Upload folder using huggingface_hub

README.md

@@ -0,0 +1,120 @@
+---
+license: mit
+library_name: chrombpnet
+tags:
+  - encode
+  - chrombpnet
+  - chromatin-accessibility
+  - DNASE
+  - stomach
+  - 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 stomach (ENCSR095GWE)
+- Model: ChromBPNet
+- Assay: DNASE-seq
+- Experiment: [ENCSR095GWE](https://www.encodeproject.org/experiments/ENCSR095GWE/)
+- Model annotation: [ENCSR602LGD](https://www.encodeproject.org/annotations/ENCSR602LGD/)
+- Biosample: stomach (Full name: Homo sapiens stomach tissue male embryo (58 days) and male embryo (76 days))
+- Cell slim(s): None
+- Organ slim(s): stomach
+- Developmental slim(s): endoderm
+- System slim(s): digestive-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.ENCSR095GWE/logfile.modelling.fold_0.ENCSR095GWE.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/ENCSR095GWE/preprocessing/bigWigs/ENCSR095GWE.bigWig",
+    "output_dir": "/oak/stanford/groups/akundaje/ziwei75/chromatin_atlas_bias/DNase_model/bias_threshold_0.8/ENCSR095GWE/fold0/",
+    "data_type": "DNASE",
+    "peaks": "/oak/stanford/groups/akundaje/ziwei75/chromatin_atlas_bias/DNase_model/bias_threshold_0.8/ENCSR095GWE/fold0/auxiliary/filtered.peaks.bed",
+    "nonpeaks": "/oak/stanford/groups/akundaje/ziwei75/chromatin_atlas_bias/DNase_model/bias_threshold_0.8/ENCSR095GWE/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/ENCSR095GWE/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/ENCSR095GWE/fold0/models/chrombpnet",
+    "chr": "chr8",
+    "pwm_width": 24,
+    "params": "/oak/stanford/groups/akundaje/ziwei75/chromatin_atlas_bias/DNase_model/bias_threshold_0.8/ENCSR095GWE/fold0/logs/chrombpnet_model_params.tsv"
+}

fold_0/logs.models.fold_0.ENCSR095GWE/logfile.modelling.fold_0.ENCSR095GWE.bias_formatting.stdout.txt

@@ -0,0 +1 @@
+Converting /oak/stanford/groups/akundaje/ziwei75/chromatin_atlas_bias/DNase_model/bias_threshold_0.8/ENCSR095GWE/fold0/models/bias_model_scaled.h5 to /oak/stanford/groups/akundaje/vhecht/chromatin-atlas-2022/DNASE/ENCSR095GWE/fold_0/new_model_format/bias_model_scaled.tar with get_new_tf_model_format.py

fold_0/logs.models.fold_0.ENCSR095GWE/logfile.modelling.fold_0.ENCSR095GWE.chrombpnet_data_params.tsv

@@ -0,0 +1,3 @@
+counts_sum_min_thresh	0.0
+counts_sum_max_thresh	9270.72
+trainings_pts_post_thresh	171381

fold_0/logs.models.fold_0.ENCSR095GWE/logfile.modelling.fold_0.ENCSR095GWE.chrombpnet_formatting.stdout.txt

@@ -0,0 +1 @@
+Converting /oak/stanford/groups/akundaje/ziwei75/chromatin_atlas_bias/DNase_model/bias_threshold_0.8/ENCSR095GWE/fold0/models/chrombpnet.h5 to /oak/stanford/groups/akundaje/vhecht/chromatin-atlas-2022/DNASE/ENCSR095GWE/fold_0/new_model_format/chrombpnet.tar with get_new_tf_model_format.py

fold_0/logs.models.fold_0.ENCSR095GWE/logfile.modelling.fold_0.ENCSR095GWE.chrombpnet_model_params.tsv

@@ -0,0 +1,9 @@
+counts_loss_weight	53.1
+filters	512
+n_dil_layers	8
+bias_model_path	/oak/stanford/groups/akundaje/ziwei75/chromatin_atlas_bias/DNase_model/bias_threshold_0.8/ENCSR095GWE/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.ENCSR095GWE/logfile.modelling.fold_0.ENCSR095GWE.chrombpnet_no_bias_formatting.stdout.txt

