Upload folder using huggingface_hub

README.md

@@ -0,0 +1,120 @@
+---
+license: mit
+library_name: chrombpnet
+tags:
+  - encode
+  - chrombpnet
+  - chromatin-accessibility
+  - DNASE
+  - endothelial
+  - 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 lung microvascular endothelial cell (ENCSR000EOD)
+- Model: ChromBPNet
+- Assay: DNASE-seq
+- Experiment: [ENCSR000EOD](https://www.encodeproject.org/experiments/ENCSR000EOD/)
+- Model annotation: [ENCSR213BXO](https://www.encodeproject.org/annotations/ENCSR213BXO/)
+- Biosample: lung microvascular endothelial cell (Full name: Homo sapiens lung microvascular endothelial cell female)
+- Cell slim(s): epithelial-cell,endothelial-cell
+- Organ slim(s): epithelium,lung,vasculature,blood-vessel
+- Developmental slim(s): mesoderm,endoderm
+- System slim(s): circulatory-system,respiratory-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.ENCSR000EOD/logfile.modelling.fold_0.ENCSR000EOD.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/ENCSR000EOD/preprocessing/bigWigs/ENCSR000EOD.bigWig",
+    "output_dir": "/oak/stanford/groups/akundaje/ziwei75/chromatin_atlas_bias/DNase_model/bias_threshold_0.8/ENCSR000EOD/fold0/",
+    "data_type": "DNASE",
+    "peaks": "/oak/stanford/groups/akundaje/ziwei75/chromatin_atlas_bias/DNase_model/bias_threshold_0.8/ENCSR000EOD/fold0/auxiliary/filtered.peaks.bed",
+    "nonpeaks": "/oak/stanford/groups/akundaje/ziwei75/chromatin_atlas_bias/DNase_model/bias_threshold_0.8/ENCSR000EOD/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/bias_threshold_0.8/ENCSR000EOD/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_threshold_0.8/ENCSR000EOD/fold0/models/chrombpnet",
+    "chr": "chr8",
+    "pwm_width": 24,
+    "params": "/oak/stanford/groups/akundaje/ziwei75/chromatin_atlas_bias/DNase_model/bias_threshold_0.8/ENCSR000EOD/fold0/logs/chrombpnet_model_params.tsv"
+}

fold_0/logs.models.fold_0.ENCSR000EOD/logfile.modelling.fold_0.ENCSR000EOD.bias_formatting.stdout.txt

@@ -0,0 +1 @@
+Converting /oak/stanford/groups/akundaje/ziwei75/chromatin_atlas_bias/DNase_model/bias_threshold_0.8/ENCSR000EOD/fold0/models/bias_model_scaled.h5 to /oak/stanford/groups/akundaje/vhecht/chromatin-atlas-2022/DNASE/ENCSR000EOD/fold_0/new_model_format/bias_model_scaled.tar with get_new_tf_model_format.py

fold_0/logs.models.fold_0.ENCSR000EOD/logfile.modelling.fold_0.ENCSR000EOD.chrombpnet_data_params.tsv

@@ -0,0 +1,3 @@
+counts_sum_min_thresh	0.0
+counts_sum_max_thresh	30314.12
+trainings_pts_post_thresh	169989

fold_0/logs.models.fold_0.ENCSR000EOD/logfile.modelling.fold_0.ENCSR000EOD.chrombpnet_formatting.stdout.txt

@@ -0,0 +1 @@
+Converting /oak/stanford/groups/akundaje/ziwei75/chromatin_atlas_bias/DNase_model/bias_threshold_0.8/ENCSR000EOD/fold0/models/chrombpnet.h5 to /oak/stanford/groups/akundaje/vhecht/chromatin-atlas-2022/DNASE/ENCSR000EOD/fold_0/new_model_format/chrombpnet.tar with get_new_tf_model_format.py

fold_0/logs.models.fold_0.ENCSR000EOD/logfile.modelling.fold_0.ENCSR000EOD.chrombpnet_model_params.tsv

@@ -0,0 +1,9 @@
+counts_loss_weight	47.5
+filters	512
+n_dil_layers	8
+bias_model_path	/oak/stanford/groups/akundaje/ziwei75/chromatin_atlas_bias/DNase_model/bias_threshold_0.8/ENCSR000EOD/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.ENCSR000EOD/logfile.modelling.fold_0.ENCSR000EOD.chrombpnet_no_bias_formatting.stdout.txt

