, i].axis("off")
77
+ fig.tight_layout(); fig.savefig(path, dpi=100); plt.close(fig)
78
+
79
+
80
+ def pixel_r(p, y):
81
+ """Mean per-image Pearson correlation between predicted and true maps (monitoring only)."""
82
+ p, y = p.flatten(1), y.flatten(1)
83
+ p, y = p - p.mean(1, keepdim=True), y - y.mean(1, keepdim=True)
84
+ return ((p * y).sum(1) / (p.norm(dim=1) * y.norm(dim=1) + 1e-12)).mean()
85
+
86
+
87
+ def _done(phase_dir, epochs):
88
+ h = os.path.join(phase_dir, "history.json")
89
+ return (os.path.exists(h) and len(json.load(open(h))) >= epochs
90
+ and os.path.exists(os.path.join(phase_dir, "best_checkpoint.pth")))
91
+
92
+
93
+ def load_expanding(G, state):
94
+ """Load a state dict into G; input convolutions saved with 1 input channel are extended to G's input channels
95
+ with zero weights for the new channels."""
96
+ own, new, expanded = G.state_dict(), {}, []
97
+ for k, v in state.items():
98
+ t = own.get(k)
99
+ if t is not None and v.dim() == 4 and t.dim() == 4 and v.shape[1] == 1 and t.shape[1] > 1 \
100
+ and v.shape[0] == t.shape[0] and v.shape[2:] == t.shape[2:]:
101
+ w = torch.zeros_like(t); w[:, :1] = v.to(t.dtype); new[k] = w; expanded.append(k)
102
+ else:
103
+ new[k] = v
104
+ G.load_state_dict(new, strict=True)
105
+ return expanded
106
+
107
+
108
+ def run_phase(G, ph, phase_dir, cfg, train_loader, val_loader, norm, device, resume, max_batches):
109
+ """One training phase with a new discriminator, optimisers and schedule; the generator continues from its
110
+ current weights. The checkpoint with the lowest validation loss of the phase is kept."""
111
+ os.makedirs(os.path.join(phase_dir, "visualizations"), exist_ok=True)
112
+ use_gan = cfg["lambda_gan"] > 0
113
+ D = build_discriminator(cfg["in_channels"]).to(device) if use_gan else None
114
+ g_opt = torch.optim.Adam(G.parameters(), lr=ph["g_lr"], betas=(cfg["beta1"], cfg["beta2"]))
115
+ d_opt = torch.optim.Adam(D.parameters(), lr=ph["d_lr"], betas=(cfg["beta1"], cfg["beta2"])) if use_gan else None
116
+ n_batches = min(len(train_loader), max_batches) if max_batches else len(train_loader)
117
+ steps = n_batches * ph["epochs"]
118
+ g_sch = cosine_with_warmup(g_opt, int(steps * cfg["warmup_frac"]), steps)
119
+ d_sch = cosine_with_warmup(d_opt, int(steps * cfg["warmup_frac"]), steps) if use_gan else None
120
+ rec_loss, rme, bce = REC_LOSSES[ph["rec_loss"]](), PerImageWFMRMELoss(), nn.BCEWithLogitsLoss()
121
+ hist, best, start = [], float("inf"), 0
122
+ last_path = os.path.join(phase_dir, "last_checkpoint.pth")
123
+ if resume and os.path.exists(last_path):
124
+ ck = torch.load(last_path, map_location="cpu", weights_only=False)
125
+ G.load_state_dict(ck["generator_state_dict"]); g_opt.load_state_dict(ck["g_optimizer"]); g_sch.load_state_dict(ck["g_scheduler"])
126
+ if use_gan:
127
+ D.load_state_dict(ck["discriminator_state_dict"]); d_opt.load_state_dict(ck["d_optimizer"]); d_sch.load_state_dict(ck["d_scheduler"])
128
+ hist, best, start = ck["history"], ck["best_val_loss"], ck["epoch"] + 1
129
+ print(f"[{ph['name']}] resumed at epoch {start}")
130
