Upload folder using huggingface_hub

README.md

@@ -0,0 +1,120 @@
+---
+license: mit
+library_name: chrombpnet
+tags:
+  - encode
+  - chrombpnet
+  - chromatin-accessibility
+  - ATAC
+  - nerve
+  - 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: ATAC in sciatic nerve (ENCSR619LHF)
+- Model: ChromBPNet
+- Assay: ATAC-seq
+- Experiment: [ENCSR619LHF](https://www.encodeproject.org/experiments/ENCSR619LHF/)
+- Model annotation: [ENCSR463ATK](https://www.encodeproject.org/annotations/ENCSR463ATK/)
+- Biosample: sciatic nerve (Full name: Homo sapiens sciatic nerve tissue female adult (47 years))
+- Cell slim(s): None
+- Organ slim(s): nerve
+- Developmental slim(s): ectoderm
+- System slim(s): peripheral-nervous-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.ENCSR619LHF/logfile.modelling.fold_0.ENCSR619LHF.args.json

@@ -0,0 +1,23 @@
+{
+    "genome": "/scratch/groups/akundaje/anusri/chromatin_atlas/reference/hg38.genome.fa",
+    "bigwig": "/scratch/groups/akundaje/anusri/chromatin_atlas/ATAC/ENCSR619LHF//preprocessing/bigWigs/ENCSR619LHF.bigWig",
+    "peaks": "/scratch/groups/akundaje/anusri/chromatin_atlas/ATAC/ENCSR619LHF//chrombpnet_model_feb15//filtered.peaks.bed",
+    "nonpeaks": "/scratch/groups/akundaje/anusri/chromatin_atlas/ATAC/ENCSR619LHF//chrombpnet_model_feb15//filtered.nonpeaks.bed",
+    "output_prefix": "/scratch/groups/akundaje/anusri/chromatin_atlas/ATAC/ENCSR619LHF//chrombpnet_model_feb15//chrombpnet",
+    "chr_fold_path": "/scratch/groups/akundaje/anusri/chromatin_atlas/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": "/scratch/groups/akundaje/anusri/chromatin_atlas/ATAC/ENCSR619LHF//chrombpnet_model_feb15//chrombpnet_model_params.tsv",
+    "seed": 1234,
+    "architecture_from_file": "/home/users/anusri/chromatin-atlas-anvil/sherlock/chrombpnet/src/training/models/chrombpnet_with_bias_model.py"
+}

fold_0/logs.models.fold_0.ENCSR619LHF/logfile.modelling.fold_0.ENCSR619LHF.bias_formatting.stdout.txt

@@ -0,0 +1 @@
+Converting /oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/ATAC/ENCSR619LHF/chrombpnet_model_feb15/bias_model_scaled.h5 to /oak/stanford/groups/akundaje/vhecht/chromatin-atlas-2022/ATAC/ENCSR619LHF/fold_0/new_model_format/bias_model_scaled.tar with get_new_tf_model_format.py

fold_0/logs.models.fold_0.ENCSR619LHF/logfile.modelling.fold_0.ENCSR619LHF.chrombpnet_data_params.tsv

@@ -0,0 +1,3 @@
+counts_sum_min_thresh	77.0
+counts_sum_max_thresh	2860.0
+trainings_pts_post_thresh	159275

fold_0/logs.models.fold_0.ENCSR619LHF/logfile.modelling.fold_0.ENCSR619LHF.chrombpnet_formatting.stdout.txt

@@ -0,0 +1 @@
+Converting /oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/ATAC/ENCSR619LHF/chrombpnet_model_feb15/chrombpnet.h5 to /oak/stanford/groups/akundaje/vhecht/chromatin-atlas-2022/ATAC/ENCSR619LHF/fold_0/new_model_format/chrombpnet.tar with get_new_tf_model_format.py

fold_0/logs.models.fold_0.ENCSR619LHF/logfile.modelling.fold_0.ENCSR619LHF.chrombpnet_model_params.tsv