@@ -0,0 +1 @@
+Converting /oak/stanford/groups/akundaje/ziwei75/chromatin_atlas_bias/DNase_model/bias_threshold_0.8/ENCSR095GWE/fold0/models/chrombpnet_nobias.h5 to /oak/stanford/groups/akundaje/vhecht/chromatin-atlas-2022/DNASE/ENCSR095GWE/fold_0/new_model_format/chrombpnet_nobias.tar with get_new_tf_model_format.py

fold_0/logs.models.fold_0.ENCSR095GWE/logfile.modelling.fold_0.ENCSR095GWE.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
+0,2.06192684173584,1142.69873046875,1252.184814453125,0.5214093327522278,1117.7364501953125,1145.4232177734375
+1,0.5505080819129944,1088.7174072265625,1117.949951171875,0.5191581845283508,1102.3438720703125,1129.9112548828125
+2,0.4971510171890259,1074.1241455078125,1100.522705078125,0.5931004881858826,1072.7783203125,1104.27197265625
+3,0.46452757716178894,1065.071044921875,1089.73779296875,0.40724071860313416,1082.2464599609375,1103.87158203125
+4,0.43967992067337036,1058.9342041015625,1082.2811279296875,0.4593840539455414,1071.87255859375,1096.2652587890625
+5,0.42308148741722107,1053.657958984375,1076.1231689453125,0.418905109167099,1084.1817626953125,1106.4248046875
+6,0.4081580340862274,1050.107666015625,1071.7806396484375,0.44923460483551025,1080.239990234375,1104.094970703125
+7,0.3955555558204651,1046.60498046875,1067.6104736328125,0.4234311878681183,1074.7138671875,1097.1982421875
+8,0.3834068775177002,1043.6025390625,1063.9627685546875,0.38592755794525146,1077.597900390625,1098.0904541015625
+9,0.36805784702301025,1041.2044677734375,1060.748046875,0.3666335940361023,1077.12744140625,1096.5958251953125

fold_0/model.bias_scaled.fold_0.ENCSR095GWE.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c80b3575d79554317d7eda250d71c87390754defcb78e133c909061b4b56a76c
+size 2691928

fold_0/model.bias_scaled.fold_0.ENCSR095GWE.tar

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1dbc04dabaeafe4cf69b1a036f375b46e524a73fd6ca6df97ea8b84fe50ebc5d
+size 1198080

fold_0/model.chrombpnet.fold_0.ENCSR095GWE.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bac283e9e0208a4189919c45abe5ea46eb14b9d6b03d0256c9540c0953cebed3
+size 77538952

fold_0/model.chrombpnet.fold_0.ENCSR095GWE.tar

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c79282801a05e8d48b530bc46ffdab8813451b5cf92c3e18389624902665dcd3
+size 27525120

fold_0/model.chrombpnet_nobias.fold_0.ENCSR095GWE.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5b0a379a5a52934d1815fe1da813c6e362fa8b2792a2a29c9638234ea678999e
+size 25582648

fold_0/model.chrombpnet_nobias.fold_0.ENCSR095GWE.tar

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ad0d74f4058bdfe1c6e0b3e38a39634230d3abe8563d56053489e15e4bfb7629
+size 26060800

fold_1/logs.models.fold_1.ENCSR095GWE/logfile.modelling.fold_1.ENCSR095GWE.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/ENCSR095GWE/preprocessing/bigWigs/ENCSR095GWE.bigWig",
+    "input_fragment_file": null,
+    "input_tagalign_file": null,
+    "output_dir": "/oak/stanford/groups/akundaje/vhecht/chromatin_atlas_bias_corrected/DNASE_model/ENCSR095GWE/fold_1",
+    "data_type": "DNASE",
+    "peaks": "/oak/stanford/groups/akundaje/vhecht/chromatin_atlas_bias_corrected/DNASE_model/ENCSR095GWE/fold_1/auxiliary/filtered.peaks.bed",
+    "nonpeaks": "/oak/stanford/groups/akundaje/vhecht/chromatin_atlas_bias_corrected/DNASE_model/ENCSR095GWE/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/ENCSR095GWE/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/ENCSR095GWE/fold_1/models/chrombpnet",
+    "bigwig": "/oak/stanford/groups/akundaje/vhecht/chromatin_atlas_bias_corrected/DNASE_model/ENCSR095GWE/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/ENCSR095GWE/fold_1/logs/chrombpnet_model_params.tsv"
+}

fold_1/logs.models.fold_1.ENCSR095GWE/logfile.modelling.fold_1.ENCSR095GWE.bias_formatting.stdout.txt

