Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,7 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+fold_0/logs.models.fold_0.ENCSR149XIL/logfile.modelling.fold_0.ENCSR149XIL.stdout_v1.txt filter=lfs diff=lfs merge=lfs -text
+fold_1/logs.models.fold_1.ENCSR149XIL/logfile.modelling.fold_1.ENCSR149XIL.stdout_v1.txt filter=lfs diff=lfs merge=lfs -text
+fold_2/logs.models.fold_2.ENCSR149XIL/logfile.modelling.fold_2.ENCSR149XIL.stdout_v1.txt filter=lfs diff=lfs merge=lfs -text
+fold_3/logs.models.fold_3.ENCSR149XIL/logfile.modelling.fold_3.ENCSR149XIL.stdout_v1.txt filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,120 @@
+---
+license: mit
+library_name: chrombpnet
+tags:
+  - encode
+  - chrombpnet
+  - chromatin-accessibility
+  - DNASE
+  - HepG2
+  - hg38
+---
+# ENCODE ChromBPNet Atlas
+As part of the ENCODE 4 Project, we trained ChromBPNet models on 1,512 ENCODE DNAse-seq and ATAC-seq across 408 biosamples. Here, we provide all models for open-source use.
+
+For more information about the models, see:
+- Main ENCODE 4 Paper
+- [A unified lexicon of predictive DNA sequence motifs from ENCODE transcription factor binding and chromatin accessibility assays](https://doi.org/10.5281/zenodo.17123347) (Deshpande et al., Zenodo 2025)
+- [ChromBPNet: bias factorized, base-resolution deep learning models of chromatin accessibility reveal cis-regulatory sequence syntax, transcription factor footprints and regulatory variants](https://doi.org/10.1101/2024.12.25.630221) (Pampari et al., bioRxiv 2024)
+
+## ChromBPNet model: DNASE in HepG2 (ENCSR149XIL)
+- Model: ChromBPNet
+- Assay: DNASE-seq
+- Experiment: [ENCSR149XIL](https://www.encodeproject.org/experiments/ENCSR149XIL/)
+- Model annotation: [ENCSR006CUK](https://www.encodeproject.org/annotations/ENCSR006CUK/)
+- Biosample: HepG2 (Full name: Homo sapiens HepG2)
+- Cell slim(s): epithelial-cell,cancer-cell
+- Organ slim(s): endocrine-gland,epithelium,liver,exocrine-gland
+- Developmental slim(s): endoderm
+- System slim(s): digestive-system,exocrine-system,endocrine-system
+- Assembly: hg38
+
+## Directory structure
+- `fold_0`: Model of 5-fold cross-validation: Fold 0
+    - `model.chrombpnet.fold_0.encid.h5`: full chrombpnet model that combines both bias and corrected model in .h5 format
+    - `model.chrombpnet_nobias.fold_0.encid.h5`: bias-corrected accessibility model in .h5 format (Use for all biological discovery)
+    - `model.bias_scaled.fold_0.encid.h5`: bias model in .h5 format
+    - `model.chrombpnet.fold_0.encid.tar`: full chrombpnet model that combines both bias and  corrected model in SavedModel format. After being untarred, it results in a directory named "chrombpnet".
+    - `model.chrombpnet_nobias.fold_0.encid.tar`: bias-corrected accessibility model in SavedModel format (Use for all biological discovery). After being untarred, it results in a directory named "chrombpnet_wo_bias".
+    - `model.bias_scaled.fold_0.encid.tar`: bias model in SavedModel format. After being untarred, it results in a directory named "bias_model_scaled".
+    - `logs.models.fold_0.encid`: folder containing log files for training models
+- `fold_1`: Model of 5-fold coss-validation: Fold 1
+- `fold_2`: Model of 5-fold cross-validation: Fold 2
+- `fold_3`: Model of 5-fold cross-validation: Fold 3
+- `fold_4`: Model of 5-fold cross-validation: Fold 4
+
+# Instructions
+## 1. Pseudocode for loading models in .h5 format 
+
+(1) Use the code in python after appropriately defining `model_in_h5_format` and `inputs`. \
+(2) `inputs` is a one hot encoded sequence of shape (N,2114,4). Here N corresponds to the 
+number of tested sequences, 2114 is the input sequence length and 4 corresponds to [A,C,G,T].
+
+```python
+import tensorflow as tf
+from tensorflow.keras.utils import get_custom_objects
+from tensorflow.keras.models import load_model
+
+custom_objects={"tf": tf}
+get_custom_objects().update(custom_objects)
+
+model=load_model(model_in_h5_format,compile=False)
+outputs = model(inputs)
+```
+
+The list `outputs` consists of two elements. The first element has a shape of (N, 1000) and
+contains logit predictions for a 1000-base-pair output. The second element, with a shape of
+(N, 1), contains logcount predictions. To transform these predictions into per-base signals, 
+follow the provided pseudo code lines below.
+
+```python
+import numpy as np
+
+def softmax(x, temp=1):
+    norm_x = x - np.mean(x,axis=1, keepdims=True)
+    return np.exp(temp*norm_x)/np.sum(np.exp(temp*norm_x), axis=1, keepdims=True)
+    
+predictions = softmax(outputs[0]) * (np.exp(outputs[1])-1)
+```
+
+## 2. Pseudocode for loading models in .tar format
+
+(1) First untar the directory as follows `tar -xvf model.tar`. \
+(2) Use the code below in python after appropriately defining `model_dir_untared` and `inputs`. \
+(3) `inputs` is a one hot encoded sequence of shape (N,2114,4). Here N corresponds to the number
+of tested sequences, 2114 is the input sequence length and 4 corresponds to ACGT.
+
+Reference: https://www.tensorflow.org/api_docs/python/tf/saved_model/load
+
+```python
+import tensorflow as tf
+
+model = tf.saved_model.load('model_dir_untared')
+outputs = model.signatures['serving_default'](**{'sequence':inputs.astype('float32')})
+```
+
+The variable `outputs` represents a dictionary containing two key-value pairs. The first key
+is `logits_profile_predictions`, holding a value with a shape of (N, 1000). This value corresponds
+to logit predictions for a 1000-base-pair output. The second key, named `logcount_predictions``, 
+is associated with a value of shape (N, 1), representing logcount predictions. To transform these
+predictions into per-base signals, utilize the provided pseudo code lines mentioned below.
+
+```python
+import numpy as np
+def softmax(x, temp=1):
+    norm_x = x - np.mean(x,axis=1, keepdims=True)
+    return np.exp(temp*norm_x)/np.sum(np.exp(temp*norm_x), axis=1, keepdims=True)
+    
+predictions = softmax(outputs["logits_profile_predictions"]) * (np.exp(outputs["logcount_predictions"])-1)
+```
+
+## Docker image to load and use the models
+- https://hub.docker.com/r/kundajelab/chrombpnet-atlas/ (tag:v1)
+
+## Code for ChromBPNet
+- https://github.com/kundajelab/chrombpnet/
+
+# License & citation
+External data users may freely download, analyze and publish results based on any ENCODE data without restrictions.
+
+Released under the [ENCODE data-use policy](https://www.encodeproject.org/about/data-use-policy/). Please cite the ENCODE Project Consortium and the model software: [ChromBPNet](https://github.com/kundajelab/chrombpnet) (Pampari et al., bioRxiv 2024).

