Upload folder using huggingface_hub

README.md

@@ -0,0 +1,120 @@
+---
+license: mit
+library_name: chrombpnet
+tags:
+  - encode
+  - chrombpnet
+  - chromatin-accessibility
+  - ATAC
+  - adrenal
+  - 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 adrenal gland (ENCSR241OBO)
+- Model: ChromBPNet
+- Assay: ATAC-seq
+- Experiment: [ENCSR241OBO](https://www.encodeproject.org/experiments/ENCSR241OBO/)
+- Model annotation: [ENCSR371OUD](https://www.encodeproject.org/annotations/ENCSR371OUD/)
+- Biosample: adrenal gland (Full name: Homo sapiens adrenal gland tissue female adult (59 years))
+- Cell slim(s): None
+- Organ slim(s): adrenal-gland,endocrine-gland
+- Developmental slim(s): mesoderm,ectoderm
+- System slim(s): 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.ENCSR241OBO/logfile.modelling.fold_0.ENCSR241OBO.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/ENCSR241OBO//preprocessing/bigWigs/ENCSR241OBO.bigWig",
+    "peaks": "/scratch/groups/akundaje/anusri/chromatin_atlas/ATAC/ENCSR241OBO//chrombpnet_model_feb15//filtered.peaks.bed",
+    "nonpeaks": "/scratch/groups/akundaje/anusri/chromatin_atlas/ATAC/ENCSR241OBO//chrombpnet_model_feb15//filtered.nonpeaks.bed",
+    "output_prefix": "/scratch/groups/akundaje/anusri/chromatin_atlas/ATAC/ENCSR241OBO//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/ENCSR241OBO//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.ENCSR241OBO/logfile.modelling.fold_0.ENCSR241OBO.bias_formatting.stdout.txt

@@ -0,0 +1 @@
+Converting /oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/ATAC/ENCSR241OBO/chrombpnet_model_feb15/bias_model_scaled.h5 to /oak/stanford/groups/akundaje/vhecht/chromatin-atlas-2022/ATAC/ENCSR241OBO/fold_0/new_model_format/bias_model_scaled.tar with get_new_tf_model_format.py

fold_0/logs.models.fold_0.ENCSR241OBO/logfile.modelling.fold_0.ENCSR241OBO.chrombpnet_data_params.tsv

@@ -0,0 +1,3 @@
+counts_sum_min_thresh	12.0
+counts_sum_max_thresh	8270.46
+trainings_pts_post_thresh	236762

fold_0/logs.models.fold_0.ENCSR241OBO/logfile.modelling.fold_0.ENCSR241OBO.chrombpnet_formatting.stdout.txt

@@ -0,0 +1 @@
+Converting /oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/ATAC/ENCSR241OBO/chrombpnet_model_feb15/chrombpnet.h5 to /oak/stanford/groups/akundaje/vhecht/chromatin-atlas-2022/ATAC/ENCSR241OBO/fold_0/new_model_format/chrombpnet.tar with get_new_tf_model_format.py

fold_0/logs.models.fold_0.ENCSR241OBO/logfile.modelling.fold_0.ENCSR241OBO.chrombpnet_model_params.tsv

@@ -0,0 +1,9 @@
+counts_loss_weight	66.3
+filters	512
+n_dil_layers	8
+bias_model_path	/scratch/groups/akundaje/anusri/chromatin_atlas/ATAC/ENCSR241OBO//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.ENCSR241OBO/logfile.modelling.fold_0.ENCSR241OBO.chrombpnet_no_bias_formatting.stdout.txt