@@ -0,0 +1 @@
+Converting /oak/stanford/groups/akundaje/ziwei75/chromatin_atlas_bias/DNase_model/bias_threshold_0.8/ENCSR000EOD/fold0/models/chrombpnet_nobias.h5 to /oak/stanford/groups/akundaje/vhecht/chromatin-atlas-2022/DNASE/ENCSR000EOD/fold_0/new_model_format/chrombpnet_nobias.tar with get_new_tf_model_format.py

fold_0/logs.models.fold_0.ENCSR000EOD/logfile.modelling.fold_0.ENCSR000EOD.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
+0,4.185336112976074,1382.6470947265625,1581.449951171875,1.165044903755188,1259.1748046875,1314.5140380859375
+1,1.1484121084213257,1223.123046875,1277.6729736328125,1.003860592842102,1196.5390625,1244.22265625
+2,1.0647081136703491,1188.9598388671875,1239.535400390625,1.0124839544296265,1194.3665771484375,1242.4595947265625
+3,1.0183923244476318,1164.0020751953125,1212.3751220703125,0.9207968711853027,1182.7032470703125,1226.43994140625
+4,0.9576426148414612,1144.4345703125,1189.9227294921875,0.8815271258354187,1167.9144287109375,1209.7867431640625
+5,0.9265061020851135,1128.0765380859375,1172.0849609375,0.8988475203514099,1177.4979248046875,1220.1937255859375
+6,0.8907192945480347,1112.616943359375,1154.926513671875,0.8533108830451965,1162.39990234375,1202.93212890625
+7,0.8659560084342957,1103.941162109375,1145.0751953125,0.8437073826789856,1140.0509033203125,1180.126953125
+8,0.8431549668312073,1095.5076904296875,1135.557373046875,0.9594011902809143,1170.0438232421875,1215.614990234375
+9,0.8215816020965576,1088.0631103515625,1127.0875244140625,0.832461953163147,1169.3455810546875,1208.8870849609375
+10,0.795839786529541,1080.6229248046875,1118.4267578125,0.8330707550048828,1176.558349609375,1216.12890625
+11,0.7755402326583862,1074.4857177734375,1111.3233642578125,0.9006442427635193,1147.7386474609375,1190.5186767578125
+12,0.7581456899642944,1068.5130615234375,1104.52490234375,0.8528908491134644,1150.9385986328125,1191.4508056640625

fold_0/model.bias_scaled.fold_0.ENCSR000EOD.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:66801301748621270696dc7f1ddf04ae1d30bec53399cd3acc62bd0285826675
+size 2691928

fold_0/model.bias_scaled.fold_0.ENCSR000EOD.tar

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:10c2eb4226d4f3ee4b4b2b72cc5d64606819a2a76b668b601d01c866c64bca51
+size 1198080

fold_0/model.chrombpnet.fold_0.ENCSR000EOD.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:af4ee6a83e738daed6de081fee020ef06d30777d00de04ab53d0c92c4bcffdb1
+size 77538952

fold_0/model.chrombpnet.fold_0.ENCSR000EOD.tar

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fd25c830c7a4f6be4cef4e11c262ebb5a36c11d2a9e1f2518f5f79ef88f20fd2
+size 27525120

fold_0/model.chrombpnet_nobias.fold_0.ENCSR000EOD.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a5e044815f9419e67666c16b6ee8edab0a1f2ebb9c93e2449a1fd2817f4608ea
+size 25582648

fold_0/model.chrombpnet_nobias.fold_0.ENCSR000EOD.tar

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f634b7c6d7e469212eee43dca12caaa59c200bb116d77918fa3b5e9d63822dfb
+size 26060800

