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 (ENCSR649PJN)
+- Model: ChromBPNet
+- Assay: DNASE-seq
+- Experiment: [ENCSR649PJN](https://www.encodeproject.org/experiments/ENCSR649PJN/)
+- Model annotation: [ENCSR099UWX](https://www.encodeproject.org/annotations/ENCSR099UWX/)
+- 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.ENCSR649PJN/logfile.modelling.fold_0.ENCSR649PJN.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/ENCSR649PJN/preprocessing/bigWigs/ENCSR649PJN.bigWig",
+    "output_dir": "/oak/stanford/groups/akundaje/ziwei75/chromatin_atlas_bias/DNase_model/bias_filtered/ENCSR649PJN//fold0/",
+    "data_type": "DNASE",
+    "peaks": "/oak/stanford/groups/akundaje/ziwei75/chromatin_atlas_bias/DNase_model/bias_filtered/ENCSR649PJN//fold0/auxiliary/filtered.peaks.bed",
+    "nonpeaks": "/oak/stanford/groups/akundaje/ziwei75/chromatin_atlas_bias/DNase_model/bias_filtered/ENCSR649PJN//fold0/auxiliary/filtered.nonpeaks.bed",
+    "chr_fold_path": "/oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/splits/fold_0.json",
+    "outlier_threshold": 0.9999,
+    "ATAC_ref_path": null,
+    "DNASE_ref_path": null,
+    "num_samples": 10000,
+    "inputlen": 2114,
+    "outputlen": 1000,
+    "seed": 1234,
+    "epochs": 50,
+    "early_stop": 5,
+    "learning_rate": 0.001,
+    "trackables": [
+        "logcount_predictions_loss",
+        "loss",
+        "logits_profile_predictions_loss",
+        "val_logcount_predictions_loss",
+        "val_loss",
+        "val_logits_profile_predictions_loss"
+    ],
+    "architecture_from_file": "/home/groups/akundaje/ziwei75/anaconda3/envs/chrombpnet/lib/python3.8/site-packages/chrombpnet/training/models/chrombpnet_with_bias_model.py",
+    "file_prefix": null,
+    "html_prefix": "./",
+    "bias_model_path": "/oak/stanford/groups/akundaje/ziwei75/chromatin_atlas_bias/DNase_bias_model/filtered_negatives_models/ENCSR649PJN/models/bias.h5",
+    "negative_sampling_ratio": 0.1,
+    "filters": 512,
+    "n_dilation_layers": 8,
+    "max_jitter": 500,
+    "batch_size": 64,
+    "output_prefix": "/oak/stanford/groups/akundaje/ziwei75/chromatin_atlas_bias/DNase_model/bias_filtered/ENCSR649PJN//fold0/models/chrombpnet",
+    "chr": "chr8",
+    "pwm_width": 24,
+    "params": "/oak/stanford/groups/akundaje/ziwei75/chromatin_atlas_bias/DNase_model/bias_filtered/ENCSR649PJN//fold0/logs/chrombpnet_model_params.tsv"
+}

fold_0/logs.models.fold_0.ENCSR649PJN/logfile.modelling.fold_0.ENCSR649PJN.bias_formatting.stdout.txt

@@ -0,0 +1 @@
+Converting /oak/stanford/groups/akundaje/ziwei75/chromatin_atlas_bias/DNase_model/bias_filtered/ENCSR649PJN/fold0/models/bias_model_scaled.h5 to /oak/stanford/groups/akundaje/vhecht/chromatin-atlas-2022/DNASE/ENCSR649PJN/fold_0/new_model_format/bias_model_scaled.tar with get_new_tf_model_format.py

fold_0/logs.models.fold_0.ENCSR649PJN/logfile.modelling.fold_0.ENCSR649PJN.chrombpnet_data_params.tsv

@@ -0,0 +1,3 @@
+counts_sum_min_thresh	0.0
+counts_sum_max_thresh	1172.67
+trainings_pts_post_thresh	170210

fold_0/logs.models.fold_0.ENCSR649PJN/logfile.modelling.fold_0.ENCSR649PJN.chrombpnet_formatting.stdout.txt