+ print(f"[{ph['name']}] {ph['epochs']} epochs, loss {ph['rec_loss']} x{ph['lambda_rec']:g}, "
131
+ f"GAN x{cfg['lambda_gan']:g}, force x{ph['lambda_force']:g}, lr {ph['g_lr']:g}", flush=True)
132
+
133
+ for epoch in range(start, ph["epochs"]):
134
+ t0 = time.time(); G.train(); D.train() if use_gan else None
135
+ acc = dict(g=0.0, rec=0.0, gan=0.0, force=0.0, d=0.0); nb = 0
136
+ for bi, batch in enumerate(train_loader):
137
+ if max_batches and bi >= max_batches:
138
+ break
139
+ x = add_settings(batch[0].to(device), batch, cfg, norm, device)
140
+ y = batch[1].to(device)
141
+ fake = G(x); p = (fake + 1) / 2
142
+ l_rec = rec_loss(p, y)
143
+ l_force = F.mse_loss(p.flatten(1).mean(1), y.flatten(1).mean(1))
144
+ l_gan = torch.zeros((), device=device)
145
+ if use_gan:
146
+ pf = D(torch.cat([x, fake], 1)); l_gan = bce(pf, torch.ones_like(pf))
147
+ l_g = ph["lambda_rec"] * l_rec + cfg["lambda_gan"] * l_gan + ph["lambda_force"] * l_force
148
+ g_opt.zero_grad(); l_g.backward(); g_opt.step()
149
+ l_d = torch.zeros(())
150
+ if use_gan:
151
+ pr = D(torch.cat([x, y * 2 - 1], 1)); pf = D(torch.cat([x, fake.detach()], 1))
152
+ l_d = 0.5 * (bce(pr, torch.ones_like(pr)) + bce(pf, torch.zeros_like(pf)))
153
+ d_opt.zero_grad(); l_d.backward(); d_opt.step(); d_sch.step()
154
+ g_sch.step()
155
+ for k, v in zip(acc, [l_g, l_rec, l_gan, l_force, l_d]):
156
+ acc[k] += float(v.detach())
157
+ nb += 1
158
+ G.eval(); v = dict(rec=0.0, rme=0.0, mse=0.0, r=0.0); nv = 0
159
+ with torch.no_grad():
160
+ for bi, batch in enumerate(val_loader):
161
+ if max_batches and bi >= max_batches:
162
+ break
163
+ x = add_settings(batch[0].to(device), batch, cfg, norm, device); y = batch[1].to(device)
164
+ p = (G(x) + 1) / 2
165
+ v["rec"] += float(rec_loss(p, y)); v["rme"] += float(rme(p, y))
166
+ v["mse"] += float(F.mse_loss(p, y)); v["r"] += float(pixel_r(p, y)); nv += 1
167
+ h = {"phase": ph["name"], "epoch": epoch, **{f"train_{k}": a / max(nb, 1) for k, a in acc.items()},
168
+ **{f"val_{k}": a / max(nv, 1) for k, a in v.items()},
169
+ "g_lr": g_opt.param_groups[0]["lr"], "epoch_seconds": time.time() - t0}
170
+ hist.append(h)
171
+ is_best = h["val_rec"] < best
172
+ best = min(best, h["val_rec"])
173
+ print(f"[{ph['name']}] epoch {epoch:3d} G {h['train_g']:.4f} (rec {h['train_rec']:.4f} gan {h['train_gan']:.4f} "
174
+ f"force {h['train_force']:.5f}) D {h['train_d']:.4f} val_rec {h['val_rec']:.4f} "
175
+ f"val_r {h['val_r']:.3f} val_rme {h['val_rme']:.3f} {'*' if is_best else ' '} {h['epoch_seconds']:.0f}s", flush=True)
176
+ if is_best:
177
+ torch.save({"epoch": epoch, "phase": ph["name"], "generator_state_dict": G.state_dict(), "config": cfg,
178
+ "val_loss": h["val_rec"], "history": hist}, os.path.join(phase_dir, "best_checkpoint.pth"))
179
+ state = {"epoch": epoch, "generator_state_dict": G.state_dict(), "g_optimizer": g_opt.state_dict(),
180
+ "g_scheduler": g_sch.state_dict(), "history": hist, "best_val_loss": best, "config": cfg}
181
+ if use_gan:
182
+ state.update(discriminator_state_dict=D.state_dict(), d_optimizer=d_opt.state_dict(), d_scheduler=d_sch.state_dict())
