Upload folder using huggingface_hub

README.md

@@ -0,0 +1,120 @@
+---
+license: mit
+library_name: chrombpnet
+tags:
+  - encode
+  - chrombpnet
+  - chromatin-accessibility
+  - DNASE
+  - muscle
+  - 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 muscle of back (ENCSR174GXG)
+- Model: ChromBPNet
+- Assay: DNASE-seq
+- Experiment: [ENCSR174GXG](https://www.encodeproject.org/experiments/ENCSR174GXG/)
+- Model annotation: [ENCSR037WSC](https://www.encodeproject.org/annotations/ENCSR037WSC/)
+- Biosample: muscle of back (Full name: Homo sapiens muscle of back tissue male embryo (101 days))
+- Cell slim(s): None
+- Organ slim(s): musculature-of-body
+- Developmental slim(s): mesoderm
+- System slim(s): musculature
+- 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.ENCSR174GXG/logfile.modelling.fold_0.ENCSR174GXG.args.json

@@ -0,0 +1,42 @@
+{
+    "cmd": "pipeline",
+    "genome": "/oak/stanford/groups/akundaje/ziwei75/atac_seq_pipeline/hg38/GRCh38_no_alt_analysis_set_GCA_000001405.15.fasta",
+    "chrom_sizes": "/oak/stanford/groups/akundaje/ziwei75/atac_seq_pipeline/hg38/GRCh38_EBV.chrom.sizes.tsv",
+    "bigwig": "/oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/DNASE/ENCSR174GXG/preprocessing/bigWigs/ENCSR174GXG.bigWig",
+    "output_dir": "/oak/stanford/groups/akundaje/ziwei75/chromatin_atlas_bias/DNase_model/bias_filtered/ENCSR174GXG//fold0/",
+    "data_type": "DNASE",
+    "peaks": "/oak/stanford/groups/akundaje/ziwei75/chromatin_atlas_bias/DNase_model/bias_filtered/ENCSR174GXG//fold0/auxiliary/filtered.peaks.bed",
+    "nonpeaks": "/oak/stanford/groups/akundaje/ziwei75/chromatin_atlas_bias/DNase_model/bias_filtered/ENCSR174GXG//fold0/auxiliary/filtered.nonpeaks.bed",
+    "chr_fold_path": "/oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/splits/fold_0.json",
+    "outlier_threshold": 0.9999,
+    "ATAC_ref_path": null,
+    "DNASE_ref_path": null,
+    "num_samples": 10000,
+    "inputlen": 2114,
+    "outputlen": 1000,
+    "seed": 1234,
+    "epochs": 50,
+    "early_stop": 5,
+    "learning_rate": 0.001,
+    "trackables": [
+        "logcount_predictions_loss",
+        "loss",
+        "logits_profile_predictions_loss",
+        "val_logcount_predictions_loss",
+        "val_loss",
+        "val_logits_profile_predictions_loss"
+    ],
+    "architecture_from_file": "/home/groups/akundaje/ziwei75/anaconda3/envs/chrombpnet/lib/python3.8/site-packages/chrombpnet/training/models/chrombpnet_with_bias_model.py",
+    "file_prefix": null,
+    "html_prefix": "./",
+    "bias_model_path": "/oak/stanford/groups/akundaje/ziwei75/chromatin_atlas_bias/DNase_bias_model/filtered_negatives_models/ENCSR174GXG/models/bias.h5",
+    "negative_sampling_ratio": 0.1,
+    "filters": 512,
+    "n_dilation_layers": 8,
+    "max_jitter": 500,
+    "batch_size": 64,
+    "output_prefix": "/oak/stanford/groups/akundaje/ziwei75/chromatin_atlas_bias/DNase_model/bias_filtered/ENCSR174GXG//fold0/models/chrombpnet",
+    "chr": "chr8",
+    "pwm_width": 24,
+    "params": "/oak/stanford/groups/akundaje/ziwei75/chromatin_atlas_bias/DNase_model/bias_filtered/ENCSR174GXG//fold0/logs/chrombpnet_model_params.tsv"
+}

fold_0/logs.models.fold_0.ENCSR174GXG/logfile.modelling.fold_0.ENCSR174GXG.chrombpnet_data_params.tsv

@@ -0,0 +1,3 @@
+counts_sum_min_thresh	0.0
+counts_sum_max_thresh	1187.53
+trainings_pts_post_thresh	170320

fold_0/logs.models.fold_0.ENCSR174GXG/logfile.modelling.fold_0.ENCSR174GXG.chrombpnet_model_params.tsv