@@ -0,0 +1,9 @@
+counts_loss_weight	34.2
+filters	512
+n_dil_layers	8
+bias_model_path	/scratch/groups/akundaje/anusri/chromatin_atlas/ATAC/ENCSR619LHF//chrombpnet_model_feb15/bias_model_scaled.h5
+inputlen	2114
+outputlen	1000
+max_jitter	500
+chr_fold_path	/scratch/groups/akundaje/anusri/chromatin_atlas/splits/fold_0.json
+negative_sampling_ratio	0.1

fold_0/logs.models.fold_0.ENCSR619LHF/logfile.modelling.fold_0.ENCSR619LHF.chrombpnet_no_bias_formatting.stdout.txt

@@ -0,0 +1 @@
+Converting /oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/ATAC/ENCSR619LHF/chrombpnet_model_feb15/chrombpnet_wo_bias.h5 to /oak/stanford/groups/akundaje/vhecht/chromatin-atlas-2022/ATAC/ENCSR619LHF/fold_0/new_model_format/chrombpnet_nobias.tar with get_new_tf_model_format.py

fold_0/logs.models.fold_0.ENCSR619LHF/logfile.modelling.fold_0.ENCSR619LHF.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
+0,1.3665615320205688,570.977294921875,617.7131958007812,0.2777297794818878,556.516357421875,566.0147705078125
+1,0.2758727967739105,555.6200561523438,565.0550537109375,0.23885950446128845,548.1174926757812,556.286376953125
+2,0.24743682146072388,548.9338989257812,557.397216796875,0.221817284822464,545.3303833007812,552.9163208007812
+3,0.231885626912117,545.2866821289062,553.2172241210938,0.22147269546985626,543.2055053710938,550.7798461914062
+4,0.2202436476945877,542.3721313476562,549.9042358398438,0.22257372736930847,542.1445922851562,549.7567138671875
+5,0.20697970688343048,539.8881225585938,546.9675903320312,0.20517504215240479,542.0517578125,549.0689086914062
+6,0.19872111082077026,537.1952514648438,543.9911499023438,0.20197917520999908,541.7953491210938,548.7031860351562
+7,0.18814797699451447,534.58935546875,541.0225830078125,0.19500674307346344,540.9908447265625,547.6598510742188
+8,0.17865166068077087,533.6552734375,539.7657470703125,0.2350805550813675,541.50048828125,549.540283203125
+9,0.17112138867378235,532.1075439453125,537.9601440429688,0.19199061393737793,541.621826171875,548.1876831054688
+10,0.16113118827342987,530.51708984375,536.0276489257812,0.18974581360816956,542.1681518554688,548.657470703125
+11,0.13705170154571533,525.0466918945312,529.7326049804688,0.1846916675567627,539.870361328125,546.1867065429688
+12,0.12504108250141144,522.244384765625,526.5203247070312,0.19172653555870056,540.4793090820312,547.0364990234375
+13,0.11603288352489471,520.0327758789062,524.0015258789062,0.18555231392383575,540.8262329101562,547.17236328125
+14,0.11019962280988693,518.9483032226562,522.7162475585938,0.19480940699577332,542.4965209960938,549.1588134765625
+15,0.0957595631480217,516.0346069335938,519.30859375,0.18978670239448547,541.6460571289062,548.1368408203125
+16,0.09130237996578217,514.4360961914062,517.5595703125,0.19043253362178802,542.03173828125,548.5446166992188

fold_0/model.bias_scaled.fold_0.ENCSR619LHF.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ad968a86ca8a06f73832eb4f6859bdee036b0b22cc208a6b171b4d30156a2ea8
+size 2688440

fold_0/model.bias_scaled.fold_0.ENCSR619LHF.tar

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a86f8021af5dd5ca26260a39b60df5d1e9d6fb469d136be1428e1ea4e585c553
+size 1198080

fold_0/model.chrombpnet.fold_0.ENCSR619LHF.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6c36f0ea5176de9e4c8e9830fe6f507daa0657ab27783624d9e34f46443d307a
+size 26448016

fold_0/model.chrombpnet.fold_0.ENCSR619LHF.tar

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0495976a9668b827ae621719a56d5a4b6afdd09847d6f8e653ece6409357db33
+size 27535360

fold_0/model.chrombpnet_nobias.fold_0.ENCSR619LHF.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:536989b5073e39fcec8d0f015c76598dcd43b56cf0dc41901910af3468bffa94
+size 25583536

fold_0/model.chrombpnet_nobias.fold_0.ENCSR619LHF.tar

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7c07ec573acbda8471650f714ed87cca9ec40edeea860d3e99413496a333f7d8
+size 26060800

fold_1/logs.models.fold_1.ENCSR619LHF/logfile.modelling.fold_1.ENCSR619LHF.args.json

