Upload folder using huggingface_hub

README.md

@@ -0,0 +1,120 @@
+---
+license: mit
+library_name: chrombpnet
+tags:
+  - encode
+  - chrombpnet
+  - chromatin-accessibility
+  - ATAC
+  - t-cell
+  - 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: ATAC in effector memory CD8-positive, alpha-beta T cell (ENCSR019XCN)
+- Model: ChromBPNet
+- Assay: ATAC-seq
+- Experiment: [ENCSR019XCN](https://www.encodeproject.org/experiments/ENCSR019XCN/)
+- Model annotation: [ENCSR564YQY](https://www.encodeproject.org/annotations/ENCSR564YQY/)
+- Biosample: effector memory CD8-positive, alpha-beta T cell (Full name: Homo sapiens effector memory CD8-positive, alpha-beta T cell male adult (36 years))
+- Cell slim(s): CD8+-T-cell,hematopoietic-cell,T-cell,leukocyte
+- Organ slim(s): blood,bodily-fluid
+- Developmental slim(s): mesoderm,endoderm
+- System slim(s): immune-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.ENCSR019XCN/logfile.modelling.fold_0.ENCSR019XCN.args.json

@@ -0,0 +1,23 @@
+{
+    "genome": "/scratch/groups/akundaje/anusri/chromatin_atlas/reference/hg38.genome.fa",
+    "bigwig": "/scratch/groups/akundaje/anusri/chromatin_atlas/ATAC/ENCSR019XCN//preprocessing/bigWigs/ENCSR019XCN.bigWig",
+    "peaks": "/scratch/groups/akundaje/anusri/chromatin_atlas/ATAC/ENCSR019XCN//chrombpnet_model_feb15//filtered.peaks.bed",
+    "nonpeaks": "/scratch/groups/akundaje/anusri/chromatin_atlas/ATAC/ENCSR019XCN//chrombpnet_model_feb15//filtered.nonpeaks.bed",
+    "output_prefix": "/scratch/groups/akundaje/anusri/chromatin_atlas/ATAC/ENCSR019XCN//chrombpnet_model_feb15//chrombpnet",
+    "chr_fold_path": "/scratch/groups/akundaje/anusri/chromatin_atlas/splits/fold_0.json",
+    "trackables": [
+        "logcount_predictions_loss",
+        "loss",
+        "logits_profile_predictions_loss",
+        "val_logcount_predictions_loss",
+        "val_loss",
+        "val_logits_profile_predictions_loss"
+    ],
+    "epochs": 50,
+    "early_stop": 5,
+    "batch_size": 64,
+    "learning_rate": 0.001,
+    "params": "/scratch/groups/akundaje/anusri/chromatin_atlas/ATAC/ENCSR019XCN//chrombpnet_model_feb15//chrombpnet_model_params.tsv",
+    "seed": 1234,
+    "architecture_from_file": "/home/users/anusri/chromatin-atlas-anvil/sherlock/chrombpnet/src/training/models/chrombpnet_with_bias_model.py"
+}

fold_0/logs.models.fold_0.ENCSR019XCN/logfile.modelling.fold_0.ENCSR019XCN.bias_formatting.stdout.txt

@@ -0,0 +1 @@
+Converting /oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/ATAC/ENCSR019XCN/chrombpnet_model_feb15/bias_model_scaled.h5 to /oak/stanford/groups/akundaje/vhecht/chromatin-atlas-2022/ATAC/ENCSR019XCN/fold_0/new_model_format/bias_model_scaled.tar with get_new_tf_model_format.py

fold_0/logs.models.fold_0.ENCSR019XCN/logfile.modelling.fold_0.ENCSR019XCN.chrombpnet_data_params.tsv

@@ -0,0 +1,3 @@
+counts_sum_min_thresh	11.0
+counts_sum_max_thresh	1693.0
+trainings_pts_post_thresh	75056

fold_0/logs.models.fold_0.ENCSR019XCN/logfile.modelling.fold_0.ENCSR019XCN.chrombpnet_formatting.stdout.txt

