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 arm (ENCSR619BNL)
+- Model: ChromBPNet
+- Assay: DNASE-seq
+- Experiment: [ENCSR619BNL](https://www.encodeproject.org/experiments/ENCSR619BNL/)
+- Model annotation: [ENCSR084NFS](https://www.encodeproject.org/annotations/ENCSR084NFS/)
+- Biosample: muscle of arm (Full name: Homo sapiens muscle of arm tissue male embryo (97 days))
+- Cell slim(s): None
+- Organ slim(s): musculature-of-body,limb
+- 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.ENCSR619BNL/logfile.modelling.fold_0.ENCSR619BNL.args.json

@@ -0,0 +1,45 @@
+{
+    "cmd": "pipeline",
+    "genome": "/scratch/groups/akundaje/anusri/chromatin_atlas/reference//hg38.genome.fa",
+    "chrom_sizes": "/scratch/groups/akundaje/anusri/chromatin_atlas/reference//chrom.sizes",
+    "input_bam_file": null,
+    "input_fragment_file": null,
+    "input_tagalign_file": null,
+    "bigwig": "/oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/DNASE//ENCSR619BNL//preprocessing/bigWigs/ENCSR619BNL.bigWig",
+    "output_dir": "/scratch/groups/akundaje/anusri/chromatin_atlas/DNASE/ENCSR619BNL//chrombpnet_model_feb15_fold_0/chrombpnet_model/",
+    "data_type": "DNASE",
+    "peaks": "/scratch/groups/akundaje/anusri/chromatin_atlas/DNASE/ENCSR619BNL//chrombpnet_model_feb15_fold_0/chrombpnet_model/auxiliary/ENCSR619BNL_filtered.peaks.bed",
+    "nonpeaks": "/scratch/groups/akundaje/anusri/chromatin_atlas/DNASE/ENCSR619BNL//chrombpnet_model_feb15_fold_0/chrombpnet_model/auxiliary/ENCSR619BNL_filtered.nonpeaks.bed",
+    "chr_fold_path": "/scratch/groups/akundaje/anusri/chromatin_atlas/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/anusri/simg/chrombpnet_latest/chrombpnet/chrombpnet/training/models/chrombpnet_with_bias_model.py",
+    "file_prefix": "ENCSR619BNL",
+    "html_prefix": "./",
+    "bias_model_path": "/scratch/groups/akundaje/anusri/chromatin_atlas/DNASE/ENCSR619BNL//chrombpnet_model_feb15_fold_0/bias_model/models/ENCSR619BNL_bias.h5",
+    "negative_sampling_ratio": 0.1,
+    "filters": 512,
+    "n_dilation_layers": 8,
+    "max_jitter": 500,
+    "batch_size": 64,
+    "output_prefix": "/scratch/groups/akundaje/anusri/chromatin_atlas/DNASE/ENCSR619BNL//chrombpnet_model_feb15_fold_0/chrombpnet_model/models/ENCSR619BNL_chrombpnet",
+    "chr": "chr8",
+    "pwm_width": 24,
+    "params": "/scratch/groups/akundaje/anusri/chromatin_atlas/DNASE/ENCSR619BNL//chrombpnet_model_feb15_fold_0/chrombpnet_model/logs/ENCSR619BNL_chrombpnet_model_params.tsv"
+}

fold_0/logs.models.fold_0.ENCSR619BNL/logfile.modelling.fold_0.ENCSR619BNL.bias_formatting.stdout.txt

@@ -0,0 +1 @@
+Converting /oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/DNASE/ENCSR619BNL/failed_models_retrained/chrombpnet_model_feb15_fold_0/chrombpnet_model/models/ENCSR619BNL_bias_model_scaled.h5 to /oak/stanford/groups/akundaje/vhecht/chromatin-atlas-2022/DNASE/ENCSR619BNL/fold_0/new_model_format/bias_model_scaled.tar with get_new_tf_model_format.py

fold_0/logs.models.fold_0.ENCSR619BNL/logfile.modelling.fold_0.ENCSR619BNL.chrombpnet_data_params.tsv