183
+ torch.save(state, last_path)
184
+ json.dump(hist, open(os.path.join(phase_dir, "history.json"), "w"), indent=1)
185
+ if epoch % 10 == 0 or epoch == ph["epochs"] - 1:
186
+ save_vis(G, val_loader, cfg, norm, device, os.path.join(phase_dir, "visualizations", f"epoch_{epoch:03d}.png"))
187
+ return hist
188
+
189
+
190
+ def train(cfg, run_dir, dataset_root=DEFAULT_DATASET_ROOT, device=None, resume=False, max_batches=None,
191
+ num_workers=2, allow_cpu=False):
192
+ device = device or ("cuda" if torch.cuda.is_available() else "cpu")
193
+ if str(device).startswith("cpu") and not allow_cpu:
194
+ raise SystemExit("CUDA is not available - refusing to train on CPU (pass --allow-cpu for a smoke test)")
195
+ if str(device).startswith("cuda"):
196
+ torch.backends.cudnn.benchmark = True
197
+ print(f"GPU: {torch.cuda.get_device_name(torch.device(device))} "
198
+ f"(CUDA_VISIBLE_DEVICES={os.environ.get('CUDA_VISIBLE_DEVICES', 'all')})")
199
+ os.makedirs(run_dir, exist_ok=True)
200
+ seed_everything(cfg["seed"])
201
+ train_loader = make_loader(cfg["train_manifest"], dataset_root, cfg["batch_size"], cfg["img_size"],
202
+ augment=cfg["augment"], shuffle=True, substrate_mode=cfg["substrate_mode"],
203
+ input_mode=cfg["input_mode"], seed=cfg["seed"], num_workers=num_workers)
204
+ if num_workers > 0: # check that worker processes work on this machine
205
+ try:
206
+ next(iter(train_loader))
207
+ except RuntimeError as e:
208
+ print(f"DataLoader workers failed ({str(e).splitlines()[0][:120]}); falling back to num_workers=0")
209
+ train_loader = make_loader(cfg["train_manifest"], dataset_root, cfg["batch_size"], cfg["img_size"],
210
+ augment=cfg["augment"], shuffle=True, substrate_mode=cfg["substrate_mode"],
211
+ input_mode=cfg["input_mode"], seed=cfg["seed"], num_workers=0)
212
+ seed_everything(cfg["seed"])
213
+ val_loader = make_loader(cfg["val_manifest"], dataset_root, cfg["batch_size"], cfg["img_size"],
214
+ substrate_mode=cfg["substrate_mode"], input_mode=cfg["input_mode"])
215
+ norm = compute_settings_normalization(config_path=CONFIG_PATH)
216
+ G = build_generator(**cfg).to(device)
217
+ n_d = n_params(build_discriminator(cfg["in_channels"])) if cfg["lambda_gan"] > 0 else 0
218
+ cfg = dict(cfg, n_params_generator=n_params(G), n_params_discriminator=n_d,
219
+ n_train=len(train_loader.dataset), n_val=len(val_loader.dataset), device=str(device),
220
+ torch_version=torch.__version__)
221
+ json.dump(cfg, open(os.path.join(run_dir, "config.json"), "w"), indent=2)
222
+ print(f"[{cfg['variant']}] G {cfg['n_params_generator']/1e6:.2f} M params, D {n_d/1e6:.2f} M; "
223
+ f"train {cfg['n_train']}, val {cfg['n_val']}, device {device}", flush=True)
224
+
225
+ all_hist = []
226
+ for ph in cfg["phases"]:
227
+ phase_dir = os.path.join(run_dir, ph["name"])
228
+ shared = cfg.get("share_phase1_with")
229
+ if ph["name"] == "phase1" and shared and not _done(phase_dir, ph["epochs"]):
230
+ src = os.path.join(os.path.dirname(run_dir), f"{shared}_seed{cfg['seed']}", "phase1")
231
+ if _done(src, ph["epochs"]):
232