fold_0/logs.models.fold_0.ENCSR149XIL/logfile.modelling.fold_0.ENCSR149XIL.args.json

@@ -0,0 +1,23 @@
+{
+    "genome": "reference/hg38.genome.fa",
+    "bigwig": "results/chrombpnet/DNASE_PE/HEPG2/data/HEPG2_unstranded.bw",
+    "peaks": "results/chrombpnet/DNASE_PE/HEPG2/HEPG2_06.08.2022_bias_128_4_1234_0.8_fold_0/chrombpnet_model/filtered.peaks.bed",
+    "nonpeaks": "results/chrombpnet/DNASE_PE/HEPG2/HEPG2_06.08.2022_bias_128_4_1234_0.8_fold_0/chrombpnet_model/filtered.nonpeaks.bed",
+    "output_prefix": "results/chrombpnet/DNASE_PE/HEPG2/HEPG2_06.08.2022_bias_128_4_1234_0.8_fold_0/chrombpnet_model/chrombpnet",
+    "chr_fold_path": "splits/fold_0.json",
+    "trackables": [
+        "logcount_predictions_loss",
+        "loss",
+        "logits_profile_predictions_loss",
+        "val_logcount_predictions_loss",
+        "val_loss",
+        "val_logits_profile_predictions_loss"
+    ],
+    "epochs": 50,
+    "early_stop": 5,
+    "batch_size": 64,
+    "learning_rate": 0.001,
+    "params": "results/chrombpnet/DNASE_PE/HEPG2/HEPG2_06.08.2022_bias_128_4_1234_0.8_fold_0/chrombpnet_model/chrombpnet_model_params.tsv",
+    "seed": 1234,
+    "architecture_from_file": "/mydata/src/training/models/chrombpnet_with_bias_model.py"
+}