@@ -0,0 +1 @@
+Converting /oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/ATAC/ENCSR241OBO/chrombpnet_model_feb15/chrombpnet_wo_bias.h5 to /oak/stanford/groups/akundaje/vhecht/chromatin-atlas-2022/ATAC/ENCSR241OBO/fold_0/new_model_format/chrombpnet_nobias.tar with get_new_tf_model_format.py

fold_0/logs.models.fold_0.ENCSR241OBO/logfile.modelling.fold_0.ENCSR241OBO.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
+0,2.444638252258301,912.0730590820312,1074.1533203125,1.3550831079483032,861.73828125,951.5794677734375
+1,1.0221853256225586,822.3748779296875,890.1476440429688,0.9820407629013062,826.0070190429688,891.1168823242188
+2,0.9394544363021851,798.2633056640625,860.5494384765625,0.9422622323036194,817.1981201171875,879.669921875
+3,0.891261100769043,782.9298706054688,842.0198364257812,0.9324159622192383,813.75390625,875.5731811523438
+4,0.8497403264045715,771.705322265625,828.0433349609375,0.8789621591567993,811.6589965820312,869.934326171875
+5,0.8184037804603577,761.6174926757812,815.8763427734375,0.8539597988128662,809.3389892578125,865.9567260742188
+6,0.7885001301765442,754.9874877929688,807.2645263671875,0.8537232279777527,809.0397338867188,865.6414184570312
+7,0.7638711929321289,748.6832275390625,799.3265380859375,0.8379963040351868,809.1064453125,864.6660766601562
+8,0.7402660846710205,744.6359252929688,793.7171020507812,0.8545724153518677,808.8140869140625,865.472412109375
+9,0.724000871181488,740.7779541015625,788.7784423828125,0.8458910584449768,807.7709350585938,863.8536987304688
+10,0.7043580412864685,738.3414916992188,785.0410766601562,0.9229452013969421,811.4337158203125,872.625
+11,0.674506664276123,735.2410278320312,779.9616088867188,0.8622950911521912,812.2622680664062,869.4331665039062
+12,0.6578496694564819,734.0907592773438,777.7053833007812,0.8774701356887817,811.3303833007812,869.5060424804688
+13,0.5705242156982422,715.2109375,753.0384521484375,0.8621117472648621,804.4351806640625,861.5930786132812
+14,0.5171595215797424,707.5350952148438,741.824462890625,0.877275824546814,806.1080322265625,864.2711791992188
+15,0.48597121238708496,703.6495971679688,735.8701171875,0.9338904619216919,810.609619140625,872.5263671875
+16,0.45605844259262085,700.3990478515625,730.6362915039062,0.8918272256851196,809.3331909179688,868.46142578125
+17,0.4014582931995392,693.0842895507812,719.698974609375,0.9004514813423157,808.0690307617188,867.7685546875
+18,0.3771345913410187,689.2164916992188,714.2217407226562,0.8995997309684753,809.9132080078125,869.556640625

fold_0/model.bias_scaled.fold_0.ENCSR241OBO.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b482b8ef1c73b5e6a4331576c907c05f9c44547d0a3cb8c85311393bea9cce79
+size 2688440

fold_0/model.bias_scaled.fold_0.ENCSR241OBO.tar

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:10917036ee4445c8cc89af432525a35a36f9adeed469e4cdd00d8688fdfd2ecd
+size 1198080

fold_0/model.chrombpnet.fold_0.ENCSR241OBO.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:15150eb1785ef7ec43e346070c25d482c624f668a0b9db0343ae97a707363017
+size 26448016

fold_0/model.chrombpnet.fold_0.ENCSR241OBO.tar

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cd1fda70ffa540ffcf27b09d8232a0677c2c4371623f8d6cca3b20a59ae46e40
+size 27535360

fold_0/model.chrombpnet_nobias.fold_0.ENCSR241OBO.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:85084f59d90156aa92e1ca3418a64d57c02fa347d4a48dbe33bc289901746bb7
+size 25583536

fold_0/model.chrombpnet_nobias.fold_0.ENCSR241OBO.tar

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cd669f87e12657d941a5f83d27e4d78fc7468d558e7f227b5f46ee1002777b83
+size 26060800

fold_1/logs.models.fold_1.ENCSR241OBO/logfile.modelling.fold_1.ENCSR241OBO.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//ENCSR241OBO//preprocessing/bigWigs/ENCSR241OBO.bigWig",
+    "peaks": "/oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/ATAC//ENCSR241OBO//chrombpnet_model_feb15_fold_1//filtered.peaks.bed",
+    "nonpeaks": "/oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/ATAC//ENCSR241OBO//chrombpnet_model_feb15_fold_1//filtered.nonpeaks.bed",
+    "output_prefix": "/oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/ATAC//ENCSR241OBO//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//ENCSR241OBO//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.ENCSR241OBO/logfile.modelling.fold_1.ENCSR241OBO.bias_formatting.stdout.txt