+ print(f"[phase1] identical to {shared} (same seed, data and phase-1 settings) - copying {src}")
233
+ shutil.copytree(src, phase_dir, dirs_exist_ok=True)
234
+ elif cfg.get("expand_from_image_only"):
235
+ raise SystemExit(f"{cfg['variant']} needs the finished image-only phase 1 of {shared} seed "
236
+ f"{cfg['seed']} in {src}")
237
+ else:
238
+ print(f"[phase1] {shared} phase 1 not finished yet - training phase 1 for this run")
239
+ if _done(phase_dir, ph["epochs"]) and (resume or shared):
240
+ print(f"[{ph['name']}] already finished - skipping")
241
+ hist = json.load(open(os.path.join(phase_dir, "history.json")))
242
+ else:
243
+ hist = run_phase(G, ph, phase_dir, cfg, train_loader, val_loader, norm, device, resume, max_batches)
244
+ all_hist += hist
245
+ best_ck = torch.load(os.path.join(phase_dir, "best_checkpoint.pth"), map_location="cpu", weights_only=False)
246
+ if cfg.get("expand_from_image_only") and ph["name"] == "phase1":
247
+ ex = load_expanding(G, best_ck["generator_state_dict"]) # image-only phase 1 -> + substrate channels
248
+ print(f"[phase1] image-only generator loaded; zero-initialised substrate weights added to {ex}")
249
+ else:
250
+ G.load_state_dict(best_ck["generator_state_dict"]) # next phase starts from this phase's best
251
+ best_ck["config"] = cfg
252
+ torch.save(best_ck, os.path.join(run_dir, "best_checkpoint.pth")) # final model = best of the last phase
253
+ json.dump(all_hist, open(os.path.join(run_dir, "history.json"), "w"), indent=1) # written last = run finished
254
+ print(f"done. final model: {best_ck['phase']} epoch {best_ck['epoch']}, val loss {best_ck['val_loss']:.4f}; in {run_dir}")
255
+ return run_dir
256
+
257
+
258
+ def main():
259
+ ap = argparse.ArgumentParser(description=__doc__, formatter_class=argparse.RawDescriptionHelpFormatter)
260
+ ap.add_argument("--variant", required=True)
261
+ ap.add_argument("--seed", type=int, default=None)
262
+ ap.add_argument("--epochs", type=int, default=None)
263
+ ap.add_argument("--g-lr", type=float, default=None); ap.add_argument("--d-lr", type=float, default=None)
264
+ ap.add_argument("--batch-size", type=int, default=None)
265
+ ap.add_argument("--dataset-root", default=DEFAULT_DATASET_ROOT)
266
+ ap.add_argument("--run-dir", default=None)
267
+ ap.add_argument("--device", default=None)
268
+ ap.add_argument("--resume", action="store_true")
269
+ ap.add_argument("--max-batches", type=int, default=None, help="limit batches per epoch (smoke test only)")
270
+ ap.add_argument("--num-workers", type=int, default=2, help="DataLoader worker processes for augmentation")
271
+ ap.add_argument("--allow-cpu", action="store_true", help="allow training without CUDA (smoke tests)")
272
+ a = ap.parse_args()
273
+ cfg = get_config(a.variant, seed=a.seed, epochs=a.epochs, g_lr=a.g_lr, d_lr=a.d_lr, batch_size=a.batch_size)
274
+ run_dir = a.run_dir or os.path.join(RUNS_DIR, f"{a.variant}_seed{cfg['seed']}")
275
+ train(cfg, run_dir, a.dataset_root, a.device, a.resume, a.max_batches, a.num_workers, a.allow_cpu)
276
+
277
+
278
+ if __name__ == "__main__":
279
+ main()