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 CD4-positive, alpha-beta T cell (ENCSR841LHT)
+- Model: ChromBPNet
+- Assay: ATAC-seq
+- Experiment: [ENCSR841LHT](https://www.encodeproject.org/experiments/ENCSR841LHT/)
+- Model annotation: [ENCSR830MQP](https://www.encodeproject.org/annotations/ENCSR830MQP/)
+- Biosample: CD4-positive, alpha-beta T cell (Full name: Homo sapiens CD4-positive, alpha-beta T cell male adult (20 years))
+- Cell slim(s): CD4+-T-cell,hematopoietic-cell,T-cell,leukocyte
+- Organ slim(s): blood,bodily-fluid
+- Developmental slim(s): endoderm,mesoderm
+- 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.ENCSR841LHT/logfile.modelling.fold_0.ENCSR841LHT.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/ENCSR841LHT//preprocessing/bigWigs/ENCSR841LHT.bigWig",
+    "peaks": "/scratch/groups/akundaje/anusri/chromatin_atlas/ATAC/ENCSR841LHT//chrombpnet_model_feb15//filtered.peaks.bed",
+    "nonpeaks": "/scratch/groups/akundaje/anusri/chromatin_atlas/ATAC/ENCSR841LHT//chrombpnet_model_feb15//filtered.nonpeaks.bed",
+    "output_prefix": "/scratch/groups/akundaje/anusri/chromatin_atlas/ATAC/ENCSR841LHT//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/ENCSR841LHT//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.ENCSR841LHT/logfile.modelling.fold_0.ENCSR841LHT.bias_formatting.stdout.txt

@@ -0,0 +1 @@
+Converting /oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/ATAC/ENCSR841LHT/chrombpnet_model_feb15/bias_model_scaled.h5 to /oak/stanford/groups/akundaje/vhecht/chromatin-atlas-2022/ATAC/ENCSR841LHT/fold_0/new_model_format/bias_model_scaled.tar with get_new_tf_model_format.py

fold_0/logs.models.fold_0.ENCSR841LHT/logfile.modelling.fold_0.ENCSR841LHT.chrombpnet_data_params.tsv

@@ -0,0 +1,3 @@
+counts_sum_min_thresh	0.0
+counts_sum_max_thresh	4698.49
+trainings_pts_post_thresh	89832

fold_0/logs.models.fold_0.ENCSR841LHT/logfile.modelling.fold_0.ENCSR841LHT.chrombpnet_formatting.stdout.txt

@@ -0,0 +1 @@
+Converting /oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/ATAC/ENCSR841LHT/chrombpnet_model_feb15/chrombpnet.h5 to /oak/stanford/groups/akundaje/vhecht/chromatin-atlas-2022/ATAC/ENCSR841LHT/fold_0/new_model_format/chrombpnet.tar with get_new_tf_model_format.py

fold_0/logs.models.fold_0.ENCSR841LHT/logfile.modelling.fold_0.ENCSR841LHT.chrombpnet_model_params.tsv

@@ -0,0 +1,9 @@
+counts_loss_weight	24.0
+filters	512
+n_dil_layers	8
+bias_model_path	/scratch/groups/akundaje/anusri/chromatin_atlas/ATAC/ENCSR841LHT//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.ENCSR841LHT/logfile.modelling.fold_0.ENCSR841LHT.chrombpnet_no_bias_formatting.stdout.txt

@@ -0,0 +1 @@
+Converting /oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/ATAC/ENCSR841LHT/chrombpnet_model_feb15/chrombpnet_wo_bias.h5 to /oak/stanford/groups/akundaje/vhecht/chromatin-atlas-2022/ATAC/ENCSR841LHT/fold_0/new_model_format/chrombpnet_nobias.tar with get_new_tf_model_format.py

fold_0/logs.models.fold_0.ENCSR841LHT/logfile.modelling.fold_0.ENCSR841LHT.epoch_loss.csv