@@ -0,0 +1,9 @@
+counts_loss_weight	4.7
+filters	512
+n_dil_layers	8
+bias_model_path	/oak/stanford/groups/akundaje/ziwei75/chromatin_atlas_bias/DNase_model/bias_filtered/ENCSR174GXG//fold0/models/bias_model_scaled.h5
+inputlen	2114
+outputlen	1000
+max_jitter	500
+chr_fold_path	/oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/splits/fold_0.json
+negative_sampling_ratio	0.1

fold_0/logs.models.fold_0.ENCSR174GXG/logfile.modelling.fold_0.ENCSR174GXG.epoch_loss.csv

@@ -0,0 +1,11 @@
+epoch,logcount_predictions_loss,logits_profile_predictions_loss,loss,val_logcount_predictions_loss,val_logits_profile_predictions_loss,val_loss
+0,4.795746326446533,227.8439178466797,250.38406372070312,0.997081995010376,225.7175750732422,230.4039306640625
+1,0.802418053150177,218.4396514892578,222.21072387695312,0.7819237112998962,223.18067932128906,226.85569763183594
+2,0.7398564219474792,216.0391387939453,219.5164794921875,0.7610508799552917,221.57882690429688,225.15579223632812
+3,0.6938852667808533,214.29832458496094,217.55917358398438,0.6775075793266296,220.56407165527344,223.7483673095703
+4,0.6593472361564636,213.28929138183594,216.38839721679688,0.6504759788513184,219.23114013671875,222.2884521484375
+5,0.6234856247901917,212.63308715820312,215.56350708007812,0.5803095698356628,219.58822631835938,222.31570434570312
+6,0.5955421328544617,211.77198791503906,214.57113647460938,0.623294472694397,219.7575225830078,222.68685913085938
+7,0.5854236483573914,210.83848571777344,213.59007263183594,0.608178436756134,220.27471923828125,223.13319396972656
+8,0.5627616047859192,210.15121459960938,212.79592895507812,0.5558485984802246,219.98118591308594,222.5937957763672
+9,0.5461359620094299,209.7554473876953,212.32247924804688,0.6013195514678955,220.43801879882812,223.26425170898438

fold_0/model.bias_scaled.fold_0.ENCSR174GXG.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d5c6b7cc9ec629bf680f05e2dcd0f2dd6761aba83ced6a4c633581506d332158
+size 2691928

fold_0/model.bias_scaled.fold_0.ENCSR174GXG.tar

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:01f3e17e1fd522973b6ef983922f9dba0e6ff534f6277ebedb49db0ea2a5e318
+size 1198080

fold_0/model.chrombpnet.fold_0.ENCSR174GXG.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ec0152c18e3455ba1366bb62f8c80875489209dd579330bc64e49a500c0171da
+size 77538952

fold_0/model.chrombpnet.fold_0.ENCSR174GXG.tar

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7d9bcb75e70a868176cb1c7b8144ca0839b7cb2b044c623841c312de3a1d7dc9
+size 27525120

fold_0/model.chrombpnet_nobias.fold_0.ENCSR174GXG.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0ce54cc3a09c237d4fbe216167f57c1baa06f5ae6ed4c29f77971d021d9e369b
+size 25582648

fold_0/model.chrombpnet_nobias.fold_0.ENCSR174GXG.tar

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:896c86280f3f1a2ca9f3231f4ae76d65615567422ce95c32de69dad5d9d9dd66
+size 26060800

fold_1/logs.models.fold_1.ENCSR174GXG/logfile.modelling.fold_1.ENCSR174GXG.args.json

