Upload folder using huggingface_hub

README.md

@@ -0,0 +1,120 @@
+---
+license: mit
+library_name: chrombpnet
+tags:
+  - encode
+  - chrombpnet
+  - chromatin-accessibility
+  - DNASE
+  - kidney
+  - 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 kidney (ENCSR774RCO)
+- Model: ChromBPNet
+- Assay: DNASE-seq
+- Experiment: [ENCSR774RCO](https://www.encodeproject.org/experiments/ENCSR774RCO/)
+- Model annotation: [ENCSR480JMB](https://www.encodeproject.org/annotations/ENCSR480JMB/)
+- Biosample: kidney (Full name: Homo sapiens kidney tissue female embryo (105 days))
+- Cell slim(s): None
+- Organ slim(s): kidney
+- Developmental slim(s): mesoderm
+- System slim(s): excretory-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.ENCSR774RCO/logfile.modelling.fold_0.ENCSR774RCO.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/ENCSR774RCO/preprocessing/bigWigs/ENCSR774RCO.bigWig",
+    "output_dir": "/oak/stanford/groups/akundaje/ziwei75/chromatin_atlas_bias/DNase_model/bias_filtered/ENCSR774RCO//fold0/",
+    "data_type": "DNASE",
+    "peaks": "/oak/stanford/groups/akundaje/ziwei75/chromatin_atlas_bias/DNase_model/bias_filtered/ENCSR774RCO//fold0/auxiliary/filtered.peaks.bed",
+    "nonpeaks": "/oak/stanford/groups/akundaje/ziwei75/chromatin_atlas_bias/DNase_model/bias_filtered/ENCSR774RCO//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/ENCSR774RCO/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/ENCSR774RCO//fold0/models/chrombpnet",
+    "chr": "chr8",
+    "pwm_width": 24,
+    "params": "/oak/stanford/groups/akundaje/ziwei75/chromatin_atlas_bias/DNase_model/bias_filtered/ENCSR774RCO//fold0/logs/chrombpnet_model_params.tsv"
+}

fold_0/logs.models.fold_0.ENCSR774RCO/logfile.modelling.fold_0.ENCSR774RCO.bias_formatting.stdout.txt

@@ -0,0 +1 @@
+Converting /oak/stanford/groups/akundaje/ziwei75/chromatin_atlas_bias/DNase_model/bias_filtered/ENCSR774RCO/fold0/models/bias_model_scaled.h5 to /oak/stanford/groups/akundaje/vhecht/chromatin-atlas-2022/DNASE/ENCSR774RCO/fold_0/new_model_format/bias_model_scaled.tar with get_new_tf_model_format.py

fold_0/logs.models.fold_0.ENCSR774RCO/logfile.modelling.fold_0.ENCSR774RCO.chrombpnet_data_params.tsv

@@ -0,0 +1,3 @@
+counts_sum_min_thresh	0.0
+counts_sum_max_thresh	20765.9
+trainings_pts_post_thresh	172797

fold_0/logs.models.fold_0.ENCSR774RCO/logfile.modelling.fold_0.ENCSR774RCO.chrombpnet_formatting.stdout.txt

@@ -0,0 +1 @@
+Converting /oak/stanford/groups/akundaje/ziwei75/chromatin_atlas_bias/DNase_model/bias_filtered/ENCSR774RCO/fold0/models/chrombpnet.h5 to /oak/stanford/groups/akundaje/vhecht/chromatin-atlas-2022/DNASE/ENCSR774RCO/fold_0/new_model_format/chrombpnet.tar with get_new_tf_model_format.py

fold_0/logs.models.fold_0.ENCSR774RCO/logfile.modelling.fold_0.ENCSR774RCO.chrombpnet_model_params.tsv

@@ -0,0 +1,9 @@
+counts_loss_weight	43.1
+filters	512
+n_dil_layers	8
+bias_model_path	/oak/stanford/groups/akundaje/ziwei75/chromatin_atlas_bias/DNase_model/bias_filtered/ENCSR774RCO//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.ENCSR774RCO/logfile.modelling.fold_0.ENCSR774RCO.chrombpnet_no_bias_formatting.stdout.txt