@@ -0,0 +1 @@
+Converting /oak/stanford/groups/akundaje/vhecht/chromatin_atlas_bias_corrected/DNASE_model/ENCSR095GWE/fold_1/models/bias_model_scaled.h5 to /oak/stanford/groups/akundaje/vhecht/chromatin-atlas-2022/DNASE/ENCSR095GWE/fold_1/new_model_format/bias_model_scaled.tar with get_new_tf_model_format.py

fold_1/logs.models.fold_1.ENCSR095GWE/logfile.modelling.fold_1.ENCSR095GWE.chrombpnet_data_params.tsv

@@ -0,0 +1,3 @@
+counts_sum_min_thresh	0.0
+counts_sum_max_thresh	9257.44
+trainings_pts_post_thresh	175159

fold_1/logs.models.fold_1.ENCSR095GWE/logfile.modelling.fold_1.ENCSR095GWE.chrombpnet_formatting.stdout.txt

@@ -0,0 +1 @@
+Converting /oak/stanford/groups/akundaje/vhecht/chromatin_atlas_bias_corrected/DNASE_model/ENCSR095GWE/fold_1/models/chrombpnet.h5 to /oak/stanford/groups/akundaje/vhecht/chromatin-atlas-2022/DNASE/ENCSR095GWE/fold_1/new_model_format/chrombpnet.tar with get_new_tf_model_format.py

fold_1/logs.models.fold_1.ENCSR095GWE/logfile.modelling.fold_1.ENCSR095GWE.chrombpnet_model_params.tsv

@@ -0,0 +1,9 @@
+counts_loss_weight	53.8
+filters	512
+n_dil_layers	8
+bias_model_path	/oak/stanford/groups/akundaje/vhecht/chromatin_atlas_bias_corrected/DNASE_model/ENCSR095GWE/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.ENCSR095GWE/logfile.modelling.fold_1.ENCSR095GWE.chrombpnet_no_bias_formatting.stdout.txt

@@ -0,0 +1 @@
+Converting /oak/stanford/groups/akundaje/vhecht/chromatin_atlas_bias_corrected/DNASE_model/ENCSR095GWE/fold_1/models/chrombpnet_nobias.h5 to /oak/stanford/groups/akundaje/vhecht/chromatin-atlas-2022/DNASE/ENCSR095GWE/fold_1/new_model_format/chrombpnet_nobias.tar with get_new_tf_model_format.py

fold_1/logs.models.fold_1.ENCSR095GWE/logfile.modelling.fold_1.ENCSR095GWE.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
+0,2.8930015563964844,1164.3914794921875,1320.03466796875,0.7833644151687622,1254.1768798828125,1296.322021484375
+1,0.5810027122497559,1098.8184814453125,1130.0751953125,0.5236353278160095,1223.1314697265625,1251.3035888671875
+2,0.5289002060890198,1082.114990234375,1110.5711669921875,0.5525802373886108,1204.360107421875,1234.0892333984375
+3,0.49828705191612244,1070.221435546875,1097.02685546875,0.45157545804977417,1189.698486328125,1213.993408203125
+4,0.4654807150363922,1061.8746337890625,1086.9190673828125,0.41087257862091064,1189.9775390625,1212.083740234375
+5,0.43822887539863586,1055.6929931640625,1079.2711181640625,0.4033484160900116,1187.15625,1208.8564453125
+6,0.416246235370636,1051.0238037109375,1073.4173583984375,0.4007035493850708,1176.3140869140625,1197.87158203125
+7,0.39903753995895386,1046.46630859375,1067.932861328125,0.37682515382766724,1168.781982421875,1189.0550537109375
+8,0.3846810460090637,1042.8138427734375,1063.5108642578125,0.37334659695625305,1183.9940185546875,1204.080078125
+9,0.37955451011657715,1040.225830078125,1060.6478271484375,0.401145875453949,1173.0794677734375,1194.6605224609375
+10,0.3625588119029999,1037.3077392578125,1056.813720703125,0.4210904836654663,1174.672607421875,1197.3265380859375
+11,0.3568156659603119,1035.074462890625,1054.2720947265625,0.41300955414772034,1171.635009765625,1193.8555908203125
+12,0.34758490324020386,1032.45361328125,1051.153564453125,0.3579091429710388,1190.2501220703125,1209.5054931640625