@@ -0,0 +1,50 @@
+{
+    "cmd": "pipeline",
+    "genome": "/oak/stanford/groups/akundaje/ziwei75/atac_seq_pipeline/hg38/GRCh38_no_alt_analysis_set_GCA_000001405.15.fasta",
+    "chrom_sizes": "/oak/stanford/groups/akundaje/ziwei75/atac_seq_pipeline/hg38/GRCh38_EBV.chrom.sizes.tsv",
+    "input_bam_file": "/oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/DNASE/ENCSR174GXG/preprocessing/bigWigs/ENCSR174GXG.bigWig",
+    "input_fragment_file": null,
+    "input_tagalign_file": null,
+    "output_dir": "/oak/stanford/groups/akundaje/vhecht/chromatin_atlas_bias_corrected/DNASE_model/ENCSR174GXG/fold_1",
+    "data_type": "DNASE",
+    "peaks": "/oak/stanford/groups/akundaje/vhecht/chromatin_atlas_bias_corrected/DNASE_model/ENCSR174GXG/fold_1/auxiliary/filtered.peaks.bed",
+    "nonpeaks": "/oak/stanford/groups/akundaje/vhecht/chromatin_atlas_bias_corrected/DNASE_model/ENCSR174GXG/fold_1/auxiliary/filtered.nonpeaks.bed",
+    "chr_fold_path": "/oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/splits/fold_1.json",
+    "outlier_threshold": 0.9999,
+    "ATAC_ref_path": null,
+    "DNASE_ref_path": null,
+    "num_samples": 10000,
+    "inputlen": 2114,
+    "outputlen": 1000,
+    "seed": 1234,
+    "epochs": 50,
+    "early_stop": 5,
+    "learning_rate": 0.001,
+    "trackables": [
+        "logcount_predictions_loss",
+        "loss",
+        "logits_profile_predictions_loss",
+        "val_logcount_predictions_loss",
+        "val_loss",
+        "val_logits_profile_predictions_loss"
+    ],
+    "architecture_from_file": "/home/users/vhecht/chrombpnet/chrombpnet/chrombpnet/training/models/chrombpnet_with_bias_model.py",
+    "file_prefix": null,
+    "html_prefix": "./",
+    "bsort": false,
+    "tmpdir": null,
+    "no_st": false,
+    "bias_model_path": "/oak/stanford/groups/akundaje/ziwei75/chromatin_atlas_bias/DNase_bias_model/filtered_negatives_models/ENCSR174GXG/models/bias.h5",
+    "negative_sampling_ratio": 0.1,
+    "filters": 512,
+    "n_dilation_layers": 8,
+    "max_jitter": 500,
+    "batch_size": 64,
+    "output_prefix": "/oak/stanford/groups/akundaje/vhecht/chromatin_atlas_bias_corrected/DNASE_model/ENCSR174GXG/fold_1/models/chrombpnet",
+    "bigwig": "/oak/stanford/groups/akundaje/vhecht/chromatin_atlas_bias_corrected/DNASE_model/ENCSR174GXG/fold_1/auxiliary/data_unstranded.bw",
+    "plus_shift": null,
+    "minus_shift": null,
+    "chr": "chr12",
+    "pwm_width": 24,
+    "params": "/oak/stanford/groups/akundaje/vhecht/chromatin_atlas_bias_corrected/DNASE_model/ENCSR174GXG/fold_1/logs/chrombpnet_model_params.tsv"
+}

fold_1/logs.models.fold_1.ENCSR174GXG/logfile.modelling.fold_1.ENCSR174GXG.chrombpnet_data_params.tsv

@@ -0,0 +1,3 @@
+counts_sum_min_thresh	0.0
+counts_sum_max_thresh	1187.03
+trainings_pts_post_thresh	172915

fold_1/logs.models.fold_1.ENCSR174GXG/logfile.modelling.fold_1.ENCSR174GXG.chrombpnet_model_params.tsv

@@ -0,0 +1,9 @@
+counts_loss_weight	4.7
+filters	512
+n_dil_layers	8
+bias_model_path	/oak/stanford/groups/akundaje/vhecht/chromatin_atlas_bias_corrected/DNASE_model/ENCSR174GXG/fold_1/models/bias_model_scaled.h5
+inputlen	2114
+outputlen	1000
+max_jitter	500
+chr_fold_path	/oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/splits/fold_1.json
+negative_sampling_ratio	0.1

fold_1/logs.models.fold_1.ENCSR174GXG/logfile.modelling.fold_1.ENCSR174GXG.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
+0,2.4292140007019043,225.99847412109375,237.4160614013672,0.9040287733078003,255.18353271484375,259.4322509765625
+1,0.7990382313728333,217.05984497070312,220.81541442871094,0.7361904978752136,249.61203002929688,253.0720672607422
+2,0.7293197512626648,214.8961639404297,218.3244171142578,0.7370749711990356,248.17852783203125,251.64283752441406
+3,0.6765596270561218,213.40994262695312,216.58963012695312,0.6177551746368408,246.57762145996094,249.4808807373047
+4,0.6421940326690674,212.21185302734375,215.23043823242188,0.6156035661697388,246.37167358398438,249.26510620117188
+5,0.6073722243309021,211.5197296142578,214.3745574951172,0.6287181973457336,246.0201873779297,248.97528076171875
+6,0.5924211740493774,210.553955078125,213.3387451171875,0.6000063419342041,245.94293212890625,248.7626190185547
+7,0.5666758418083191,209.92391967773438,212.58724975585938,0.591720461845398,245.6487274169922,248.42987060546875
+8,0.5446022152900696,209.1760711669922,211.73558044433594,0.5395278930664062,245.33273315429688,247.8685302734375
+9,0.5356770753860474,208.4800567626953,210.99801635742188,0.5286213755607605,244.25277709960938,246.73721313476562
+10,0.5208098292350769,207.8638916015625,210.3115997314453,0.5465372800827026,247.00704956054688,249.57582092285156
+11,0.5100057125091553,207.3852081298828,209.78184509277344,0.6696978807449341,246.54978942871094,249.697509765625
+12,0.5013205409049988,206.9498748779297,209.30593872070312,0.5265597105026245,247.077392578125,249.5522918701172
+13,0.4918968379497528,206.49505615234375,208.80711364746094,0.5783799290657043,248.35507202148438,251.07359313964844
+14,0.4796728789806366,205.8839111328125,208.1383514404297,0.6069904565811157,247.32212829589844,250.17486572265625