@@ -0,0 +1,23 @@
+{
+    "genome": "/scratch/groups/akundaje/anusri/chromatin_atlas/reference/hg38.genome.fa",
+    "bigwig": "/oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/ATAC//ENCSR619LHF//preprocessing/bigWigs/ENCSR619LHF.bigWig",
+    "peaks": "/oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/ATAC//ENCSR619LHF//chrombpnet_model_feb15_fold_1//filtered.peaks.bed",
+    "nonpeaks": "/oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/ATAC//ENCSR619LHF//chrombpnet_model_feb15_fold_1//filtered.nonpeaks.bed",
+    "output_prefix": "/oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/ATAC//ENCSR619LHF//chrombpnet_model_feb15_fold_1//chrombpnet",
+    "chr_fold_path": "/scratch/groups/akundaje/anusri/chromatin_atlas/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": "/oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/ATAC//ENCSR619LHF//chrombpnet_model_feb15_fold_1//chrombpnet_model_params.tsv",
+    "seed": 1234,
+    "architecture_from_file": "/home/users/anusri/chromatin-atlas-anvil/sherlock/chrombpnet/src/training/models/chrombpnet_with_bias_model.py"
+}

fold_1/logs.models.fold_1.ENCSR619LHF/logfile.modelling.fold_1.ENCSR619LHF.bias_formatting.stdout.txt

@@ -0,0 +1 @@
+Converting /oak/stanford/groups/akundaje/vhecht/chromatin-atlas-2022/ATAC/ENCSR619LHF/chrombpnet_model_feb15_fold_1/bias_model_scaled.h5 to /oak/stanford/groups/akundaje/vhecht/chromatin-atlas-2022/ATAC/ENCSR619LHF/fold_1/new_model_format/bias_model_scaled.tar with get_new_tf_model_format.py

fold_1/logs.models.fold_1.ENCSR619LHF/logfile.modelling.fold_1.ENCSR619LHF.chrombpnet_data_params.tsv

@@ -0,0 +1,3 @@
+counts_sum_min_thresh	81.0
+counts_sum_max_thresh	2870.0
+trainings_pts_post_thresh	160890

fold_1/logs.models.fold_1.ENCSR619LHF/logfile.modelling.fold_1.ENCSR619LHF.chrombpnet_formatting.stdout.txt

@@ -0,0 +1 @@
+Converting /oak/stanford/groups/akundaje/vhecht/chromatin-atlas-2022/ATAC/ENCSR619LHF/chrombpnet_model_feb15_fold_1/chrombpnet.h5 to /oak/stanford/groups/akundaje/vhecht/chromatin-atlas-2022/ATAC/ENCSR619LHF/fold_1/new_model_format/chrombpnet.tar with get_new_tf_model_format.py

fold_1/logs.models.fold_1.ENCSR619LHF/logfile.modelling.fold_1.ENCSR619LHF.chrombpnet_model_params.tsv

@@ -0,0 +1,9 @@
+counts_loss_weight	34.4
+filters	512
+n_dil_layers	8
+bias_model_path	/oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/ATAC//ENCSR619LHF//chrombpnet_model_feb15_fold_1/bias_model_scaled.h5
+inputlen	2114
+outputlen	1000
+max_jitter	500
+chr_fold_path	/scratch/groups/akundaje/anusri/chromatin_atlas/splits/fold_1.json
+negative_sampling_ratio	0.1

fold_1/logs.models.fold_1.ENCSR619LHF/logfile.modelling.fold_1.ENCSR619LHF.chrombpnet_no_bias_formatting.stdout.txt