@@ -0,0 +1 @@
+Converting /oak/stanford/groups/akundaje/ziwei75/chromatin_atlas_bias/DNase_model/bias_filtered/ENCSR649PJN/fold0/models/chrombpnet.h5 to /oak/stanford/groups/akundaje/vhecht/chromatin-atlas-2022/DNASE/ENCSR649PJN/fold_0/new_model_format/chrombpnet.tar with get_new_tf_model_format.py

fold_0/logs.models.fold_0.ENCSR649PJN/logfile.modelling.fold_0.ENCSR649PJN.chrombpnet_model_params.tsv

@@ -0,0 +1,9 @@
+counts_loss_weight	4.6
+filters	512
+n_dil_layers	8
+bias_model_path	/oak/stanford/groups/akundaje/ziwei75/chromatin_atlas_bias/DNase_model/bias_filtered/ENCSR649PJN//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.ENCSR649PJN/logfile.modelling.fold_0.ENCSR649PJN.chrombpnet_no_bias_formatting.stdout.txt

@@ -0,0 +1 @@
+Converting /oak/stanford/groups/akundaje/ziwei75/chromatin_atlas_bias/DNase_model/bias_filtered/ENCSR649PJN/fold0/models/chrombpnet_nobias.h5 to /oak/stanford/groups/akundaje/vhecht/chromatin-atlas-2022/DNASE/ENCSR649PJN/fold_0/new_model_format/chrombpnet_nobias.tar with get_new_tf_model_format.py

fold_0/logs.models.fold_0.ENCSR649PJN/logfile.modelling.fold_0.ENCSR649PJN.epoch_loss.csv

@@ -0,0 +1,17 @@
+epoch,logcount_predictions_loss,logits_profile_predictions_loss,loss,val_logcount_predictions_loss,val_logits_profile_predictions_loss,val_loss
+0,5.967965602874756,215.96682739257812,243.4190673828125,1.0606416463851929,217.95896911621094,222.83787536621094
+1,0.855125367641449,208.04705810546875,211.98072814941406,0.7443621158599854,214.9122314453125,218.33644104003906
+2,0.7594290375709534,205.6165313720703,209.10983276367188,0.7168261408805847,211.57965087890625,214.87716674804688
+3,0.7204814553260803,203.91555786132812,207.22975158691406,0.6718589067459106,211.3121337890625,214.40260314941406
+4,0.6729836463928223,202.84310913085938,205.93896484375,0.6354091167449951,211.45681762695312,214.3798065185547
+5,0.6440838575363159,202.04551696777344,205.00820922851562,0.6459977030754089,210.44415283203125,213.4156036376953
+6,0.6193262934684753,201.15769958496094,204.0064697265625,0.6338004469871521,210.23333740234375,213.14889526367188
+7,0.5965703129768372,200.47207641601562,203.21656799316406,0.6168294548988342,210.68785095214844,213.52525329589844
+8,0.5753414034843445,199.88833618164062,202.5347900390625,0.6391820311546326,209.7085418701172,212.64877319335938
+9,0.5605887770652771,199.45220947265625,202.03097534179688,0.5810825228691101,211.4359130859375,214.10897827148438
+10,0.5476375818252563,198.67848205566406,201.19778442382812,0.5783047676086426,209.74838256835938,212.40859985351562
+11,0.5414371490478516,197.917236328125,200.40792846679688,0.5780309438705444,210.04965209960938,212.70855712890625
+12,0.5245844125747681,197.4334259033203,199.8466796875,0.5567233562469482,210.0187225341797,212.5797119140625
+13,0.5148270130157471,197.2169647216797,199.58543395996094,0.5590811371803284,210.7871551513672,213.3589324951172
+14,0.5076430439949036,196.708251953125,199.04359436035156,0.56895911693573,210.3797149658203,212.99696350097656
+15,0.4964577853679657,196.3555908203125,198.63919067382812,0.5501043200492859,210.0323486328125,212.5628662109375

fold_0/model.bias_scaled.fold_0.ENCSR649PJN.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ac2e28db6963cef21343f7d63f1bd5b0fa07f7eec3cde5451d04cb92b939f693
+size 2691928

fold_0/model.bias_scaled.fold_0.ENCSR649PJN.tar

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2b7674419b61bb075489919d6e00acf26aa90249617cc5610dab7195e0f968c0
+size 1198080

fold_0/model.chrombpnet.fold_0.ENCSR649PJN.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9be6f94355e9a6f21c90599b2ae47c7f613ad44f42c962732317110dedc4e9b5
+size 77538952