fold_1/logs.models.fold_1.ENCSR000EOD/logfile.modelling.fold_1.ENCSR000EOD.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/ENCSR000EOD/preprocessing/bigWigs/ENCSR000EOD.bigWig",
+    "input_fragment_file": null,
+    "input_tagalign_file": null,
+    "output_dir": "/oak/stanford/groups/akundaje/vhecht/chromatin_atlas_bias_corrected/DNASE_model/ENCSR000EOD/fold_1",
+    "data_type": "DNASE",
+    "peaks": "/oak/stanford/groups/akundaje/vhecht/chromatin_atlas_bias_corrected/DNASE_model/ENCSR000EOD/fold_1/auxiliary/filtered.peaks.bed",
+    "nonpeaks": "/oak/stanford/groups/akundaje/vhecht/chromatin_atlas_bias_corrected/DNASE_model/ENCSR000EOD/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/bias_threshold_0.8/ENCSR000EOD/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/ENCSR000EOD/fold_1/models/chrombpnet",
+    "bigwig": "/oak/stanford/groups/akundaje/vhecht/chromatin_atlas_bias_corrected/DNASE_model/ENCSR000EOD/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/ENCSR000EOD/fold_1/logs/chrombpnet_model_params.tsv"
+}

fold_1/logs.models.fold_1.ENCSR000EOD/logfile.modelling.fold_1.ENCSR000EOD.bias_formatting.stdout.txt

@@ -0,0 +1 @@
+Converting /oak/stanford/groups/akundaje/vhecht/chromatin_atlas_bias_corrected/DNASE_model/ENCSR000EOD/fold_1/models/bias_model_scaled.h5 to /oak/stanford/groups/akundaje/vhecht/chromatin-atlas-2022/DNASE/ENCSR000EOD/fold_1/new_model_format/bias_model_scaled.tar with get_new_tf_model_format.py

fold_1/logs.models.fold_1.ENCSR000EOD/logfile.modelling.fold_1.ENCSR000EOD.chrombpnet_data_params.tsv

@@ -0,0 +1,3 @@
+counts_sum_min_thresh	0.0
+counts_sum_max_thresh	30561.54
+trainings_pts_post_thresh	175240

fold_1/logs.models.fold_1.ENCSR000EOD/logfile.modelling.fold_1.ENCSR000EOD.chrombpnet_formatting.stdout.txt

@@ -0,0 +1 @@
+Converting /oak/stanford/groups/akundaje/vhecht/chromatin_atlas_bias_corrected/DNASE_model/ENCSR000EOD/fold_1/models/chrombpnet.h5 to /oak/stanford/groups/akundaje/vhecht/chromatin-atlas-2022/DNASE/ENCSR000EOD/fold_1/new_model_format/chrombpnet.tar with get_new_tf_model_format.py

fold_1/logs.models.fold_1.ENCSR000EOD/logfile.modelling.fold_1.ENCSR000EOD.chrombpnet_model_params.tsv

@@ -0,0 +1,9 @@
+counts_loss_weight	47.8
+filters	512
+n_dil_layers	8
+bias_model_path	/oak/stanford/groups/akundaje/vhecht/chromatin_atlas_bias_corrected/DNASE_model/ENCSR000EOD/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.ENCSR000EOD/logfile.modelling.fold_1.ENCSR000EOD.chrombpnet_no_bias_formatting.stdout.txt

@@ -0,0 +1 @@
+Converting /oak/stanford/groups/akundaje/vhecht/chromatin_atlas_bias_corrected/DNASE_model/ENCSR000EOD/fold_1/models/chrombpnet_nobias.h5 to /oak/stanford/groups/akundaje/vhecht/chromatin-atlas-2022/DNASE/ENCSR000EOD/fold_1/new_model_format/chrombpnet_nobias.tar with get_new_tf_model_format.py

fold_1/logs.models.fold_1.ENCSR000EOD/logfile.modelling.fold_1.ENCSR000EOD.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
+0,1.3046766519546509,1344.6702880859375,1407.033447265625,1.1152527332305908,1490.475830078125,1543.7840576171875
+1,1.0870506763458252,1188.8255615234375,1240.787353515625,1.0451105833053589,1404.6695556640625,1454.6248779296875
+2,1.0031086206436157,1153.9083251953125,1201.8564453125,0.9499503970146179,1422.6337890625,1468.0408935546875
+3,0.9509497284889221,1130.5294189453125,1175.9849853515625,0.9121850728988647,1388.5023193359375,1432.1058349609375
+4,0.9210560321807861,1111.4844970703125,1155.512451171875,0.8849051594734192,1403.3438720703125,1445.6419677734375
+5,0.8748050332069397,1099.915283203125,1141.732421875,0.9354947209358215,1353.985107421875,1398.7012939453125
+6,0.8453530669212341,1089.27734375,1129.6861572265625,0.8619661927223206,1380.6572265625,1421.8592529296875
+7,0.814285397529602,1078.4666748046875,1117.3909912109375,0.8871968388557434,1356.3681640625,1398.7760009765625
+8,0.7895246744155884,1073.3179931640625,1111.0565185546875,0.8507312536239624,1415.5189208984375,1456.1839599609375
+9,0.7770193219184875,1065.5975341796875,1102.7396240234375,0.8481398820877075,1375.58447265625,1416.1263427734375
+10,0.7608545422554016,1063.1458740234375,1099.5146484375,1.0171501636505127,1414.3614501953125,1462.9814453125

