Upload folder using huggingface_hub

README.md

@@ -0,0 +1,120 @@
+---
+license: mit
+library_name: chrombpnet
+tags:
+  - encode
+  - chrombpnet
+  - chromatin-accessibility
+  - ATAC
+  - GM21723
+  - 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 GM21723 (ENCSR233HSC)
+- Model: ChromBPNet
+- Assay: ATAC-seq
+- Experiment: [ENCSR233HSC](https://www.encodeproject.org/experiments/ENCSR233HSC/)
+- Model annotation: [ENCSR615NIB](https://www.encodeproject.org/annotations/ENCSR615NIB/)
+- Biosample: GM21723 (Full name: Homo sapiens GM21723)
+- Cell slim(s): None
+- Organ slim(s): None
+- Developmental slim(s): None
+- System slim(s): None
+- 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.ENCSR233HSC/logfile.modelling.fold_0.ENCSR233HSC.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/ENCSR233HSC//preprocessing/bigWigs/ENCSR233HSC.bigWig",
+    "peaks": "/scratch/groups/akundaje/anusri/chromatin_atlas/ATAC/ENCSR233HSC//chrombpnet_model_feb15//filtered.peaks.bed",
+    "nonpeaks": "/scratch/groups/akundaje/anusri/chromatin_atlas/ATAC/ENCSR233HSC//chrombpnet_model_feb15//filtered.nonpeaks.bed",
+    "output_prefix": "/scratch/groups/akundaje/anusri/chromatin_atlas/ATAC/ENCSR233HSC//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/ENCSR233HSC//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.ENCSR233HSC/logfile.modelling.fold_0.ENCSR233HSC.chrombpnet_data_params.tsv

@@ -0,0 +1,3 @@
+counts_sum_min_thresh	8.0
+counts_sum_max_thresh	1886.0
+trainings_pts_post_thresh	147094

fold_0/logs.models.fold_0.ENCSR233HSC/logfile.modelling.fold_0.ENCSR233HSC.chrombpnet_model_params.tsv

@@ -0,0 +1,9 @@
+counts_loss_weight	17.4
+filters	512
+n_dil_layers	8
+bias_model_path	/scratch/groups/akundaje/anusri/chromatin_atlas/ATAC/ENCSR233HSC//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.ENCSR233HSC/logfile.modelling.fold_0.ENCSR233HSC.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
+0,7.7863450050354,420.82525634765625,556.3073120117188,0.8899790644645691,429.0420227050781,444.52740478515625
+1,0.8465948700904846,401.3337707519531,416.0647277832031,0.7809559106826782,415.2019958496094,428.7906799316406
+2,0.7725882530212402,392.3178405761719,405.76025390625,0.729872465133667,409.88922119140625,422.5887756347656
+3,0.7296285629272461,387.6964416503906,400.3922119140625,0.7092165946960449,407.0070495605469,419.34759521484375
+4,0.6930258870124817,384.3878173828125,396.4459533691406,0.7352755665779114,405.26300048828125,418.05670166015625
+5,0.6620458364486694,381.80474853515625,393.32476806640625,0.8256971836090088,405.0299987792969,419.39697265625
+6,0.6312423944473267,379.12689208984375,390.1100769042969,0.6688517332077026,403.78973388671875,415.4277038574219
+7,0.6057142019271851,377.1294250488281,387.6686096191406,0.6695141792297363,403.8473815917969,415.4966125488281
+8,0.5834611058235168,374.3680114746094,384.52032470703125,0.6537730693817139,403.5810241699219,414.9565734863281
+9,0.5508319139480591,372.5328674316406,382.117431640625,0.6520036458969116,403.9227600097656,415.2676696777344
+10,0.5252915024757385,371.06854248046875,380.2087707519531,0.6753978133201599,403.82696533203125,415.578857421875
+11,0.49114730954170227,369.55633544921875,378.10260009765625,0.6303966641426086,404.0766296386719,415.04559326171875
+12,0.41011953353881836,364.0579528808594,371.1943664550781,0.6496000289916992,402.1979064941406,413.5010986328125
+13,0.3625815212726593,361.3529357910156,367.66229248046875,0.6584353446960449,403.1868591308594,414.6435852050781
+14,0.32897505164146423,359.25592041015625,364.98089599609375,0.6594452261924744,404.082275390625,415.556640625
+15,0.3064996302127838,358.15966796875,363.4928894042969,0.7502395510673523,405.2588195800781,418.3130187988281
+16,0.2613809108734131,355.1839599609375,359.73187255859375,0.7362696528434753,405.5762634277344,418.3872985839844
+17,0.2446507215499878,353.78656005859375,358.0440979003906,0.7121848464012146,406.3263854980469,418.7183532714844