fold_0/model.chrombpnet.fold_0.ENCSR649PJN.tar

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c02689671a7c7428600afb8332009f84d74281c85316e1829e41889cde63b17b
+size 27525120

fold_0/model.chrombpnet_nobias.fold_0.ENCSR649PJN.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7787c0e1f5eb6376357481655df1ce51ae18dc519a9bb96805dbee590f41b9c1
+size 25582648

fold_0/model.chrombpnet_nobias.fold_0.ENCSR649PJN.tar

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6dad900327c04c85390f4dfb78f250fea0dfa6a224e75f1c326225729b2c95e5
+size 26060800

fold_1/logs.models.fold_1.ENCSR649PJN/logfile.modelling.fold_1.ENCSR649PJN.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/ENCSR649PJN/preprocessing/bigWigs/ENCSR649PJN.bigWig",
+    "input_fragment_file": null,
+    "input_tagalign_file": null,
+    "output_dir": "/oak/stanford/groups/akundaje/vhecht/chromatin_atlas_bias_corrected/DNASE_model/ENCSR649PJN/fold_1",
+    "data_type": "DNASE",
+    "peaks": "/oak/stanford/groups/akundaje/vhecht/chromatin_atlas_bias_corrected/DNASE_model/ENCSR649PJN/fold_1/auxiliary/filtered.peaks.bed",
+    "nonpeaks": "/oak/stanford/groups/akundaje/vhecht/chromatin_atlas_bias_corrected/DNASE_model/ENCSR649PJN/fold_1/auxiliary/filtered.nonpeaks.bed",
+    "chr_fold_path": "/oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/splits/fold_1.json",
+    "outlier_threshold": 0.9999,
+    "ATAC_ref_path": null,
+    "DNASE_ref_path": null,
+    "num_samples": 10000,
+    "inputlen": 2114,
+    "outputlen": 1000,
+    "seed": 1234,
+    "epochs": 50,
+    "early_stop": 5,
+    "learning_rate": 0.001,
+    "trackables": [
+        "logcount_predictions_loss",
+        "loss",
+        "logits_profile_predictions_loss",
+        "val_logcount_predictions_loss",
+        "val_loss",
+        "val_logits_profile_predictions_loss"
+    ],
+    "architecture_from_file": "/home/users/vhecht/chrombpnet/chrombpnet/chrombpnet/training/models/chrombpnet_with_bias_model.py",
+    "file_prefix": null,
+    "html_prefix": "./",
+    "bsort": false,
+    "tmpdir": null,
+    "no_st": false,
+    "bias_model_path": "/oak/stanford/groups/akundaje/ziwei75/chromatin_atlas_bias/DNase_bias_model/filtered_negatives_models/ENCSR649PJN/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/ENCSR649PJN/fold_1/models/chrombpnet",
+    "bigwig": "/oak/stanford/groups/akundaje/vhecht/chromatin_atlas_bias_corrected/DNASE_model/ENCSR649PJN/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/ENCSR649PJN/fold_1/logs/chrombpnet_model_params.tsv"
+}

fold_1/logs.models.fold_1.ENCSR649PJN/logfile.modelling.fold_1.ENCSR649PJN.bias_formatting.stdout.txt

@@ -0,0 +1 @@
+Converting /oak/stanford/groups/akundaje/vhecht/chromatin_atlas_bias_corrected/DNASE_model/ENCSR649PJN/fold_1/models/bias_model_scaled.h5 to /oak/stanford/groups/akundaje/vhecht/chromatin-atlas-2022/DNASE/ENCSR649PJN/fold_1/new_model_format/bias_model_scaled.tar with get_new_tf_model_format.py

fold_1/logs.models.fold_1.ENCSR649PJN/logfile.modelling.fold_1.ENCSR649PJN.chrombpnet_data_params.tsv

@@ -0,0 +1,3 @@
+counts_sum_min_thresh	0.0
+counts_sum_max_thresh	1264.88
+trainings_pts_post_thresh	172530

fold_1/logs.models.fold_1.ENCSR649PJN/logfile.modelling.fold_1.ENCSR649PJN.chrombpnet_formatting.stdout.txt

@@ -0,0 +1 @@
+Converting /oak/stanford/groups/akundaje/vhecht/chromatin_atlas_bias_corrected/DNASE_model/ENCSR649PJN/fold_1/models/chrombpnet.h5 to /oak/stanford/groups/akundaje/vhecht/chromatin-atlas-2022/DNASE/ENCSR649PJN/fold_1/new_model_format/chrombpnet.tar with get_new_tf_model_format.py

fold_1/logs.models.fold_1.ENCSR649PJN/logfile.modelling.fold_1.ENCSR649PJN.chrombpnet_model_params.tsv