fold_1/model.bias_scaled.fold_1.ENCSR000EOD.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f4c9a8379a991f6d011173934c7185b3e7e0275bc8de44b9bbe48e981ad6f24f
+size 2691928

fold_1/model.bias_scaled.fold_1.ENCSR000EOD.tar

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:138c69bd3a75196c9698e49fb5ca32f953de61db5d9c46c1e2c35c9c9e78e328
+size 1198080

fold_1/model.chrombpnet.fold_1.ENCSR000EOD.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:816f1009660e0c9f964cdcd1952f0850d22a092084fa7ee8c304238771b602e7
+size 77538840

fold_1/model.chrombpnet.fold_1.ENCSR000EOD.tar

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d086b7b676e688a3ee20f3e28076066bacb6f0b19668c3c96169c16e08f3bc08
+size 27525120

fold_1/model.chrombpnet_nobias.fold_1.ENCSR000EOD.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b90f22efe6821a2d8f761e637a81fadc35b353204180953181a9b52aa66f2469
+size 25582648

fold_1/model.chrombpnet_nobias.fold_1.ENCSR000EOD.tar

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e2e5e62a9fa50afca215cd66b1eb0ba24f2cb727b046ecff32cf7791586d5e8b
+size 26060800

fold_2/logs.models.fold_2.ENCSR000EOD/logfile.modelling.fold_2.ENCSR000EOD.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/ENCSR000EOD/preprocessing/bigWigs/ENCSR000EOD.bigWig",
+    "input_fragment_file": null,
+    "input_tagalign_file": null,
+    "output_dir": "/oak/stanford/groups/akundaje/vhecht/chromatin_atlas_bias_corrected/DNASE_model/ENCSR000EOD/fold_2",
+    "data_type": "DNASE",
+    "peaks": "/oak/stanford/groups/akundaje/vhecht/chromatin_atlas_bias_corrected/DNASE_model/ENCSR000EOD/fold_2/auxiliary/filtered.peaks.bed",
+    "nonpeaks": "/oak/stanford/groups/akundaje/vhecht/chromatin_atlas_bias_corrected/DNASE_model/ENCSR000EOD/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/bias_threshold_0.8/ENCSR000EOD/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/ENCSR000EOD/fold_2/models/chrombpnet",
+    "bigwig": "/oak/stanford/groups/akundaje/vhecht/chromatin_atlas_bias_corrected/DNASE_model/ENCSR000EOD/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/ENCSR000EOD/fold_2/logs/chrombpnet_model_params.tsv"
+}

fold_2/logs.models.fold_2.ENCSR000EOD/logfile.modelling.fold_2.ENCSR000EOD.bias_formatting.stdout.txt

@@ -0,0 +1 @@
+Converting /oak/stanford/groups/akundaje/vhecht/chromatin_atlas_bias_corrected/DNASE_model/ENCSR000EOD/fold_2/models/bias_model_scaled.h5 to /oak/stanford/groups/akundaje/vhecht/chromatin-atlas-2022/DNASE/ENCSR000EOD/fold_2/new_model_format/bias_model_scaled.tar with get_new_tf_model_format.py

fold_2/logs.models.fold_2.ENCSR000EOD/logfile.modelling.fold_2.ENCSR000EOD.chrombpnet_data_params.tsv

@@ -0,0 +1,3 @@
+counts_sum_min_thresh	0.0
+counts_sum_max_thresh	29802.69
+trainings_pts_post_thresh	178536

fold_2/logs.models.fold_2.ENCSR000EOD/logfile.modelling.fold_2.ENCSR000EOD.chrombpnet_formatting.stdout.txt