@@ -0,0 +1 @@
+Converting /oak/stanford/groups/akundaje/vhecht/chromatin-atlas-2022/ATAC/ENCSR619LHF/chrombpnet_model_feb15_fold_1/chrombpnet_wo_bias.h5 to /oak/stanford/groups/akundaje/vhecht/chromatin-atlas-2022/ATAC/ENCSR619LHF/fold_1/new_model_format/chrombpnet_nobias.tar with get_new_tf_model_format.py

fold_1/logs.models.fold_1.ENCSR619LHF/logfile.modelling.fold_1.ENCSR619LHF.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
+0,0.7244714498519897,550.6602172851562,575.5820922851562,0.3325057327747345,595.9275512695312,607.3662109375
+1,0.2447028011083603,534.19189453125,542.6106567382812,0.2605791985988617,588.2598876953125,597.2241821289062
+2,0.22490045428276062,529.1614379882812,536.8981323242188,0.24767477810382843,586.46240234375,594.9827880859375
+3,0.20971623063087463,525.6364135742188,532.850341796875,0.2481204718351364,586.2003173828125,594.735595703125
+4,0.19701054692268372,523.703857421875,530.48046875,0.2746446132659912,584.72998046875,594.177490234375
+5,0.18410316109657288,520.9842529296875,527.318359375,0.2250390499830246,584.8347778320312,592.5762939453125
+6,0.1735600233078003,519.8988647460938,525.8695068359375,0.23721852898597717,584.3671264648438,592.5275268554688
+7,0.16440822184085846,518.5863037109375,524.2424926757812,0.22299131751060486,583.8783569335938,591.5491333007812
+8,0.15237505733966827,516.8468627929688,522.0878295898438,0.2368180751800537,586.2998657226562,594.4465942382812
+9,0.14561091363430023,516.1944580078125,521.2039184570312,0.23421862721443176,585.4903564453125,593.5471801757812
+10,0.13820956647396088,515.0641479492188,519.8185424804688,0.2753757834434509,585.9588012695312,595.4317626953125
+11,0.11357611417770386,511.0643005371094,514.9717407226562,0.22810475528240204,583.1427001953125,590.9896240234375
+12,0.10137961059808731,508.61553955078125,512.1029663085938,0.21993833780288696,583.8826293945312,591.4482421875
+13,0.09475775808095932,507.1305236816406,510.390625,0.22026582062244415,584.4299926757812,592.0070190429688
+14,0.0887172743678093,506.07061767578125,509.12237548828125,0.22804240882396698,585.188232421875,593.0326538085938
+15,0.07866176217794418,503.53948974609375,506.24615478515625,0.24630355834960938,585.8273315429688,594.3004150390625
+16,0.07400637120008469,502.5065612792969,505.05218505859375,0.2255984991788864,586.1912841796875,593.9517822265625

fold_1/model.bias_scaled.fold_1.ENCSR619LHF.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d168892ad17a02140aa34c1f7ade3e7772cee78a46dc66c1c6245dbf00f8c987
+size 2688440

fold_1/model.bias_scaled.fold_1.ENCSR619LHF.tar

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:67dee104ff210cb14543c5565630ea6e2dfc04020a8b32c7dccbf3592aa21f0f
+size 1198080

fold_1/model.chrombpnet.fold_1.ENCSR619LHF.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dde5fd003e82d5c0ff20ce017debbffda001325e52636055156113ab98e17bba
+size 26447928

fold_1/model.chrombpnet.fold_1.ENCSR619LHF.tar

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:891ff0573e39a16f6af73dc084ee17cf0074e437dc594cad6c145308cf518aea
+size 27525120

fold_1/model.chrombpnet_nobias.fold_1.ENCSR619LHF.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2d5bead89279a028adcba8bc77384cda25cf5c80e9804b46df64b201afb5948e
+size 25583536

fold_1/model.chrombpnet_nobias.fold_1.ENCSR619LHF.tar

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bae4019e93af7e94e43a63631a9e935af4f68cc089d80d6702d01bd7bff905b5
+size 26060800

fold_2/logs.models.fold_2.ENCSR619LHF/logfile.modelling.fold_2.ENCSR619LHF.args.json