fold_0/logs.models.fold_0.ENCSR149XIL/logfile.modelling.fold_0.ENCSR149XIL.chrombpnet.params.json

@@ -0,0 +1,11 @@
+{
+    "counts_loss_weight": "23.6",
+    "filters": "512",
+    "n_dil_layers": "8",
+    "bias_model_path": "results/chrombpnet/DNASE_PE/HEPG2/HEPG2_06.08.2022_bias_128_4_1234_0.8_fold_0/chrombpnet_model/bias_model_scaled.h5",
+    "inputlen": "2114",
+    "outputlen": "1000",
+    "max_jitter": "500",
+    "chr_fold_path": "splits/fold_0.json",
+    "negative_sampling_ratio": "0.1"
+}

fold_0/logs.models.fold_0.ENCSR149XIL/logfile.modelling.fold_0.ENCSR149XIL.chrombpnet_data_params.tsv

@@ -0,0 +1,3 @@
+counts_sum_min_thresh	24.0
+counts_sum_max_thresh	5058.83
+trainings_pts_post_thresh	157737

fold_0/logs.models.fold_0.ENCSR149XIL/logfile.modelling.fold_0.ENCSR149XIL.chrombpnet_model_params.tsv

@@ -0,0 +1,9 @@
+counts_loss_weight	23.6
+filters	512
+n_dil_layers	8
+bias_model_path	results/chrombpnet/DNASE_PE/HEPG2/HEPG2_06.08.2022_bias_128_4_1234_0.8_fold_0/chrombpnet_model/bias_model_scaled.h5
+inputlen	2114
+outputlen	1000
+max_jitter	500
+chr_fold_path	splits/fold_0.json
+negative_sampling_ratio	0.1

fold_0/logs.models.fold_0.ENCSR149XIL/logfile.modelling.fold_0.ENCSR149XIL.epoch_loss.csv

@@ -0,0 +1,21 @@
+epoch,logcount_predictions_loss,logits_profile_predictions_loss,loss,val_logcount_predictions_loss,val_logits_profile_predictions_loss,val_loss
+0,1.8586431741714478,783.5877685546875,827.451904296875,0.7625074982643127,787.6505737304688,805.6458129882812
+1,0.7904894351959229,720.1884155273438,738.8430786132812,0.6817762851715088,758.6968383789062,774.7867431640625
+2,0.7368709444999695,702.9209594726562,720.3121337890625,0.6972478032112122,764.1160278320312,780.5715942382812
+3,0.6966291069984436,692.9837646484375,709.4241943359375,0.7009695768356323,752.6982421875,769.2410888671875
+4,0.6747046113014221,685.53173828125,701.4537353515625,0.6405949592590332,740.6015014648438,755.71923828125
+5,0.6469643712043762,679.1580200195312,694.42626953125,0.670920193195343,749.3623657226562,765.1958618164062
+6,0.6279658079147339,674.880859375,689.700927734375,0.6347630023956299,748.443603515625,763.4241333007812
+7,0.612751841545105,672.0081787109375,686.4696655273438,0.6461305022239685,736.6702880859375,751.9187622070312
+8,0.5926315188407898,668.47705078125,682.4638671875,0.6156713962554932,735.3665771484375,749.896484375
+9,0.5768236517906189,665.5355224609375,679.1475219726562,0.6137552261352539,740.5673828125,755.05224609375
+10,0.5589054822921753,663.16455078125,676.354736328125,0.6126865744590759,741.4617309570312,755.9210205078125
+11,0.5462303161621094,661.6257934570312,674.5161743164062,0.620571494102478,742.6611328125,757.3067626953125
+12,0.5337945222854614,660.3777465820312,672.9746704101562,0.6201422810554504,730.7467651367188,745.3818359375
+13,0.524074912071228,658.9896850585938,671.3577880859375,0.6271715760231018,732.2919311523438,747.0931396484375
+14,0.5052937269210815,656.5836791992188,668.5072631835938,0.605384349822998,729.178466796875,743.4656372070312
+15,0.4896944761276245,655.8970336914062,667.4535522460938,0.6602228283882141,732.9867553710938,748.568359375
+16,0.48004040122032166,654.6798095703125,666.0089111328125,0.6147953867912292,745.2626342773438,759.771240234375
+17,0.47006991505622864,654.5709838867188,665.66455078125,0.6520988345146179,731.505615234375,746.8952026367188
+18,0.45601215958595276,652.5884399414062,663.3499145507812,0.614874541759491,737.3208618164062,751.8322143554688
+19,0.43833643198013306,651.884033203125,662.2286987304688,0.8243728876113892,736.106201171875,755.5612182617188

