Spaces:
Sleeping
Sleeping
Update app.py
Browse files
app.py
CHANGED
|
@@ -87,8 +87,8 @@ def simulate_digest_and_plot_gradio(plasmid_seq_record, enzyme_name, plasmid_lab
|
|
| 87 |
ax.set_xticks([])
|
| 88 |
ax.tick_params(axis='y', labelsize=8)
|
| 89 |
|
| 90 |
-
well_top_y = ax.get_ylim()[0]
|
| 91 |
-
well_line_y = well_top_y * 1.01
|
| 92 |
well_depth_y = well_top_y * 0.98
|
| 93 |
|
| 94 |
ax.plot([lane_center - band_width/1.5, lane_center + band_width/1.5], [well_line_y, well_line_y],
|
|
@@ -103,12 +103,15 @@ def simulate_digest_and_plot_gradio(plasmid_seq_record, enzyme_name, plasmid_lab
|
|
| 103 |
|
| 104 |
def analyze_plasmids_gradio(file1_path, file2_path, current_plasmid_choice_for_plot):
|
| 105 |
"""
|
| 106 |
-
Analyzes two plasmid files to find unique restriction enzymes
|
| 107 |
-
|
|
|
|
| 108 |
and an update for the enzyme selection dropdown.
|
| 109 |
"""
|
| 110 |
initial_enzyme_dd_update = gr.update(choices=["Analyze plasmids first"], value="Analyze plasmids first", interactive=False)
|
| 111 |
-
|
|
|
|
|
|
|
| 112 |
# Check if example files exist if paths match example paths
|
| 113 |
example_file_error_msg = ""
|
| 114 |
if file1_path == EXAMPLE_PLASMID1_PATH and not os.path.exists(EXAMPLE_PLASMID1_PATH):
|
|
@@ -117,11 +120,11 @@ def analyze_plasmids_gradio(file1_path, file2_path, current_plasmid_choice_for_p
|
|
| 117 |
example_file_error_msg += f"Example file not found: {EXAMPLE_PLASMID2_PATH}. Please create it in the '{EXAMPLE_DIR}' directory.\n"
|
| 118 |
|
| 119 |
if example_file_error_msg:
|
| 120 |
-
|
| 121 |
|
| 122 |
|
| 123 |
if file1_path is None or file2_path is None:
|
| 124 |
-
return "Error: Please upload or load both plasmid files.",
|
| 125 |
|
| 126 |
try:
|
| 127 |
def read_plasmid(filepath, filename_for_error):
|
|
@@ -140,7 +143,7 @@ def analyze_plasmids_gradio(file1_path, file2_path, current_plasmid_choice_for_p
|
|
| 140 |
plasmid2_seq_rec = read_plasmid(file2_path, p2_orig_filename)
|
| 141 |
|
| 142 |
except Exception as e:
|
| 143 |
-
return str(e),
|
| 144 |
|
| 145 |
valid_enzyme_objects = []
|
| 146 |
for enz_name in AllEnzymes.elements():
|
|
@@ -152,17 +155,17 @@ def analyze_plasmids_gradio(file1_path, file2_path, current_plasmid_choice_for_p
|
|
| 152 |
valid_enzyme_objects.append(enzyme_obj)
|
| 153 |
|
| 154 |
if not valid_enzyme_objects:
|
| 155 |
-
|
| 156 |
|
| 157 |
enzymes_batch = RestrictionBatch(valid_enzyme_objects)
|
| 158 |
analysis1 = Analysis(enzymes_batch, plasmid1_seq_rec.seq, linear=False)
|
| 159 |
analysis2 = Analysis(enzymes_batch, plasmid2_seq_rec.seq, linear=False)
|
| 160 |
|
| 161 |
-
|
| 162 |
-
|
| 163 |
|
| 164 |
-
unique_to_1_obj = sorted(list(
|
| 165 |
-
unique_to_2_obj = sorted(list(
|
| 166 |
|
| 167 |
unique_to_1_names = [str(e) for e in unique_to_1_obj]
|
| 168 |
unique_to_2_names = [str(e) for e in unique_to_2_obj]
|
|
@@ -173,9 +176,32 @@ def analyze_plasmids_gradio(file1_path, file2_path, current_plasmid_choice_for_p
|
|
| 173 |
msg1 = f"Enzymes cutting only {p1_display_label} ({len(unique_to_1_names)}):\n" + ", ".join(unique_to_1_names) if unique_to_1_names else f"No unique enzymes found for {p1_display_label}."
|
| 174 |
msg2 = f"Enzymes cutting only {p2_display_label} ({len(unique_to_2_names)}):\n" + ", ".join(unique_to_2_names) if unique_to_2_names else f"No unique enzymes found for {p2_display_label}."
|
| 175 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 176 |
status = "Analysis complete."