fold_1/model.bias_scaled.fold_1.ENCSR174GXG.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0e8db2a90a71bee702553976b813dc5bbd7123968f58d0611a751da0e6df0b3f
+size 2691928

fold_1/model.bias_scaled.fold_1.ENCSR174GXG.tar

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6aa85d9c1fb52522b36f81e46f09ef0b885ab14d24ba4d55803c6955d7a16797
+size 1198080

fold_1/model.chrombpnet.fold_1.ENCSR174GXG.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6020bed9166e49c6dcbbd4471f2d31e41773cecab0c75998933c1a3ca649d5b2
+size 77538840

fold_1/model.chrombpnet.fold_1.ENCSR174GXG.tar

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:34593b4829f38451bfecfe8cd5355fbb18e7bf98cc659e4b60f40156bc400364
+size 27525120

fold_1/model.chrombpnet_nobias.fold_1.ENCSR174GXG.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f42a0a17be8eb4e8b04dfba76bd79395cd04adce90bdee553160acafb43bae53
+size 25582648

fold_1/model.chrombpnet_nobias.fold_1.ENCSR174GXG.tar

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bef282ed6a10ab70c9d09a18cef0a34625b78647b29d1d40246d67594085aab6
+size 26060800

fold_2/logs.models.fold_2.ENCSR174GXG/logfile.modelling.fold_2.ENCSR174GXG.args.json

@@ -0,0 +1,50 @@
+{
+    "cmd": "pipeline",
+    "genome": "/oak/stanford/groups/akundaje/ziwei75/atac_seq_pipeline/hg38/GRCh38_no_alt_analysis_set_GCA_000001405.15.fasta",
+    "chrom_sizes": "/oak/stanford/groups/akundaje/ziwei75/atac_seq_pipeline/hg38/GRCh38_EBV.chrom.sizes.tsv",
+    "input_bam_file": "/oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/DNASE/ENCSR174GXG/preprocessing/bigWigs/ENCSR174GXG.bigWig",
+    "input_fragment_file": null,
+    "input_tagalign_file": null,
+    "output_dir": "/oak/stanford/groups/akundaje/vhecht/chromatin_atlas_bias_corrected/DNASE_model/ENCSR174GXG/fold_2",
+    "data_type": "DNASE",
+    "peaks": "/oak/stanford/groups/akundaje/vhecht/chromatin_atlas_bias_corrected/DNASE_model/ENCSR174GXG/fold_2/auxiliary/filtered.peaks.bed",
+    "nonpeaks": "/oak/stanford/groups/akundaje/vhecht/chromatin_atlas_bias_corrected/DNASE_model/ENCSR174GXG/fold_2/auxiliary/filtered.nonpeaks.bed",
+    "chr_fold_path": "/oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/splits/fold_2.json",
+    "outlier_threshold": 0.9999,
+    "ATAC_ref_path": null,
+    "DNASE_ref_path": null,
+    "num_samples": 10000,
+    "inputlen": 2114,
+    "outputlen": 1000,
+    "seed": 1234,
+    "epochs": 50,
+    "early_stop": 5,
+    "learning_rate": 0.001,
+    "trackables": [
+        "logcount_predictions_loss",
+        "loss",
+        "logits_profile_predictions_loss",
+        "val_logcount_predictions_loss",
+        "val_loss",
+        "val_logits_profile_predictions_loss"
+    ],
+    "architecture_from_file": "/home/users/vhecht/chrombpnet/chrombpnet/chrombpnet/training/models/chrombpnet_with_bias_model.py",
+    "file_prefix": null,
+    "html_prefix": "./",
+    "bsort": false,
+    "tmpdir": null,
+    "no_st": false,
+    "bias_model_path": "/oak/stanford/groups/akundaje/ziwei75/chromatin_atlas_bias/DNase_bias_model/filtered_negatives_models/ENCSR174GXG/models/bias.h5",
+    "negative_sampling_ratio": 0.1,
+    "filters": 512,
+    "n_dilation_layers": 8,
+    "max_jitter": 500,
+    "batch_size": 64,
+    "output_prefix": "/oak/stanford/groups/akundaje/vhecht/chromatin_atlas_bias_corrected/DNASE_model/ENCSR174GXG/fold_2/models/chrombpnet",
+    "bigwig": "/oak/stanford/groups/akundaje/vhecht/chromatin_atlas_bias_corrected/DNASE_model/ENCSR174GXG/fold_2/auxiliary/data_unstranded.bw",
+    "plus_shift": null,
+    "minus_shift": null,
+    "chr": "chr22",
+    "pwm_width": 24,
+    "params": "/oak/stanford/groups/akundaje/vhecht/chromatin_atlas_bias_corrected/DNASE_model/ENCSR174GXG/fold_2/logs/chrombpnet_model_params.tsv"
+}