fold_0/logs.models.fold_0.ENCSR149XIL/logfile.modelling.fold_0.ENCSR149XIL.stdout_v1.txt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:29d3fdadcf44f947d569a04d1890cda24e2044ed7f311962c4ff180edcdb6242
+size 13793981

fold_0/model.bias_scaled.fold_0.ENCSR149XIL.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:68356ecb470f2e981ff248f0746d8c338512844d44a08796ebd17b0b68923169
+size 2688440

fold_0/model.bias_scaled.fold_0.ENCSR149XIL.tar

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9d6da7710859dc416c371c2728fabf539351bf9c5940c3f28170ee06b9539894
+size 1198080

fold_0/model.chrombpnet.fold_0.ENCSR149XIL.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8a9ee8b292805201c77084af907863edf79baa2f4fcccb273ef036225ac6e893
+size 77540320

fold_0/model.chrombpnet.fold_0.ENCSR149XIL.tar

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2e98e503a2144941c2fa9d0caa3be340bc4ba5c29a8b7ccce555724f0f9f076c
+size 27535360

fold_0/model.chrombpnet_nobias.fold_0.ENCSR149XIL.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dd39ac49d485608ff836abb57199bc28c6e8d0fabd9b74da13cd80b77247e2ea
+size 25583536

fold_0/model.chrombpnet_nobias.fold_0.ENCSR149XIL.tar

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:36224e95aae7c1188877b743d428412cc38f6eb9184aefdd561e1c3baba973eb
+size 26060800

fold_1/logs.models.fold_1.ENCSR149XIL/logfile.modelling.fold_1.ENCSR149XIL.args.json

@@ -0,0 +1,23 @@
+{
+    "genome": "reference/hg38.genome.fa",
+    "bigwig": "HEPG2_DNASE_PE/data/HEPG2_unstranded.bw",
+    "peaks": "models/HEPG2_07.13.2022_bias_128_4_1234_0.8_fold_1_data_type_DNASE_PE/chrombpnet_model/filtered.peaks.bed",
+    "nonpeaks": "models/HEPG2_07.13.2022_bias_128_4_1234_0.8_fold_1_data_type_DNASE_PE/chrombpnet_model/filtered.nonpeaks.bed",
+    "output_prefix": "models/HEPG2_07.13.2022_bias_128_4_1234_0.8_fold_1_data_type_DNASE_PE/chrombpnet_model/chrombpnet",
+    "chr_fold_path": "splits/fold_1.json",
+    "trackables": [
+        "logcount_predictions_loss",
+        "loss",
+        "logits_profile_predictions_loss",
+        "val_logcount_predictions_loss",
+        "val_loss",
+        "val_logits_profile_predictions_loss"
+    ],
+    "epochs": 50,
+    "early_stop": 5,
+    "batch_size": 64,
+    "learning_rate": 0.001,
+    "params": "models/HEPG2_07.13.2022_bias_128_4_1234_0.8_fold_1_data_type_DNASE_PE/chrombpnet_model/chrombpnet_model_params.tsv",
+    "seed": 1234,
+    "architecture_from_file": "/scratch/chrombpnet/src/training/models/chrombpnet_with_bias_model.py"
+}

fold_1/logs.models.fold_1.ENCSR149XIL/logfile.modelling.fold_1.ENCSR149XIL.chrombpnet.params.json