@@ -0,0 +1 @@
+Converting /oak/stanford/groups/akundaje/ziwei75/chromatin_atlas_bias/DNase_model/bias_filtered/ENCSR774RCO/fold0/models/chrombpnet_nobias.h5 to /oak/stanford/groups/akundaje/vhecht/chromatin-atlas-2022/DNASE/ENCSR774RCO/fold_0/new_model_format/chrombpnet_nobias.tar with get_new_tf_model_format.py

fold_0/logs.models.fold_0.ENCSR774RCO/logfile.modelling.fold_0.ENCSR774RCO.epoch_loss.csv

@@ -0,0 +1,13 @@
+epoch,logcount_predictions_loss,logits_profile_predictions_loss,loss,val_logcount_predictions_loss,val_logits_profile_predictions_loss,val_loss
+0,5.624374866485596,1173.169921875,1415.5806884765625,0.888613760471344,1076.2823486328125,1114.5823974609375
+1,0.9018009305000305,1061.306396484375,1100.1771240234375,0.7246612906455994,1021.9990234375,1053.23193359375
+2,0.8278359174728394,1021.8986206054688,1057.5770263671875,0.6771675944328308,1024.178466796875,1053.3648681640625
+3,0.7518166899681091,999.5403442382812,1031.9432373046875,0.6336832642555237,992.1878051757812,1019.4999389648438
+4,0.7121780514717102,983.9818115234375,1014.6761474609375,0.6765972971916199,972.1826782226562,1001.3442993164062
+5,0.677373468875885,971.035400390625,1000.2304077148438,0.5920522212982178,976.2021484375,1001.7195434570312
+6,0.6503617763519287,962.30615234375,990.3364868164062,0.5822967290878296,956.161865234375,981.2587890625
+7,0.6174785494804382,953.8268432617188,980.4403076171875,0.5606294274330139,963.1842041015625,987.3475952148438
+8,0.6015608906745911,946.951416015625,972.8779907226562,0.5710030198097229,965.196533203125,989.8071899414062
+9,0.5769136548042297,942.234130859375,967.0962524414062,0.5353858470916748,959.6563720703125,982.7315673828125
+10,0.5683141350746155,937.5071411132812,962.002197265625,0.5164819955825806,961.547607421875,983.8081665039062
+11,0.5536116361618042,933.3881225585938,957.2483520507812,0.5808032155036926,958.6378784179688,983.6702880859375

fold_0/model.bias_scaled.fold_0.ENCSR774RCO.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ad5f660c1e1ce4f8fd842efd0c700846bb110780d6f8f941da048beda26cc07a
+size 2691928

fold_0/model.bias_scaled.fold_0.ENCSR774RCO.tar

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:02b1ac45bc098d4c019b5b761240ec07323a44023f675d97e913988822e5fef1
+size 1198080

fold_0/model.chrombpnet.fold_0.ENCSR774RCO.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:af72ab465fa7276370b9af56ddd62edcebee23a0305f1647c2c1df93182e61cb
+size 77538952

fold_0/model.chrombpnet.fold_0.ENCSR774RCO.tar

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6840c7e3ce45c8e5c0cc2a16fb3b7867ebcdaf5f68e38343f42de9e68218cc58
+size 27525120

fold_0/model.chrombpnet_nobias.fold_0.ENCSR774RCO.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c69009a66ff74cd0029a73ca131038429a91ced2db86a7f6a222281940e66953
+size 25582648

fold_0/model.chrombpnet_nobias.fold_0.ENCSR774RCO.tar

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:63ce2bcde21ec9050d45da6030286b9ce2ff08eb5e3af0e2c3def5eccf387eb2
+size 26060800

fold_1/logs.models.fold_1.ENCSR774RCO/logfile.modelling.fold_1.ENCSR774RCO.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/ENCSR774RCO/preprocessing/bigWigs/ENCSR774RCO.bigWig",
+    "input_fragment_file": null,
+    "input_tagalign_file": null,
+    "output_dir": "/oak/stanford/groups/akundaje/vhecht/chromatin_atlas_bias_corrected/DNASE_model/ENCSR774RCO/fold_1",
+    "data_type": "DNASE",
+    "peaks": "/oak/stanford/groups/akundaje/vhecht/chromatin_atlas_bias_corrected/DNASE_model/ENCSR774RCO/fold_1/auxiliary/filtered.peaks.bed",
+    "nonpeaks": "/oak/stanford/groups/akundaje/vhecht/chromatin_atlas_bias_corrected/DNASE_model/ENCSR774RCO/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/ENCSR774RCO/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/ENCSR774RCO/fold_1/models/chrombpnet",
+    "bigwig": "/oak/stanford/groups/akundaje/vhecht/chromatin_atlas_bias_corrected/DNASE_model/ENCSR774RCO/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/ENCSR774RCO/fold_1/logs/chrombpnet_model_params.tsv"
+}

fold_1/logs.models.fold_1.ENCSR774RCO/logfile.modelling.fold_1.ENCSR774RCO.bias_formatting.stdout.txt