|
| 177 |
-
if not unique_to_1_names and not unique_to_2_names:
|
| 178 |
-
status += " No enzymes found
|
| 179 |
|
| 180 |
dd_choices = []
|
| 181 |
if current_plasmid_choice_for_plot == "Plasmid 1":
|
|
@@ -185,11 +211,12 @@ def analyze_plasmids_gradio(file1_path, file2_path, current_plasmid_choice_for_p
|
|
| 185 |
|
| 186 |
if (current_plasmid_choice_for_plot == "Plasmid 1" and unique_to_1_names) or \
|
| 187 |
(current_plasmid_choice_for_plot == "Plasmid 2" and unique_to_2_names):
|
| 188 |
-
|
| 189 |
else:
|
| 190 |
-
|
| 191 |
|
| 192 |
-
return status, msg1, msg2, plasmid1_seq_rec, plasmid2_seq_rec,
|
|
|
|
| 193 |
|
| 194 |
def plot_selected_digest_controller(plasmid_choice_label, enzyme_name, p1_data, p2_data):
|
| 195 |
"""
|
|
@@ -217,8 +244,8 @@ def plot_selected_digest_controller(plasmid_choice_label, enzyme_name, p1_data,
|
|
| 217 |
return fig_placeholder
|
| 218 |
target_plasmid_rec = p1_data
|
| 219 |
target_label = "Plasmid 1"
|
| 220 |
-
if hasattr(p1_data, 'name') and p1_data.name: target_label += f" ({p1_data.name})"
|
| 221 |
-
elif hasattr(p1_data, 'id') and p1_data.id: target_label += f" ({p1_data.id})"
|
| 222 |
elif plasmid_choice_label == "Plasmid 2":
|
| 223 |
if p2_data is None:
|
| 224 |
ax_placeholder.clear()
|
|
@@ -227,8 +254,8 @@ def plot_selected_digest_controller(plasmid_choice_label, enzyme_name, p1_data,
|
|
| 227 |
return fig_placeholder
|
| 228 |
target_plasmid_rec = p2_data
|
| 229 |
target_label = "Plasmid 2"
|
| 230 |
-
if hasattr(p2_data, 'name') and p2_data.name: target_label += f" ({p2_data.name})"
|
| 231 |
-
elif hasattr(p2_data, 'id') and p2_data.id: target_label += f" ({p2_data.id})"
|
| 232 |
else:
|
| 233 |
ax_placeholder.clear()
|
| 234 |
ax_placeholder.text(0.5, 0.5, "Invalid plasmid selection.", ha='center', va='center', wrap=True, color='red')
|
|
@@ -256,67 +283,70 @@ def load_examples_and_auto_process():
|
|
| 256 |
Loads example files, triggers analysis, and then attempts to auto-plot.
|
| 257 |
"""
|
| 258 |
# Step 1: Perform analysis with example files
|
| 259 |
-
|
| 260 |
-
|
| 261 |
analyze_plasmids_gradio(EXAMPLE_PLASMID1_PATH, EXAMPLE_PLASMID2_PATH, "Plasmid 1")
|
| 262 |
|
| 263 |
# If analysis failed (e.g., files not found), p1_rec or p2_rec might be None
|
| 264 |
if p1_rec is None or p2_rec is None :
|
| 265 |
-
# Create a placeholder plot for error
|
| 266 |
fig_error, ax_error = plt.subplots(figsize=(6,8))
|
| 267 |
-
ax_error.text(0.5, 0.5, "Error during example analysis
|
| 268 |
ax_error.set_xticks([]); ax_error.set_yticks([])
|
| 269 |
plt.tight_layout()
|
| 270 |
-
|
|
|
|
| 271 |
gr.update(choices=["Error"], value="Error", interactive=False), \
|
| 272 |
-
gr.update(value="Plasmid 1"), fig_error
|
| 273 |
|
| 274 |
-
# Step 2: Determine auto-plot parameters
|
| 275 |
auto_plot_plasmid_label = None
|
| 276 |
auto_plot_enzyme_name = None
|
| 277 |
auto_plot_plasmid_data = None
|
| 278 |
-
final_radio_choice = "Plasmid 1" # Default
|
|
|
|
| 279 |
|
| 280 |
if p1_enz_names:
|
| 281 |
auto_plot_plasmid_label = "Plasmid 1"
|
| 282 |
auto_plot_enzyme_name = p1_enz_names[0]
|
| 283 |
auto_plot_plasmid_data = p1_rec
|
| 284 |
final_radio_choice = "Plasmid 1"
|
| 285 |
-
|
| 286 |
-
enz_dd_update = gr.update(choices=["Select an enzyme"] + p1_enz_names, value=auto_plot_enzyme_name, interactive=True)
|
| 287 |
-
|
| 288 |
elif p2_enz_names:
|
| 289 |
auto_plot_plasmid_label = "Plasmid 2"