@@ -0,0 +1,23 @@
+{
+    "genome": "/scratch/groups/akundaje/anusri/chromatin_atlas/reference/hg38.genome.fa",
+    "bigwig": "/oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/ATAC//ENCSR619LHF//preprocessing/bigWigs/ENCSR619LHF.bigWig",
+    "peaks": "/oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/ATAC//ENCSR619LHF//chrombpnet_model_feb15_fold_2//filtered.peaks.bed",
+    "nonpeaks": "/oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/ATAC//ENCSR619LHF//chrombpnet_model_feb15_fold_2//filtered.nonpeaks.bed",
+    "output_prefix": "/oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/ATAC//ENCSR619LHF//chrombpnet_model_feb15_fold_2//chrombpnet",
+    "chr_fold_path": "/scratch/groups/akundaje/anusri/chromatin_atlas/splits/fold_2.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": "/oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/ATAC//ENCSR619LHF//chrombpnet_model_feb15_fold_2//chrombpnet_model_params.tsv",
+    "seed": 1234,
+    "architecture_from_file": "/home/users/anusri/chromatin-atlas-anvil/sherlock/chrombpnet/src/training/models/chrombpnet_with_bias_model.py"
+}

fold_2/logs.models.fold_2.ENCSR619LHF/logfile.modelling.fold_2.ENCSR619LHF.bias_formatting.stdout.txt

@@ -0,0 +1 @@
+Converting /oak/stanford/groups/akundaje/vhecht/chromatin-atlas-2022/ATAC/ENCSR619LHF/chrombpnet_model_feb15_fold_2/bias_model_scaled.h5 to /oak/stanford/groups/akundaje/vhecht/chromatin-atlas-2022/ATAC/ENCSR619LHF/fold_2/new_model_format/bias_model_scaled.tar with get_new_tf_model_format.py

fold_2/logs.models.fold_2.ENCSR619LHF/logfile.modelling.fold_2.ENCSR619LHF.chrombpnet_data_params.tsv

@@ -0,0 +1,3 @@
+counts_sum_min_thresh	84.0
+counts_sum_max_thresh	2866.0
+trainings_pts_post_thresh	165983

fold_2/logs.models.fold_2.ENCSR619LHF/logfile.modelling.fold_2.ENCSR619LHF.chrombpnet_formatting.stdout.txt

@@ -0,0 +1 @@
+Converting /oak/stanford/groups/akundaje/vhecht/chromatin-atlas-2022/ATAC/ENCSR619LHF/chrombpnet_model_feb15_fold_2/chrombpnet.h5 to /oak/stanford/groups/akundaje/vhecht/chromatin-atlas-2022/ATAC/ENCSR619LHF/fold_2/new_model_format/chrombpnet.tar with get_new_tf_model_format.py

fold_2/logs.models.fold_2.ENCSR619LHF/logfile.modelling.fold_2.ENCSR619LHF.chrombpnet_model_params.tsv

@@ -0,0 +1,9 @@
+counts_loss_weight	34.4
+filters	512
+n_dil_layers	8
+bias_model_path	/oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/ATAC//ENCSR619LHF//chrombpnet_model_feb15_fold_2/bias_model_scaled.h5
+inputlen	2114
+outputlen	1000
+max_jitter	500
+chr_fold_path	/scratch/groups/akundaje/anusri/chromatin_atlas/splits/fold_2.json
+negative_sampling_ratio	0.1

fold_2/logs.models.fold_2.ENCSR619LHF/logfile.modelling.fold_2.ENCSR619LHF.chrombpnet_no_bias_formatting.stdout.txt