@@ -0,0 +1,20 @@
+epoch,logcount_predictions_loss,logits_profile_predictions_loss,loss,val_logcount_predictions_loss,val_logits_profile_predictions_loss,val_loss
+0,10.141473770141602,589.7286376953125,833.1234741210938,2.1474454402923584,581.4052734375,632.944091796875
+1,2.1238725185394287,538.0767211914062,589.05029296875,1.8158777952194214,529.608642578125,573.1897583007812
+2,1.9471925497055054,504.5617370605469,551.2938842773438,1.8819692134857178,517.39990234375,562.5670776367188
+3,1.8207108974456787,489.99737548828125,533.6946411132812,1.6536431312561035,508.5122985839844,548.1995849609375
+4,1.733585000038147,481.0901794433594,522.6957397460938,1.511855959892273,505.4205627441406,541.705078125
+5,1.6488823890686035,471.80523681640625,511.37872314453125,1.4964754581451416,498.86474609375,534.7801513671875
+6,1.5685009956359863,465.43914794921875,503.0827331542969,1.5660665035247803,497.057861328125,534.6433715820312
+7,1.5024899244308472,457.5056457519531,493.56524658203125,1.4210206270217896,495.87957763671875,529.9840698242188
+8,1.4762263298034668,451.7134704589844,487.1430358886719,1.3989510536193848,498.5085144042969,532.083251953125
+9,1.4133846759796143,445.7016906738281,479.62255859375,1.4026650190353394,496.2536926269531,529.9176025390625
+10,1.32749342918396,439.4276123046875,471.287353515625,1.3713663816452026,492.15374755859375,525.0665893554688
+11,1.2930498123168945,436.9586181640625,467.9918518066406,1.354710578918457,493.5810546875,526.09375
+12,1.2240755558013916,431.9456787109375,461.3239440917969,1.4805762767791748,495.7550964355469,531.2889404296875
+13,1.1754299402236938,428.7445373535156,456.95465087890625,1.3745028972625732,492.0623474121094,525.0504150390625
+14,1.0910751819610596,426.0188903808594,452.2040710449219,1.3719168901443481,494.267333984375,527.193359375
+15,1.0481855869293213,423.15399169921875,448.31060791015625,1.4202715158462524,496.1307373046875,530.2173461914062
+16,0.9922895431518555,421.27294921875,445.0879211425781,1.372549057006836,494.41058349609375,527.3516235351562
+17,0.8107411861419678,410.6351623535156,430.0930480957031,1.4422378540039062,490.5979309082031,525.2116088867188
+18,0.7226861119270325,404.546875,421.8912048339844,1.4031431674957275,492.2762145996094,525.95166015625

fold_0/model.bias_scaled.fold_0.ENCSR841LHT.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:604467d5675902c8245c0bfcdd5786617aad709ad99200ba46dbf1e9a7646564
+size 2688440

fold_0/model.bias_scaled.fold_0.ENCSR841LHT.tar

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f40af8c31e2e1d43074fb46745f939663400338d57679e5019c6d54621ccbe21
+size 1198080

fold_0/model.chrombpnet.fold_0.ENCSR841LHT.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:13e04f6e82dfcd01242bcfe8eeb0d039bce8a9ecf3a54fbf110d62eb4fa16169
+size 26448016

fold_0/model.chrombpnet.fold_0.ENCSR841LHT.tar

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:25ef011639a091c3e6b08bcd4f6a53c5ee9996b4bd7a4beef0064615e75fb6d4
+size 27535360

fold_0/model.chrombpnet_nobias.fold_0.ENCSR841LHT.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:223e34ac87ab63f2d60fab0142af2fa197cb1d3fd9880204ba07dca440ddb750
+size 25583536

fold_0/model.chrombpnet_nobias.fold_0.ENCSR841LHT.tar

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a637d712bcc26de66d9eb7bda6d96449ed47a06107d57f26dfdbd4ade352137b
+size 26060800

fold_1/logs.models.fold_1.ENCSR841LHT/logfile.modelling.fold_1.ENCSR841LHT.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//ENCSR841LHT//preprocessing/bigWigs/ENCSR841LHT.bigWig",
+    "peaks": "/oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/ATAC//ENCSR841LHT//chrombpnet_model_feb15_fold_1//filtered.peaks.bed",
+    "nonpeaks": "/oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/ATAC//ENCSR841LHT//chrombpnet_model_feb15_fold_1//filtered.nonpeaks.bed",
+    "output_prefix": "/oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/ATAC//ENCSR841LHT//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//ENCSR841LHT//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.ENCSR841LHT/logfile.modelling.fold_1.ENCSR841LHT.bias_formatting.stdout.txt