fold_2/logs.models.fold_2.ENCSR174GXG/logfile.modelling.fold_2.ENCSR174GXG.chrombpnet_data_params.tsv

@@ -0,0 +1,3 @@
+counts_sum_min_thresh	0.0
+counts_sum_max_thresh	1186.05
+trainings_pts_post_thresh	177828

fold_2/logs.models.fold_2.ENCSR174GXG/logfile.modelling.fold_2.ENCSR174GXG.chrombpnet_model_params.tsv

@@ -0,0 +1,9 @@
+counts_loss_weight	4.7
+filters	512
+n_dil_layers	8
+bias_model_path	/oak/stanford/groups/akundaje/vhecht/chromatin_atlas_bias_corrected/DNASE_model/ENCSR174GXG/fold_2/models/bias_model_scaled.h5
+inputlen	2114
+outputlen	1000
+max_jitter	500
+chr_fold_path	/oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/splits/fold_2.json
+negative_sampling_ratio	0.1

fold_2/logs.models.fold_2.ENCSR174GXG/logfile.modelling.fold_2.ENCSR174GXG.epoch_loss.csv

@@ -0,0 +1,12 @@
+epoch,logcount_predictions_loss,logits_profile_predictions_loss,loss,val_logcount_predictions_loss,val_logits_profile_predictions_loss,val_loss
+0,1.461429476737976,224.5366973876953,231.40516662597656,0.8690145015716553,225.90065002441406,229.98512268066406
+1,0.7535123825073242,216.532470703125,220.07421875,0.6573521494865417,223.11961364746094,226.20912170410156
+2,0.689079999923706,214.69964599609375,217.93838500976562,0.6374906301498413,220.6950225830078,223.69117736816406
+3,0.6484922766685486,213.26918029785156,216.31687927246094,0.644101619720459,221.38438415527344,224.41156005859375
+4,0.616865336894989,212.54751586914062,215.44662475585938,0.5916975140571594,221.72177124023438,224.5027313232422
+5,0.589046061038971,211.61001586914062,214.3784942626953,0.5888481736183167,220.1258544921875,222.8935089111328
+6,0.5668309926986694,210.71722412109375,213.38137817382812,0.6318099498748779,220.9106903076172,223.8802032470703
+7,0.5508906245231628,210.11590576171875,212.70474243164062,0.6419588327407837,220.7510528564453,223.76837158203125
+8,0.5360237956047058,209.83746337890625,212.3564910888672,0.5728834271430969,220.72535705566406,223.41778564453125
+9,0.5224805474281311,208.71173095703125,211.1677703857422,0.5696813464164734,222.55691528320312,225.23443603515625
+10,0.5089629292488098,208.50668334960938,210.89903259277344,0.5748754143714905,222.26573181152344,224.96774291992188

fold_2/model.bias_scaled.fold_2.ENCSR174GXG.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:68aaad3088f98536c99924fee27c2e5b991f72c383a3a00d102e554289d0699b
+size 2691928

fold_2/model.bias_scaled.fold_2.ENCSR174GXG.tar

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:801bd4290bf9b1eaaab46ea5ecd0615c27b9c2d789e543147762ce6fc312c94c
+size 1198080

fold_2/model.chrombpnet.fold_2.ENCSR174GXG.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3f7071c70672c0b8714143b57b3985e49940308cdf1e748ec325767610e8a970
+size 77538840

fold_2/model.chrombpnet.fold_2.ENCSR174GXG.tar

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4cbc794a5e16eac5f8f5650d034c493c046fb95d8aaf3d6edaa6de5d4232ba43
+size 27525120

fold_2/model.chrombpnet_nobias.fold_2.ENCSR174GXG.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:624111e5c310f01165ef8ab9d5a7d749a3fb067dacf983b51832c1df3f639e5a
+size 25582648

fold_2/model.chrombpnet_nobias.fold_2.ENCSR174GXG.tar

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ac3142ca601bbcfb940ab3006c2dbc187e7ba5b07cb0f1fec27a3ac8c3696da6
+size 26060800

fold_3/logs.models.fold_3.ENCSR174GXG/logfile.modelling.fold_3.ENCSR174GXG.args.json