@@ -0,0 +1,3 @@
+counts_sum_min_thresh	0.0
+counts_sum_max_thresh	695.97
+trainings_pts_post_thresh	170564

fold_0/logs.models.fold_0.ENCSR619BNL/logfile.modelling.fold_0.ENCSR619BNL.chrombpnet_formatting.stdout.txt

@@ -0,0 +1 @@
+Converting /oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/DNASE/ENCSR619BNL/failed_models_retrained/chrombpnet_model_feb15_fold_0/chrombpnet_model/models/ENCSR619BNL_chrombpnet.h5 to /oak/stanford/groups/akundaje/vhecht/chromatin-atlas-2022/DNASE/ENCSR619BNL/fold_0/new_model_format/chrombpnet.tar with get_new_tf_model_format.py

fold_0/logs.models.fold_0.ENCSR619BNL/logfile.modelling.fold_0.ENCSR619BNL.chrombpnet_model_params.tsv

@@ -0,0 +1,9 @@
+counts_loss_weight	5.3
+filters	512
+n_dil_layers	8
+bias_model_path	/scratch/groups/akundaje/anusri/chromatin_atlas/DNASE/ENCSR619BNL//chrombpnet_model_feb15_fold_0/chrombpnet_model/models/ENCSR619BNL_bias_model_scaled.h5
+inputlen	2114
+outputlen	1000
+max_jitter	500
+chr_fold_path	/scratch/groups/akundaje/anusri/chromatin_atlas/splits/fold_0.json
+negative_sampling_ratio	0.1

fold_0/logs.models.fold_0.ENCSR619BNL/logfile.modelling.fold_0.ENCSR619BNL.chrombpnet_no_bias_formatting.stdout.txt

@@ -0,0 +1 @@
+Converting /oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/DNASE/ENCSR619BNL/failed_models_retrained/chrombpnet_model_feb15_fold_0/chrombpnet_model/models/ENCSR619BNL_chrombpnet_nobias.h5 to /oak/stanford/groups/akundaje/vhecht/chromatin-atlas-2022/DNASE/ENCSR619BNL/fold_0/new_model_format/chrombpnet_nobias.tar with get_new_tf_model_format.py

fold_0/logs.models.fold_0.ENCSR619BNL/logfile.modelling.fold_0.ENCSR619BNL.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
+0,1.3232842683792114,222.66561889648438,229.6790008544922,0.6818878650665283,223.65635681152344,227.27041625976562
+1,0.5583170652389526,217.8521728515625,220.81141662597656,0.5006343722343445,222.00218200683594,224.65545654296875
+2,0.5069165229797363,216.85565185546875,219.5425262451172,0.5286344885826111,221.79541015625,224.5972442626953
+3,0.48330947756767273,215.8408203125,218.40274047851562,0.4383445680141449,221.82310485839844,224.14625549316406
+4,0.460163414478302,215.1038360595703,217.5427703857422,0.43120962381362915,220.9139404296875,223.1994171142578
+5,0.43700772523880005,214.5636444091797,216.88006591796875,0.42612019181251526,221.3193359375,223.57774353027344
+6,0.4231550693511963,213.7183380126953,215.96102905273438,0.42460036277770996,221.6961669921875,223.9467010498047
+7,0.4114542007446289,213.16632080078125,215.3467559814453,0.4258621633052826,222.06280517578125,224.32003784179688
+8,0.39971238374710083,212.33270263671875,214.45111083984375,0.4193635582923889,221.77935791015625,224.0019989013672
+9,0.38935962319374084,211.8031005859375,213.86647033691406,0.42817649245262146,222.34765625,224.61697387695312

fold_0/model.bias_scaled.fold_0.ENCSR619BNL.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8a461a0246f0f183503a04be3053297f5087942180d41b9f3cf75e1bb82cd094
+size 2691928

fold_0/model.bias_scaled.fold_0.ENCSR619BNL.tar

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dab516b2eccce54c6d199d44771a92b233eab630f918d6aee37f76e7e2a18543
+size 1198080