fold_0/model.bias_scaled.fold_0.ENCSR233HSC.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7c7879dbd3ab77a4df7053b6812a75ff43fc492680ea36be1242b76c9e98c4f8
+size 2688440

fold_0/model.bias_scaled.fold_0.ENCSR233HSC.tar

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:adda8d4aaa6f6e807bf8bf4a02ad630f58aebb7049871f9b7e24e20e41a03315
+size 1198080

fold_0/model.chrombpnet.fold_0.ENCSR233HSC.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:923c676c8ff11b887eb25b436df17739a0a96f0141390bfb895701ef073cd6b0
+size 26448040

fold_0/model.chrombpnet.fold_0.ENCSR233HSC.tar

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:37196bf87793eab81e014ed9a6cee8a3c1b5bb4b4bba355e74d3d332ab9e47e1
+size 27525120

fold_0/model.chrombpnet_nobias.fold_0.ENCSR233HSC.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:22516dba53c78891bcc83a84df2093a304f175dda97d4fb47fd4075341a4ccdb
+size 25583536

fold_0/model.chrombpnet_nobias.fold_0.ENCSR233HSC.tar

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ab8616acf5a955e5fb447f7b9e98de500bee5f5d0a5eb31146b726a0f8ed8584
+size 26060800

fold_1/logs.models.fold_1.ENCSR233HSC/logfile.modelling.fold_1.ENCSR233HSC.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//ENCSR233HSC//preprocessing/bigWigs/ENCSR233HSC.bigWig",
+    "peaks": "/scratch/groups/akundaje/anusri/chromatin_atlas/ATAC/ENCSR233HSC//chrombpnet_model_feb15_fold_1//filtered.peaks.bed",
+    "nonpeaks": "/scratch/groups/akundaje/anusri/chromatin_atlas/ATAC/ENCSR233HSC//chrombpnet_model_feb15_fold_1//filtered.nonpeaks.bed",
+    "output_prefix": "/scratch/groups/akundaje/anusri/chromatin_atlas/ATAC/ENCSR233HSC//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": "/scratch/groups/akundaje/anusri/chromatin_atlas/ATAC/ENCSR233HSC//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.ENCSR233HSC/logfile.modelling.fold_1.ENCSR233HSC.chrombpnet_data_params.tsv

@@ -0,0 +1,3 @@
+counts_sum_min_thresh	7.0
+counts_sum_max_thresh	1902.0
+trainings_pts_post_thresh	152050

fold_1/logs.models.fold_1.ENCSR233HSC/logfile.modelling.fold_1.ENCSR233HSC.chrombpnet_model_params.tsv

@@ -0,0 +1,9 @@
+counts_loss_weight	17.3
+filters	512
+n_dil_layers	8
+bias_model_path	/scratch/groups/akundaje/anusri/chromatin_atlas/ATAC/ENCSR233HSC//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.ENCSR233HSC/logfile.modelling.fold_1.ENCSR233HSC.epoch_loss.csv

@@ -0,0 +1,14 @@
+epoch,logcount_predictions_loss,logits_profile_predictions_loss,loss,val_logcount_predictions_loss,val_logits_profile_predictions_loss,val_loss
+0,3.2424938678741455,409.1450500488281,465.2401428222656,0.8176157474517822,418.6035461425781,432.7481384277344
+1,0.8161407113075256,387.3173522949219,401.43646240234375,0.6896918416023254,408.1920166015625,420.1236267089844
+2,0.7397699952125549,381.2168884277344,394.0151062011719,0.6664558053016663,404.06353759765625,415.59307861328125
+3,0.7021012306213379,376.86383056640625,389.0105285644531,0.6592892408370972,401.78887939453125,413.1944885253906
+4,0.6646694540977478,373.7894592285156,385.2884826660156,0.6124492883682251,400.0355529785156,410.6310119628906
+5,0.6299858689308167,370.5417175292969,381.4406433105469,0.5968949794769287,398.9794616699219,409.3057556152344
+6,0.6042933464050293,369.0892639160156,379.54364013671875,0.5741918683052063,398.8770751953125,408.81060791015625
+7,0.5722175240516663,366.8166809082031,376.71624755859375,0.5741657018661499,398.3056335449219,408.2386474609375
+8,0.5413028001785278,365.25579833984375,374.6204528808594,0.585637092590332,398.59906005859375,408.730712890625
+9,0.5095682144165039,363.3838806152344,372.1991882324219,0.5990728735923767,398.5811767578125,408.94537353515625
+10,0.4752385914325714,362.09405517578125,370.3152770996094,0.7906329035758972,399.1820068359375,412.8600769042969
+11,0.38168400526046753,357.4849853515625,364.0883483886719,0.6187199354171753,398.13104248046875,408.83514404296875
+12,0.33580055832862854,355.1566467285156,360.966064453125,0.6456819772720337,398.7730712890625,409.9434509277344