@@ -0,0 +1,50 @@
+{
+    "cmd": "pipeline",
+    "genome": "/oak/stanford/groups/akundaje/ziwei75/atac_seq_pipeline/hg38/GRCh38_no_alt_analysis_set_GCA_000001405.15.fasta",
+    "chrom_sizes": "/oak/stanford/groups/akundaje/ziwei75/atac_seq_pipeline/hg38/GRCh38_EBV.chrom.sizes.tsv",
+    "input_bam_file": "/oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/DNASE/ENCSR174GXG/preprocessing/bigWigs/ENCSR174GXG.bigWig",
+    "input_fragment_file": null,
+    "input_tagalign_file": null,
+    "output_dir": "/oak/stanford/groups/akundaje/vhecht/chromatin_atlas_bias_corrected/DNASE_model/ENCSR174GXG/fold_3",
+    "data_type": "DNASE",
+    "peaks": "/oak/stanford/groups/akundaje/vhecht/chromatin_atlas_bias_corrected/DNASE_model/ENCSR174GXG/fold_3/auxiliary/filtered.peaks.bed",
+    "nonpeaks": "/oak/stanford/groups/akundaje/vhecht/chromatin_atlas_bias_corrected/DNASE_model/ENCSR174GXG/fold_3/auxiliary/filtered.nonpeaks.bed",
+    "chr_fold_path": "/oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/splits/fold_3.json",
+    "outlier_threshold": 0.9999,
+    "ATAC_ref_path": null,
+    "DNASE_ref_path": null,
+    "num_samples": 10000,
+    "inputlen": 2114,
+    "outputlen": 1000,
+    "seed": 1234,
+    "epochs": 50,
+    "early_stop": 5,
+    "learning_rate": 0.001,
+    "trackables": [
+        "logcount_predictions_loss",
+        "loss",
+        "logits_profile_predictions_loss",
+        "val_logcount_predictions_loss",
+        "val_loss",
+        "val_logits_profile_predictions_loss"
+    ],
+    "architecture_from_file": "/home/users/vhecht/chrombpnet/chrombpnet/chrombpnet/training/models/chrombpnet_with_bias_model.py",
+    "file_prefix": null,
+    "html_prefix": "./",
+    "bsort": false,
+    "tmpdir": null,
+    "no_st": false,
+    "bias_model_path": "/oak/stanford/groups/akundaje/ziwei75/chromatin_atlas_bias/DNase_bias_model/filtered_negatives_models/ENCSR174GXG/models/bias.h5",
+    "negative_sampling_ratio": 0.1,
+    "filters": 512,
+    "n_dilation_layers": 8,
+    "max_jitter": 500,
+    "batch_size": 64,
+    "output_prefix": "/oak/stanford/groups/akundaje/vhecht/chromatin_atlas_bias_corrected/DNASE_model/ENCSR174GXG/fold_3/models/chrombpnet",
+    "bigwig": "/oak/stanford/groups/akundaje/vhecht/chromatin_atlas_bias_corrected/DNASE_model/ENCSR174GXG/fold_3/auxiliary/data_unstranded.bw",
+    "plus_shift": null,
+    "minus_shift": null,
+    "chr": "chr6",
+    "pwm_width": 24,
+    "params": "/oak/stanford/groups/akundaje/vhecht/chromatin_atlas_bias_corrected/DNASE_model/ENCSR174GXG/fold_3/logs/chrombpnet_model_params.tsv"
+}

fold_3/logs.models.fold_3.ENCSR174GXG/logfile.modelling.fold_3.ENCSR174GXG.chrombpnet_data_params.tsv

@@ -0,0 +1,3 @@
+counts_sum_min_thresh	0.0
+counts_sum_max_thresh	1220.9
+trainings_pts_post_thresh	171462

fold_3/logs.models.fold_3.ENCSR174GXG/logfile.modelling.fold_3.ENCSR174GXG.chrombpnet_model_params.tsv

@@ -0,0 +1,9 @@
+counts_loss_weight	4.7
+filters	512
+n_dil_layers	8
+bias_model_path	/oak/stanford/groups/akundaje/vhecht/chromatin_atlas_bias_corrected/DNASE_model/ENCSR174GXG/fold_3/models/bias_model_scaled.h5
+inputlen	2114
+outputlen	1000
+max_jitter	500
+chr_fold_path	/oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/splits/fold_3.json
+negative_sampling_ratio	0.1

fold_3/logs.models.fold_3.ENCSR174GXG/logfile.modelling.fold_3.ENCSR174GXG.epoch_loss.csv