@@ -0,0 +1 @@
+Converting /oak/stanford/groups/akundaje/vhecht/chromatin_atlas_bias_corrected/DNASE_model/ENCSR000EOD/fold_2/models/chrombpnet.h5 to /oak/stanford/groups/akundaje/vhecht/chromatin-atlas-2022/DNASE/ENCSR000EOD/fold_2/new_model_format/chrombpnet.tar with get_new_tf_model_format.py

fold_2/logs.models.fold_2.ENCSR000EOD/logfile.modelling.fold_2.ENCSR000EOD.chrombpnet_model_params.tsv

@@ -0,0 +1,9 @@
+counts_loss_weight	47.3
+filters	512
+n_dil_layers	8
+bias_model_path	/oak/stanford/groups/akundaje/vhecht/chromatin_atlas_bias_corrected/DNASE_model/ENCSR000EOD/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.ENCSR000EOD/logfile.modelling.fold_2.ENCSR000EOD.chrombpnet_no_bias_formatting.stdout.txt

@@ -0,0 +1 @@
+Converting /oak/stanford/groups/akundaje/vhecht/chromatin_atlas_bias_corrected/DNASE_model/ENCSR000EOD/fold_2/models/chrombpnet_nobias.h5 to /oak/stanford/groups/akundaje/vhecht/chromatin-atlas-2022/DNASE/ENCSR000EOD/fold_2/new_model_format/chrombpnet_nobias.tar with get_new_tf_model_format.py

fold_2/logs.models.fold_2.ENCSR000EOD/logfile.modelling.fold_2.ENCSR000EOD.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
+0,2.8265371322631836,1361.8953857421875,1495.5908203125,1.2636609077453613,1288.5081787109375,1348.2806396484375
+1,1.1071110963821411,1206.0045166015625,1258.37109375,1.1090525388717651,1220.463134765625,1272.92138671875
+2,1.024401307106018,1168.0367431640625,1216.4901123046875,1.011311411857605,1194.7625732421875,1242.5966796875
+3,0.9669870138168335,1144.87939453125,1190.6192626953125,0.9060859680175781,1200.213134765625,1243.0706787109375
+4,0.9280655980110168,1126.9595947265625,1170.857421875,0.8788361549377441,1209.5712890625,1251.1405029296875
+5,0.8842219114303589,1112.03857421875,1153.8604736328125,0.9220743775367737,1193.09912109375,1236.7132568359375
+6,0.859324038028717,1100.7933349609375,1141.43994140625,0.8239219784736633,1180.7872314453125,1219.759033203125
+7,0.8374284505844116,1091.28369140625,1130.89501953125,0.8650991320610046,1172.6309814453125,1213.5498046875
+8,0.8151019811630249,1084.52734375,1123.08349609375,0.8218944668769836,1156.675048828125,1195.550048828125
+9,0.7930280566215515,1078.9390869140625,1116.4498291015625,0.8185073733329773,1161.8922119140625,1200.608154296875
+10,0.7757435441017151,1072.684814453125,1109.378662109375,0.7981416583061218,1160.864501953125,1198.6170654296875
+11,0.7525548338890076,1064.983642578125,1100.579833984375,0.8608452081680298,1167.80126953125,1208.52001953125
+12,0.7373886108398438,1062.17041015625,1097.049560546875,0.8074741959571838,1160.972900390625,1199.1669921875
+13,0.7283893823623657,1058.018798828125,1092.4720458984375,0.8727598786354065,1180.974365234375,1222.255859375

fold_2/model.bias_scaled.fold_2.ENCSR000EOD.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d690994b6b5abaa60ec2da1b0b17fd1d3091c546faaf3795c7e2f04a0cb32093
+size 2691928

fold_2/model.bias_scaled.fold_2.ENCSR000EOD.tar

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a6634d52ba86d7ab708976ad2bfb3319dfc26d8b3e932d5fa6c6ed6a32b98e2d
+size 1198080

fold_2/model.chrombpnet.fold_2.ENCSR000EOD.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e376c3f33e0bf2d82616547f299ef05cd74b671a440c738e20577b60fd2ce8a3
+size 77538840

fold_2/model.chrombpnet.fold_2.ENCSR000EOD.tar

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d270393b50c6a04effd62d0c66339e24fe8e3bb3d381b84964d44ee2ed767807
+size 27525120