|
| 290 |
auto_plot_enzyme_name = p2_enz_names[0]
|
| 291 |
auto_plot_plasmid_data = p2_rec
|
| 292 |
final_radio_choice = "Plasmid 2"
|
| 293 |
-
|
| 294 |
-
|
| 295 |
-
else:
|
| 296 |
-
# No unique enzymes for auto-plotting, update dropdown to reflect current choice (P1 default)
|
| 297 |
if final_radio_choice == "Plasmid 1":
|
| 298 |
-
|
| 299 |
-
|
| 300 |
-
|
| 301 |
|
| 302 |
# Step 3: Generate plot if possible
|
| 303 |
if auto_plot_enzyme_name and auto_plot_plasmid_data:
|
| 304 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 305 |
else:
|
| 306 |
-
# Create a placeholder plot if no auto-plot target
|
| 307 |
fig_placeholder, ax_placeholder = plt.subplots(figsize=(6, 8))
|
| 308 |
ax_placeholder.text(0.5, 0.5, "No unique enzymes found for automatic plotting.", ha='center', va='center', wrap=True)
|
| 309 |
ax_placeholder.set_xticks([]); ax_placeholder.set_yticks([])
|
| 310 |
plt.tight_layout()
|
| 311 |
gel_fig = fig_placeholder
|
| 312 |
-
|
| 313 |
-
|
| 314 |
-
enz_dd_update = gr.update(choices=["No unique enzymes found"], value="No unique enzymes found", interactive=False)
|
| 315 |
-
|
| 316 |
|
| 317 |
# Return all updates
|
| 318 |
-
return status, msg1, msg2, p1_rec, p2_rec, p1_enz_names, p2_enz_names, \
|
| 319 |
-
|
| 320 |
|
| 321 |
|
| 322 |
# --- Gradio Interface Definition ---
|
|
@@ -325,10 +355,13 @@ with gr.Blocks(theme=gr.themes.Default()) as demo:
|
|
| 325 |
gr.Markdown(
|
| 326 |
"**Instructions:**\n"
|
| 327 |
"1. Upload two plasmid sequence files (GenBank `.gb`/`.gbk` or FASTA `.fasta`/`.fna`/`.fa` format) OR click 'Load Example Files'.\n"
|
| 328 |
-
"2. If uploading manually, click `Analyze Plasmids`. Results will show
|
| 329 |
-
"
|
|
|
|
|
|
|
|
|
|
| 330 |
"4. Choose a specific enzyme from the dropdown list.\n"
|
| 331 |
-
"5. Click `Generate Gel Plot` to visualize the digestion pattern.\n"
|
| 332 |
f"Note: For 'Load Example Files', ensure `plasmid1_example.gb` and `plasmid2_example.gb` are in a folder named `{EXAMPLE_DIR}` next to this script."
|
| 333 |
)
|
| 334 |
|
|
@@ -336,6 +369,7 @@ with gr.Blocks(theme=gr.themes.Default()) as demo:
|
|
| 336 |
plasmid2_data_state = gr.State()
|
| 337 |
p1_unique_enzymes_list_state = gr.State([])
|
| 338 |
p2_unique_enzymes_list_state = gr.State([])
|
|
|
|
| 339 |
|
| 340 |
with gr.Row():
|
| 341 |
with gr.Column(scale=1):
|
|
@@ -343,16 +377,17 @@ with gr.Blocks(theme=gr.themes.Default()) as demo:
|
|
| 343 |
file_p1 = gr.File(label="Plasmid 1 File (e.g., .gb, .fasta)", type="filepath", file_types=[".gb", ".gbk", ".fasta", ".fna", ".fa"])
|
| 344 |
file_p2 = gr.File(label="Plasmid 2 File (e.g., .gb, .fasta)", type="filepath", file_types=[".gb", ".gbk", ".fasta", ".fna", ".fa"])
|
| 345 |
|
| 346 |
-
_current_plasmid_choice_for_plot_hidden = gr.Textbox(value="Plasmid 1", visible=False)
|
| 347 |
|
| 348 |
-
analyze_btn = gr.Button("Analyze Uploaded Plasmids", variant="secondary")
|
| 349 |
example_btn = gr.Button("Load Example Files & Auto-Analyze/Plot", variant="primary", elem_id="example_button")
|
| 350 |
|
| 351 |
with gr.Column(scale=2):
|
| 352 |
gr.Markdown("### Analysis Results")
|
| 353 |
-
status_message_txt = gr.Textbox(label="Status", interactive=False, lines=1, max_lines=3)
|
| 354 |
unique_enzymes_p1_txt = gr.Textbox(label="Enzymes cutting only Plasmid 1", interactive=False, lines=3, max_lines=6)
|
| 355 |