@@ -0,0 +1,10 @@
+epoch,logcount_predictions_loss,logits_profile_predictions_loss,loss,val_logcount_predictions_loss,val_logits_profile_predictions_loss,val_loss
+0,1.4941494464874268,225.23155212402344,232.2536163330078,0.7609269618988037,232.32106018066406,235.89739990234375
+1,0.7567368745803833,216.7832794189453,220.33982849121094,0.7262336015701294,230.5752716064453,233.98866271972656
+2,0.685114860534668,214.7761688232422,217.99627685546875,0.6436171531677246,228.52389526367188,231.54888916015625
+3,0.6482933759689331,213.49330139160156,216.54025268554688,0.6450005769729614,228.3138885498047,231.34547424316406
+4,0.6099511384963989,212.52914428710938,215.39602661132812,0.6306595802307129,229.865966796875,232.83009338378906
+5,0.5880255103111267,211.7587890625,214.52239990234375,0.5490193963050842,229.06936645507812,231.6495361328125
+6,0.564172089099884,211.15614318847656,213.80770874023438,0.5763393044471741,229.53001403808594,232.2388916015625
+7,0.5437242984771729,210.34970092773438,212.9051055908203,0.5379306077957153,230.0176544189453,232.54586791992188
+8,0.5305664539337158,209.44053649902344,211.9342803955078,0.5810309648513794,229.63662719726562,232.36741638183594

fold_3/model.bias_scaled.fold_3.ENCSR174GXG.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1c6b61a4ca7613bb7561df817c7b25b3aba89d855e06534d07fd71cffcf05996
+size 2691928

fold_3/model.bias_scaled.fold_3.ENCSR174GXG.tar

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2822d8967a72b672c3d71388acdc8d1f98e49421a46d140fcfb69731e6538169
+size 1198080

fold_3/model.chrombpnet.fold_3.ENCSR174GXG.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ae5ab80bd18720d60568c95bfd50992a89bec4733b50a8cd25cf864cb9121e96
+size 77538840

fold_3/model.chrombpnet.fold_3.ENCSR174GXG.tar

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:38b94d22eada7c28870befa29a8cf619c913bc65a67ce73446dc383be7665143
+size 27525120

fold_3/model.chrombpnet_nobias.fold_3.ENCSR174GXG.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c46e8ba33291cc7a3f96415edec77d7473184e29ee849700b4821c6fd9013c0d
+size 25582648

fold_3/model.chrombpnet_nobias.fold_3.ENCSR174GXG.tar

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8dc1f0ec9e541657b6ef18f397b89c70a7dd1a1978facfcc385b0127f112b591
+size 26060800

fold_4/logs.models.fold_4.ENCSR174GXG/logfile.modelling.fold_4.ENCSR174GXG.args.json

@@ -0,0 +1,50 @@
+{
+    "cmd": "pipeline",
+    "genome": "/oak/stanford/groups/akundaje/ziwei75/atac_seq_pipeline/hg38/GRCh38_no_alt_analysis_set_GCA_000001405.15.fasta",
+    "chrom_sizes": "/oak/stanford/groups/akundaje/ziwei75/atac_seq_pipeline/hg38/GRCh38_EBV.chrom.sizes.tsv",
+    "input_bam_file": "/oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/DNASE/ENCSR174GXG/preprocessing/bigWigs/ENCSR174GXG.bigWig",
+    "input_fragment_file": null,
+    "input_tagalign_file": null,
+    "output_dir": "/oak/stanford/groups/akundaje/vhecht/chromatin_atlas_bias_corrected/DNASE_model/ENCSR174GXG/fold_4",
+    "data_type": "DNASE",
+    "peaks": "/oak/stanford/groups/akundaje/vhecht/chromatin_atlas_bias_corrected/DNASE_model/ENCSR174GXG/fold_4/auxiliary/filtered.peaks.bed",
+    "nonpeaks": "/oak/stanford/groups/akundaje/vhecht/chromatin_atlas_bias_corrected/DNASE_model/ENCSR174GXG/fold_4/auxiliary/filtered.nonpeaks.bed",
+    "chr_fold_path": "/oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/splits/fold_4.json",
+    "outlier_threshold": 0.9999,
+    "ATAC_ref_path": null,
+    "DNASE_ref_path": null,
+    "num_samples": 10000,
+    "inputlen": 2114,
+    "outputlen": 1000,
+    "seed": 1234,
+    "epochs": 50,
+    "early_stop": 5,
+    "learning_rate": 0.001,
+    "trackables": [
+        "logcount_predictions_loss",
+        "loss",
+        "logits_profile_predictions_loss",
+        "val_logcount_predictions_loss",
+        "val_loss",
+        "val_logits_profile_predictions_loss"
+    ],
+    "architecture_from_file": "/home/users/vhecht/chrombpnet/chrombpnet/chrombpnet/training/models/chrombpnet_with_bias_model.py",
+    "file_prefix": null,
+    "html_prefix": "./",
+    "bsort": false,
+    "tmpdir": null,
+    "no_st": false,
+    "bias_model_path": "/oak/stanford/groups/akundaje/ziwei75/chromatin_atlas_bias/DNase_bias_model/filtered_negatives_models/ENCSR174GXG/models/bias.h5",
+    "negative_sampling_ratio": 0.1,
+    "filters": 512,
+    "n_dilation_layers": 8,
+    "max_jitter": 500,
+    "batch_size": 64,
+    "output_prefix": "/oak/stanford/groups/akundaje/vhecht/chromatin_atlas_bias_corrected/DNASE_model/ENCSR174GXG/fold_4/models/chrombpnet",
+    "bigwig": "/oak/stanford/groups/akundaje/vhecht/chromatin_atlas_bias_corrected/DNASE_model/ENCSR174GXG/fold_4/auxiliary/data_unstranded.bw",
+    "plus_shift": null,
+    "minus_shift": null,
+    "chr": "chr10",
+    "pwm_width": 24,
+    "params": "/oak/stanford/groups/akundaje/vhecht/chromatin_atlas_bias_corrected/DNASE_model/ENCSR174GXG/fold_4/logs/chrombpnet_model_params.tsv"
+}