@@ -0,0 +1 @@
+Converting /oak/stanford/groups/akundaje/vhecht/chromatin_atlas_bias_corrected/DNASE_model/ENCSR774RCO/fold_1/models/bias_model_scaled.h5 to /oak/stanford/groups/akundaje/vhecht/chromatin-atlas-2022/DNASE/ENCSR774RCO/fold_1/new_model_format/bias_model_scaled.tar with get_new_tf_model_format.py

fold_1/logs.models.fold_1.ENCSR774RCO/logfile.modelling.fold_1.ENCSR774RCO.chrombpnet_data_params.tsv

@@ -0,0 +1,3 @@
+counts_sum_min_thresh	0.0
+counts_sum_max_thresh	20919.0
+trainings_pts_post_thresh	174107

fold_1/logs.models.fold_1.ENCSR774RCO/logfile.modelling.fold_1.ENCSR774RCO.chrombpnet_formatting.stdout.txt

@@ -0,0 +1 @@
+Converting /oak/stanford/groups/akundaje/vhecht/chromatin_atlas_bias_corrected/DNASE_model/ENCSR774RCO/fold_1/models/chrombpnet.h5 to /oak/stanford/groups/akundaje/vhecht/chromatin-atlas-2022/DNASE/ENCSR774RCO/fold_1/new_model_format/chrombpnet.tar with get_new_tf_model_format.py

fold_1/logs.models.fold_1.ENCSR774RCO/logfile.modelling.fold_1.ENCSR774RCO.chrombpnet_model_params.tsv

@@ -0,0 +1,9 @@
+counts_loss_weight	43.2
+filters	512
+n_dil_layers	8
+bias_model_path	/oak/stanford/groups/akundaje/vhecht/chromatin_atlas_bias_corrected/DNASE_model/ENCSR774RCO/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.ENCSR774RCO/logfile.modelling.fold_1.ENCSR774RCO.chrombpnet_no_bias_formatting.stdout.txt

@@ -0,0 +1 @@
+Converting /oak/stanford/groups/akundaje/vhecht/chromatin_atlas_bias_corrected/DNASE_model/ENCSR774RCO/fold_1/models/chrombpnet_nobias.h5 to /oak/stanford/groups/akundaje/vhecht/chromatin-atlas-2022/DNASE/ENCSR774RCO/fold_1/new_model_format/chrombpnet_nobias.tar with get_new_tf_model_format.py

fold_1/logs.models.fold_1.ENCSR774RCO/logfile.modelling.fold_1.ENCSR774RCO.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
+0,1.8279098272323608,1110.4459228515625,1189.4100341796875,0.7636237144470215,1236.48974609375,1269.4786376953125
+1,0.7922080159187317,1006.4722290039062,1040.6954345703125,0.8271291851997375,1154.5479736328125,1190.279541015625
+2,0.7202000617980957,977.040283203125,1008.1527709960938,0.6671724915504456,1163.731201171875,1192.55224609375
+3,0.6876082420349121,962.4088134765625,992.1141967773438,0.6898422241210938,1133.2940673828125,1163.0955810546875
+4,0.645817220211029,951.56884765625,979.4683227539062,0.5943273901939392,1143.762939453125,1169.4381103515625
+5,0.6095696091651917,943.2150268554688,969.5481567382812,0.5497521162033081,1140.6068115234375,1164.3568115234375
+6,0.5882793664932251,935.5223388671875,960.9360961914062,0.5260191559791565,1132.210205078125,1154.93359375
+7,0.5688278079032898,930.4284057617188,955.000244140625,0.5219519138336182,1118.3929443359375,1140.94140625
+8,0.5526368618011475,926.3982543945312,950.2726440429688,0.5190746188163757,1132.4903564453125,1154.913818359375
+9,0.5407286286354065,922.1099243164062,945.4691162109375,0.5059817433357239,1109.5771484375,1131.4359130859375
+10,0.5300923585891724,919.0714111328125,941.9716796875,0.5091530084609985,1110.2255859375,1132.220458984375
+11,0.5154476165771484,915.9873046875,938.2554931640625,0.5391430854797363,1138.561279296875,1161.8524169921875
+12,0.506982684135437,914.0757446289062,935.9793090820312,0.49698811769485474,1124.4735107421875,1145.943115234375
+13,0.49640294909477234,910.5130615234375,931.9573364257812,0.6010048389434814,1125.4456787109375,1151.4097900390625
+14,0.4916282892227173,907.864501953125,929.1019897460938,0.5006110668182373,1132.709716796875,1154.3359375