fold_1/model.bias_scaled.fold_1.ENCSR233HSC.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7c7879dbd3ab77a4df7053b6812a75ff43fc492680ea36be1242b76c9e98c4f8
+size 2688440

fold_1/model.bias_scaled.fold_1.ENCSR233HSC.tar

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d21102905602edb2955c939c21e10aef3d9b74aa5fdb73b837c0f73a693db9fa
+size 1198080

fold_1/model.chrombpnet.fold_1.ENCSR233HSC.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cb48d386b4f265cbe75c15c86c389d0f28c47b8c38d040f0900b5e543c3a3622
+size 26448040

fold_1/model.chrombpnet.fold_1.ENCSR233HSC.tar

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:50c17c36e80ad420b321f067fe896a9f0978f4fc185fba79c1d1a3587704fcc1
+size 27525120

fold_1/model.chrombpnet_nobias.fold_1.ENCSR233HSC.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b5d9ece247f72b635fa1fdbd5b5097cd1c5f931f916a88048ee2423985bc0874
+size 25583536

fold_1/model.chrombpnet_nobias.fold_1.ENCSR233HSC.tar

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:66f2b2d83b95ba6c112085a43bafbd4fcd645d82c5f5ebf2856b67dd2623e3de
+size 26060800

fold_2/logs.models.fold_2.ENCSR233HSC/logfile.modelling.fold_2.ENCSR233HSC.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//ENCSR233HSC//preprocessing/bigWigs/ENCSR233HSC.bigWig",
+    "peaks": "/scratch/groups/akundaje/anusri/chromatin_atlas/ATAC/ENCSR233HSC//chrombpnet_model_feb15_fold_2//filtered.peaks.bed",
+    "nonpeaks": "/scratch/groups/akundaje/anusri/chromatin_atlas/ATAC/ENCSR233HSC//chrombpnet_model_feb15_fold_2//filtered.nonpeaks.bed",
+    "output_prefix": "/scratch/groups/akundaje/anusri/chromatin_atlas/ATAC/ENCSR233HSC//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": "/scratch/groups/akundaje/anusri/chromatin_atlas/ATAC/ENCSR233HSC//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.ENCSR233HSC/logfile.modelling.fold_2.ENCSR233HSC.chrombpnet_data_params.tsv

@@ -0,0 +1,3 @@
+counts_sum_min_thresh	8.0
+counts_sum_max_thresh	1884.3
+trainings_pts_post_thresh	155962

fold_2/logs.models.fold_2.ENCSR233HSC/logfile.modelling.fold_2.ENCSR233HSC.chrombpnet_model_params.tsv

@@ -0,0 +1,9 @@
+counts_loss_weight	17.3
+filters	512
+n_dil_layers	8
+bias_model_path	/scratch/groups/akundaje/anusri/chromatin_atlas/ATAC/ENCSR233HSC//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.ENCSR233HSC/logfile.modelling.fold_2.ENCSR233HSC.epoch_loss.csv