fold_0/model.chrombpnet.fold_0.ENCSR619BNL.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:72a9ad4f52143639a87bccec4f74a889778a85fdaef2b67149f17e36662b18d8
+size 77538904

fold_0/model.chrombpnet.fold_0.ENCSR619BNL.tar

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fb73d070f61af961b5aec9bbac051fc4944416b7cc5a5c7ee4bfd8d8510ac7c5
+size 27525120

fold_0/model.chrombpnet_nobias.fold_0.ENCSR619BNL.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2606a131b64a0608a19afb567953607eac204635d727c3937aa0e2d1d8381da5
+size 25582648

fold_0/model.chrombpnet_nobias.fold_0.ENCSR619BNL.tar

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:62ee9fb5be88062fa15974e9026b5f51e1f8313d75819f010a5723364d057b31
+size 26060800

fold_1/logs.models.fold_1.ENCSR619BNL/logfile.modelling.fold_1.ENCSR619BNL.args.json

@@ -0,0 +1,45 @@
+{
+    "cmd": "train",
+    "genome": "/scratch/groups/akundaje/anusri/chromatin_atlas/reference//hg38.genome.fa",
+    "chrom_sizes": "/scratch/groups/akundaje/anusri/chromatin_atlas/reference//chrom.sizes",
+    "input_bam_file": null,
+    "input_fragment_file": null,
+    "input_tagalign_file": null,
+    "bigwig": "/oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/DNASE//ENCSR619BNL//preprocessing/bigWigs/ENCSR619BNL.bigWig",
+    "output_dir": "/scratch/groups/akundaje/anusri/chromatin_atlas/DNASE/ENCSR619BNL//chrombpnet_model_feb15_fold_1/chrombpnet_model/",
+    "data_type": "DNASE",
+    "peaks": "/scratch/groups/akundaje/anusri/chromatin_atlas/DNASE/ENCSR619BNL//chrombpnet_model_feb15_fold_1/chrombpnet_model/auxiliary/ENCSR619BNL_filtered.peaks.bed",
+    "nonpeaks": "/scratch/groups/akundaje/anusri/chromatin_atlas/DNASE/ENCSR619BNL//chrombpnet_model_feb15_fold_1/chrombpnet_model/auxiliary/ENCSR619BNL_filtered.nonpeaks.bed",
+    "chr_fold_path": "/scratch/groups/akundaje/anusri/chromatin_atlas/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/groups/akundaje/anusri/simg/chrombpnet_latest/chrombpnet/chrombpnet/training/models/chrombpnet_with_bias_model.py",
+    "file_prefix": "ENCSR619BNL",
+    "html_prefix": "./",
+    "bias_model_path": "/scratch/groups/akundaje/anusri/chromatin_atlas/DNASE/ENCSR619BNL//chrombpnet_model_feb15_fold_0/bias_model/models/ENCSR619BNL_bias.h5",
+    "negative_sampling_ratio": 0.1,
+    "filters": 512,
+    "n_dilation_layers": 8,
+    "max_jitter": 500,
+    "batch_size": 64,
+    "output_prefix": "/scratch/groups/akundaje/anusri/chromatin_atlas/DNASE/ENCSR619BNL//chrombpnet_model_feb15_fold_1/chrombpnet_model/models/ENCSR619BNL_chrombpnet",
+    "chr": "chr12",
+    "pwm_width": 24,
+    "params": "/scratch/groups/akundaje/anusri/chromatin_atlas/DNASE/ENCSR619BNL//chrombpnet_model_feb15_fold_1/chrombpnet_model/logs/ENCSR619BNL_chrombpnet_model_params.tsv"
+}

fold_1/logs.models.fold_1.ENCSR619BNL/logfile.modelling.fold_1.ENCSR619BNL.bias_formatting.stdout.txt