unique_enzymes_p2_txt = gr.Textbox(label="Enzymes cutting only Plasmid 2", interactive=False, lines=3, max_lines=6)
|
|
|
|
| 356 |
|
| 357 |
gr.Markdown("---")
|
| 358 |
gr.Markdown("### 2. Visualize Digestion on Virtual Gel")
|
|
@@ -361,18 +396,18 @@ with gr.Blocks(theme=gr.themes.Default()) as demo:
|
|
| 361 |
with gr.Column(scale=1):
|
| 362 |
plasmid_to_plot_choice_radio = gr.Radio(
|
| 363 |
choices=["Plasmid 1", "Plasmid 2"],
|
| 364 |
-
label="Select Plasmid for Gel Visualization",
|
| 365 |
value="Plasmid 1",
|
| 366 |
interactive=True
|
| 367 |
)
|
| 368 |
|
| 369 |
enzyme_for_plot_dropdown = gr.Dropdown(
|
| 370 |
-
label="Select Unique Enzyme",
|
| 371 |
choices=["Analyze plasmids first"],
|
| 372 |
value="Analyze plasmids first",
|
| 373 |
interactive=False
|
| 374 |
)
|
| 375 |
-
plot_btn = gr.Button("Generate Gel Plot for Selection", variant="secondary", elem_id="plot_button")
|
| 376 |
|
| 377 |
with gr.Column(scale=2):
|
| 378 |
gel_plot_output = gr.Plot(label="Virtual Agarose Gel")
|
|
@@ -385,30 +420,33 @@ with gr.Blocks(theme=gr.themes.Default()) as demo:
|
|
| 385 |
plasmid_to_plot_choice_radio.change(
|
| 386 |
fn=lambda x: x,
|
| 387 |
inputs=[plasmid_to_plot_choice_radio],
|
| 388 |
-
outputs=[_current_plasmid_choice_for_plot_hidden]
|
| 389 |
)
|
| 390 |
|
| 391 |
analyze_btn.click(
|
| 392 |
fn=analyze_plasmids_gradio,
|
| 393 |
-
inputs=[file_p1, file_p2, _current_plasmid_choice_for_plot_hidden],
|
| 394 |
outputs=[
|
| 395 |
status_message_txt, unique_enzymes_p1_txt, unique_enzymes_p2_txt,
|
|
|
|
| 396 |
plasmid1_data_state, plasmid2_data_state,
|
| 397 |
p1_unique_enzymes_list_state, p2_unique_enzymes_list_state,
|
|
|
|
| 398 |
enzyme_for_plot_dropdown
|
| 399 |
]
|
| 400 |
)
|
| 401 |
|
| 402 |
example_btn.click(
|
| 403 |
fn=load_examples_and_auto_process,
|
| 404 |
-
inputs=[],
|
| 405 |
outputs=[
|
| 406 |
status_message_txt, unique_enzymes_p1_txt, unique_enzymes_p2_txt,
|
|
|
|
| 407 |
plasmid1_data_state, plasmid2_data_state,
|
| 408 |
p1_unique_enzymes_list_state, p2_unique_enzymes_list_state,
|
| 409 |
-
enzyme_for_plot_dropdown,
|
| 410 |
-
plasmid_to_plot_choice_radio,
|
| 411 |
-
gel_plot_output
|
| 412 |
]
|
| 413 |
)
|
| 414 |
|
|
@@ -425,11 +463,13 @@ with gr.Blocks(theme=gr.themes.Default()) as demo:
|
|
| 425 |
)
|
| 426 |
|
| 427 |
if __name__ == '__main__':
|
| 428 |
-
# Create eg_files directory if it doesn't exist (optional, good for local testing)
|
| 429 |
if not os.path.exists(EXAMPLE_DIR):
|
| 430 |
os.makedirs(EXAMPLE_DIR)
|
| 431 |
-
print(f"Created directory: {EXAMPLE_DIR}. Please add example plasmid files to it.")
|
| 432 |
-
|
| 433 |
-
|
|
|
|
|
|
|
|
|
|
| 434 |
|
| 435 |
demo.launch()
|
|
|
|
| 87 |
ax.set_xticks([])
|
| 88 |
ax.tick_params(axis='y', labelsize=8)
|
| 89 |
|
| 90 |
+
well_top_y = ax.get_ylim()[0]
|
| 91 |
+
well_line_y = well_top_y * 1.01
|
| 92 |
well_depth_y = well_top_y * 0.98
|
| 93 |
|
| 94 |
ax.plot([lane_center - band_width/1.5, lane_center + band_width/1.5], [well_line_y, well_line_y],
|
|
|
|
| 103 |
|
| 104 |
def analyze_plasmids_gradio(file1_path, file2_path, current_plasmid_choice_for_plot):
|
| 105 |
"""
|
| 106 |
+
Analyzes two plasmid files to find unique restriction enzymes and
|
| 107 |
+
enzymes that cut both plasmids but with different fragmentation patterns.
|
| 108 |
+
Returns status messages, plasmid data, lists of enzyme names,
|
| 109 |
and an update for the enzyme selection dropdown.