fold_4/logs.models.fold_4.ENCSR174GXG/logfile.modelling.fold_4.ENCSR174GXG.chrombpnet_data_params.tsv

@@ -0,0 +1,3 @@
+counts_sum_min_thresh	0.0
+counts_sum_max_thresh	1128.31
+trainings_pts_post_thresh	177334

fold_4/logs.models.fold_4.ENCSR174GXG/logfile.modelling.fold_4.ENCSR174GXG.chrombpnet_model_params.tsv

@@ -0,0 +1,9 @@
+counts_loss_weight	4.7
+filters	512
+n_dil_layers	8
+bias_model_path	/oak/stanford/groups/akundaje/vhecht/chromatin_atlas_bias_corrected/DNASE_model/ENCSR174GXG/fold_4/models/bias_model_scaled.h5
+inputlen	2114
+outputlen	1000
+max_jitter	500
+chr_fold_path	/oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/splits/fold_4.json
+negative_sampling_ratio	0.1

fold_4/logs.models.fold_4.ENCSR174GXG/logfile.modelling.fold_4.ENCSR174GXG.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
+0,1.7137771844863892,224.47703552246094,232.5320281982422,0.750210702419281,227.7150421142578,231.24102783203125
+1,0.758743166923523,215.42372131347656,218.98977661132812,0.7252897620201111,223.99569702148438,227.40467834472656
+2,0.6907864809036255,213.64820861816406,216.89471435546875,0.6572441458702087,223.17373657226562,226.26275634765625
+3,0.6406905055046082,212.2106170654297,215.22142028808594,0.6275631189346313,222.34603881835938,225.29551696777344
+4,0.6020628809928894,211.49468994140625,214.32447814941406,0.595069169998169,223.26821899414062,226.06509399414062
+5,0.5816932320594788,210.23910522460938,212.97280883789062,0.5768014788627625,223.97035217285156,226.68118286132812
+6,0.5621258020401001,209.6497039794922,212.29150390625,0.7386547327041626,223.57920837402344,227.05093383789062
+7,0.5459752678871155,209.02369689941406,211.58973693847656,0.5476324558258057,222.67218017578125,225.24598693847656
+8,0.5232372879981995,208.4209442138672,210.8799591064453,0.5488978624343872,223.17660522460938,225.75656127929688
+9,0.5062418580055237,207.6410369873047,210.02020263671875,0.5921849012374878,223.47036743164062,226.25364685058594
+10,0.49702349305152893,207.24859619140625,209.5845947265625,0.581825315952301,222.65658569335938,225.3909912109375
+11,0.4892026484012604,206.8651123046875,209.16456604003906,0.5541087985038757,222.15585327148438,224.76011657714844
+12,0.4746726453304291,206.20872497558594,208.4397430419922,0.5332787036895752,224.51992797851562,227.0263214111328
+13,0.46927058696746826,205.72718811035156,207.9326629638672,0.5851246118545532,224.1490020751953,226.8990020751953
+14,0.45855915546417236,205.1465606689453,207.30174255371094,0.5513436794281006,224.19854736328125,226.78977966308594
+15,0.45219141244888306,204.8529815673828,206.9781494140625,0.5638715624809265,224.01527404785156,226.66546630859375
+16,0.44819700717926025,204.41673278808594,206.52317810058594,0.5711077451705933,223.71571350097656,226.3999786376953