@@ -0,0 +1 @@
+Converting /oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/DNASE/ENCSR619BNL/failed_models_retrained/chrombpnet_model_feb15_fold_1/chrombpnet_model/models/ENCSR619BNL_bias_model_scaled.h5 to /oak/stanford/groups/akundaje/vhecht/chromatin-atlas-2022/DNASE/ENCSR619BNL/fold_1/new_model_format/bias_model_scaled.tar with get_new_tf_model_format.py

fold_1/logs.models.fold_1.ENCSR619BNL/logfile.modelling.fold_1.ENCSR619BNL.chrombpnet_data_params.tsv

@@ -0,0 +1,3 @@
+counts_sum_min_thresh	0.0
+counts_sum_max_thresh	706.25
+trainings_pts_post_thresh	173368

fold_1/logs.models.fold_1.ENCSR619BNL/logfile.modelling.fold_1.ENCSR619BNL.chrombpnet_formatting.stdout.txt

@@ -0,0 +1 @@
+Converting /oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/DNASE/ENCSR619BNL/failed_models_retrained/chrombpnet_model_feb15_fold_1/chrombpnet_model/models/ENCSR619BNL_chrombpnet.h5 to /oak/stanford/groups/akundaje/vhecht/chromatin-atlas-2022/DNASE/ENCSR619BNL/fold_1/new_model_format/chrombpnet.tar with get_new_tf_model_format.py

fold_1/logs.models.fold_1.ENCSR619BNL/logfile.modelling.fold_1.ENCSR619BNL.chrombpnet_model_params.tsv

@@ -0,0 +1,9 @@
+counts_loss_weight	5.3
+filters	512
+n_dil_layers	8
+bias_model_path	/scratch/groups/akundaje/anusri/chromatin_atlas/DNASE/ENCSR619BNL//chrombpnet_model_feb15_fold_1/chrombpnet_model/models/ENCSR619BNL_bias_model_scaled.h5
+inputlen	2114
+outputlen	1000
+max_jitter	500
+chr_fold_path	/scratch/groups/akundaje/anusri/chromatin_atlas/splits/fold_1.json
+negative_sampling_ratio	0.1

fold_1/logs.models.fold_1.ENCSR619BNL/logfile.modelling.fold_1.ENCSR619BNL.chrombpnet_no_bias_formatting.stdout.txt

@@ -0,0 +1 @@
+Converting /oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/DNASE/ENCSR619BNL/failed_models_retrained/chrombpnet_model_feb15_fold_1/chrombpnet_model/models/ENCSR619BNL_chrombpnet_nobias.h5 to /oak/stanford/groups/akundaje/vhecht/chromatin-atlas-2022/DNASE/ENCSR619BNL/fold_1/new_model_format/chrombpnet_nobias.tar with get_new_tf_model_format.py

fold_1/logs.models.fold_1.ENCSR619BNL/logfile.modelling.fold_1.ENCSR619BNL.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
+0,4.754672527313232,223.83619689941406,249.03611755371094,0.7157800793647766,249.24563598632812,253.039306640625
+1,0.6024771332740784,219.1633758544922,222.3565216064453,0.5529043078422546,247.82098388671875,250.75161743164062
+2,0.5603039860725403,217.40606689453125,220.37582397460938,0.49465885758399963,246.681396484375,249.30308532714844
+3,0.5246159434318542,216.20611572265625,218.98660278320312,0.47698014974594116,244.8751220703125,247.40310668945312
+4,0.4921342432498932,215.56947326660156,218.1776123046875,0.4475700855255127,244.4949188232422,246.86692810058594
+5,0.467482328414917,215.26979064941406,217.74745178222656,0.42944198846817017,244.2589111328125,246.53504943847656
+6,0.45081406831741333,214.718994140625,217.10826110839844,0.4989970028400421,244.37457275390625,247.01927185058594
+7,0.4322896897792816,213.8999481201172,216.19122314453125,0.4148983061313629,243.9756317138672,246.17474365234375
+8,0.41657161712646484,213.38575744628906,215.59364318847656,0.4152144193649292,245.2055206298828,247.40623474121094
+9,0.4064919054508209,212.86346435546875,215.01785278320312,0.4024210572242737,245.23193359375,247.36474609375
+10,0.39593982696533203,212.179931640625,214.27809143066406,0.40430378913879395,245.2644500732422,247.40740966796875
+11,0.38592529296875,211.45542907714844,213.50099182128906,0.4088464677333832,246.44375610351562,248.6106719970703
+12,0.379146009683609,210.64866638183594,212.65818786621094,0.4107520878314972,246.50408935546875,248.6812286376953