fold_1/model.bias_scaled.fold_1.ENCSR095GWE.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3ce221c364e9785f22e0bf9cde6f68d9da9878a4ffd5d0ad071e2af2229ff804
+size 2691928

fold_1/model.bias_scaled.fold_1.ENCSR095GWE.tar

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5fe08a0d0eadd670f5c37dd86671751b3e36f5a6cb67362be9a1c2c1f16d2a2c
+size 1198080

fold_1/model.chrombpnet.fold_1.ENCSR095GWE.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:43d702b8b6b223759fd57ff72b5aae10aa177b5ced5da7ee1f1c011005305330
+size 77538840

fold_1/model.chrombpnet.fold_1.ENCSR095GWE.tar

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8236a461696a343adf752c1d65a4531d6ab0c9d9f8d108e4f159d08f43bd4ed0
+size 27525120

fold_1/model.chrombpnet_nobias.fold_1.ENCSR095GWE.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eb09c2eaeb71fa5162dbca09f1a91c9fd25090326817ee19f5fb7544e9f6b8f8
+size 25582648

fold_1/model.chrombpnet_nobias.fold_1.ENCSR095GWE.tar

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a43744cddb1ea7a5f48a5f7a4b206d16c8f4b856ed29ecc004ed987405699cb3
+size 26060800

fold_2/logs.models.fold_2.ENCSR095GWE/logfile.modelling.fold_2.ENCSR095GWE.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/ENCSR095GWE/preprocessing/bigWigs/ENCSR095GWE.bigWig",
+    "input_fragment_file": null,
+    "input_tagalign_file": null,
+    "output_dir": "/oak/stanford/groups/akundaje/vhecht/chromatin_atlas_bias_corrected/DNASE_model/ENCSR095GWE/fold_2",
+    "data_type": "DNASE",
+    "peaks": "/oak/stanford/groups/akundaje/vhecht/chromatin_atlas_bias_corrected/DNASE_model/ENCSR095GWE/fold_2/auxiliary/filtered.peaks.bed",
+    "nonpeaks": "/oak/stanford/groups/akundaje/vhecht/chromatin_atlas_bias_corrected/DNASE_model/ENCSR095GWE/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/ENCSR095GWE/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/ENCSR095GWE/fold_2/models/chrombpnet",
+    "bigwig": "/oak/stanford/groups/akundaje/vhecht/chromatin_atlas_bias_corrected/DNASE_model/ENCSR095GWE/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/ENCSR095GWE/fold_2/logs/chrombpnet_model_params.tsv"
+}

fold_2/logs.models.fold_2.ENCSR095GWE/logfile.modelling.fold_2.ENCSR095GWE.bias_formatting.stdout.txt

@@ -0,0 +1 @@
+Converting /oak/stanford/groups/akundaje/vhecht/chromatin_atlas_bias_corrected/DNASE_model/ENCSR095GWE/fold_2/models/bias_model_scaled.h5 to /oak/stanford/groups/akundaje/vhecht/chromatin-atlas-2022/DNASE/ENCSR095GWE/fold_2/new_model_format/bias_model_scaled.tar with get_new_tf_model_format.py

fold_2/logs.models.fold_2.ENCSR095GWE/logfile.modelling.fold_2.ENCSR095GWE.chrombpnet_data_params.tsv

@@ -0,0 +1,3 @@
+counts_sum_min_thresh	0.0
+counts_sum_max_thresh	9283.51
+trainings_pts_post_thresh	179490

fold_2/logs.models.fold_2.ENCSR095GWE/logfile.modelling.fold_2.ENCSR095GWE.chrombpnet_formatting.stdout.txt

@@ -0,0 +1 @@
+Converting /oak/stanford/groups/akundaje/vhecht/chromatin_atlas_bias_corrected/DNASE_model/ENCSR095GWE/fold_2/models/chrombpnet.h5 to /oak/stanford/groups/akundaje/vhecht/chromatin-atlas-2022/DNASE/ENCSR095GWE/fold_2/new_model_format/chrombpnet.tar with get_new_tf_model_format.py

fold_2/logs.models.fold_2.ENCSR095GWE/logfile.modelling.fold_2.ENCSR095GWE.chrombpnet_model_params.tsv