@@ -0,0 +1 @@
+Converting /oak/stanford/groups/akundaje/vhecht/chromatin-atlas-2022/ATAC/ENCSR241OBO/chrombpnet_model_feb15_fold_1/bias_model_scaled.h5 to /oak/stanford/groups/akundaje/vhecht/chromatin-atlas-2022/ATAC/ENCSR241OBO/fold_1/new_model_format/bias_model_scaled.tar with get_new_tf_model_format.py

fold_1/logs.models.fold_1.ENCSR241OBO/logfile.modelling.fold_1.ENCSR241OBO.chrombpnet_data_params.tsv

@@ -0,0 +1,3 @@
+counts_sum_min_thresh	12.0
+counts_sum_max_thresh	8209.51
+trainings_pts_post_thresh	241285

fold_1/logs.models.fold_1.ENCSR241OBO/logfile.modelling.fold_1.ENCSR241OBO.chrombpnet_formatting.stdout.txt

@@ -0,0 +1 @@
+Converting /oak/stanford/groups/akundaje/vhecht/chromatin-atlas-2022/ATAC/ENCSR241OBO/chrombpnet_model_feb15_fold_1/chrombpnet.h5 to /oak/stanford/groups/akundaje/vhecht/chromatin-atlas-2022/ATAC/ENCSR241OBO/fold_1/new_model_format/chrombpnet.tar with get_new_tf_model_format.py

fold_1/logs.models.fold_1.ENCSR241OBO/logfile.modelling.fold_1.ENCSR241OBO.chrombpnet_model_params.tsv

@@ -0,0 +1,9 @@
+counts_loss_weight	65.5
+filters	512
+n_dil_layers	8
+bias_model_path	/oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/ATAC//ENCSR241OBO//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.ENCSR241OBO/logfile.modelling.fold_1.ENCSR241OBO.chrombpnet_no_bias_formatting.stdout.txt

@@ -0,0 +1 @@
+Converting /oak/stanford/groups/akundaje/vhecht/chromatin-atlas-2022/ATAC/ENCSR241OBO/chrombpnet_model_feb15_fold_1/chrombpnet_wo_bias.h5 to /oak/stanford/groups/akundaje/vhecht/chromatin-atlas-2022/ATAC/ENCSR241OBO/fold_1/new_model_format/chrombpnet_nobias.tar with get_new_tf_model_format.py

fold_1/logs.models.fold_1.ENCSR241OBO/logfile.modelling.fold_1.ENCSR241OBO.epoch_loss.csv

@@ -0,0 +1,15 @@
+epoch,logcount_predictions_loss,logits_profile_predictions_loss,loss,val_logcount_predictions_loss,val_logits_profile_predictions_loss,val_loss
+0,2.5670998096466064,869.507568359375,1037.65283203125,1.2590937614440918,924.8685302734375,1007.339599609375
+1,1.0483769178390503,783.1873168945312,851.8572387695312,1.0238597393035889,878.6337280273438,945.696044921875
+2,0.9525963664054871,758.5357055664062,820.9315795898438,0.9130935668945312,865.8522338867188,925.6598510742188
+3,0.888221025466919,744.8168334960938,802.9946899414062,0.8681021332740784,854.4976806640625,911.3583374023438
+4,0.8411770462989807,733.2899169921875,788.3873901367188,0.9399829506874084,853.3984375,914.9669799804688
+5,0.807830810546875,724.1116333007812,777.022705078125,0.831640899181366,849.6272583007812,904.0994262695312
+6,0.776530385017395,717.1533813476562,768.0159301757812,0.8251211047172546,848.9594116210938,903.0042724609375
+7,0.7477059960365295,712.1912841796875,761.166259765625,0.8659656643867493,853.2479858398438,909.9690551757812
+8,0.7248525619506836,706.96435546875,754.44091796875,0.8205978870391846,848.0755615234375,901.8247680664062
+9,0.694957971572876,703.833251953125,749.3535766601562,0.8262822031974792,848.2413940429688,902.3633422851562
+10,0.6731883883476257,701.866455078125,745.9609375,0.9350607991218567,855.3330688476562,916.5802612304688
+11,0.6487280130386353,699.9331665039062,742.423828125,0.9016377925872803,850.4959716796875,909.553466796875
+12,0.5522041320800781,685.2263793945312,721.397705078125,0.8792897462844849,846.53662109375,904.1303100585938
+13,0.5073556303977966,677.9464111328125,711.1785278320312,0.8534778952598572,846.0446166992188,901.9471435546875