@@ -0,0 +1 @@
+Converting /oak/stanford/groups/akundaje/vhecht/chromatin-atlas-2022/ATAC/ENCSR841LHT/chrombpnet_model_feb15_fold_1/bias_model_scaled.h5 to /oak/stanford/groups/akundaje/vhecht/chromatin-atlas-2022/ATAC/ENCSR841LHT/fold_1/new_model_format/bias_model_scaled.tar with get_new_tf_model_format.py

fold_1/logs.models.fold_1.ENCSR841LHT/logfile.modelling.fold_1.ENCSR841LHT.chrombpnet_data_params.tsv

@@ -0,0 +1,3 @@
+counts_sum_min_thresh	0.0
+counts_sum_max_thresh	4649.44
+trainings_pts_post_thresh	92745

fold_1/logs.models.fold_1.ENCSR841LHT/logfile.modelling.fold_1.ENCSR841LHT.chrombpnet_formatting.stdout.txt

@@ -0,0 +1 @@
+Converting /oak/stanford/groups/akundaje/vhecht/chromatin-atlas-2022/ATAC/ENCSR841LHT/chrombpnet_model_feb15_fold_1/chrombpnet.h5 to /oak/stanford/groups/akundaje/vhecht/chromatin-atlas-2022/ATAC/ENCSR841LHT/fold_1/new_model_format/chrombpnet.tar with get_new_tf_model_format.py

fold_1/logs.models.fold_1.ENCSR841LHT/logfile.modelling.fold_1.ENCSR841LHT.chrombpnet_model_params.tsv

@@ -0,0 +1,9 @@
+counts_loss_weight	24.1
+filters	512
+n_dil_layers	8
+bias_model_path	/oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/ATAC//ENCSR841LHT//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.ENCSR841LHT/logfile.modelling.fold_1.ENCSR841LHT.chrombpnet_no_bias_formatting.stdout.txt

@@ -0,0 +1 @@
+Converting /oak/stanford/groups/akundaje/vhecht/chromatin-atlas-2022/ATAC/ENCSR841LHT/chrombpnet_model_feb15_fold_1/chrombpnet_wo_bias.h5 to /oak/stanford/groups/akundaje/vhecht/chromatin-atlas-2022/ATAC/ENCSR841LHT/fold_1/new_model_format/chrombpnet_nobias.tar with get_new_tf_model_format.py

fold_1/logs.models.fold_1.ENCSR841LHT/logfile.modelling.fold_1.ENCSR841LHT.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
+0,9.886469841003418,564.260498046875,802.5242309570312,2.2260489463806152,606.75341796875,660.401123046875
+1,2.1128458976745605,514.164794921875,565.0845336914062,1.8418910503387451,562.7112426757812,607.1010131835938
+2,1.9071245193481445,481.5558166503906,527.5172729492188,1.8022596836090088,539.090087890625,582.5244140625
+3,1.8189759254455566,467.84246826171875,511.679931640625,2.094369411468506,540.8605346679688,591.334716796875
+4,1.7061830759048462,456.9288024902344,498.04766845703125,1.6266671419143677,524.9042358398438,564.10693359375
+5,1.6191442012786865,447.80059814453125,486.8221435546875,1.682671308517456,524.9535522460938,565.5059204101562
+6,1.5238395929336548,441.2793884277344,478.00445556640625,1.5928876399993896,521.5151977539062,559.9037475585938
+7,1.5014710426330566,434.731201171875,470.91632080078125,1.432420253753662,518.991455078125,553.5127563476562
+8,1.4109418392181396,430.754150390625,464.7575988769531,1.474583387374878,517.3755493164062,552.9129028320312
+9,1.3782000541687012,425.6434326171875,458.8582458496094,1.5064529180526733,512.6679077148438,548.9733276367188
+10,1.2944538593292236,422.328125,453.52459716796875,1.619735836982727,519.603515625,558.6392211914062
+11,1.2419384717941284,417.6477355957031,447.578857421875,1.4865331649780273,511.57635498046875,547.4015502929688
+12,1.1685525178909302,415.63385009765625,443.7956237792969,1.4407788515090942,513.3699951171875,548.0927124023438
+13,1.1129705905914307,411.88177490234375,438.7041320800781,1.3899778127670288,514.0721435546875,547.5704956054688
+14,1.0253485441207886,410.2402038574219,434.9512939453125,1.5953222513198853,513.1087036132812,551.5560302734375
+15,0.8462099432945251,399.80859375,420.2020568847656,1.565381407737732,510.1202087402344,547.8460083007812
+16,0.7492034435272217,394.9886779785156,413.0442810058594,1.7556060552597046,512.47509765625,554.7850341796875