@@ -0,0 +1,16 @@
+epoch,logcount_predictions_loss,logits_profile_predictions_loss,loss,val_logcount_predictions_loss,val_logits_profile_predictions_loss,val_loss
+0,6.835094928741455,411.6783142089844,529.9252319335938,1.1245059967041016,418.7801513671875,438.2339782714844
+1,0.8300843238830566,391.2469177246094,405.6075744628906,0.8262087106704712,407.3504638671875,421.64385986328125
+2,0.7607391476631165,383.1548767089844,396.3154602050781,0.8165369629859924,402.8648986816406,416.99078369140625
+3,0.7150829434394836,379.20379638671875,391.5747375488281,0.7075617909431458,400.0373840332031,412.2781982421875
+4,0.6815012097358704,375.7225646972656,387.5128173828125,0.6971667408943176,397.1046142578125,409.16583251953125
+5,0.6474606990814209,373.5513610839844,384.7527770996094,0.685151219367981,396.3331604003906,408.18646240234375
+6,0.6196792721748352,370.72772216796875,381.447998046875,0.6455233097076416,395.46209716796875,406.6297912597656
+7,0.5931943655014038,368.8797912597656,379.1425476074219,0.6859512329101562,395.95660400390625,407.823486328125
+8,0.556681215763092,367.40234375,377.0331726074219,0.6474558115005493,394.6982421875,405.8994445800781
+9,0.5301685333251953,365.25408935546875,374.42596435546875,0.6381757259368896,394.745361328125,405.785888671875
+10,0.49754905700683594,364.03662109375,372.6442565917969,0.6278458833694458,395.110595703125,405.9722595214844
+11,0.4658602476119995,362.95257568359375,371.01239013671875,0.6159049868583679,395.2440490722656,405.899169921875
+12,0.4396764934062958,361.878173828125,369.4846496582031,0.7505278587341309,395.55072021484375,408.53485107421875
+13,0.35423070192337036,357.35797119140625,363.4860534667969,0.6284244656562805,394.93505859375,405.806884765625
+14,0.3129725158214569,354.8974914550781,360.3121337890625,0.6580759286880493,395.35345458984375,406.738037109375

fold_2/model.bias_scaled.fold_2.ENCSR233HSC.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:21d473ebb57e05f9c21495a33e710ebaadabf1ee88b53b7d5dc07241f5740da3
+size 2688440

fold_2/model.bias_scaled.fold_2.ENCSR233HSC.tar

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:db57ba4714713ecb2da127d934cf6ba215d826ad0e955141a92ce4954726832a
+size 1198080

fold_2/model.chrombpnet.fold_2.ENCSR233HSC.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0f49225a29c6ec9275a1fc543ef351c2122aa9aa50a6e88dc24aa8003f8db4b1
+size 26448040

fold_2/model.chrombpnet.fold_2.ENCSR233HSC.tar

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:690b5c41a9b8d1185e0e0488fee9ba6719f3f4bce5bf06d138a6aa3570babcd7
+size 27525120

fold_2/model.chrombpnet_nobias.fold_2.ENCSR233HSC.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:513b36239c8d2c7cbef1691aad6cc5ad1f1f7a450fffe4af5f57af5c415fcae8
+size 25583536

fold_2/model.chrombpnet_nobias.fold_2.ENCSR233HSC.tar

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a71892d3a34a306867ce2b00d530146d836180f728eac3e37519bb9476ac1b78
+size 26060800

fold_3/logs.models.fold_3.ENCSR233HSC/logfile.modelling.fold_3.ENCSR233HSC.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//ENCSR233HSC//preprocessing/bigWigs/ENCSR233HSC.bigWig",
+    "peaks": "/scratch/groups/akundaje/anusri/chromatin_atlas/ATAC/ENCSR233HSC//chrombpnet_model_feb15_fold_3//filtered.peaks.bed",
+    "nonpeaks": "/scratch/groups/akundaje/anusri/chromatin_atlas/ATAC/ENCSR233HSC//chrombpnet_model_feb15_fold_3//filtered.nonpeaks.bed",
+    "output_prefix": "/scratch/groups/akundaje/anusri/chromatin_atlas/ATAC/ENCSR233HSC//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": "/scratch/groups/akundaje/anusri/chromatin_atlas/ATAC/ENCSR233HSC//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.ENCSR233HSC/logfile.modelling.fold_3.ENCSR233HSC.chrombpnet_data_params.tsv

@@ -0,0 +1,3 @@
+counts_sum_min_thresh	8.0
+counts_sum_max_thresh	1909.0
+trainings_pts_post_thresh	153190

fold_3/logs.models.fold_3.ENCSR233HSC/logfile.modelling.fold_3.ENCSR233HSC.chrombpnet_model_params.tsv