|
| 110 |
"""
|
| 111 |
initial_enzyme_dd_update = gr.update(choices=["Analyze plasmids first"], value="Analyze plasmids first", interactive=False)
|
| 112 |
+
empty_return_for_error = ["", "", "", None, None, [], [], [], initial_enzyme_dd_update]
|
| 113 |
+
|
| 114 |
+
|
| 115 |
# Check if example files exist if paths match example paths
|
| 116 |
example_file_error_msg = ""
|
| 117 |
if file1_path == EXAMPLE_PLASMID1_PATH and not os.path.exists(EXAMPLE_PLASMID1_PATH):
|
|
|
|
| 120 |
example_file_error_msg += f"Example file not found: {EXAMPLE_PLASMID2_PATH}. Please create it in the '{EXAMPLE_DIR}' directory.\n"
|
| 121 |
|
| 122 |
if example_file_error_msg:
|
| 123 |
+
return example_file_error_msg, *empty_return_for_error
|
| 124 |
|
| 125 |
|
| 126 |
if file1_path is None or file2_path is None:
|
| 127 |
+
return "Error: Please upload or load both plasmid files.", *empty_return_for_error
|
| 128 |
|
| 129 |
try:
|
| 130 |
def read_plasmid(filepath, filename_for_error):
|
|
|
|
| 143 |
plasmid2_seq_rec = read_plasmid(file2_path, p2_orig_filename)
|
| 144 |
|
| 145 |
except Exception as e:
|
| 146 |
+
return str(e), *empty_return_for_error
|
| 147 |
|
| 148 |
valid_enzyme_objects = []
|
| 149 |
for enz_name in AllEnzymes.elements():
|
|
|
|
| 155 |
valid_enzyme_objects.append(enzyme_obj)
|
| 156 |
|
| 157 |
if not valid_enzyme_objects:
|
| 158 |
+
return "Error: Could not load any restriction enzymes from Biopython.", *empty_return_for_error
|
| 159 |
|
| 160 |
enzymes_batch = RestrictionBatch(valid_enzyme_objects)
|
| 161 |
analysis1 = Analysis(enzymes_batch, plasmid1_seq_rec.seq, linear=False)
|
| 162 |
analysis2 = Analysis(enzymes_batch, plasmid2_seq_rec.seq, linear=False)
|
| 163 |
|
| 164 |
+
enzymes_cutting_p1_obj = set(analysis1.with_sites().keys())
|
| 165 |
+
enzymes_cutting_p2_obj = set(analysis2.with_sites().keys())
|
| 166 |
|
| 167 |
+
unique_to_1_obj = sorted(list(enzymes_cutting_p1_obj - enzymes_cutting_p2_obj), key=lambda e: str(e))
|
| 168 |
+
unique_to_2_obj = sorted(list(enzymes_cutting_p2_obj - enzymes_cutting_p1_obj), key=lambda e: str(e))
|
| 169 |
|
| 170 |
unique_to_1_names = [str(e) for e in unique_to_1_obj]
|
| 171 |
unique_to_2_names = [str(e) for e in unique_to_2_obj]
|
|
|
|
| 176 |
msg1 = f"Enzymes cutting only {p1_display_label} ({len(unique_to_1_names)}):\n" + ", ".join(unique_to_1_names) if unique_to_1_names else f"No unique enzymes found for {p1_display_label}."
|
| 177 |
msg2 = f"Enzymes cutting only {p2_display_label} ({len(unique_to_2_names)}):\n" + ", ".join(unique_to_2_names) if unique_to_2_names else f"No unique enzymes found for {p2_display_label}."
|
| 178 |
|
| 179 |
+
# New: Find enzymes cutting both but with different fragments
|
| 180 |
+
common_enzymes_obj = enzymes_cutting_p1_obj.intersection(enzymes_cutting_p2_obj)
|
| 181 |
+
common_diff_fragments_enzymes_names = []
|
| 182 |
+
for enzyme_obj in common_enzymes_obj:
|
| 183 |
+
try:
|
| 184 |
+
fragments1_seqs = enzyme_obj.catalyse(plasmid1_seq_rec.seq)
|
| 185 |
+
fragments2_seqs = enzyme_obj.catalyse(plasmid2_seq_rec.seq)
|
| 186 |
+
|
| 187 |
+
lengths1 = sorted([len(f) for f in fragments1_seqs])
|
| 188 |
+
lengths2 = sorted([len(f) for f in fragments2_seqs])
|
| 189 |
+
|
| 190 |
+
if lengths1 != lengths2:
|
| 191 |
+
common_diff_fragments_enzymes_names.append(str(enzyme_obj))
|
| 192 |
+
except Exception as e_cat_common:
|
| 193 |
+
print(f"Warning: Error during catalysis comparison for common enzyme {str(enzyme_obj)}: {e_cat_common}")
|
| 194 |
+
# Optionally skip this enzyme or log more formally
|
| 195 |
+
|
| 196 |
+
common_diff_fragments_enzymes_names = sorted(list(set(common_diff_fragments_enzymes_names)))
|
| 197 |
+
|
| 198 |
+
msg_common_diff = f"Enzymes cutting BOTH plasmids with DIFFERENT fragments ({len(common_diff_fragments_enzymes_names)}):\n" + \
|
| 199 |
+
", ".join(common_diff_fragments_enzymes_names) if common_diff_fragments_enzymes_names \
|
| 200 |
+
else "No enzymes found that cut both plasmids with different fragment patterns."
|
| 201 |
+
|
| 202 |
status = "Analysis complete."
|
| 203 |
+
if not unique_to_1_names and not unique_to_2_names and not common_diff_fragments_enzymes_names:
|
| 204 |
+
status += " No differentiating enzymes found."