@@ -0,0 +1 @@
+Converting /oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/ATAC/ENCSR019XCN/chrombpnet_model_feb15/chrombpnet.h5 to /oak/stanford/groups/akundaje/vhecht/chromatin-atlas-2022/ATAC/ENCSR019XCN/fold_0/new_model_format/chrombpnet.tar with get_new_tf_model_format.py

fold_0/logs.models.fold_0.ENCSR019XCN/logfile.modelling.fold_0.ENCSR019XCN.chrombpnet_model_params.tsv

@@ -0,0 +1,9 @@
+counts_loss_weight	13.6
+filters	512
+n_dil_layers	8
+bias_model_path	/scratch/groups/akundaje/anusri/chromatin_atlas/ATAC/ENCSR019XCN//chrombpnet_model_feb15/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.ENCSR019XCN/logfile.modelling.fold_0.ENCSR019XCN.chrombpnet_no_bias_formatting.stdout.txt

@@ -0,0 +1 @@
+Converting /oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/ATAC/ENCSR019XCN/chrombpnet_model_feb15/chrombpnet_wo_bias.h5 to /oak/stanford/groups/akundaje/vhecht/chromatin-atlas-2022/ATAC/ENCSR019XCN/fold_0/new_model_format/chrombpnet_nobias.tar with get_new_tf_model_format.py

fold_0/logs.models.fold_0.ENCSR019XCN/logfile.modelling.fold_0.ENCSR019XCN.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
+0,0.8817774057388306,360.1568298339844,372.1488952636719,0.5910998582839966,346.60797119140625,354.64697265625
+1,0.6499277949333191,336.4602355957031,345.2994689941406,0.5691637396812439,334.7531433105469,342.4938659667969
+2,0.5805355310440063,326.8238220214844,334.718994140625,0.5468509793281555,330.9002380371094,338.33740234375
+3,0.5382965207099915,320.59991455078125,327.9205627441406,0.7126139402389526,331.8131103515625,341.5047302246094
+4,0.5123132467269897,317.190185546875,324.15789794921875,0.5087306499481201,329.403076171875,336.3218688964844
+5,0.4770551323890686,312.6270751953125,319.1151123046875,0.5018623471260071,328.0028381347656,334.82818603515625
+6,0.4510042071342468,309.2554931640625,315.38922119140625,0.4669845700263977,328.3958435058594,334.7468566894531
+7,0.4152732193470001,306.68212890625,312.32965087890625,0.4425407350063324,329.74542236328125,335.76397705078125
+8,0.4023512005805969,304.5519714355469,310.0240173339844,0.488000750541687,330.9416809082031,337.57843017578125
+9,0.37319716811180115,302.82110595703125,307.89630126953125,0.47654420137405396,330.3121643066406,336.7931823730469
+10,0.29960885643959045,296.9220275878906,300.9967041015625,0.44538962841033936,329.1834716796875,335.2408447265625
+11,0.2741934359073639,292.8747253417969,296.60394287109375,0.4451645612716675,330.64239501953125,336.6966552734375

fold_0/model.bias_scaled.fold_0.ENCSR019XCN.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:faa3e66a10ed4624d044e3ada8a5552433dff92e4652c88869bdb7fc8f693ed8
+size 2688440

fold_0/model.bias_scaled.fold_0.ENCSR019XCN.tar

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b45b4b11c4b1c3ef5a99517b4e3f6886c94816f561fb785d95aa84f3dd540d76
+size 1198080

fold_0/model.chrombpnet.fold_0.ENCSR019XCN.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f7527f66e2ef3a6f03dccbf5c9b3426e79c4497efbf86577094912c3ec6a76ab
+size 26448016

fold_0/model.chrombpnet.fold_0.ENCSR019XCN.tar

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c914c7b5502e0624e8df5ec557084a6a3fd5d67e5ed0c510bb96a0dbe91e7419
+size 27535360

fold_0/model.chrombpnet_nobias.fold_0.ENCSR019XCN.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e342439b9a9c38cf96d87f878160b0984f2ac986316af81e6ba524ea834466a4
+size 25583536

fold_0/model.chrombpnet_nobias.fold_0.ENCSR019XCN.tar

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7e45be3495942d06f39d8010bdbcaac435e96ffd11801c10086ba2bf2f1164bf
+size 26060800

fold_1/logs.models.fold_1.ENCSR019XCN/logfile.modelling.fold_1.ENCSR019XCN.args.json