@@ -0,0 +1,9 @@
+counts_loss_weight	4.7
+filters	512
+n_dil_layers	8
+bias_model_path	/oak/stanford/groups/akundaje/vhecht/chromatin_atlas_bias_corrected/DNASE_model/ENCSR649PJN/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.ENCSR649PJN/logfile.modelling.fold_1.ENCSR649PJN.chrombpnet_no_bias_formatting.stdout.txt

@@ -0,0 +1 @@
+Converting /oak/stanford/groups/akundaje/vhecht/chromatin_atlas_bias_corrected/DNASE_model/ENCSR649PJN/fold_1/models/chrombpnet_nobias.h5 to /oak/stanford/groups/akundaje/vhecht/chromatin-atlas-2022/DNASE/ENCSR649PJN/fold_1/new_model_format/chrombpnet_nobias.tar with get_new_tf_model_format.py

fold_1/logs.models.fold_1.ENCSR649PJN/logfile.modelling.fold_1.ENCSR649PJN.epoch_loss.csv

@@ -0,0 +1,16 @@
+epoch,logcount_predictions_loss,logits_profile_predictions_loss,loss,val_logcount_predictions_loss,val_logits_profile_predictions_loss,val_loss
+0,1.6214804649353027,214.7259063720703,222.346435546875,0.7800909876823425,234.8141632080078,238.48060607910156
+1,0.7778463959693909,206.6686553955078,210.32443237304688,0.7057173252105713,232.96498107910156,236.28182983398438
+2,0.7116174697875977,204.45458984375,207.7991180419922,0.6607666611671448,230.3150634765625,233.4205322265625
+3,0.6637783050537109,202.94720458984375,206.06689453125,0.6920579075813293,228.75343322753906,232.006103515625
+4,0.6339744329452515,201.9883270263672,204.96792602539062,0.617335319519043,229.30496215820312,232.20639038085938
+5,0.6163660883903503,200.9308624267578,203.82801818847656,0.5762021541595459,228.94004821777344,231.64820861816406
+6,0.5896767973899841,200.6460418701172,203.4176025390625,0.5568812489509583,228.74961853027344,231.36695861816406
+7,0.5705805420875549,199.65113830566406,202.3328857421875,0.5504284501075745,229.2815399169922,231.86866760253906
+8,0.5529249310493469,199.50082397460938,202.0997772216797,0.5542203187942505,229.50460815429688,232.10939025878906
+9,0.5396430492401123,198.76046752929688,201.2970733642578,0.5455542802810669,228.255859375,230.81997680664062
+10,0.5332522392272949,198.3297576904297,200.8361358642578,0.5323803424835205,229.60089111328125,232.10311889648438
+11,0.5156835317611694,197.75112915039062,200.1750030517578,0.6215651631355286,229.27398681640625,232.19546508789062
+12,0.5094215869903564,197.35256958007812,199.74684143066406,0.6064612865447998,229.9601593017578,232.8104248046875
+13,0.5011780261993408,196.76513671875,199.1206817626953,0.5363137722015381,229.6217803955078,232.14236450195312
+14,0.4907800555229187,196.41705322265625,198.7237091064453,0.5721378326416016,231.5216064453125,234.21067810058594

fold_1/model.bias_scaled.fold_1.ENCSR649PJN.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2d397cfadead2419e2fe484f6fd326917ab22d421d1c2ff64296cdc6c50bbdea
+size 2691928

fold_1/model.bias_scaled.fold_1.ENCSR649PJN.tar

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:db7b1a04dc56ef86192b53963cfc2bacf641442ca75c83ee180cbaab03f70e4b
+size 1198080

fold_1/model.chrombpnet.fold_1.ENCSR649PJN.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2333f9300f752adb12fa5af8528e158cb1967ef551a3967805945e56ec00f346
+size 77538840

fold_1/model.chrombpnet.fold_1.ENCSR649PJN.tar

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:10b0869e2d114656319a49105af8dbc03c5a70788ca40707cb90e4120eca4a25
+size 27525120