fold_1/model.bias_scaled.fold_1.ENCSR774RCO.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1d0cb792a7afdfc870855375ecf43509660a807a404fe5eef9e643bab386b430
+size 2691928

fold_1/model.bias_scaled.fold_1.ENCSR774RCO.tar

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5f00823b656ba805993f03eb79502a7ca164cf495a07b66f234a193b1e0c8e44
+size 1198080

fold_1/model.chrombpnet.fold_1.ENCSR774RCO.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dcfddccf756299398b85c95d08fc49323f4bf6e61f77827f1a1ad1f4347dee5b
+size 77538840

fold_1/model.chrombpnet.fold_1.ENCSR774RCO.tar

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:11af9922cc2b65bf46c1c020fa31b601df3d1cb15a9aef8cba85bdfc0fcb5d87
+size 27525120

fold_1/model.chrombpnet_nobias.fold_1.ENCSR774RCO.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d92438d467faee52a8d0c031b32369dfe2fa87f9fd580010aadd96f8512753ea
+size 25582648

fold_1/model.chrombpnet_nobias.fold_1.ENCSR774RCO.tar

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e680dc277441d07babf42566502725e5f5d6514348a4780c69f77efbb8bebe80
+size 26060800

fold_2/logs.models.fold_2.ENCSR774RCO/logfile.modelling.fold_2.ENCSR774RCO.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/ENCSR774RCO/preprocessing/bigWigs/ENCSR774RCO.bigWig",
+    "input_fragment_file": null,
+    "input_tagalign_file": null,
+    "output_dir": "/oak/stanford/groups/akundaje/vhecht/chromatin_atlas_bias_corrected/DNASE_model/ENCSR774RCO/fold_2",
+    "data_type": "DNASE",
+    "peaks": "/oak/stanford/groups/akundaje/vhecht/chromatin_atlas_bias_corrected/DNASE_model/ENCSR774RCO/fold_2/auxiliary/filtered.peaks.bed",
+    "nonpeaks": "/oak/stanford/groups/akundaje/vhecht/chromatin_atlas_bias_corrected/DNASE_model/ENCSR774RCO/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/ENCSR774RCO/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/ENCSR774RCO/fold_2/models/chrombpnet",
+    "bigwig": "/oak/stanford/groups/akundaje/vhecht/chromatin_atlas_bias_corrected/DNASE_model/ENCSR774RCO/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/ENCSR774RCO/fold_2/logs/chrombpnet_model_params.tsv"
+}

fold_2/logs.models.fold_2.ENCSR774RCO/logfile.modelling.fold_2.ENCSR774RCO.bias_formatting.stdout.txt

@@ -0,0 +1 @@
+Converting /oak/stanford/groups/akundaje/vhecht/chromatin_atlas_bias_corrected/DNASE_model/ENCSR774RCO/fold_2/models/bias_model_scaled.h5 to /oak/stanford/groups/akundaje/vhecht/chromatin-atlas-2022/DNASE/ENCSR774RCO/fold_2/new_model_format/bias_model_scaled.tar with get_new_tf_model_format.py

fold_2/logs.models.fold_2.ENCSR774RCO/logfile.modelling.fold_2.ENCSR774RCO.chrombpnet_data_params.tsv

@@ -0,0 +1,3 @@
+counts_sum_min_thresh	0.0
+counts_sum_max_thresh	20832.31
+trainings_pts_post_thresh	179132

fold_2/logs.models.fold_2.ENCSR774RCO/logfile.modelling.fold_2.ENCSR774RCO.chrombpnet_formatting.stdout.txt