|
| 205 |
|
| 206 |
dd_choices = []
|
| 207 |
if current_plasmid_choice_for_plot == "Plasmid 1":
|
|
|
|
| 211 |
|
| 212 |
if (current_plasmid_choice_for_plot == "Plasmid 1" and unique_to_1_names) or \
|
| 213 |
(current_plasmid_choice_for_plot == "Plasmid 2" and unique_to_2_names):
|
| 214 |
+
current_dd_update = gr.update(choices=["Select an enzyme"] + dd_choices, value="Select an enzyme", interactive=True)
|
| 215 |
else:
|
| 216 |
+
current_dd_update = gr.update(choices=dd_choices, value=dd_choices[0], interactive=False if not dd_choices or "No unique" in dd_choices[0] else True)
|
| 217 |
|
| 218 |
+
return status, msg1, msg2, msg_common_diff, plasmid1_seq_rec, plasmid2_seq_rec, \
|
| 219 |
+
unique_to_1_names, unique_to_2_names, common_diff_fragments_enzymes_names, current_dd_update
|
| 220 |
|
| 221 |
def plot_selected_digest_controller(plasmid_choice_label, enzyme_name, p1_data, p2_data):
|
| 222 |
"""
|
|
|
|
| 244 |
return fig_placeholder
|
| 245 |
target_plasmid_rec = p1_data
|
| 246 |
target_label = "Plasmid 1"
|
| 247 |
+
if hasattr(p1_data, 'name') and p1_data.name and p1_data.name !="<unknown name>": target_label += f" ({p1_data.name})"
|
| 248 |
+
elif hasattr(p1_data, 'id') and p1_data.id and p1_data.id !="<unknown id>": target_label += f" ({p1_data.id})"
|
| 249 |
elif plasmid_choice_label == "Plasmid 2":
|
| 250 |
if p2_data is None:
|
| 251 |
ax_placeholder.clear()
|
|
|
|
| 254 |
return fig_placeholder
|
| 255 |
target_plasmid_rec = p2_data
|
| 256 |
target_label = "Plasmid 2"
|
| 257 |
+
if hasattr(p2_data, 'name') and p2_data.name and p2_data.name !="<unknown name>": target_label += f" ({p2_data.name})"
|
| 258 |
+
elif hasattr(p2_data, 'id') and p2_data.id and p2_data.id !="<unknown id>": target_label += f" ({p2_data.id})"
|
| 259 |
else:
|
| 260 |
ax_placeholder.clear()
|
| 261 |
ax_placeholder.text(0.5, 0.5, "Invalid plasmid selection.", ha='center', va='center', wrap=True, color='red')
|
|
|
|
| 283 |
Loads example files, triggers analysis, and then attempts to auto-plot.
|
| 284 |
"""
|
| 285 |
# Step 1: Perform analysis with example files
|
| 286 |
+
status, msg1, msg2, msg_common_diff, p1_rec, p2_rec, p1_enz_names, p2_enz_names, \
|
| 287 |
+
_common_diff_list_ignore, enz_dd_update_from_analysis = \
|
| 288 |
analyze_plasmids_gradio(EXAMPLE_PLASMID1_PATH, EXAMPLE_PLASMID2_PATH, "Plasmid 1")
|
| 289 |
|
| 290 |
# If analysis failed (e.g., files not found), p1_rec or p2_rec might be None
|
| 291 |
if p1_rec is None or p2_rec is None :
|
|
|
|
| 292 |
fig_error, ax_error = plt.subplots(figsize=(6,8))
|
| 293 |
+
ax_error.text(0.5, 0.5, f"Error during example analysis:\n{status}", ha='center', va='center', color='red', wrap=True) # Display actual error
|
| 294 |
ax_error.set_xticks([]); ax_error.set_yticks([])
|
| 295 |
plt.tight_layout()
|
| 296 |
+
# Ensure all expected output values are provided
|
| 297 |
+
return status, msg1, msg2, msg_common_diff, None, None, [], [], \
|
| 298 |
gr.update(choices=["Error"], value="Error", interactive=False), \
|
| 299 |
+
gr.update(value="Plasmid 1"), fig_error
|
| 300 |
|
| 301 |
+
# Step 2: Determine auto-plot parameters and update dropdown based on analysis
|
| 302 |
auto_plot_plasmid_label = None
|
| 303 |
auto_plot_enzyme_name = None
|
| 304 |
auto_plot_plasmid_data = None
|
| 305 |
+
final_radio_choice = "Plasmid 1" # Default
|
| 306 |
+
final_enz_dd_update = enz_dd_update_from_analysis # Use directly from analysis initially
|
| 307 |
|
| 308 |
if p1_enz_names:
|
| 309 |
auto_plot_plasmid_label = "Plasmid 1"
|
| 310 |
auto_plot_enzyme_name = p1_enz_names[0]
|
| 311 |
auto_plot_plasmid_data = p1_rec
|
| 312 |
final_radio_choice = "Plasmid 1"
|
| 313 |
+
final_enz_dd_update = gr.update(choices=["Select an enzyme"] + p1_enz_names, value=auto_plot_enzyme_name, interactive=True)