@@ -0,0 +1,23 @@
+{
+    "genome": "/scratch/groups/akundaje/anusri/chromatin_atlas/reference/hg38.genome.fa",
+    "bigwig": "/oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/ATAC//ENCSR019XCN//preprocessing/bigWigs/ENCSR019XCN.bigWig",
+    "peaks": "/oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/ATAC//ENCSR019XCN//chrombpnet_model_feb15_fold_1//filtered.peaks.bed",
+    "nonpeaks": "/oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/ATAC//ENCSR019XCN//chrombpnet_model_feb15_fold_1//filtered.nonpeaks.bed",
+    "output_prefix": "/oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/ATAC//ENCSR019XCN//chrombpnet_model_feb15_fold_1//chrombpnet",
+    "chr_fold_path": "/scratch/groups/akundaje/anusri/chromatin_atlas/splits/fold_1.json",
+    "trackables": [
+        "logcount_predictions_loss",
+        "loss",
+        "logits_profile_predictions_loss",
+        "val_logcount_predictions_loss",
+        "val_loss",
+        "val_logits_profile_predictions_loss"
+    ],
+    "epochs": 50,
+    "early_stop": 5,
+    "batch_size": 64,
+    "learning_rate": 0.001,
+    "params": "/oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/ATAC//ENCSR019XCN//chrombpnet_model_feb15_fold_1//chrombpnet_model_params.tsv",
+    "seed": 1234,
+    "architecture_from_file": "/home/users/anusri/chromatin-atlas-anvil/sherlock/chrombpnet/src/training/models/chrombpnet_with_bias_model.py"
+}

fold_1/logs.models.fold_1.ENCSR019XCN/logfile.modelling.fold_1.ENCSR019XCN.bias_formatting.stdout.txt

@@ -0,0 +1 @@
+Converting /oak/stanford/groups/akundaje/vhecht/chromatin-atlas-2022/ATAC/ENCSR019XCN/chrombpnet_model_feb15_fold_1/bias_model_scaled.h5 to /oak/stanford/groups/akundaje/vhecht/chromatin-atlas-2022/ATAC/ENCSR019XCN/fold_1/new_model_format/bias_model_scaled.tar with get_new_tf_model_format.py

fold_1/logs.models.fold_1.ENCSR019XCN/logfile.modelling.fold_1.ENCSR019XCN.chrombpnet_data_params.tsv

@@ -0,0 +1,3 @@
+counts_sum_min_thresh	11.0
+counts_sum_max_thresh	1700.51
+trainings_pts_post_thresh	76800

fold_1/logs.models.fold_1.ENCSR019XCN/logfile.modelling.fold_1.ENCSR019XCN.chrombpnet_formatting.stdout.txt

@@ -0,0 +1 @@
+Converting /oak/stanford/groups/akundaje/vhecht/chromatin-atlas-2022/ATAC/ENCSR019XCN/chrombpnet_model_feb15_fold_1/chrombpnet.h5 to /oak/stanford/groups/akundaje/vhecht/chromatin-atlas-2022/ATAC/ENCSR019XCN/fold_1/new_model_format/chrombpnet.tar with get_new_tf_model_format.py

fold_1/logs.models.fold_1.ENCSR019XCN/logfile.modelling.fold_1.ENCSR019XCN.chrombpnet_model_params.tsv

@@ -0,0 +1,9 @@
+counts_loss_weight	14.0
+filters	512
+n_dil_layers	8
+bias_model_path	/oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/ATAC//ENCSR019XCN//chrombpnet_model_feb15_fold_1/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.ENCSR019XCN/logfile.modelling.fold_1.ENCSR019XCN.chrombpnet_no_bias_formatting.stdout.txt