@@ -0,0 +1 @@
+Converting /oak/stanford/groups/akundaje/vhecht/chromatin_atlas_bias_corrected/DNASE_model/ENCSR774RCO/fold_2/models/chrombpnet.h5 to /oak/stanford/groups/akundaje/vhecht/chromatin-atlas-2022/DNASE/ENCSR774RCO/fold_2/new_model_format/chrombpnet.tar with get_new_tf_model_format.py

fold_2/logs.models.fold_2.ENCSR774RCO/logfile.modelling.fold_2.ENCSR774RCO.chrombpnet_model_params.tsv

@@ -0,0 +1,9 @@
+counts_loss_weight	43.1
+filters	512
+n_dil_layers	8
+bias_model_path	/oak/stanford/groups/akundaje/vhecht/chromatin_atlas_bias_corrected/DNASE_model/ENCSR774RCO/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.ENCSR774RCO/logfile.modelling.fold_2.ENCSR774RCO.chrombpnet_no_bias_formatting.stdout.txt

@@ -0,0 +1 @@
+Converting /oak/stanford/groups/akundaje/vhecht/chromatin_atlas_bias_corrected/DNASE_model/ENCSR774RCO/fold_2/models/chrombpnet_nobias.h5 to /oak/stanford/groups/akundaje/vhecht/chromatin-atlas-2022/DNASE/ENCSR774RCO/fold_2/new_model_format/chrombpnet_nobias.tar with get_new_tf_model_format.py

fold_2/logs.models.fold_2.ENCSR774RCO/logfile.modelling.fold_2.ENCSR774RCO.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
+0,2.710033416748047,1117.6949462890625,1234.4952392578125,0.8132009506225586,1083.0821533203125,1118.131103515625
+1,0.7823137640953064,1015.87353515625,1049.5914306640625,0.715737521648407,1047.8958740234375,1078.74365234375
+2,0.7215437889099121,986.2702026367188,1017.370361328125,0.7098080515861511,1032.103515625,1062.6964111328125
+3,0.67390376329422,969.9757690429688,999.021484375,0.6350417733192444,1022.86328125,1050.2332763671875
+4,0.640583872795105,960.2802734375,987.8894653320312,0.6025529503822327,1023.635986328125,1049.6063232421875
+5,0.6121644973754883,950.7333984375,977.1175537109375,0.5899467468261719,1007.5360107421875,1032.962890625
+6,0.5933865308761597,943.5311889648438,969.1062622070312,0.5949277877807617,1013.2064208984375,1038.847900390625
+7,0.56657475233078,938.8013916015625,963.2189331054688,0.6042069792747498,1021.6652221679688,1047.706787109375
+8,0.5483545064926147,934.7247924804688,958.3577880859375,0.5628511309623718,1025.0391845703125,1049.297607421875
+9,0.5387235879898071,929.2985229492188,952.5191650390625,0.5641261339187622,1001.2677612304688,1025.58203125
+10,0.5166808366775513,926.8214721679688,949.0913696289062,0.5439023971557617,997.232421875,1020.674560546875
+11,0.5069386959075928,923.3770141601562,945.2250366210938,0.5798385143280029,1006.4572143554688,1031.4483642578125
+12,0.4986240863800049,920.6632690429688,942.1548461914062,0.6102644205093384,1001.4600219726562,1027.7623291015625
+13,0.49174943566322327,917.2242431640625,938.4179077148438,0.560673713684082,1016.3815307617188,1040.546630859375
+14,0.47869351506233215,915.1611938476562,935.79296875,0.5478009581565857,1017.251953125,1040.86181640625
+15,0.4782799184322357,913.303955078125,933.9180297851562,0.5607653260231018,1022.0839233398438,1046.2530517578125

fold_2/model.bias_scaled.fold_2.ENCSR774RCO.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:113b4b67c9dcc21cdad8d5e4a00970b4d9cf80c99e84253da163422324667c50
+size 2691928

fold_2/model.bias_scaled.fold_2.ENCSR774RCO.tar

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c604e2f0603032796cf5fcc8d335cc49e73372948e955199cdb130affad404b5
+size 1198080

fold_2/model.chrombpnet.fold_2.ENCSR774RCO.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a514357d2468047d8f616873b4f9f795951dcc1afb089111185ba95ffa1a4895
+size 77538840