fold_1/model.bias_scaled.fold_1.ENCSR619BNL.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bf248a66aa019cd14b4ad8cbd1b480c9269aea6993b08a5ad444e69b7253a935
+size 2691928

fold_1/model.bias_scaled.fold_1.ENCSR619BNL.tar

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a9c5551e04fe20faae93e5457ce2bb5039af11288128cd7bac48a49a371c5569
+size 1198080

fold_1/model.chrombpnet.fold_1.ENCSR619BNL.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d07e7fb2a2e0d554dbf3a866dc573c9bfe59518f70cade7f4646d7da5419d183
+size 77538904

fold_1/model.chrombpnet.fold_1.ENCSR619BNL.tar

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1a8bdd887246a5e8aa065662dec588be957b21b676235077d4f97456106a5903
+size 27525120

fold_1/model.chrombpnet_nobias.fold_1.ENCSR619BNL.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7d7c279a1ed869f869ad8bea2b54705f34531d58b583a9c301060362458dfd00
+size 25582648

fold_1/model.chrombpnet_nobias.fold_1.ENCSR619BNL.tar

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4eab690023dbb9c6cf69d918581aa0f8f3e84c5b6659c0b9ccae4d0d0c1874d6
+size 26060800

fold_2/logs.models.fold_2.ENCSR619BNL/logfile.modelling.fold_2.ENCSR619BNL.args.json

@@ -0,0 +1,45 @@
+{
+    "cmd": "train",
+    "genome": "/scratch/groups/akundaje/anusri/chromatin_atlas/reference//hg38.genome.fa",
+    "chrom_sizes": "/scratch/groups/akundaje/anusri/chromatin_atlas/reference//chrom.sizes",
+    "input_bam_file": null,
+    "input_fragment_file": null,
+    "input_tagalign_file": null,
+    "bigwig": "/oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/DNASE//ENCSR619BNL//preprocessing/bigWigs/ENCSR619BNL.bigWig",
+    "output_dir": "/scratch/groups/akundaje/anusri/chromatin_atlas/DNASE/ENCSR619BNL//chrombpnet_model_feb15_fold_2/chrombpnet_model/",
+    "data_type": "DNASE",
+    "peaks": "/scratch/groups/akundaje/anusri/chromatin_atlas/DNASE/ENCSR619BNL//chrombpnet_model_feb15_fold_2/chrombpnet_model/auxiliary/ENCSR619BNL_filtered.peaks.bed",
+    "nonpeaks": "/scratch/groups/akundaje/anusri/chromatin_atlas/DNASE/ENCSR619BNL//chrombpnet_model_feb15_fold_2/chrombpnet_model/auxiliary/ENCSR619BNL_filtered.nonpeaks.bed",
+    "chr_fold_path": "/scratch/groups/akundaje/anusri/chromatin_atlas/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/groups/akundaje/anusri/simg/chrombpnet_latest/chrombpnet/chrombpnet/training/models/chrombpnet_with_bias_model.py",
+    "file_prefix": "ENCSR619BNL",
+    "html_prefix": "./",
+    "bias_model_path": "/scratch/groups/akundaje/anusri/chromatin_atlas/DNASE/ENCSR619BNL//chrombpnet_model_feb15_fold_0/bias_model/models/ENCSR619BNL_bias.h5",
+    "negative_sampling_ratio": 0.1,
+    "filters": 512,
+    "n_dilation_layers": 8,
+    "max_jitter": 500,
+    "batch_size": 64,
+    "output_prefix": "/scratch/groups/akundaje/anusri/chromatin_atlas/DNASE/ENCSR619BNL//chrombpnet_model_feb15_fold_2/chrombpnet_model/models/ENCSR619BNL_chrombpnet",
+    "chr": "chr22",
+    "pwm_width": 24,
+    "params": "/scratch/groups/akundaje/anusri/chromatin_atlas/DNASE/ENCSR619BNL//chrombpnet_model_feb15_fold_2/chrombpnet_model/logs/ENCSR619BNL_chrombpnet_model_params.tsv"
+}