fold_1/model.bias_scaled.fold_1.ENCSR841LHT.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3c59911f486451b3acd33327f544d77c39839aa07255b8387c6285bfe34f114c
+size 2688440

fold_1/model.bias_scaled.fold_1.ENCSR841LHT.tar

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:db12f52b957b440be9b57953a67e9fd33c70b86c6839c1dec3811446af021f1f
+size 1198080

fold_1/model.chrombpnet.fold_1.ENCSR841LHT.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b9afd44ae5e17f9d7a767142b3a1ceea5fd2a700281003fb642358c02b867c9e
+size 26447928

fold_1/model.chrombpnet.fold_1.ENCSR841LHT.tar

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1576cbf449736f1178c6b28c49bb95588208dbb672437207ccab378269ebe542
+size 27525120

fold_1/model.chrombpnet_nobias.fold_1.ENCSR841LHT.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0b0d6a99a42f9ea242b38d8d14d07e662c9fe09f0d98b10d4bbb06795ce0e83f
+size 25583536

fold_1/model.chrombpnet_nobias.fold_1.ENCSR841LHT.tar

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e7c14bd904f1edb43ba8f8e784a40ff963f27a86e91359c43eeafa3e3c6f551e
+size 26060800

fold_2/logs.models.fold_2.ENCSR841LHT/logfile.modelling.fold_2.ENCSR841LHT.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//ENCSR841LHT//preprocessing/bigWigs/ENCSR841LHT.bigWig",
+    "peaks": "/oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/ATAC//ENCSR841LHT//chrombpnet_model_feb15_fold_2//filtered.peaks.bed",
+    "nonpeaks": "/oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/ATAC//ENCSR841LHT//chrombpnet_model_feb15_fold_2//filtered.nonpeaks.bed",
+    "output_prefix": "/oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/ATAC//ENCSR841LHT//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//ENCSR841LHT//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.ENCSR841LHT/logfile.modelling.fold_2.ENCSR841LHT.bias_formatting.stdout.txt

@@ -0,0 +1 @@
+Converting /oak/stanford/groups/akundaje/vhecht/chromatin-atlas-2022/ATAC/ENCSR841LHT/chrombpnet_model_feb15_fold_2/bias_model_scaled.h5 to /oak/stanford/groups/akundaje/vhecht/chromatin-atlas-2022/ATAC/ENCSR841LHT/fold_2/new_model_format/bias_model_scaled.tar with get_new_tf_model_format.py

fold_2/logs.models.fold_2.ENCSR841LHT/logfile.modelling.fold_2.ENCSR841LHT.chrombpnet_data_params.tsv

@@ -0,0 +1,3 @@
+counts_sum_min_thresh	0.0
+counts_sum_max_thresh	4666.19
+trainings_pts_post_thresh	94749

fold_2/logs.models.fold_2.ENCSR841LHT/logfile.modelling.fold_2.ENCSR841LHT.chrombpnet_formatting.stdout.txt