|
|
|
|
|
|
|
| 314 |
elif p2_enz_names:
|
| 315 |
auto_plot_plasmid_label = "Plasmid 2"
|
| 316 |
auto_plot_enzyme_name = p2_enz_names[0]
|
| 317 |
auto_plot_plasmid_data = p2_rec
|
| 318 |
final_radio_choice = "Plasmid 2"
|
| 319 |
+
final_enz_dd_update = gr.update(choices=["Select an enzyme"] + p2_enz_names, value=auto_plot_enzyme_name, interactive=True)
|
| 320 |
+
else: # No unique enzymes for either, dropdown should reflect current radio choice (P1 default from analyze call)
|
|
|
|
|
|
|
| 321 |
if final_radio_choice == "Plasmid 1":
|
| 322 |
+
final_enz_dd_update = gr.update(choices=[f"No unique enzymes for P1 ({os.path.basename(EXAMPLE_PLASMID1_PATH)})"],
|
| 323 |
+
value=f"No unique enzymes for P1 ({os.path.basename(EXAMPLE_PLASMID1_PATH)})", interactive=False)
|
| 324 |
+
# No explicit else for P2 needed here as P1 is the default for initial dropdown population
|
| 325 |
|
| 326 |
# Step 3: Generate plot if possible
|
| 327 |
if auto_plot_enzyme_name and auto_plot_plasmid_data:
|
| 328 |
+
# Use the actual name from p1_data or p2_data for the label if available
|
| 329 |
+
plot_label_detail = ""
|
| 330 |
+
if auto_plot_plasmid_label == "Plasmid 1":
|
| 331 |
+
if hasattr(p1_rec, 'name') and p1_rec.name and p1_rec.name != "<unknown name>": plot_label_detail = f" ({p1_rec.name})"
|
| 332 |
+
elif hasattr(p1_rec, 'id') and p1_rec.id and p1_rec.id != "<unknown id>": plot_label_detail = f" ({p1_rec.id})"
|
| 333 |
+
elif auto_plot_plasmid_label == "Plasmid 2":
|
| 334 |
+
if hasattr(p2_rec, 'name') and p2_rec.name and p2_rec.name != "<unknown name>": plot_label_detail = f" ({p2_rec.name})"
|
| 335 |
+
elif hasattr(p2_rec, 'id') and p2_rec.id and p2_rec.id != "<unknown id>": plot_label_detail = f" ({p2_rec.id})"
|
| 336 |
+
|
| 337 |
+
gel_fig = simulate_digest_and_plot_gradio(auto_plot_plasmid_data, auto_plot_enzyme_name, f"{auto_plot_plasmid_label}{plot_label_detail}")
|
| 338 |
else:
|
|
|
|
| 339 |
fig_placeholder, ax_placeholder = plt.subplots(figsize=(6, 8))
|
| 340 |
ax_placeholder.text(0.5, 0.5, "No unique enzymes found for automatic plotting.", ha='center', va='center', wrap=True)
|
| 341 |
ax_placeholder.set_xticks([]); ax_placeholder.set_yticks([])
|
| 342 |
plt.tight_layout()
|
| 343 |
gel_fig = fig_placeholder
|
| 344 |
+
if not p1_enz_names and not p2_enz_names:
|
| 345 |
+
final_enz_dd_update = gr.update(choices=["No unique enzymes found"], value="No unique enzymes found", interactive=False)
|
|
|
|
|
|
|
| 346 |
|
| 347 |
# Return all updates
|
| 348 |
+
return status, msg1, msg2, msg_common_diff, p1_rec, p2_rec, p1_enz_names, p2_enz_names, \
|
| 349 |
+
final_enz_dd_update, gr.update(value=final_radio_choice), gel_fig
|
| 350 |
|
| 351 |
|
| 352 |
# --- Gradio Interface Definition ---
|
|
|
|
| 355 |
gr.Markdown(
|
| 356 |
"**Instructions:**\n"
|
| 357 |
"1. Upload two plasmid sequence files (GenBank `.gb`/`.gbk` or FASTA `.fasta`/`.fna`/`.fa` format) OR click 'Load Example Files'.\n"
|
| 358 |
+
"2. If uploading manually, click `Analyze Uploaded Plasmids`. Results will show:\n"
|
| 359 |
+
" a. Enzymes that uniquely cut only Plasmid 1.\n"
|
| 360 |
+
" b. Enzymes that uniquely cut only Plasmid 2.\n"
|
| 361 |
+
" c. Enzymes that cut **both** plasmids but produce different fragment patterns.\n"
|
| 362 |
+
"3. Select which plasmid's **unique** enzymes you want to consider for plotting.\n"
|
| 363 |
"4. Choose a specific enzyme from the dropdown list.\n"
|
| 364 |
+
"5. Click `Generate Gel Plot` to visualize the digestion pattern for the selected plasmid and enzyme.\n"
|
| 365 |
f"Note: For 'Load Example Files', ensure `plasmid1_example.gb` and `plasmid2_example.gb` are in a folder named `{EXAMPLE_DIR}` next to this script."