@@ -0,0 +1 @@
+Converting /oak/stanford/groups/akundaje/vhecht/chromatin-atlas-2022/ATAC/ENCSR619LHF/chrombpnet_model_feb15_fold_2/chrombpnet_wo_bias.h5 to /oak/stanford/groups/akundaje/vhecht/chromatin-atlas-2022/ATAC/ENCSR619LHF/fold_2/new_model_format/chrombpnet_nobias.tar with get_new_tf_model_format.py

fold_2/logs.models.fold_2.ENCSR619LHF/logfile.modelling.fold_2.ENCSR619LHF.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
+0,0.8285759091377258,550.5069580078125,579.0105590820312,0.25100019574165344,553.98974609375,562.6239013671875
+1,0.24999913573265076,537.0682373046875,545.6683349609375,0.2187381088733673,550.1881713867188,557.7127685546875
+2,0.22629716992378235,531.8599243164062,539.6441040039062,0.20904044806957245,547.0596923828125,554.2508544921875
+3,0.21275684237480164,528.6725463867188,535.9910888671875,0.20511601865291595,546.177978515625,553.2337036132812
+4,0.20047198235988617,526.328125,533.2242431640625,0.22009415924549103,544.4647216796875,552.0360107421875
+5,0.1864962875843048,524.314208984375,530.7293701171875,0.20311573147773743,544.4949340820312,551.4821166992188
+6,0.1753302663564682,522.5172729492188,528.5490112304688,0.22508516907691956,543.971435546875,551.714599609375
+7,0.1654948592185974,521.4180297851562,527.1117553710938,0.20102940499782562,544.755859375,551.6714477539062
+8,0.15495634078979492,519.9425659179688,525.2742309570312,0.19080021977424622,544.72509765625,551.2886352539062
+9,0.14714744687080383,519.156982421875,524.2186889648438,0.1972619742155075,544.5787353515625,551.3648681640625
+10,0.14034238457679749,518.0960083007812,522.924072265625,0.19137226045131683,544.5353393554688,551.118408203125
+11,0.13280098140239716,517.3922119140625,521.9591674804688,0.19004690647125244,545.058349609375,551.5957641601562
+12,0.12865407764911652,516.81103515625,521.2366333007812,0.1940668225288391,545.5259399414062,552.201904296875
+13,0.1230759397149086,516.2971801757812,520.53125,0.19538693130016327,545.3203125,552.0418090820312
+14,0.09953921288251877,512.34716796875,515.7718505859375,0.190805584192276,543.8062744140625,550.3699951171875
+15,0.08926184475421906,510.3108825683594,513.3817749023438,0.19163310527801514,544.1698608398438,550.7620849609375
+16,0.08447770029306412,509.361572265625,512.2683715820312,0.19042973220348358,544.7312622070312,551.28173828125
+17,0.0801747739315033,508.3254699707031,511.08331298828125,0.19502316415309906,545.2627563476562,551.97119140625
+18,0.06990456581115723,506.40264892578125,508.8077697753906,0.19347289204597473,545.3070068359375,551.9623413085938
+19,0.06724525988101959,504.852783203125,507.1666564941406,0.20016714930534363,545.9636840820312,552.8494873046875

fold_2/model.bias_scaled.fold_2.ENCSR619LHF.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:39d0c4fc4d135cccb124eda0e300d0f0c7ec4474e7078360526c6e17b8f86b58
+size 2688440

fold_2/model.bias_scaled.fold_2.ENCSR619LHF.tar

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:127fb612489f6ee2572a6d9e9553260919052abbc79c0239f287093cdc9ad275
+size 1198080

fold_2/model.chrombpnet.fold_2.ENCSR619LHF.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b2a7fbafb01d096c6c21530872e181369639cd9d6f92a76a325f224f6b6c2a05
+size 26447928

fold_2/model.chrombpnet.fold_2.ENCSR619LHF.tar

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b1c31242cc745fbb9c76bb385359dad46fd6970f771b24136f863d12f24f7884
+size 27525120

fold_2/model.chrombpnet_nobias.fold_2.ENCSR619LHF.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7bcca101c50ff7ec7450c52aa7c55b0cc713a97a3d803a89d80f9aa5adbadb50
+size 25583536

fold_2/model.chrombpnet_nobias.fold_2.ENCSR619LHF.tar

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:80fd33357454c1da597e81cc9e142742bcb5f854c779c7df0f5560cf2057ffe0
+size 26060800

fold_3/logs.models.fold_3.ENCSR619LHF/logfile.modelling.fold_3.ENCSR619LHF.args.json