@@ -0,0 +1,9 @@
+counts_loss_weight	17.3
+filters	512
+n_dil_layers	8
+bias_model_path	/scratch/groups/akundaje/anusri/chromatin_atlas/ATAC/ENCSR233HSC//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.ENCSR233HSC/logfile.modelling.fold_3.ENCSR233HSC.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
+0,8.976065635681152,411.5568542480469,566.8427124023438,0.9205687642097473,424.54339599609375,440.4691162109375
+1,0.8131083846092224,391.5087890625,405.57623291015625,0.8004679679870605,415.2185363769531,429.0665588378906
+2,0.757564902305603,382.9791564941406,396.08551025390625,0.7608223557472229,407.6604919433594,420.82293701171875
+3,0.7208784222602844,378.99371337890625,391.4651794433594,0.7097057700157166,405.516845703125,417.794677734375
+4,0.6861416697502136,376.1109619140625,387.9814453125,0.7353146076202393,404.5780334472656,417.29925537109375
+5,0.651038646697998,373.419189453125,384.68255615234375,0.6725754737854004,401.5502624511719,413.1859436035156
+6,0.6245077252388,371.661376953125,382.4649353027344,0.6545359492301941,399.7099304199219,411.03350830078125
+7,0.5966131091117859,369.66802978515625,379.9895324707031,0.6333138346672058,399.17584228515625,410.1322937011719
+8,0.5641828179359436,367.5639953613281,377.323486328125,0.6646084785461426,399.9779968261719,411.4755859375
+9,0.5403679609298706,365.7572326660156,375.10577392578125,0.6310431957244873,399.4191589355469,410.3362121582031
+10,0.5118304491043091,364.5878601074219,373.4429626464844,0.6508740186691284,400.03729248046875,411.2972717285156
+11,0.42268434166908264,359.5216979980469,366.8340148925781,0.6561209559440613,398.3426208496094,409.693603515625
+12,0.3763985335826874,356.78680419921875,363.2980041503906,0.6556077599525452,399.0743103027344,410.4163818359375
+13,0.33948493003845215,354.99676513671875,360.8703308105469,0.63240647315979,400.47265625,411.4132995605469
+14,0.30765044689178467,353.9229736328125,359.24517822265625,0.697524905204773,400.8667297363281,412.9339294433594
+15,0.2616581916809082,351.2901611328125,355.8167419433594,0.6506236791610718,401.0113525390625,412.26708984375
+16,0.2455032914876938,349.64642333984375,353.8940124511719,0.7027994394302368,402.1224365234375,414.2808837890625

fold_3/model.bias_scaled.fold_3.ENCSR233HSC.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7899abfc0c700af5aad787a6d9a454e7fdec3218625b70dac1f78e3b85494be1
+size 2688440

fold_3/model.bias_scaled.fold_3.ENCSR233HSC.tar

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:787da973059d030d81b961fc181d116cc91630e86e99bbe20bbf5b190e11a0f7
+size 1198080

fold_3/model.chrombpnet.fold_3.ENCSR233HSC.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:87ae840ae6b09a102918cf877e11c9cb76faee6187ae34793745abc4fd75a87c
+size 26448040

fold_3/model.chrombpnet.fold_3.ENCSR233HSC.tar

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8f25c3449222fe6abb21cdb02776889f6593213ca29429c5d2f733093cfbf738
+size 27525120

fold_3/model.chrombpnet_nobias.fold_3.ENCSR233HSC.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a6b68ab30aa558559e3e3a3bf5164de72c5e6018e3edb830a30f99c406f7f469
+size 25583536

fold_3/model.chrombpnet_nobias.fold_3.ENCSR233HSC.tar

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a7ad4ee59caa9f2184819c18e451803dd1e80275d1e2870aa8a85e6fe7fd4705
+size 26060800

fold_4/logs.models.fold_4.ENCSR233HSC/logfile.modelling.fold_4.ENCSR233HSC.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//ENCSR233HSC//preprocessing/bigWigs/ENCSR233HSC.bigWig",
+    "peaks": "/scratch/groups/akundaje/anusri/chromatin_atlas/ATAC/ENCSR233HSC//chrombpnet_model_feb15_fold_4//filtered.peaks.bed",
+    "nonpeaks": "/scratch/groups/akundaje/anusri/chromatin_atlas/ATAC/ENCSR233HSC//chrombpnet_model_feb15_fold_4//filtered.nonpeaks.bed",
+    "output_prefix": "/scratch/groups/akundaje/anusri/chromatin_atlas/ATAC/ENCSR233HSC//chrombpnet_model_feb15_fold_4//chrombpnet",
+    "chr_fold_path": "/scratch/groups/akundaje/anusri/chromatin_atlas/splits/fold_4.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/ENCSR233HSC//chrombpnet_model_feb15_fold_4//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_4/logs.models.fold_4.ENCSR233HSC/logfile.modelling.fold_4.ENCSR233HSC.chrombpnet_data_params.tsv