@@ -0,0 +1 @@
+Converting /oak/stanford/groups/akundaje/vhecht/chromatin-atlas-2022/ATAC/ENCSR841LHT/chrombpnet_model_feb15_fold_2/chrombpnet.h5 to /oak/stanford/groups/akundaje/vhecht/chromatin-atlas-2022/ATAC/ENCSR841LHT/fold_2/new_model_format/chrombpnet.tar with get_new_tf_model_format.py

fold_2/logs.models.fold_2.ENCSR841LHT/logfile.modelling.fold_2.ENCSR841LHT.chrombpnet_model_params.tsv

@@ -0,0 +1,9 @@
+counts_loss_weight	24.1
+filters	512
+n_dil_layers	8
+bias_model_path	/oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/ATAC//ENCSR841LHT//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.ENCSR841LHT/logfile.modelling.fold_2.ENCSR841LHT.chrombpnet_no_bias_formatting.stdout.txt

@@ -0,0 +1 @@
+Converting /oak/stanford/groups/akundaje/vhecht/chromatin-atlas-2022/ATAC/ENCSR841LHT/chrombpnet_model_feb15_fold_2/chrombpnet_wo_bias.h5 to /oak/stanford/groups/akundaje/vhecht/chromatin-atlas-2022/ATAC/ENCSR841LHT/fold_2/new_model_format/chrombpnet_nobias.tar with get_new_tf_model_format.py

fold_2/logs.models.fold_2.ENCSR841LHT/logfile.modelling.fold_2.ENCSR841LHT.epoch_loss.csv

@@ -0,0 +1,23 @@
+epoch,logcount_predictions_loss,logits_profile_predictions_loss,loss,val_logcount_predictions_loss,val_logits_profile_predictions_loss,val_loss
+0,17.02288818359375,566.4822387695312,976.732666015625,2.2086594104766846,588.7182006835938,641.9468994140625
+1,2.0777037143707275,517.9937133789062,568.0661010742188,1.9776743650436401,533.7743530273438,581.4364624023438
+2,1.895782470703125,484.8062438964844,530.4940795898438,1.7538001537322998,514.5792236328125,556.845947265625
+3,1.7913531064987183,469.9443054199219,513.116455078125,1.8274250030517578,506.7508239746094,550.7916259765625
+4,1.6938384771347046,459.6197204589844,500.44158935546875,1.5820462703704834,501.4002990722656,539.5275268554688
+5,1.6093943119049072,453.3151550292969,492.1019287109375,1.6412217617034912,493.6519775390625,533.2056884765625
+6,1.5775625705718994,447.19903564453125,485.218994140625,1.6289622783660889,491.6595764160156,530.9176635742188
+7,1.506413459777832,442.0194091796875,478.32391357421875,1.5248490571975708,491.1277770996094,527.8765869140625
+8,1.44308340549469,436.3973083496094,471.1755065917969,1.5366859436035156,486.0006408691406,523.034912109375
+9,1.3929353952407837,431.7327880859375,465.3024597167969,1.5559929609298706,489.9841613769531,527.4835205078125
+10,1.3307011127471924,426.7481689453125,458.8180236816406,1.5413395166397095,488.8568420410156,526.0029907226562
+11,1.2804452180862427,421.5994873046875,452.4586181640625,1.5104892253875732,485.7210998535156,522.1236572265625
+12,1.1956626176834106,419.6153869628906,448.43060302734375,1.446994662284851,484.23858642578125,519.1112670898438
+13,1.1521897315979004,415.59136962890625,443.35919189453125,1.5017509460449219,484.3652648925781,520.5574340820312
+14,1.0712406635284424,413.6318359375,439.4486999511719,1.5182592868804932,485.4910583496094,522.0809936523438
+15,1.0357837677001953,410.26300048828125,435.2250671386719,1.5259788036346436,487.5144348144531,524.29052734375
+16,0.8352243900299072,401.24462890625,421.37353515625,1.4411472082138062,480.4181213378906,515.1497802734375
+17,0.7402347922325134,395.30780029296875,413.14752197265625,1.569393515586853,485.9602966308594,523.78271484375
+18,0.6851525902748108,393.0710144042969,409.5830383300781,1.6818856000900269,484.1363525390625,524.6698608398438
+19,0.6399852633476257,392.05963134765625,407.4833984375,1.6450395584106445,484.6141662597656,524.2595825195312
+20,0.5504961013793945,387.10546875,400.372314453125,1.566665768623352,483.4476318359375,521.2041625976562
+21,0.5166730284690857,384.1522521972656,396.6041259765625,1.7434628009796143,486.3551025390625,528.3724975585938