@@ -0,0 +1,11 @@
+{
+    "counts_loss_weight": "23.6",
+    "filters": "512",
+    "n_dil_layers": "8",
+    "bias_model_path": "models/HEPG2_07.13.2022_bias_128_4_1234_0.8_fold_1_data_type_DNASE_PE/chrombpnet_model/bias_model_scaled.h5",
+    "inputlen": "2114",
+    "outputlen": "1000",
+    "max_jitter": "500",
+    "chr_fold_path": "splits/fold_1.json",
+    "negative_sampling_ratio": "0.1"
+}

fold_1/logs.models.fold_1.ENCSR149XIL/logfile.modelling.fold_1.ENCSR149XIL.chrombpnet_data_params.tsv

@@ -0,0 +1,3 @@
+counts_sum_min_thresh	24.0
+counts_sum_max_thresh	4974.84
+trainings_pts_post_thresh	156225

fold_1/logs.models.fold_1.ENCSR149XIL/logfile.modelling.fold_1.ENCSR149XIL.chrombpnet_model_params.tsv

@@ -0,0 +1,9 @@
+counts_loss_weight	23.6
+filters	512
+n_dil_layers	8
+bias_model_path	models/HEPG2_07.13.2022_bias_128_4_1234_0.8_fold_1_data_type_DNASE_PE/chrombpnet_model/bias_model_scaled.h5
+inputlen	2114
+outputlen	1000
+max_jitter	500
+chr_fold_path	splits/fold_1.json
+negative_sampling_ratio	0.1

fold_1/logs.models.fold_1.ENCSR149XIL/logfile.modelling.fold_1.ENCSR149XIL.epoch_loss.csv

@@ -0,0 +1,18 @@
+epoch,logcount_predictions_loss,logits_profile_predictions_loss,loss,val_logcount_predictions_loss,val_logits_profile_predictions_loss,val_loss
+0,2.7160086631774902,783.3927612304688,847.4912109375,0.8848746418952942,832.6495971679688,853.531982421875
+1,0.8323684334754944,718.556884765625,738.201416015625,1.0540248155593872,802.8994140625,827.7747802734375
+2,0.7597503662109375,699.5315551757812,717.4620361328125,0.728026270866394,793.7456665039062,810.92724609375
+3,0.722489595413208,688.87353515625,705.9241943359375,0.7032780051231384,790.855712890625,807.4527587890625
+4,0.6833001971244812,680.341796875,696.4686279296875,0.7472972273826599,778.2113647460938,795.847900390625
+5,0.6619024276733398,674.3301391601562,689.9500122070312,0.6921755075454712,772.8952026367188,789.2303466796875
+6,0.6335767507553101,669.6817626953125,684.6342163085938,0.6713157892227173,790.9915161132812,806.8341064453125
+7,0.6177946329116821,665.60595703125,680.1859741210938,0.6494790315628052,774.916259765625,790.2435913085938
+8,0.6072438955307007,660.9243774414062,675.2533569335938,0.6825321316719055,769.4947509765625,785.6024780273438
+9,0.5753155946731567,657.8514404296875,671.428466796875,0.685223400592804,765.098388671875,781.2694091796875
+10,0.5649620294570923,657.240966796875,670.5761108398438,0.6583570837974548,768.1043090820312,783.6419067382812
+11,0.5524120330810547,653.5458374023438,666.5831909179688,0.6261001229286194,765.16259765625,779.9388427734375
+12,0.5337667465209961,651.2423706054688,663.8394165039062,0.6451011896133423,772.8038940429688,788.028076171875
+13,0.5226174592971802,650.6633911132812,662.99755859375,0.6160789132118225,767.0772705078125,781.6168212890625
+14,0.5072084665298462,649.0960083007812,661.065673828125,0.6344965100288391,767.9884643554688,782.9630737304688
+15,0.4892769157886505,647.4235229492188,658.9714965820312,0.6158895492553711,771.56494140625,786.1000366210938
+16,0.47532540559768677,646.5631713867188,657.7813720703125,0.711609423160553,776.4169921875,793.21142578125

fold_1/logs.models.fold_1.ENCSR149XIL/logfile.modelling.fold_1.ENCSR149XIL.stdout_v1.txt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d73fc3c6cee07eaea2ac448ef192e452c732536b0a7ae70d0db331d6bf2ef847
+size 11466230