@@ -0,0 +1 @@
+Converting /oak/stanford/groups/akundaje/vhecht/chromatin-atlas-2022/ATAC/ENCSR019XCN/chrombpnet_model_feb15_fold_1/chrombpnet_wo_bias.h5 to /oak/stanford/groups/akundaje/vhecht/chromatin-atlas-2022/ATAC/ENCSR019XCN/fold_1/new_model_format/chrombpnet_nobias.tar with get_new_tf_model_format.py

fold_1/logs.models.fold_1.ENCSR019XCN/logfile.modelling.fold_1.ENCSR019XCN.epoch_loss.csv

@@ -0,0 +1,18 @@
+epoch,logcount_predictions_loss,logits_profile_predictions_loss,loss,val_logcount_predictions_loss,val_logits_profile_predictions_loss,val_loss
+0,4.398952960968018,354.7334899902344,416.3186340332031,1.111432433128357,388.6282653808594,404.1882629394531
+1,0.7454067468643188,336.27410888671875,346.7099914550781,0.7873163819313049,371.5514831542969,382.5739440917969
+2,0.6566077470779419,325.689208984375,334.88140869140625,0.6252068281173706,364.90087890625,373.65374755859375
+3,0.6159478425979614,321.5684814453125,330.19140625,0.6365053653717041,362.6813659667969,371.5924987792969
+4,0.5819348096847534,317.127685546875,325.2746887207031,0.5615071654319763,360.47119140625,368.3321838378906
+5,0.5539623498916626,314.4226989746094,322.177978515625,0.5517837405204773,358.38824462890625,366.11309814453125
+6,0.5175879597663879,311.16949462890625,318.4157409667969,0.5493265390396118,357.0660705566406,364.75677490234375
+7,0.49806636571884155,309.1829833984375,316.15570068359375,0.7239760160446167,356.6708679199219,366.80645751953125
+8,0.4720021188259125,306.7876281738281,313.39556884765625,0.5393075942993164,357.6314697265625,365.1819152832031
+9,0.4517485797405243,304.0592956542969,310.3839111328125,0.6378399133682251,355.8486022949219,364.7783203125
+10,0.37932226061820984,298.1876525878906,303.497802734375,0.5204280018806458,355.5707092285156,362.8566589355469
+11,0.3412483036518097,294.90264892578125,299.67999267578125,0.5050400495529175,355.46221923828125,362.5328063964844
+12,0.3133305609226227,293.2235107421875,297.6098327636719,0.5201048254966736,355.8741149902344,363.15545654296875
+13,0.29608914256095886,291.47430419921875,295.619873046875,0.517298698425293,357.3664245605469,364.6086120605469
+14,0.2702879011631012,288.97015380859375,292.7542419433594,0.5037065744400024,357.85797119140625,364.90972900390625
+15,0.22868101298809052,285.77410888671875,288.9754333496094,0.5061832070350647,358.4739685058594,365.5605163574219
+16,0.21360860764980316,283.6716613769531,286.6619873046875,0.5346372723579407,360.6546630859375,368.1395568847656

fold_1/model.bias_scaled.fold_1.ENCSR019XCN.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:819eaa4dc33702b8bf01a4978a663e30e76fbe3f21400f515a92982836bc37c3
+size 2688440

fold_1/model.bias_scaled.fold_1.ENCSR019XCN.tar

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:de4e5b5e1c8bd80183f420715392af2150fa9bc9ad8507b622d063f11c71401c
+size 1198080

fold_1/model.chrombpnet.fold_1.ENCSR019XCN.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c565a5c015188a616b530273d5bc3b3b9cce2222f6e6f3c36ffd6bec8a9a9688
+size 26447928

fold_1/model.chrombpnet.fold_1.ENCSR019XCN.tar

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ac389b8db41389ba445a5bc9fb1706540ebe4987e37f8635d610f8ddfe8642de
+size 27525120

fold_1/model.chrombpnet_nobias.fold_1.ENCSR019XCN.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ef8f1965d236bdf6e21cc34ac6f3c9c67c90149ade9933c2375d989e3ef99440
+size 25583536

fold_1/model.chrombpnet_nobias.fold_1.ENCSR019XCN.tar

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:70eb2ed220fc0a23b73edf7dd7de25d38f7eb6587899ddbec790d197f9b5520d
+size 26060800

fold_2/logs.models.fold_2.ENCSR019XCN/logfile.modelling.fold_2.ENCSR019XCN.args.json