fold_1/model.bias_scaled.fold_1.ENCSR241OBO.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1bdb37c96fc307fe715a82457c7a976f8dddb9d75398b7c2d4861f762531c39a
+size 2688440

fold_1/model.bias_scaled.fold_1.ENCSR241OBO.tar

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ddd58775784b797fdec00b4002b9bcfbc6d73efa2718b9a757b487059cedcf50
+size 1198080

fold_1/model.chrombpnet.fold_1.ENCSR241OBO.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c3ca097ae8ab193dac77745722d0bf13b1a47dbdfe4125cf824d6f40bda3d2f8
+size 26447928

fold_1/model.chrombpnet.fold_1.ENCSR241OBO.tar

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6e7e0132a052fc3be5dde1dec4007d842f7a1048157322d2ca066c3be560db6c
+size 27525120

fold_1/model.chrombpnet_nobias.fold_1.ENCSR241OBO.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:68d942d4e6aec825ec45930bb822b0a35c070ed25b644363eb96607069c87586
+size 25583536

fold_1/model.chrombpnet_nobias.fold_1.ENCSR241OBO.tar

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:32f83b0ede7631545f98c572a9489624895fc30568d9e0010300cec9688d7062
+size 26060800

fold_2/logs.models.fold_2.ENCSR241OBO/logfile.modelling.fold_2.ENCSR241OBO.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//ENCSR241OBO//preprocessing/bigWigs/ENCSR241OBO.bigWig",
+    "peaks": "/oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/ATAC//ENCSR241OBO//chrombpnet_model_feb15_fold_2//filtered.peaks.bed",
+    "nonpeaks": "/oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/ATAC//ENCSR241OBO//chrombpnet_model_feb15_fold_2//filtered.nonpeaks.bed",
+    "output_prefix": "/oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/ATAC//ENCSR241OBO//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//ENCSR241OBO//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.ENCSR241OBO/logfile.modelling.fold_2.ENCSR241OBO.bias_formatting.stdout.txt

@@ -0,0 +1 @@
+Converting /oak/stanford/groups/akundaje/vhecht/chromatin-atlas-2022/ATAC/ENCSR241OBO/chrombpnet_model_feb15_fold_2/bias_model_scaled.h5 to /oak/stanford/groups/akundaje/vhecht/chromatin-atlas-2022/ATAC/ENCSR241OBO/fold_2/new_model_format/bias_model_scaled.tar with get_new_tf_model_format.py

fold_2/logs.models.fold_2.ENCSR241OBO/logfile.modelling.fold_2.ENCSR241OBO.chrombpnet_data_params.tsv

@@ -0,0 +1,3 @@
+counts_sum_min_thresh	13.0
+counts_sum_max_thresh	8268.0
+trainings_pts_post_thresh	248972

fold_2/logs.models.fold_2.ENCSR241OBO/logfile.modelling.fold_2.ENCSR241OBO.chrombpnet_formatting.stdout.txt

@@ -0,0 +1 @@
+Converting /oak/stanford/groups/akundaje/vhecht/chromatin-atlas-2022/ATAC/ENCSR241OBO/chrombpnet_model_feb15_fold_2/chrombpnet.h5 to /oak/stanford/groups/akundaje/vhecht/chromatin-atlas-2022/ATAC/ENCSR241OBO/fold_2/new_model_format/chrombpnet.tar with get_new_tf_model_format.py

fold_2/logs.models.fold_2.ENCSR241OBO/logfile.modelling.fold_2.ENCSR241OBO.chrombpnet_model_params.tsv