fold_1/model.bias_scaled.fold_1.ENCSR149XIL.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:db402adfb5f90e5c1dba7de46b46a79700a222397b3bc8ce632a6765372647cf
+size 2688440

fold_1/model.bias_scaled.fold_1.ENCSR149XIL.tar

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d58b6a754eed69e98e1096cd63501dc524d9bae0c119346d499f65796c291a51
+size 1198080

fold_1/model.chrombpnet.fold_1.ENCSR149XIL.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5c895675229a6114460d26f7bb9c5f98d9ec1a3daeffb6b1ee8d7515c48cd62a
+size 77540352

fold_1/model.chrombpnet.fold_1.ENCSR149XIL.tar

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bf87235ab2bc93b170ed760918603d9edb374408786c602247413439ab2a6d7d
+size 27535360

fold_1/model.chrombpnet_nobias.fold_1.ENCSR149XIL.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:80366f2344f6fee5e3a6536fa85880165ea21f6729a27010e37d1aa5843b988b
+size 25583536

fold_1/model.chrombpnet_nobias.fold_1.ENCSR149XIL.tar

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3b7c17fac1f3826d7e719792a120517675d5d4bf1921e7fb2d5bdb8b2fb5b281
+size 26060800

fold_2/logs.models.fold_2.ENCSR149XIL/logfile.modelling.fold_2.ENCSR149XIL.chrombpnet.params.json

@@ -0,0 +1,11 @@
+{
+    "counts_loss_weight": "23.7",
+    "filters": "512",
+    "n_dil_layers": "8",
+    "bias_model_path": "models/HEPG2_07.07.2022_bias_128_4_1234_0.8_fold_2_data_type_DNASE_PE/chrombpnet_model/bias_model_scaled.h5",
+    "inputlen": "2114",
+    "outputlen": "1000",
+    "max_jitter": "500",
+    "chr_fold_path": "splits/fold_2.json",
+    "negative_sampling_ratio": "0.1"
+}

fold_2/logs.models.fold_2.ENCSR149XIL/logfile.modelling.fold_2.ENCSR149XIL.chrombpnet_data_params.tsv

@@ -0,0 +1,3 @@
+counts_sum_min_thresh	25.0
+counts_sum_max_thresh	5127.0
+trainings_pts_post_thresh	168274

fold_2/logs.models.fold_2.ENCSR149XIL/logfile.modelling.fold_2.ENCSR149XIL.chrombpnet_model_params.tsv

@@ -0,0 +1,9 @@
+counts_loss_weight	23.7
+filters	512
+n_dil_layers	8
+bias_model_path	models/HEPG2_07.07.2022_bias_128_4_1234_0.8_fold_2_data_type_DNASE_PE/chrombpnet_model/bias_model_scaled.h5
+inputlen	2114
+outputlen	1000
+max_jitter	500
+chr_fold_path	splits/fold_2.json
+negative_sampling_ratio	0.1

fold_2/logs.models.fold_2.ENCSR149XIL/logfile.modelling.fold_2.ENCSR149XIL.epoch_loss.csv