@@ -0,0 +1,23 @@
+{
+    "genome": "/scratch/groups/akundaje/anusri/chromatin_atlas/reference/hg38.genome.fa",
+    "bigwig": "/oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/ATAC//ENCSR019XCN//preprocessing/bigWigs/ENCSR019XCN.bigWig",
+    "peaks": "/oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/ATAC//ENCSR019XCN//chrombpnet_model_feb15_fold_2//filtered.peaks.bed",
+    "nonpeaks": "/oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/ATAC//ENCSR019XCN//chrombpnet_model_feb15_fold_2//filtered.nonpeaks.bed",
+    "output_prefix": "/oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/ATAC//ENCSR019XCN//chrombpnet_model_feb15_fold_2//chrombpnet",
+    "chr_fold_path": "/scratch/groups/akundaje/anusri/chromatin_atlas/splits/fold_2.json",
+    "trackables": [
+        "logcount_predictions_loss",
+        "loss",
+        "logits_profile_predictions_loss",
+        "val_logcount_predictions_loss",
+        "val_loss",
+        "val_logits_profile_predictions_loss"
+    ],
+    "epochs": 50,
+    "early_stop": 5,
+    "batch_size": 64,
+    "learning_rate": 0.001,
+    "params": "/oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/ATAC//ENCSR019XCN//chrombpnet_model_feb15_fold_2//chrombpnet_model_params.tsv",
+    "seed": 1234,
+    "architecture_from_file": "/home/users/anusri/chromatin-atlas-anvil/sherlock/chrombpnet/src/training/models/chrombpnet_with_bias_model.py"
+}

fold_2/logs.models.fold_2.ENCSR019XCN/logfile.modelling.fold_2.ENCSR019XCN.bias_formatting.stdout.txt

@@ -0,0 +1 @@
+Converting /oak/stanford/groups/akundaje/vhecht/chromatin-atlas-2022/ATAC/ENCSR019XCN/chrombpnet_model_feb15_fold_2/bias_model_scaled.h5 to /oak/stanford/groups/akundaje/vhecht/chromatin-atlas-2022/ATAC/ENCSR019XCN/fold_2/new_model_format/bias_model_scaled.tar with get_new_tf_model_format.py

fold_2/logs.models.fold_2.ENCSR019XCN/logfile.modelling.fold_2.ENCSR019XCN.chrombpnet_data_params.tsv

@@ -0,0 +1,3 @@
+counts_sum_min_thresh	11.0
+counts_sum_max_thresh	1693.01
+trainings_pts_post_thresh	79249

fold_2/logs.models.fold_2.ENCSR019XCN/logfile.modelling.fold_2.ENCSR019XCN.chrombpnet_formatting.stdout.txt

@@ -0,0 +1 @@
+Converting /oak/stanford/groups/akundaje/vhecht/chromatin-atlas-2022/ATAC/ENCSR019XCN/chrombpnet_model_feb15_fold_2/chrombpnet.h5 to /oak/stanford/groups/akundaje/vhecht/chromatin-atlas-2022/ATAC/ENCSR019XCN/fold_2/new_model_format/chrombpnet.tar with get_new_tf_model_format.py

fold_2/logs.models.fold_2.ENCSR019XCN/logfile.modelling.fold_2.ENCSR019XCN.chrombpnet_model_params.tsv

@@ -0,0 +1,9 @@
+counts_loss_weight	13.8
+filters	512
+n_dil_layers	8
+bias_model_path	/oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/ATAC//ENCSR019XCN//chrombpnet_model_feb15_fold_2/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.ENCSR019XCN/logfile.modelling.fold_2.ENCSR019XCN.chrombpnet_no_bias_formatting.stdout.txt