fold_2/model.chrombpnet.fold_2.ENCSR774RCO.tar

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bb764a2876614ec46bda37aa184f99a7f921821360c1eafe2c46a9c08825ef67
+size 27525120

fold_2/model.chrombpnet_nobias.fold_2.ENCSR774RCO.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6755b5a2812b2f90f3b7f037df58cbf7b5a5373c7fde50e753d31f4d346945f8
+size 25582648

fold_2/model.chrombpnet_nobias.fold_2.ENCSR774RCO.tar

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fd4fd9a478168a13efe09c91af5d04a9aa2668a8c9fa54eb0a43cedf23a4b29b
+size 26060800

fold_3/logs.models.fold_3.ENCSR774RCO/logfile.modelling.fold_3.ENCSR774RCO.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/ENCSR774RCO/preprocessing/bigWigs/ENCSR774RCO.bigWig",
+    "input_fragment_file": null,
+    "input_tagalign_file": null,
+    "output_dir": "/oak/stanford/groups/akundaje/vhecht/chromatin_atlas_bias_corrected/DNASE_model/ENCSR774RCO/fold_3",
+    "data_type": "DNASE",
+    "peaks": "/oak/stanford/groups/akundaje/vhecht/chromatin_atlas_bias_corrected/DNASE_model/ENCSR774RCO/fold_3/auxiliary/filtered.peaks.bed",
+    "nonpeaks": "/oak/stanford/groups/akundaje/vhecht/chromatin_atlas_bias_corrected/DNASE_model/ENCSR774RCO/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/ENCSR774RCO/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/ENCSR774RCO/fold_3/models/chrombpnet",
+    "bigwig": "/oak/stanford/groups/akundaje/vhecht/chromatin_atlas_bias_corrected/DNASE_model/ENCSR774RCO/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/ENCSR774RCO/fold_3/logs/chrombpnet_model_params.tsv"
+}

fold_3/logs.models.fold_3.ENCSR774RCO/logfile.modelling.fold_3.ENCSR774RCO.bias_formatting.stdout.txt

@@ -0,0 +1 @@
+Converting /oak/stanford/groups/akundaje/vhecht/chromatin_atlas_bias_corrected/DNASE_model/ENCSR774RCO/fold_3/models/bias_model_scaled.h5 to /oak/stanford/groups/akundaje/vhecht/chromatin-atlas-2022/DNASE/ENCSR774RCO/fold_3/new_model_format/bias_model_scaled.tar with get_new_tf_model_format.py

fold_3/logs.models.fold_3.ENCSR774RCO/logfile.modelling.fold_3.ENCSR774RCO.chrombpnet_data_params.tsv

@@ -0,0 +1,3 @@
+counts_sum_min_thresh	0.0
+counts_sum_max_thresh	21003.51
+trainings_pts_post_thresh	172855

fold_3/logs.models.fold_3.ENCSR774RCO/logfile.modelling.fold_3.ENCSR774RCO.chrombpnet_formatting.stdout.txt

@@ -0,0 +1 @@
+Converting /oak/stanford/groups/akundaje/vhecht/chromatin_atlas_bias_corrected/DNASE_model/ENCSR774RCO/fold_3/models/chrombpnet.h5 to /oak/stanford/groups/akundaje/vhecht/chromatin-atlas-2022/DNASE/ENCSR774RCO/fold_3/new_model_format/chrombpnet.tar with get_new_tf_model_format.py

fold_3/logs.models.fold_3.ENCSR774RCO/logfile.modelling.fold_3.ENCSR774RCO.chrombpnet_model_params.tsv

@@ -0,0 +1,9 @@
+counts_loss_weight	43.2
+filters	512
+n_dil_layers	8
+bias_model_path	/oak/stanford/groups/akundaje/vhecht/chromatin_atlas_bias_corrected/DNASE_model/ENCSR774RCO/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.ENCSR774RCO/logfile.modelling.fold_3.ENCSR774RCO.chrombpnet_no_bias_formatting.stdout.txt

@@ -0,0 +1 @@
+Converting /oak/stanford/groups/akundaje/vhecht/chromatin_atlas_bias_corrected/DNASE_model/ENCSR774RCO/fold_3/models/chrombpnet_nobias.h5 to /oak/stanford/groups/akundaje/vhecht/chromatin-atlas-2022/DNASE/ENCSR774RCO/fold_3/new_model_format/chrombpnet_nobias.tar with get_new_tf_model_format.py