fold_1/model.chrombpnet_nobias.fold_1.ENCSR649PJN.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:27fee33aa376e13f00893dd32d02f2dd708f20f2b2bac81750d6e9abb22dcc1c
+size 25582648

fold_1/model.chrombpnet_nobias.fold_1.ENCSR649PJN.tar

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f2754374c4502875d9a0479587dce8a716beb48e20df5407f1f3a785c9f2766d
+size 26060800

fold_2/logs.models.fold_2.ENCSR649PJN/logfile.modelling.fold_2.ENCSR649PJN.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/ENCSR649PJN/preprocessing/bigWigs/ENCSR649PJN.bigWig",
+    "input_fragment_file": null,
+    "input_tagalign_file": null,
+    "output_dir": "/oak/stanford/groups/akundaje/vhecht/chromatin_atlas_bias_corrected/DNASE_model/ENCSR649PJN/fold_2",
+    "data_type": "DNASE",
+    "peaks": "/oak/stanford/groups/akundaje/vhecht/chromatin_atlas_bias_corrected/DNASE_model/ENCSR649PJN/fold_2/auxiliary/filtered.peaks.bed",
+    "nonpeaks": "/oak/stanford/groups/akundaje/vhecht/chromatin_atlas_bias_corrected/DNASE_model/ENCSR649PJN/fold_2/auxiliary/filtered.nonpeaks.bed",
+    "chr_fold_path": "/oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/splits/fold_2.json",
+    "outlier_threshold": 0.9999,
+    "ATAC_ref_path": null,
+    "DNASE_ref_path": null,
+    "num_samples": 10000,
+    "inputlen": 2114,
+    "outputlen": 1000,
+    "seed": 1234,
+    "epochs": 50,
+    "early_stop": 5,
+    "learning_rate": 0.001,
+    "trackables": [
+        "logcount_predictions_loss",
+        "loss",
+        "logits_profile_predictions_loss",
+        "val_logcount_predictions_loss",
+        "val_loss",
+        "val_logits_profile_predictions_loss"
+    ],
+    "architecture_from_file": "/home/users/vhecht/chrombpnet/chrombpnet/chrombpnet/training/models/chrombpnet_with_bias_model.py",
+    "file_prefix": null,
+    "html_prefix": "./",
+    "bsort": false,
+    "tmpdir": null,
+    "no_st": false,
+    "bias_model_path": "/oak/stanford/groups/akundaje/ziwei75/chromatin_atlas_bias/DNase_bias_model/filtered_negatives_models/ENCSR649PJN/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/ENCSR649PJN/fold_2/models/chrombpnet",
+    "bigwig": "/oak/stanford/groups/akundaje/vhecht/chromatin_atlas_bias_corrected/DNASE_model/ENCSR649PJN/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/ENCSR649PJN/fold_2/logs/chrombpnet_model_params.tsv"
+}

fold_2/logs.models.fold_2.ENCSR649PJN/logfile.modelling.fold_2.ENCSR649PJN.bias_formatting.stdout.txt

@@ -0,0 +1 @@
+Converting /oak/stanford/groups/akundaje/vhecht/chromatin_atlas_bias_corrected/DNASE_model/ENCSR649PJN/fold_2/models/bias_model_scaled.h5 to /oak/stanford/groups/akundaje/vhecht/chromatin-atlas-2022/DNASE/ENCSR649PJN/fold_2/new_model_format/bias_model_scaled.tar with get_new_tf_model_format.py

fold_2/logs.models.fold_2.ENCSR649PJN/logfile.modelling.fold_2.ENCSR649PJN.chrombpnet_data_params.tsv

@@ -0,0 +1,3 @@
+counts_sum_min_thresh	0.0
+counts_sum_max_thresh	1196.43
+trainings_pts_post_thresh	177509

fold_2/logs.models.fold_2.ENCSR649PJN/logfile.modelling.fold_2.ENCSR649PJN.chrombpnet_formatting.stdout.txt

@@ -0,0 +1 @@
+Converting /oak/stanford/groups/akundaje/vhecht/chromatin_atlas_bias_corrected/DNASE_model/ENCSR649PJN/fold_2/models/chrombpnet.h5 to /oak/stanford/groups/akundaje/vhecht/chromatin-atlas-2022/DNASE/ENCSR649PJN/fold_2/new_model_format/chrombpnet.tar with get_new_tf_model_format.py

fold_2/logs.models.fold_2.ENCSR649PJN/logfile.modelling.fold_2.ENCSR649PJN.chrombpnet_model_params.tsv