@@ -0,0 +1 @@
+Converting /oak/stanford/groups/akundaje/vhecht/chromatin-atlas-2022/ATAC/ENCSR019XCN/chrombpnet_model_feb15_fold_2/chrombpnet_wo_bias.h5 to /oak/stanford/groups/akundaje/vhecht/chromatin-atlas-2022/ATAC/ENCSR019XCN/fold_2/new_model_format/chrombpnet_nobias.tar with get_new_tf_model_format.py

fold_2/logs.models.fold_2.ENCSR019XCN/logfile.modelling.fold_2.ENCSR019XCN.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
+0,4.072404861450195,353.82427978515625,410.0242614746094,0.836228609085083,367.7013244628906,379.2413635253906
+1,0.7168405055999756,335.3590393066406,345.251708984375,0.6786351203918457,353.9054870605469,363.2706604003906
+2,0.646172046661377,324.93865966796875,333.8560791015625,0.5919049382209778,344.26678466796875,352.43499755859375
+3,0.6013822555541992,320.8887023925781,329.18817138671875,0.5535079836845398,342.2389221191406,349.8773193359375
+4,0.5753811001777649,317.4890441894531,325.42901611328125,0.5682930946350098,339.1198425292969,346.9623718261719
+5,0.5519405007362366,314.1438293457031,321.76055908203125,0.6313509941101074,338.5759582519531,347.2885437011719
+6,0.5179682374000549,311.2581787109375,318.40631103515625,0.5220243334770203,337.8745422363281,345.07855224609375
+7,0.4952371120452881,308.81793212890625,315.6525573730469,0.5332357287406921,338.77996826171875,346.1385803222656
+8,0.4767955243587494,306.4997863769531,313.07952880859375,0.5188847184181213,335.6171875,342.7778015136719
+9,0.45452913641929626,304.74871826171875,311.0215759277344,0.620613157749176,336.81317138671875,345.3775634765625
+10,0.4315270185470581,301.7572326660156,307.71221923828125,0.5019526481628418,335.6156311035156,342.54248046875
+11,0.4136574864387512,301.0716857910156,306.78009033203125,0.49708324670791626,336.4151611328125,343.2748718261719
+12,0.3853999376296997,299.2221984863281,304.5406494140625,0.5951229929924011,337.884521484375,346.0973205566406
+13,0.3627646863460541,298.0439147949219,303.0498962402344,0.5170068144798279,335.9688720703125,343.10357666015625
+14,0.2913641035556793,292.3919677734375,296.4124755859375,0.5078776478767395,336.6908874511719,343.69964599609375
+15,0.26332002878189087,289.3237609863281,292.9573669433594,0.5023642182350159,337.67059326171875,344.60321044921875

fold_2/model.bias_scaled.fold_2.ENCSR019XCN.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:01b823537b9e3e994bf72ac7fbba8b082c73263605dbbef0936e024f09ef7758
+size 2688440

fold_2/model.bias_scaled.fold_2.ENCSR019XCN.tar

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:49efab7758f911ea00077a158b47d116d342d27af04884c87b682f65e32b6cc8
+size 1198080

fold_2/model.chrombpnet.fold_2.ENCSR019XCN.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:940b2507d26a8cdb7afab60c9fd595e455afe1d66337acef70adc40a4008456e
+size 26447928

fold_2/model.chrombpnet.fold_2.ENCSR019XCN.tar

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b8fba96121d9751e2bf3395a6a16d2e1323506e4edeb48d9a49008b2562e784e
+size 27525120

fold_2/model.chrombpnet_nobias.fold_2.ENCSR019XCN.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e24e9fc322d09fdef60a15e1382a3d7fd67e61fa397e802c690963df034d0e27
+size 25583536

fold_2/model.chrombpnet_nobias.fold_2.ENCSR019XCN.tar

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1b0ed7108e91dd1b138abf4f2d7937214bc5bc3f35c663015991d7c1ec4c3c60
+size 26060800

fold_3/logs.models.fold_3.ENCSR019XCN/logfile.modelling.fold_3.ENCSR019XCN.args.json