fold_2/logs.models.fold_2.ENCSR619BNL/logfile.modelling.fold_2.ENCSR619BNL.bias_formatting.stdout.txt

@@ -0,0 +1 @@
+Converting /oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/DNASE/ENCSR619BNL/failed_models_retrained/chrombpnet_model_feb15_fold_2/chrombpnet_model/models/ENCSR619BNL_bias_model_scaled.h5 to /oak/stanford/groups/akundaje/vhecht/chromatin-atlas-2022/DNASE/ENCSR619BNL/fold_2/new_model_format/bias_model_scaled.tar with get_new_tf_model_format.py

fold_2/logs.models.fold_2.ENCSR619BNL/logfile.modelling.fold_2.ENCSR619BNL.chrombpnet_data_params.tsv

@@ -0,0 +1,3 @@
+counts_sum_min_thresh	0.0
+counts_sum_max_thresh	690.17
+trainings_pts_post_thresh	178206

fold_2/logs.models.fold_2.ENCSR619BNL/logfile.modelling.fold_2.ENCSR619BNL.chrombpnet_formatting.stdout.txt

@@ -0,0 +1 @@
+Converting /oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/DNASE/ENCSR619BNL/failed_models_retrained/chrombpnet_model_feb15_fold_2/chrombpnet_model/models/ENCSR619BNL_chrombpnet.h5 to /oak/stanford/groups/akundaje/vhecht/chromatin-atlas-2022/DNASE/ENCSR619BNL/fold_2/new_model_format/chrombpnet.tar with get_new_tf_model_format.py

fold_2/logs.models.fold_2.ENCSR619BNL/logfile.modelling.fold_2.ENCSR619BNL.chrombpnet_model_params.tsv

@@ -0,0 +1,9 @@
+counts_loss_weight	5.3
+filters	512
+n_dil_layers	8
+bias_model_path	/scratch/groups/akundaje/anusri/chromatin_atlas/DNASE/ENCSR619BNL//chrombpnet_model_feb15_fold_2/chrombpnet_model/models/ENCSR619BNL_bias_model_scaled.h5
+inputlen	2114
+outputlen	1000
+max_jitter	500
+chr_fold_path	/scratch/groups/akundaje/anusri/chromatin_atlas/splits/fold_2.json
+negative_sampling_ratio	0.1

fold_2/logs.models.fold_2.ENCSR619BNL/logfile.modelling.fold_2.ENCSR619BNL.chrombpnet_no_bias_formatting.stdout.txt

@@ -0,0 +1 @@
+Converting /oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/DNASE/ENCSR619BNL/failed_models_retrained/chrombpnet_model_feb15_fold_2/chrombpnet_model/models/ENCSR619BNL_chrombpnet_nobias.h5 to /oak/stanford/groups/akundaje/vhecht/chromatin-atlas-2022/DNASE/ENCSR619BNL/fold_2/new_model_format/chrombpnet_nobias.tar with get_new_tf_model_format.py