@@ -0,0 +1,9 @@
+counts_loss_weight	4.7
+filters	512
+n_dil_layers	8
+bias_model_path	/oak/stanford/groups/akundaje/vhecht/chromatin_atlas_bias_corrected/DNASE_model/ENCSR649PJN/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.ENCSR649PJN/logfile.modelling.fold_2.ENCSR649PJN.chrombpnet_no_bias_formatting.stdout.txt

@@ -0,0 +1 @@
+Converting /oak/stanford/groups/akundaje/vhecht/chromatin_atlas_bias_corrected/DNASE_model/ENCSR649PJN/fold_2/models/chrombpnet_nobias.h5 to /oak/stanford/groups/akundaje/vhecht/chromatin-atlas-2022/DNASE/ENCSR649PJN/fold_2/new_model_format/chrombpnet_nobias.tar with get_new_tf_model_format.py

fold_2/logs.models.fold_2.ENCSR649PJN/logfile.modelling.fold_2.ENCSR649PJN.epoch_loss.csv

@@ -0,0 +1,10 @@
+epoch,logcount_predictions_loss,logits_profile_predictions_loss,loss,val_logcount_predictions_loss,val_logits_profile_predictions_loss,val_loss
+0,1.491939663887024,213.1607208251953,220.17298889160156,1.165381908416748,212.2357635498047,217.71319580078125
+1,0.7342745661735535,205.7106170654297,209.1615447998047,0.7862656712532043,210.2234649658203,213.9188995361328
+2,0.6741521954536438,203.7443084716797,206.91299438476562,0.7009404897689819,208.6019744873047,211.89645385742188
+3,0.632621705532074,202.7152099609375,205.6886749267578,0.5965461730957031,207.52801513671875,210.3316650390625
+4,0.6090807318687439,201.80589294433594,204.6685791015625,0.597568929195404,208.46112060546875,211.26968383789062
+5,0.581695020198822,201.09471130371094,203.82839965820312,0.5876322984695435,208.05799865722656,210.8198699951172
+6,0.5625433921813965,200.426513671875,203.07037353515625,0.571067750453949,209.11106872558594,211.79513549804688
+7,0.5534482598304749,199.7774200439453,202.3787841796875,0.5687699913978577,209.69320678710938,212.3662567138672
+8,0.5430980324745178,199.36785888671875,201.92042541503906,0.5660051107406616,208.89894104003906,211.55914306640625

fold_2/model.bias_scaled.fold_2.ENCSR649PJN.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5da951c36a8eeb0e47ca3d442a905f310aba3760e10e43aee227d4f41389f346
+size 2691928

fold_2/model.bias_scaled.fold_2.ENCSR649PJN.tar

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a1f71a5c5b62d9f5ac9136d1c2a110832a23da30fb7206b6a9f5fad810cc21d9
+size 1198080

fold_2/model.chrombpnet.fold_2.ENCSR649PJN.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:722af604c22a71c3f61d7b66731407557956ce3e8af3528e40704fa87a507882
+size 77538840

fold_2/model.chrombpnet.fold_2.ENCSR649PJN.tar

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:913376368757f7e0b8d73673a7772ff1ee62918e52fd9ccce28b9e7687f421f3
+size 27525120

fold_2/model.chrombpnet_nobias.fold_2.ENCSR649PJN.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:900104e4e33d89ca997a87fbafa872d2646ce28bbc1bf9fab573ecc0abde76a3
+size 25582648

fold_2/model.chrombpnet_nobias.fold_2.ENCSR649PJN.tar

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:41e7a6dda70bb4a8480ca22cd69823b3dc2e212c5f46f8f5d57c0ef0a41515c4
+size 26060800