@@ -0,0 +1,23 @@
+{
+    "genome": "/scratch/groups/akundaje/anusri/chromatin_atlas/reference/hg38.genome.fa",
+    "bigwig": "/oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/ATAC//ENCSR019XCN//preprocessing/bigWigs/ENCSR019XCN.bigWig",
+    "peaks": "/oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/ATAC//ENCSR019XCN//chrombpnet_model_feb15_fold_3//filtered.peaks.bed",
+    "nonpeaks": "/oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/ATAC//ENCSR019XCN//chrombpnet_model_feb15_fold_3//filtered.nonpeaks.bed",
+    "output_prefix": "/oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/ATAC//ENCSR019XCN//chrombpnet_model_feb15_fold_3//chrombpnet",
+    "chr_fold_path": "/scratch/groups/akundaje/anusri/chromatin_atlas/splits/fold_3.json",
+    "trackables": [
+        "logcount_predictions_loss",
+        "loss",
+        "logits_profile_predictions_loss",
+        "val_logcount_predictions_loss",
+        "val_loss",
+        "val_logits_profile_predictions_loss"
+    ],
+    "epochs": 50,
+    "early_stop": 5,
+    "batch_size": 64,
+    "learning_rate": 0.001,
+    "params": "/oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/ATAC//ENCSR019XCN//chrombpnet_model_feb15_fold_3//chrombpnet_model_params.tsv",
+    "seed": 1234,
+    "architecture_from_file": "/home/users/anusri/chromatin-atlas-anvil/sherlock/chrombpnet/src/training/models/chrombpnet_with_bias_model.py"
+}

fold_3/logs.models.fold_3.ENCSR019XCN/logfile.modelling.fold_3.ENCSR019XCN.bias_formatting.stdout.txt

@@ -0,0 +1 @@
+Converting /oak/stanford/groups/akundaje/vhecht/chromatin-atlas-2022/ATAC/ENCSR019XCN/chrombpnet_model_feb15_fold_3/bias_model_scaled.h5 to /oak/stanford/groups/akundaje/vhecht/chromatin-atlas-2022/ATAC/ENCSR019XCN/fold_3/new_model_format/bias_model_scaled.tar with get_new_tf_model_format.py

fold_3/logs.models.fold_3.ENCSR019XCN/logfile.modelling.fold_3.ENCSR019XCN.chrombpnet_data_params.tsv

@@ -0,0 +1,3 @@
+counts_sum_min_thresh	11.0
+counts_sum_max_thresh	1694.06
+trainings_pts_post_thresh	76710

fold_3/logs.models.fold_3.ENCSR019XCN/logfile.modelling.fold_3.ENCSR019XCN.chrombpnet_formatting.stdout.txt

@@ -0,0 +1 @@
+Converting /oak/stanford/groups/akundaje/vhecht/chromatin-atlas-2022/ATAC/ENCSR019XCN/chrombpnet_model_feb15_fold_3/chrombpnet.h5 to /oak/stanford/groups/akundaje/vhecht/chromatin-atlas-2022/ATAC/ENCSR019XCN/fold_3/new_model_format/chrombpnet.tar with get_new_tf_model_format.py

fold_3/logs.models.fold_3.ENCSR019XCN/logfile.modelling.fold_3.ENCSR019XCN.chrombpnet_model_params.tsv

@@ -0,0 +1,9 @@
+counts_loss_weight	14.0
+filters	512
+n_dil_layers	8
+bias_model_path	/oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/ATAC//ENCSR019XCN//chrombpnet_model_feb15_fold_3/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.ENCSR019XCN/logfile.modelling.fold_3.ENCSR019XCN.chrombpnet_no_bias_formatting.stdout.txt

@@ -0,0 +1 @@
+Converting /oak/stanford/groups/akundaje/vhecht/chromatin-atlas-2022/ATAC/ENCSR019XCN/chrombpnet_model_feb15_fold_3/chrombpnet_wo_bias.h5 to /oak/stanford/groups/akundaje/vhecht/chromatin-atlas-2022/ATAC/ENCSR019XCN/fold_3/new_model_format/chrombpnet_nobias.tar with get_new_tf_model_format.py