@@ -0,0 +1,9 @@
+counts_loss_weight	66.1
+filters	512
+n_dil_layers	8
+bias_model_path	/oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/ATAC//ENCSR241OBO//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.ENCSR241OBO/logfile.modelling.fold_2.ENCSR241OBO.chrombpnet_no_bias_formatting.stdout.txt

@@ -0,0 +1 @@
+Converting /oak/stanford/groups/akundaje/vhecht/chromatin-atlas-2022/ATAC/ENCSR241OBO/chrombpnet_model_feb15_fold_2/chrombpnet_wo_bias.h5 to /oak/stanford/groups/akundaje/vhecht/chromatin-atlas-2022/ATAC/ENCSR241OBO/fold_2/new_model_format/chrombpnet_nobias.tar with get_new_tf_model_format.py

fold_2/logs.models.fold_2.ENCSR241OBO/logfile.modelling.fold_2.ENCSR241OBO.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
+0,2.7614099979400635,904.8223266601562,1087.352294921875,1.0890357494354248,874.8001098632812,946.7859497070312
+1,1.0775141716003418,806.4932250976562,877.7194213867188,1.0028576850891113,829.7764282226562,896.0657958984375
+2,0.9851935505867004,776.0379638671875,841.1603393554688,0.9370134472846985,814.64990234375,876.5868530273438
+3,0.910965085029602,758.87109375,819.0853881835938,0.8909763693809509,803.6893310546875,862.5833740234375
+4,0.8665092587471008,746.8054809570312,804.0803833007812,0.926537036895752,798.0208129882812,859.2652587890625
+5,0.8304476141929626,736.5508422851562,791.443359375,0.9196366667747498,799.820068359375,860.6079711914062
+6,0.7911993861198425,728.9271240234375,781.2254638671875,0.8251739740371704,794.7763061523438,849.3204345703125
+7,0.7681577205657959,721.99853515625,772.7734985351562,0.8867068290710449,797.4364624023438,856.0477294921875
+8,0.7347140908241272,717.5897827148438,766.1552734375,1.032910943031311,793.9800415039062,862.255859375
+9,0.7096884250640869,714.007568359375,760.9183959960938,0.8419424891471863,794.5814208984375,850.2335205078125
+10,0.6199497580528259,696.7958374023438,737.773193359375,0.8483012914657593,790.27978515625,846.3522338867188
+11,0.5732157826423645,689.5724487304688,727.4632568359375,0.833744466304779,790.2259521484375,845.336181640625
+12,0.5328515768051147,685.4863891601562,720.7076416015625,0.833982527256012,789.0059204101562,844.1320190429688
+13,0.5010800361633301,682.1348266601562,715.2574462890625,0.8712939620018005,793.9575805664062,851.5501098632812
+14,0.4684840440750122,679.9243774414062,710.890380859375,0.8662265539169312,793.017578125,850.2747802734375
+15,0.4462583661079407,677.6978149414062,707.1954345703125,0.851432204246521,792.8719482421875,849.1515502929688
+16,0.3852183222770691,671.3521118164062,696.8150024414062,0.8929669260978699,793.8832397460938,852.9088134765625
+17,0.3660259246826172,668.0157470703125,692.21044921875,0.8836596608161926,794.0985107421875,852.5089111328125

fold_2/model.bias_scaled.fold_2.ENCSR241OBO.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2942a1ac13a21c3480af8d4ae05ee30de457428802b3c8652543d2f5da5f5b79
+size 2688440

fold_2/model.bias_scaled.fold_2.ENCSR241OBO.tar

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d3c69af81e671a8b92509d6c31a6d2b59f3d47b495c9e2a852fec0935c09181d
+size 1198080