@@ -0,0 +1,23 @@
+{
+    "genome": "/scratch/groups/akundaje/anusri/chromatin_atlas/reference/hg38.genome.fa",
+    "bigwig": "/oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/ATAC//ENCSR619LHF//preprocessing/bigWigs/ENCSR619LHF.bigWig",
+    "peaks": "/oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/ATAC//ENCSR619LHF//chrombpnet_model_feb15_fold_3//filtered.peaks.bed",
+    "nonpeaks": "/oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/ATAC//ENCSR619LHF//chrombpnet_model_feb15_fold_3//filtered.nonpeaks.bed",
+    "output_prefix": "/oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/ATAC//ENCSR619LHF//chrombpnet_model_feb15_fold_3//chrombpnet",
+    "chr_fold_path": "/scratch/groups/akundaje/anusri/chromatin_atlas/splits/fold_3.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": "/oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/ATAC//ENCSR619LHF//chrombpnet_model_feb15_fold_3//chrombpnet_model_params.tsv",
+    "seed": 1234,
+    "architecture_from_file": "/home/users/anusri/chromatin-atlas-anvil/sherlock/chrombpnet/src/training/models/chrombpnet_with_bias_model.py"
+}

fold_3/logs.models.fold_3.ENCSR619LHF/logfile.modelling.fold_3.ENCSR619LHF.bias_formatting.stdout.txt

@@ -0,0 +1 @@
+Converting /oak/stanford/groups/akundaje/vhecht/chromatin-atlas-2022/ATAC/ENCSR619LHF/chrombpnet_model_feb15_fold_3/bias_model_scaled.h5 to /oak/stanford/groups/akundaje/vhecht/chromatin-atlas-2022/ATAC/ENCSR619LHF/fold_3/new_model_format/bias_model_scaled.tar with get_new_tf_model_format.py

fold_3/logs.models.fold_3.ENCSR619LHF/logfile.modelling.fold_3.ENCSR619LHF.chrombpnet_data_params.tsv

@@ -0,0 +1,3 @@
+counts_sum_min_thresh	81.0
+counts_sum_max_thresh	2874.61
+trainings_pts_post_thresh	160245

fold_3/logs.models.fold_3.ENCSR619LHF/logfile.modelling.fold_3.ENCSR619LHF.chrombpnet_formatting.stdout.txt

@@ -0,0 +1 @@
+Converting /oak/stanford/groups/akundaje/vhecht/chromatin-atlas-2022/ATAC/ENCSR619LHF/chrombpnet_model_feb15_fold_3/chrombpnet.h5 to /oak/stanford/groups/akundaje/vhecht/chromatin-atlas-2022/ATAC/ENCSR619LHF/fold_3/new_model_format/chrombpnet.tar with get_new_tf_model_format.py

fold_3/logs.models.fold_3.ENCSR619LHF/logfile.modelling.fold_3.ENCSR619LHF.chrombpnet_model_params.tsv

@@ -0,0 +1,9 @@
+counts_loss_weight	34.4
+filters	512
+n_dil_layers	8
+bias_model_path	/oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/ATAC//ENCSR619LHF//chrombpnet_model_feb15_fold_3/bias_model_scaled.h5
+inputlen	2114
+outputlen	1000
+max_jitter	500
+chr_fold_path	/scratch/groups/akundaje/anusri/chromatin_atlas/splits/fold_3.json
+negative_sampling_ratio	0.1

fold_3/logs.models.fold_3.ENCSR619LHF/logfile.modelling.fold_3.ENCSR619LHF.chrombpnet_no_bias_formatting.stdout.txt

@@ -0,0 +1 @@
+Converting /oak/stanford/groups/akundaje/vhecht/chromatin-atlas-2022/ATAC/ENCSR619LHF/chrombpnet_model_feb15_fold_3/chrombpnet_wo_bias.h5 to /oak/stanford/groups/akundaje/vhecht/chromatin-atlas-2022/ATAC/ENCSR619LHF/fold_3/new_model_format/chrombpnet_nobias.tar with get_new_tf_model_format.py