fold_3/logs.models.fold_3.ENCSR649PJN/logfile.modelling.fold_3.ENCSR649PJN.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/ENCSR649PJN/preprocessing/bigWigs/ENCSR649PJN.bigWig",
+    "input_fragment_file": null,
+    "input_tagalign_file": null,
+    "output_dir": "/oak/stanford/groups/akundaje/vhecht/chromatin_atlas_bias_corrected/DNASE_model/ENCSR649PJN/fold_3",
+    "data_type": "DNASE",
+    "peaks": "/oak/stanford/groups/akundaje/vhecht/chromatin_atlas_bias_corrected/DNASE_model/ENCSR649PJN/fold_3/auxiliary/filtered.peaks.bed",
+    "nonpeaks": "/oak/stanford/groups/akundaje/vhecht/chromatin_atlas_bias_corrected/DNASE_model/ENCSR649PJN/fold_3/auxiliary/filtered.nonpeaks.bed",
+    "chr_fold_path": "/oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/splits/fold_3.json",
+    "outlier_threshold": 0.9999,
+    "ATAC_ref_path": null,
+    "DNASE_ref_path": null,
+    "num_samples": 10000,
+    "inputlen": 2114,
+    "outputlen": 1000,
+    "seed": 1234,
+    "epochs": 50,
+    "early_stop": 5,
+    "learning_rate": 0.001,
+    "trackables": [
+        "logcount_predictions_loss",
+        "loss",
+        "logits_profile_predictions_loss",
+        "val_logcount_predictions_loss",
+        "val_loss",
+        "val_logits_profile_predictions_loss"
+    ],
+    "architecture_from_file": "/home/users/vhecht/chrombpnet/chrombpnet/chrombpnet/training/models/chrombpnet_with_bias_model.py",
+    "file_prefix": null,
+    "html_prefix": "./",
+    "bsort": false,
+    "tmpdir": null,
+    "no_st": false,
+    "bias_model_path": "/oak/stanford/groups/akundaje/ziwei75/chromatin_atlas_bias/DNase_bias_model/filtered_negatives_models/ENCSR649PJN/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/ENCSR649PJN/fold_3/models/chrombpnet",
+    "bigwig": "/oak/stanford/groups/akundaje/vhecht/chromatin_atlas_bias_corrected/DNASE_model/ENCSR649PJN/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/ENCSR649PJN/fold_3/logs/chrombpnet_model_params.tsv"
+}

fold_3/logs.models.fold_3.ENCSR649PJN/logfile.modelling.fold_3.ENCSR649PJN.bias_formatting.stdout.txt

@@ -0,0 +1 @@
+Converting /oak/stanford/groups/akundaje/vhecht/chromatin_atlas_bias_corrected/DNASE_model/ENCSR649PJN/fold_3/models/bias_model_scaled.h5 to /oak/stanford/groups/akundaje/vhecht/chromatin-atlas-2022/DNASE/ENCSR649PJN/fold_3/new_model_format/bias_model_scaled.tar with get_new_tf_model_format.py

fold_3/logs.models.fold_3.ENCSR649PJN/logfile.modelling.fold_3.ENCSR649PJN.chrombpnet_data_params.tsv

@@ -0,0 +1,3 @@
+counts_sum_min_thresh	0.0
+counts_sum_max_thresh	1293.88
+trainings_pts_post_thresh	171639

fold_3/logs.models.fold_3.ENCSR649PJN/logfile.modelling.fold_3.ENCSR649PJN.chrombpnet_formatting.stdout.txt

@@ -0,0 +1 @@
+Converting /oak/stanford/groups/akundaje/vhecht/chromatin_atlas_bias_corrected/DNASE_model/ENCSR649PJN/fold_3/models/chrombpnet.h5 to /oak/stanford/groups/akundaje/vhecht/chromatin-atlas-2022/DNASE/ENCSR649PJN/fold_3/new_model_format/chrombpnet.tar with get_new_tf_model_format.py

fold_3/logs.models.fold_3.ENCSR649PJN/logfile.modelling.fold_3.ENCSR649PJN.chrombpnet_model_params.tsv

@@ -0,0 +1,9 @@
+counts_loss_weight	4.7
+filters	512
+n_dil_layers	8
+bias_model_path	/oak/stanford/groups/akundaje/vhecht/chromatin_atlas_bias_corrected/DNASE_model/ENCSR649PJN/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.ENCSR649PJN/logfile.modelling.fold_3.ENCSR649PJN.chrombpnet_no_bias_formatting.stdout.txt

@@ -0,0 +1 @@
+Converting /oak/stanford/groups/akundaje/vhecht/chromatin_atlas_bias_corrected/DNASE_model/ENCSR649PJN/fold_3/models/chrombpnet_nobias.h5 to /oak/stanford/groups/akundaje/vhecht/chromatin-atlas-2022/DNASE/ENCSR649PJN/fold_3/new_model_format/chrombpnet_nobias.tar with get_new_tf_model_format.py