@@ -0,0 +1,21 @@
+epoch,logcount_predictions_loss,logits_profile_predictions_loss,loss,val_logcount_predictions_loss,val_logits_profile_predictions_loss,val_loss
+0,1.7780704498291016,798.0667724609375,840.207763671875,0.8405828475952148,756.022705078125,775.9445190429688
+1,0.7893288135528564,733.26318359375,751.9707641601562,0.7748401165008545,724.78857421875,743.1524047851562
+2,0.7327795624732971,715.7318725585938,733.0993041992188,0.7714395523071289,719.4630126953125,737.7460327148438
+3,0.7010683417320251,705.91015625,722.5260009765625,0.7122006416320801,718.9901733398438,735.8689575195312
+4,0.6698248982429504,697.2886352539062,713.1629638671875,0.6494258642196655,713.0451049804688,728.4365844726562
+5,0.6512414813041687,692.6605834960938,708.095947265625,0.686150312423706,712.5093383789062,728.7708740234375
+6,0.632262647151947,686.9073486328125,701.8922729492188,0.6611154675483704,711.3394775390625,727.0078735351562
+7,0.6080864667892456,683.6890869140625,698.1011352539062,0.6406891345977783,707.704833984375,722.8892211914062
+8,0.5900904536247253,679.4542846679688,693.4390869140625,0.6394379734992981,711.0972900390625,726.2521362304688
+9,0.5821489095687866,678.1852416992188,691.9801635742188,0.6471285223960876,701.0146484375,716.3518676757812
+10,0.5627459287643433,675.88037109375,689.2176513671875,0.6742681264877319,708.9393920898438,724.9195556640625
+11,0.5548050999641418,674.0723876953125,687.22119140625,0.6265104413032532,703.2545776367188,718.1026000976562
+12,0.5380526185035706,671.4716186523438,684.2225952148438,0.6852681040763855,703.8733520507812,720.1144409179688
+13,0.5247398614883423,669.9281616210938,682.3653564453125,0.6861340403556824,702.885498046875,719.1471557617188
+14,0.5082777142524719,669.0418701171875,681.0864868164062,0.6297059655189514,699.6806030273438,714.6046142578125
+15,0.4978810250759125,668.0320434570312,679.8325805664062,0.614916980266571,705.1763305664062,719.749755859375
+16,0.4904002249240875,665.963134765625,677.5858764648438,0.6249411702156067,705.1491088867188,719.960205078125
+17,0.4735621213912964,665.603515625,676.826904296875,0.6001379489898682,707.0398559570312,721.2636108398438
+18,0.4640873968601227,665.024658203125,676.0235595703125,0.7123560309410095,709.2037353515625,726.0864868164062
+19,0.4542595446109772,663.3477172851562,674.1134643554688,0.6216472387313843,711.8184814453125,726.5519409179688

fold_2/logs.models.fold_2.ENCSR149XIL/logfile.modelling.fold_2.ENCSR149XIL.stdout_v1.txt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c11e61cebadec1c0de059a1464df21bbc0b5a01ecbb16a95c34fcf51f6dba6da
+size 14990734

fold_2/model.bias_scaled.fold_2.ENCSR149XIL.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6b03de6ef02a21f6b39f4cbf38b10cf35460197adb0c81e42088a5c858ebe43c
+size 2688440

fold_2/model.bias_scaled.fold_2.ENCSR149XIL.tar

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f2b2b6169ebe9081d58c6830d6563eadc125d7417853c10c1f0568f14504b42c
+size 1198080

fold_2/model.chrombpnet.fold_2.ENCSR149XIL.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6e59a3d36712e05171a4d62a61a98d922fd38e6613d9cf371b9a12801ab26aad
+size 77540352

fold_2/model.chrombpnet.fold_2.ENCSR149XIL.tar

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:95d6a7ac7a09c98900f5a1127a72ddb0d918cb1c386aac7aefa29f3f02419680
+size 27535360

fold_2/model.chrombpnet_nobias.fold_2.ENCSR149XIL.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e8f9126bb930789dc5fd05de85af1446447be137db7937154489d617d42e7a73
+size 25583536

fold_2/model.chrombpnet_nobias.fold_2.ENCSR149XIL.tar

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8b476b5ec41c215dc2e7378fbd17a653ac60a82f346d6dae990aefd8a81b9d8a
+size 26060800

fold_3/logs.models.fold_3.ENCSR149XIL/logfile.modelling.fold_3.ENCSR149XIL.chrombpnet.params.json

@@ -0,0 +1,11 @@
+{
+    "counts_loss_weight": "23.6",
+    "filters": "512",
+    "n_dil_layers": "8",
+    "bias_model_path": "models/HEPG2_07.07.2022_bias_128_4_1234_0.8_fold_3_data_type_DNASE_PE/chrombpnet_model/bias_model_scaled.h5",
+    "inputlen": "2114",
+    "outputlen": "1000",
+    "max_jitter": "500",
+    "chr_fold_path": "splits/fold_3.json",
+    "negative_sampling_ratio": "0.1"
+}

fold_3/logs.models.fold_3.ENCSR149XIL/logfile.modelling.fold_3.ENCSR149XIL.chrombpnet_data_params.tsv

@@ -0,0 +1,3 @@
+counts_sum_min_thresh	22.0
+counts_sum_max_thresh	4988.2
+trainings_pts_post_thresh	157347

fold_3/logs.models.fold_3.ENCSR149XIL/logfile.modelling.fold_3.ENCSR149XIL.chrombpnet_model_params.tsv