@@ -0,0 +1,9 @@
+counts_loss_weight	53.5
+filters	512
+n_dil_layers	8
+bias_model_path	/oak/stanford/groups/akundaje/vhecht/chromatin_atlas_bias_corrected/DNASE_model/ENCSR095GWE/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.ENCSR095GWE/logfile.modelling.fold_2.ENCSR095GWE.chrombpnet_no_bias_formatting.stdout.txt

@@ -0,0 +1 @@
+Converting /oak/stanford/groups/akundaje/vhecht/chromatin_atlas_bias_corrected/DNASE_model/ENCSR095GWE/fold_2/models/chrombpnet_nobias.h5 to /oak/stanford/groups/akundaje/vhecht/chromatin-atlas-2022/DNASE/ENCSR095GWE/fold_2/new_model_format/chrombpnet_nobias.tar with get_new_tf_model_format.py

fold_2/logs.models.fold_2.ENCSR095GWE/logfile.modelling.fold_2.ENCSR095GWE.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
+0,1.7643661499023438,1131.59228515625,1225.9842529296875,0.5978891253471375,1123.68603515625,1155.6732177734375
+1,0.5188822746276855,1086.091796875,1113.850830078125,0.4836629629135132,1107.57470703125,1133.450439453125
+2,0.47326794266700745,1071.1759033203125,1096.49609375,0.44354116916656494,1098.5145263671875,1122.2440185546875
+3,0.4360990822315216,1063.11572265625,1086.4461669921875,0.42591190338134766,1090.32275390625,1113.109130859375
+4,0.41021794080734253,1058.0321044921875,1079.9794921875,0.4152602255344391,1094.2958984375,1116.5125732421875
+5,0.4014905095100403,1052.6767578125,1074.1539306640625,0.4330199956893921,1087.626953125,1110.7935791015625
+6,0.38670048117637634,1048.2735595703125,1068.9619140625,0.4084222912788391,1086.6676025390625,1108.517578125
+7,0.3726902902126312,1045.7022705078125,1065.64111328125,0.40692055225372314,1090.140625,1111.91064453125
+8,0.36133795976638794,1042.58447265625,1061.91748046875,0.3928358256816864,1092.5491943359375,1113.5657958984375
+9,0.34961801767349243,1039.2108154296875,1057.915771484375,0.38800936937332153,1089.2509765625,1110.009033203125
+10,0.34276676177978516,1038.012939453125,1056.350341796875,0.4098263084888458,1096.39453125,1118.3206787109375
+11,0.3331567943096161,1035.880126953125,1053.7037353515625,0.39476338028907776,1078.49072265625,1099.6112060546875
+12,0.3241574764251709,1034.010009765625,1051.3514404296875,0.39400532841682434,1092.423583984375,1113.503173828125
+13,0.31842970848083496,1031.9425048828125,1048.9801025390625,0.4057542681694031,1101.8770751953125,1123.5853271484375
+14,0.3130089342594147,1031.738037109375,1048.4853515625,0.3886359632015228,1093.2308349609375,1114.0234375
+15,0.3031877279281616,1030.300537109375,1046.5206298828125,0.38974857330322266,1092.944091796875,1113.795166015625
+16,0.29997992515563965,1029.7376708984375,1045.78662109375,0.434227854013443,1086.882080078125,1110.1126708984375

fold_2/model.bias_scaled.fold_2.ENCSR095GWE.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1e8c4e9b84bdffd290c1ad61d91619cfdcecb79eba9ba7ea468a444298a508b6
+size 2691928

fold_2/model.bias_scaled.fold_2.ENCSR095GWE.tar

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f17bdeb43447a109e8482c5855348b87b248eab98d7799ed22489fbc52834d9f
+size 1198080

fold_2/model.chrombpnet.fold_2.ENCSR095GWE.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:72e84512204919c0e72bffac38a46e9fd380c5709c707c3d114924d711d00f2c
+size 77538840

fold_2/model.chrombpnet.fold_2.ENCSR095GWE.tar

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e4a86015d9668af45815cba45771faf885ddc77f44fa57d08c1b89442241f0f6
+size 27525120