fold_2/logs.models.fold_2.ENCSR619BNL/logfile.modelling.fold_2.ENCSR619BNL.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
+0,1.6549738645553589,223.3644256591797,232.13552856445312,0.6760233640670776,225.31329345703125,228.89617919921875
+1,0.5762621164321899,218.72116088867188,221.7750244140625,0.5176473259925842,224.39451599121094,227.13807678222656
+2,0.5203877687454224,217.23941040039062,219.99766540527344,0.4779370427131653,222.6845245361328,225.21759033203125
+3,0.48550334572792053,216.43064880371094,219.00355529785156,0.46243059635162354,223.89515686035156,226.34600830078125
+4,0.4628565013408661,215.80691528320312,218.2598876953125,0.4481479525566101,223.33770751953125,225.712890625
+5,0.44103172421455383,214.9916229248047,217.3291015625,0.43346697092056274,222.292236328125,224.58963012695312
+6,0.42682042717933655,214.84661865234375,217.10879516601562,0.4689171314239502,222.74908447265625,225.23439025878906
+7,0.41009321808815,213.76304626464844,215.93687438964844,0.46627292037010193,222.87393188476562,225.34512329101562
+8,0.4028647840023041,213.4446258544922,215.57992553710938,0.49567991495132446,223.31797790527344,225.94512939453125
+9,0.38827407360076904,212.54481506347656,214.6027374267578,0.4560485780239105,223.7475128173828,226.16453552246094
+10,0.38057875633239746,212.27743530273438,214.29440307617188,0.4430394172668457,223.50851440429688,225.85670471191406

fold_2/model.bias_scaled.fold_2.ENCSR619BNL.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:29ebcaf121192aaf40616de9a8ff814bb1dec5ba4a04db3a9ef470e73edfb34f
+size 2691928

fold_2/model.bias_scaled.fold_2.ENCSR619BNL.tar

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:88c5403b68a74dc7823a1d7dedac71f32d4d58f4cdcb462ec5c592e67bacfa3d
+size 1198080

fold_2/model.chrombpnet.fold_2.ENCSR619BNL.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1be4b89a94116cee1c6d2f657403329152384a6feee4634f0ec6c6e7ca2b41eb
+size 77538904

fold_2/model.chrombpnet.fold_2.ENCSR619BNL.tar

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f8acf6f9d2f7ccb78a77ecd877ebc618a949022af00ae6da91d3650e03f36da5
+size 27525120

fold_2/model.chrombpnet_nobias.fold_2.ENCSR619BNL.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c2fe1c11e7e53b261686b89aa7dfbfe53f143ef39789f94f23b8188cea72ea83
+size 25582648

fold_2/model.chrombpnet_nobias.fold_2.ENCSR619BNL.tar

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:614b43df1b66ff0a09b27b7541d99e9e94a61754f2b85e8def4dda1a3c198767
+size 26060800

fold_3/logs.models.fold_3.ENCSR619BNL/logfile.modelling.fold_3.ENCSR619BNL.args.json

@@ -0,0 +1,45 @@
+{
+    "cmd": "train",
+    "genome": "/scratch/groups/akundaje/anusri/chromatin_atlas/reference//hg38.genome.fa",
+    "chrom_sizes": "/scratch/groups/akundaje/anusri/chromatin_atlas/reference//chrom.sizes",
+    "input_bam_file": null,
+    "input_fragment_file": null,
+    "input_tagalign_file": null,
+    "bigwig": "/oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/DNASE//ENCSR619BNL//preprocessing/bigWigs/ENCSR619BNL.bigWig",
+    "output_dir": "/scratch/groups/akundaje/anusri/chromatin_atlas/DNASE/ENCSR619BNL//chrombpnet_model_feb15_fold_3/chrombpnet_model/",
+    "data_type": "DNASE",
+    "peaks": "/scratch/groups/akundaje/anusri/chromatin_atlas/DNASE/ENCSR619BNL//chrombpnet_model_feb15_fold_3/chrombpnet_model/auxiliary/ENCSR619BNL_filtered.peaks.bed",
+    "nonpeaks": "/scratch/groups/akundaje/anusri/chromatin_atlas/DNASE/ENCSR619BNL//chrombpnet_model_feb15_fold_3/chrombpnet_model/auxiliary/ENCSR619BNL_filtered.nonpeaks.bed",
+    "chr_fold_path": "/scratch/groups/akundaje/anusri/chromatin_atlas/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/groups/akundaje/anusri/simg/chrombpnet_latest/chrombpnet/chrombpnet/training/models/chrombpnet_with_bias_model.py",
+    "file_prefix": "ENCSR619BNL",
+    "html_prefix": "./",
+    "bias_model_path": "/scratch/groups/akundaje/anusri/chromatin_atlas/DNASE/ENCSR619BNL//chrombpnet_model_feb15_fold_0/bias_model/models/ENCSR619BNL_bias.h5",
+    "negative_sampling_ratio": 0.1,
+    "filters": 512,
+    "n_dilation_layers": 8,
+    "max_jitter": 500,
+    "batch_size": 64,
+    "output_prefix": "/scratch/groups/akundaje/anusri/chromatin_atlas/DNASE/ENCSR619BNL//chrombpnet_model_feb15_fold_3/chrombpnet_model/models/ENCSR619BNL_chrombpnet",
+    "chr": "chr6",
+    "pwm_width": 24,
+    "params": "/scratch/groups/akundaje/anusri/chromatin_atlas/DNASE/ENCSR619BNL//chrombpnet_model_feb15_fold_3/chrombpnet_model/logs/ENCSR619BNL_chrombpnet_model_params.tsv"
+}