@@ -0,0 +1,9 @@
+counts_loss_weight	23.6
+filters	512
+n_dil_layers	8
+bias_model_path	models/HEPG2_07.07.2022_bias_128_4_1234_0.8_fold_3_data_type_DNASE_PE/chrombpnet_model/bias_model_scaled.h5
+inputlen	2114
+outputlen	1000
+max_jitter	500
+chr_fold_path	splits/fold_3.json
+negative_sampling_ratio	0.1

fold_3/logs.models.fold_3.ENCSR149XIL/logfile.modelling.fold_3.ENCSR149XIL.epoch_loss.csv

@@ -0,0 +1,19 @@
+epoch,logcount_predictions_loss,logits_profile_predictions_loss,loss,val_logcount_predictions_loss,val_logits_profile_predictions_loss,val_loss
+0,1.4193753004074097,791.48876953125,824.985595703125,0.7805492877960205,781.6251220703125,800.0460205078125
+1,0.7786723375320435,721.2662353515625,739.6435546875,0.7125132083892822,755.082763671875,771.8985595703125
+2,0.7225978374481201,702.5689697265625,719.6222534179688,0.697835385799408,737.1134033203125,753.5819702148438
+3,0.6967244148254395,693.1700439453125,709.6132202148438,0.7542037963867188,736.5390625,754.3381958007812
+4,0.6623961329460144,686.6959838867188,702.3273315429688,0.653588056564331,734.9500122070312,750.3755493164062
+5,0.6404021382331848,679.505859375,694.6201171875,0.6325311660766602,729.4718017578125,744.3994140625
+6,0.6223130226135254,675.6190795898438,690.3063354492188,0.6339677572250366,750.60400390625,765.5653076171875
+7,0.5958355665206909,672.296142578125,686.3594360351562,0.7489045262336731,728.1064453125,745.7798461914062
+8,0.5855081677436829,669.8174438476562,683.6354370117188,0.6368769407272339,725.6259155273438,740.6561279296875
+9,0.5673568248748779,667.0934448242188,680.4830932617188,0.756542444229126,730.931884765625,748.7857666015625
+10,0.5533503293991089,665.1425170898438,678.2005615234375,0.6375311017036438,728.6796264648438,743.7251586914062
+11,0.5369099974632263,662.5427856445312,675.213134765625,0.6260153651237488,724.8697509765625,739.6435546875
+12,0.5206872820854187,661.8475341796875,674.1357421875,0.6225676536560059,720.4855346679688,735.17822265625
+13,0.5061537623405457,659.2510375976562,671.1956176757812,0.6234879493713379,724.6674194335938,739.3819580078125
+14,0.49225863814353943,658.62548828125,670.2423095703125,0.640030026435852,727.3377075195312,742.4425048828125
+15,0.48207542300224304,656.9098510742188,668.2861938476562,0.6645805835723877,724.4338989257812,740.1182250976562
+16,0.46639224886894226,655.9859008789062,666.9929809570312,0.6189056634902954,729.82177734375,744.4281616210938
+17,0.45978373289108276,655.3770141601562,666.2286376953125,0.6264524459838867,724.34912109375,739.1332397460938

fold_3/logs.models.fold_3.ENCSR149XIL/logfile.modelling.fold_3.ENCSR149XIL.stdout_v1.txt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a443232a8334071fb78e2d793e00366c9938c531ac1f0edbb60efac84d09cea5
+size 12535609

fold_3/model.bias_scaled.fold_3.ENCSR149XIL.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c2b556aee7e9aab1f3fdb4860117c9beff259cfe16a51e63577afe5968a9ea33
+size 2688440

fold_3/model.bias_scaled.fold_3.ENCSR149XIL.tar

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d08700bc9554d5977f09520db6ed2cdbf446148ac3b6fd54aca215375361ead4
+size 1198080

fold_3/model.chrombpnet.fold_3.ENCSR149XIL.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:25a5f551ce93400fea990e9625aa0b337e888a16eedcf980f3312d64037d421c
+size 77540352

fold_3/model.chrombpnet.fold_3.ENCSR149XIL.tar

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7b581df637d8c4095891518536476c5e5ad170b75861a69b577aa6cad54516db
+size 27535360