@@ -0,0 +1,3 @@
+counts_sum_min_thresh	8.0
+counts_sum_max_thresh	1925.0
+trainings_pts_post_thresh	155081

fold_4/logs.models.fold_4.ENCSR233HSC/logfile.modelling.fold_4.ENCSR233HSC.chrombpnet_model_params.tsv

@@ -0,0 +1,9 @@
+counts_loss_weight	17.2
+filters	512
+n_dil_layers	8
+bias_model_path	/scratch/groups/akundaje/anusri/chromatin_atlas/ATAC/ENCSR233HSC//chrombpnet_model_feb15_fold_4/bias_model_scaled.h5
+inputlen	2114
+outputlen	1000
+max_jitter	500
+chr_fold_path	/scratch/groups/akundaje/anusri/chromatin_atlas/splits/fold_4.json
+negative_sampling_ratio	0.1

fold_4/logs.models.fold_4.ENCSR233HSC/logfile.modelling.fold_4.ENCSR233HSC.epoch_loss.csv

@@ -0,0 +1,20 @@
+epoch,logcount_predictions_loss,logits_profile_predictions_loss,loss,val_logcount_predictions_loss,val_logits_profile_predictions_loss,val_loss
+0,5.755629062652588,411.5138244628906,510.51068115234375,0.8642345666885376,427.2705993652344,442.1353454589844
+1,0.8228622078895569,389.8169250488281,403.9704895019531,0.7611573934555054,415.94097900390625,429.032958984375
+2,0.7510384917259216,382.9769592285156,395.89459228515625,0.7669361233711243,411.0111389160156,424.2023620605469
+3,0.7121178507804871,378.4663391113281,390.71533203125,0.691937267780304,408.0657653808594,419.9672546386719
+4,0.6738265752792358,375.4420166015625,387.0312805175781,0.7615420818328857,406.9808044433594,420.07928466796875
+5,0.6390275359153748,372.43695068359375,383.4281311035156,0.6519671082496643,406.4142761230469,417.628173828125
+6,0.6042369604110718,370.7354431152344,381.1277160644531,0.7470909357070923,403.38690185546875,416.2366027832031
+7,0.580008327960968,368.6769104003906,378.6528625488281,0.649199366569519,404.1201477050781,415.2863464355469
+8,0.5473331809043884,366.7745056152344,376.188720703125,0.6651778817176819,403.8007507324219,415.2415466308594
+9,0.5227746963500977,365.12445068359375,374.11590576171875,0.6388061046600342,403.54388427734375,414.53143310546875
+10,0.4919285774230957,363.84771728515625,372.30914306640625,0.648116409778595,403.9587707519531,415.106201171875
+11,0.4637714624404907,362.98638916015625,370.96295166015625,0.63718581199646,403.8951721191406,414.85491943359375
+12,0.4347045123577118,361.7830810546875,369.2604675292969,0.6987290382385254,404.4194030761719,416.4375
+13,0.3455667793750763,357.53411865234375,363.4781188964844,0.6441291570663452,403.2315368652344,414.3105773925781
+14,0.3065880239009857,354.88543701171875,360.15899658203125,0.6451406478881836,403.85247802734375,414.9490051269531
+15,0.2777882218360901,353.790771484375,358.5683898925781,0.6670001745223999,404.8014221191406,416.2735595703125
+16,0.2579498291015625,352.5757141113281,357.012451171875,0.6803897619247437,405.760498046875,417.4632568359375
+17,0.22169364988803864,350.1966552734375,354.0103759765625,0.7252733707427979,406.53900146484375,419.013916015625
+18,0.20767202973365784,349.1732177734375,352.7455749511719,0.672278642654419,406.763916015625,418.3270263671875