fold_3/logs.models.fold_3.ENCSR619BNL/logfile.modelling.fold_3.ENCSR619BNL.bias_formatting.stdout.txt

@@ -0,0 +1 @@
+Converting /oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/DNASE/ENCSR619BNL/failed_models_retrained/chrombpnet_model_feb15_fold_3/chrombpnet_model/models/ENCSR619BNL_bias_model_scaled.h5 to /oak/stanford/groups/akundaje/vhecht/chromatin-atlas-2022/DNASE/ENCSR619BNL/fold_3/new_model_format/bias_model_scaled.tar with get_new_tf_model_format.py

fold_3/logs.models.fold_3.ENCSR619BNL/logfile.modelling.fold_3.ENCSR619BNL.chrombpnet_data_params.tsv

@@ -0,0 +1,3 @@
+counts_sum_min_thresh	0.0
+counts_sum_max_thresh	714.23
+trainings_pts_post_thresh	172365

fold_3/logs.models.fold_3.ENCSR619BNL/logfile.modelling.fold_3.ENCSR619BNL.chrombpnet_formatting.stdout.txt

@@ -0,0 +1 @@
+Converting /oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/DNASE/ENCSR619BNL/failed_models_retrained/chrombpnet_model_feb15_fold_3/chrombpnet_model/models/ENCSR619BNL_chrombpnet.h5 to /oak/stanford/groups/akundaje/vhecht/chromatin-atlas-2022/DNASE/ENCSR619BNL/fold_3/new_model_format/chrombpnet.tar with get_new_tf_model_format.py

fold_3/logs.models.fold_3.ENCSR619BNL/logfile.modelling.fold_3.ENCSR619BNL.chrombpnet_model_params.tsv

@@ -0,0 +1,9 @@
+counts_loss_weight	5.3
+filters	512
+n_dil_layers	8
+bias_model_path	/scratch/groups/akundaje/anusri/chromatin_atlas/DNASE/ENCSR619BNL//chrombpnet_model_feb15_fold_3/chrombpnet_model/models/ENCSR619BNL_bias_model_scaled.h5
+inputlen	2114
+outputlen	1000
+max_jitter	500
+chr_fold_path	/scratch/groups/akundaje/anusri/chromatin_atlas/splits/fold_3.json
+negative_sampling_ratio	0.1

fold_3/logs.models.fold_3.ENCSR619BNL/logfile.modelling.fold_3.ENCSR619BNL.chrombpnet_no_bias_formatting.stdout.txt

@@ -0,0 +1 @@
+Converting /oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/DNASE/ENCSR619BNL/failed_models_retrained/chrombpnet_model_feb15_fold_3/chrombpnet_model/models/ENCSR619BNL_chrombpnet_nobias.h5 to /oak/stanford/groups/akundaje/vhecht/chromatin-atlas-2022/DNASE/ENCSR619BNL/fold_3/new_model_format/chrombpnet_nobias.tar with get_new_tf_model_format.py