fold_2/model.chrombpnet_nobias.fold_2.ENCSR000EOD.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:699bbef584f7554b3fc037c8d198d77025a5ee80228171f0fabd5b96dfb9006f
+size 25582648

fold_2/model.chrombpnet_nobias.fold_2.ENCSR000EOD.tar

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3ce6240a84a39bbc642eab933eba456125597588226885ce7f95f1cb7c6d332f
+size 26060800

fold_3/logs.models.fold_3.ENCSR000EOD/logfile.modelling.fold_3.ENCSR000EOD.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/ENCSR000EOD/preprocessing/bigWigs/ENCSR000EOD.bigWig",
+    "input_fragment_file": null,
+    "input_tagalign_file": null,
+    "output_dir": "/oak/stanford/groups/akundaje/vhecht/chromatin_atlas_bias_corrected/DNASE_model/ENCSR000EOD/fold_1",
+    "data_type": "DNASE",
+    "peaks": "/oak/stanford/groups/akundaje/vhecht/chromatin_atlas_bias_corrected/DNASE_model/ENCSR000EOD/fold_1/auxiliary/filtered.peaks.bed",
+    "nonpeaks": "/oak/stanford/groups/akundaje/vhecht/chromatin_atlas_bias_corrected/DNASE_model/ENCSR000EOD/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/bias_threshold_0.8/ENCSR000EOD/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/ENCSR000EOD/fold_1/models/chrombpnet",
+    "bigwig": "/oak/stanford/groups/akundaje/vhecht/chromatin_atlas_bias_corrected/DNASE_model/ENCSR000EOD/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/ENCSR000EOD/fold_1/logs/chrombpnet_model_params.tsv"
+}

fold_3/logs.models.fold_3.ENCSR000EOD/logfile.modelling.fold_3.ENCSR000EOD.bias_formatting.stdout.txt

@@ -0,0 +1 @@
+Converting /oak/stanford/groups/akundaje/vhecht/chromatin_atlas_bias_corrected/DNASE_model/ENCSR000EOD/fold_1/models/bias_model_scaled.h5 to /oak/stanford/groups/akundaje/vhecht/chromatin-atlas-2022/DNASE/ENCSR000EOD/fold_3/new_model_format/bias_model_scaled.tar with get_new_tf_model_format.py

fold_3/logs.models.fold_3.ENCSR000EOD/logfile.modelling.fold_3.ENCSR000EOD.chrombpnet_data_params.tsv

@@ -0,0 +1,3 @@
+counts_sum_min_thresh	0.0
+counts_sum_max_thresh	30561.54
+trainings_pts_post_thresh	175240

fold_3/logs.models.fold_3.ENCSR000EOD/logfile.modelling.fold_3.ENCSR000EOD.chrombpnet_formatting.stdout.txt

@@ -0,0 +1 @@
+Converting /oak/stanford/groups/akundaje/vhecht/chromatin_atlas_bias_corrected/DNASE_model/ENCSR000EOD/fold_1/models/chrombpnet.h5 to /oak/stanford/groups/akundaje/vhecht/chromatin-atlas-2022/DNASE/ENCSR000EOD/fold_3/new_model_format/chrombpnet.tar with get_new_tf_model_format.py

fold_3/logs.models.fold_3.ENCSR000EOD/logfile.modelling.fold_3.ENCSR000EOD.chrombpnet_model_params.tsv

@@ -0,0 +1,9 @@
+counts_loss_weight	47.8
+filters	512
+n_dil_layers	8
+bias_model_path	/oak/stanford/groups/akundaje/vhecht/chromatin_atlas_bias_corrected/DNASE_model/ENCSR000EOD/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_3/logs.models.fold_3.ENCSR000EOD/logfile.modelling.fold_3.ENCSR000EOD.chrombpnet_no_bias_formatting.stdout.txt

@@ -0,0 +1 @@
+Converting /oak/stanford/groups/akundaje/vhecht/chromatin_atlas_bias_corrected/DNASE_model/ENCSR000EOD/fold_1/models/chrombpnet_nobias.h5 to /oak/stanford/groups/akundaje/vhecht/chromatin-atlas-2022/DNASE/ENCSR000EOD/fold_3/new_model_format/chrombpnet_nobias.tar with get_new_tf_model_format.py