|
| 366 |
)
|
| 367 |
|
|
|
|
| 369 |
plasmid2_data_state = gr.State()
|
| 370 |
p1_unique_enzymes_list_state = gr.State([])
|
| 371 |
p2_unique_enzymes_list_state = gr.State([])
|
| 372 |
+
# common_diff_enzymes_list_state = gr.State([]) # Not strictly needed as state if only displayed
|
| 373 |
|
| 374 |
with gr.Row():
|
| 375 |
with gr.Column(scale=1):
|
|
|
|
| 377 |
file_p1 = gr.File(label="Plasmid 1 File (e.g., .gb, .fasta)", type="filepath", file_types=[".gb", ".gbk", ".fasta", ".fna", ".fa"])
|
| 378 |
file_p2 = gr.File(label="Plasmid 2 File (e.g., .gb, .fasta)", type="filepath", file_types=[".gb", ".gbk", ".fasta", ".fna", ".fa"])
|
| 379 |
|
| 380 |
+
_current_plasmid_choice_for_plot_hidden = gr.Textbox(value="Plasmid 1", visible=False) # For analysis logic with dropdown
|
| 381 |
|
| 382 |
+
analyze_btn = gr.Button("Analyze Uploaded Plasmids", variant="secondary")
|
| 383 |
example_btn = gr.Button("Load Example Files & Auto-Analyze/Plot", variant="primary", elem_id="example_button")
|
| 384 |
|
| 385 |
with gr.Column(scale=2):
|
| 386 |
gr.Markdown("### Analysis Results")
|
| 387 |
+
status_message_txt = gr.Textbox(label="Status", interactive=False, lines=1, max_lines=3)
|
| 388 |
unique_enzymes_p1_txt = gr.Textbox(label="Enzymes cutting only Plasmid 1", interactive=False, lines=3, max_lines=6)
|
| 389 |
unique_enzymes_p2_txt = gr.Textbox(label="Enzymes cutting only Plasmid 2", interactive=False, lines=3, max_lines=6)
|
| 390 |
+
common_diff_enzymes_txt = gr.Textbox(label="Enzymes cutting BOTH plasmids (different fragments)", interactive=False, lines=3, max_lines=6) # New Textbox
|
| 391 |
|
| 392 |
gr.Markdown("---")
|
| 393 |
gr.Markdown("### 2. Visualize Digestion on Virtual Gel")
|
|
|
|
| 396 |
with gr.Column(scale=1):
|
| 397 |
plasmid_to_plot_choice_radio = gr.Radio(
|
| 398 |
choices=["Plasmid 1", "Plasmid 2"],
|
| 399 |
+
label="Select Plasmid for Gel Visualization (of its unique enzymes)",
|
| 400 |
value="Plasmid 1",
|
| 401 |
interactive=True
|
| 402 |
)
|
| 403 |
|
| 404 |
enzyme_for_plot_dropdown = gr.Dropdown(
|
| 405 |
+
label="Select Unique Enzyme for Chosen Plasmid",
|
| 406 |
choices=["Analyze plasmids first"],
|
| 407 |
value="Analyze plasmids first",
|
| 408 |
interactive=False
|
| 409 |
)
|
| 410 |
+
plot_btn = gr.Button("Generate Gel Plot for Selection", variant="secondary", elem_id="plot_button")
|
| 411 |
|
| 412 |
with gr.Column(scale=2):
|
| 413 |
gel_plot_output = gr.Plot(label="Virtual Agarose Gel")
|
|
|
|
| 420 |
plasmid_to_plot_choice_radio.change(
|
| 421 |
fn=lambda x: x,
|
| 422 |
inputs=[plasmid_to_plot_choice_radio],
|
| 423 |
+
outputs=[_current_plasmid_choice_for_plot_hidden] # Keep this to inform analyze_plasmids_gradio logic for initial dd
|
| 424 |
)
|
| 425 |
|
| 426 |
analyze_btn.click(
|
| 427 |
fn=analyze_plasmids_gradio,
|
| 428 |
+
inputs=[file_p1, file_p2, _current_plasmid_choice_for_plot_hidden], # Pass the hidden value
|
| 429 |
outputs=[
|
| 430 |
status_message_txt, unique_enzymes_p1_txt, unique_enzymes_p2_txt,
|
| 431 |
+
common_diff_enzymes_txt, # New output for the new textbox
|
| 432 |
plasmid1_data_state, plasmid2_data_state,
|
| 433 |
p1_unique_enzymes_list_state, p2_unique_enzymes_list_state,
|
| 434 |
+
gr.State(), # Placeholder for common_diff_fragments_enzymes_names list (returned but not stored in state)
|
| 435 |
enzyme_for_plot_dropdown
|
| 436 |
]
|
| 437 |
)
|
| 438 |
|
| 439 |
example_btn.click(
|
| 440 |
fn=load_examples_and_auto_process,
|
| 441 |
+
inputs=[],
|
| 442 |
outputs=[
|
| 443 |
status_message_txt, unique_enzymes_p1_txt, unique_enzymes_p2_txt,
|
| 444 |
+
common_diff_enzymes_txt, # New output
|
| 445 |
plasmid1_data_state, plasmid2_data_state,
|
| 446 |
p1_unique_enzymes_list_state, p2_unique_enzymes_list_state,
|
| 447 |
+
enzyme_for_plot_dropdown,
|
| 448 |
+
plasmid_to_plot_choice_radio,
|
| 449 |
+
gel_plot_output
|
| 450 |
]
|
| 451 |
)
|
| 452 |
|
|
|
|
| 463 |
)
|
| 464 |
|
| 465 |
if __name__ == '__main__':
|
|
|
|
| 466 |
if not os.path.exists(EXAMPLE_DIR):
|
| 467 |
os.makedirs(EXAMPLE_DIR)
|
| 468 |
+
print(f"Created directory: {EXAMPLE_DIR}. Please add example plasmid files (plasmid1_example.gb, plasmid2_example.gb) to it for the example button to work.")
|
| 469 |
+
|
| 470 |
+
# Check for example files and print a message if they are missing
|
| 471 |
+
if not os.path.exists(EXAMPLE_PLASMID1_PATH) or not os.path.exists(EXAMPLE_PLASMID2_PATH):
|
| 472 |
+
print(f"Warning: Example files (plasmid1_example.gb, plasmid2_example.gb) not found in '{EXAMPLE_DIR}'. The 'Load Example Files' button might not work as expected.")
|
| 473 |
+
print("You can create dummy GenBank or FASTA files with these names for testing if needed.")
|
| 474 |
|
| 475 |
demo.launch()
|