fold_2/model.chrombpnet.fold_2.ENCSR241OBO.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a5c408a0211cee59755da8be659625a487947e5003e3f3e53380c764f7c3c0c5
+size 26447928

fold_2/model.chrombpnet.fold_2.ENCSR241OBO.tar

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:baca4d637859bd5bfd82c6bf27bf54a262e8ce994c0b1be73cdc2807c5f5572b
+size 27525120

fold_2/model.chrombpnet_nobias.fold_2.ENCSR241OBO.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e39c3b879c000b5b954131d7673edfbdd0fe7288724be141103a54a7c9b5510
+size 25583536

fold_2/model.chrombpnet_nobias.fold_2.ENCSR241OBO.tar

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:08f9984e26a293cb5719c7af472b70489d2ef0ba1ef79c9186d53f55fe606fef
+size 26060800

fold_3/logs.models.fold_3.ENCSR241OBO/logfile.modelling.fold_3.ENCSR241OBO.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//ENCSR241OBO//preprocessing/bigWigs/ENCSR241OBO.bigWig",
+    "peaks": "/scratch/groups/akundaje/anusri/chromatin_atlas/ATAC/ENCSR241OBO//chrombpnet_model_feb15_fold_3//filtered.peaks.bed",
+    "nonpeaks": "/scratch/groups/akundaje/anusri/chromatin_atlas/ATAC/ENCSR241OBO//chrombpnet_model_feb15_fold_3//filtered.nonpeaks.bed",
+    "output_prefix": "/scratch/groups/akundaje/anusri/chromatin_atlas/ATAC/ENCSR241OBO//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/ENCSR241OBO//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.ENCSR241OBO/logfile.modelling.fold_3.ENCSR241OBO.bias_formatting.stdout.txt

@@ -0,0 +1 @@
+Converting /oak/stanford/groups/akundaje/vhecht/chromatin-atlas-2022/ATAC/ENCSR241OBO/chrombpnet_model_feb15_fold_3/bias_model_scaled.h5 to /oak/stanford/groups/akundaje/vhecht/chromatin-atlas-2022/ATAC/ENCSR241OBO/fold_3/new_model_format/bias_model_scaled.tar with get_new_tf_model_format.py

fold_3/logs.models.fold_3.ENCSR241OBO/logfile.modelling.fold_3.ENCSR241OBO.chrombpnet_data_params.tsv

@@ -0,0 +1,3 @@
+counts_sum_min_thresh	12.0
+counts_sum_max_thresh	8313.0
+trainings_pts_post_thresh	240776

fold_3/logs.models.fold_3.ENCSR241OBO/logfile.modelling.fold_3.ENCSR241OBO.chrombpnet_formatting.stdout.txt

@@ -0,0 +1 @@
+Converting /oak/stanford/groups/akundaje/vhecht/chromatin-atlas-2022/ATAC/ENCSR241OBO/chrombpnet_model_feb15_fold_3/chrombpnet.h5 to /oak/stanford/groups/akundaje/vhecht/chromatin-atlas-2022/ATAC/ENCSR241OBO/fold_3/new_model_format/chrombpnet.tar with get_new_tf_model_format.py

fold_3/logs.models.fold_3.ENCSR241OBO/logfile.modelling.fold_3.ENCSR241OBO.chrombpnet_model_params.tsv

@@ -0,0 +1,9 @@
+counts_loss_weight	65.9
+filters	512
+n_dil_layers	8
+bias_model_path	/scratch/groups/akundaje/anusri/chromatin_atlas/ATAC/ENCSR241OBO//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.ENCSR241OBO/logfile.modelling.fold_3.ENCSR241OBO.chrombpnet_no_bias_formatting.stdout.txt

@@ -0,0 +1 @@
+Converting /oak/stanford/groups/akundaje/vhecht/chromatin-atlas-2022/ATAC/ENCSR241OBO/chrombpnet_model_feb15_fold_3/chrombpnet_wo_bias.h5 to /oak/stanford/groups/akundaje/vhecht/chromatin-atlas-2022/ATAC/ENCSR241OBO/fold_3/new_model_format/chrombpnet_nobias.tar with get_new_tf_model_format.py