fold_2/model.chrombpnet_nobias.fold_2.ENCSR095GWE.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:653f97b3fc4ec77bb50edcaedd0616bf58873b8e3d4f82157aa4f8d7c0509fe5
+size 25582648

fold_2/model.chrombpnet_nobias.fold_2.ENCSR095GWE.tar

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b76f6b98e53147697fd53952e50a785445450f9f3cc491e72569c42afcb50843
+size 26060800

fold_3/logs.models.fold_3.ENCSR095GWE/logfile.modelling.fold_3.ENCSR095GWE.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/ENCSR095GWE/preprocessing/bigWigs/ENCSR095GWE.bigWig",
+    "input_fragment_file": null,
+    "input_tagalign_file": null,
+    "output_dir": "/oak/stanford/groups/akundaje/vhecht/chromatin_atlas_bias_corrected/DNASE_model/ENCSR095GWE/fold_3",
+    "data_type": "DNASE",
+    "peaks": "/oak/stanford/groups/akundaje/vhecht/chromatin_atlas_bias_corrected/DNASE_model/ENCSR095GWE/fold_3/auxiliary/filtered.peaks.bed",
+    "nonpeaks": "/oak/stanford/groups/akundaje/vhecht/chromatin_atlas_bias_corrected/DNASE_model/ENCSR095GWE/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/bias_threshold_0.8/ENCSR095GWE/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/ENCSR095GWE/fold_3/models/chrombpnet",
+    "bigwig": "/oak/stanford/groups/akundaje/vhecht/chromatin_atlas_bias_corrected/DNASE_model/ENCSR095GWE/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/ENCSR095GWE/fold_3/logs/chrombpnet_model_params.tsv"
+}

fold_3/logs.models.fold_3.ENCSR095GWE/logfile.modelling.fold_3.ENCSR095GWE.bias_formatting.stdout.txt

@@ -0,0 +1 @@
+Converting /oak/stanford/groups/akundaje/vhecht/chromatin_atlas_bias_corrected/DNASE_model/ENCSR095GWE/fold_3/models/bias_model_scaled.h5 to /oak/stanford/groups/akundaje/vhecht/chromatin-atlas-2022/DNASE/ENCSR095GWE/fold_3/new_model_format/bias_model_scaled.tar with get_new_tf_model_format.py

fold_3/logs.models.fold_3.ENCSR095GWE/logfile.modelling.fold_3.ENCSR095GWE.chrombpnet_data_params.tsv

@@ -0,0 +1,3 @@
+counts_sum_min_thresh	0.0
+counts_sum_max_thresh	9472.34
+trainings_pts_post_thresh	174190

fold_3/logs.models.fold_3.ENCSR095GWE/logfile.modelling.fold_3.ENCSR095GWE.chrombpnet_formatting.stdout.txt

@@ -0,0 +1 @@
+Converting /oak/stanford/groups/akundaje/vhecht/chromatin_atlas_bias_corrected/DNASE_model/ENCSR095GWE/fold_3/models/chrombpnet.h5 to /oak/stanford/groups/akundaje/vhecht/chromatin-atlas-2022/DNASE/ENCSR095GWE/fold_3/new_model_format/chrombpnet.tar with get_new_tf_model_format.py

fold_3/logs.models.fold_3.ENCSR095GWE/logfile.modelling.fold_3.ENCSR095GWE.chrombpnet_model_params.tsv

@@ -0,0 +1,9 @@
+counts_loss_weight	53.8
+filters	512
+n_dil_layers	8
+bias_model_path	/oak/stanford/groups/akundaje/vhecht/chromatin_atlas_bias_corrected/DNASE_model/ENCSR095GWE/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.ENCSR095GWE/logfile.modelling.fold_3.ENCSR095GWE.chrombpnet_no_bias_formatting.stdout.txt

@@ -0,0 +1 @@
+Converting /oak/stanford/groups/akundaje/vhecht/chromatin_atlas_bias_corrected/DNASE_model/ENCSR095GWE/fold_3/models/chrombpnet_nobias.h5 to /oak/stanford/groups/akundaje/vhecht/chromatin-atlas-2022/DNASE/ENCSR095GWE/fold_3/new_model_format/chrombpnet_nobias.tar with get_new_tf_model_format.py