fold_2/model.bias_scaled.fold_2.ENCSR841LHT.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d12ffd77c6cdea75878f05dd52c47da17007280b9838f3a84a7e76d5c3aa8b3e
+size 2688440

fold_2/model.bias_scaled.fold_2.ENCSR841LHT.tar

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4436734886f43dccdbcee5a172c6b1e7b6a613ccb2a876f85b90a85a1a7cf5a1
+size 1198080

fold_2/model.chrombpnet.fold_2.ENCSR841LHT.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:774693663b686c44d6fcc0f1cecc7b214e59a2b29d30e8808c38b46e04041301
+size 26447928

fold_2/model.chrombpnet.fold_2.ENCSR841LHT.tar

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ca86bac17af32bd5e0e3c7e52c8354344bff27056d54a27e7edea807fc66aad2
+size 27525120

fold_2/model.chrombpnet_nobias.fold_2.ENCSR841LHT.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dfb18b5691fcd0dc86cdb0d15af476ae86d689cf4ff04cd8c7df31e1ad1942f0
+size 25583536

fold_2/model.chrombpnet_nobias.fold_2.ENCSR841LHT.tar

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:777ac1b194a7451f2f45fa11110fd8bc99eef5649458a02099e08e815668aab2
+size 26060800

fold_3/logs.models.fold_3.ENCSR841LHT/logfile.modelling.fold_3.ENCSR841LHT.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//ENCSR841LHT//preprocessing/bigWigs/ENCSR841LHT.bigWig",
+    "peaks": "/oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/ATAC//ENCSR841LHT//chrombpnet_model_feb15_fold_3//filtered.peaks.bed",
+    "nonpeaks": "/oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/ATAC//ENCSR841LHT//chrombpnet_model_feb15_fold_3//filtered.nonpeaks.bed",
+    "output_prefix": "/oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/ATAC//ENCSR841LHT//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//ENCSR841LHT//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.ENCSR841LHT/logfile.modelling.fold_3.ENCSR841LHT.bias_formatting.stdout.txt

@@ -0,0 +1 @@
+Converting /oak/stanford/groups/akundaje/vhecht/chromatin-atlas-2022/ATAC/ENCSR841LHT/chrombpnet_model_feb15_fold_3/bias_model_scaled.h5 to /oak/stanford/groups/akundaje/vhecht/chromatin-atlas-2022/ATAC/ENCSR841LHT/fold_3/new_model_format/bias_model_scaled.tar with get_new_tf_model_format.py

fold_3/logs.models.fold_3.ENCSR841LHT/logfile.modelling.fold_3.ENCSR841LHT.chrombpnet_data_params.tsv

@@ -0,0 +1,3 @@
+counts_sum_min_thresh	0.0
+counts_sum_max_thresh	4658.0
+trainings_pts_post_thresh	92357

fold_3/logs.models.fold_3.ENCSR841LHT/logfile.modelling.fold_3.ENCSR841LHT.chrombpnet_formatting.stdout.txt

@@ -0,0 +1 @@
+Converting /oak/stanford/groups/akundaje/vhecht/chromatin-atlas-2022/ATAC/ENCSR841LHT/chrombpnet_model_feb15_fold_3/chrombpnet.h5 to /oak/stanford/groups/akundaje/vhecht/chromatin-atlas-2022/ATAC/ENCSR841LHT/fold_3/new_model_format/chrombpnet.tar with get_new_tf_model_format.py

fold_3/logs.models.fold_3.ENCSR841LHT/logfile.modelling.fold_3.ENCSR841LHT.chrombpnet_model_params.tsv

@@ -0,0 +1,9 @@
+counts_loss_weight	24.1
+filters	512
+n_dil_layers	8
+bias_model_path	/oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/ATAC//ENCSR841LHT//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.ENCSR841LHT/logfile.modelling.fold_3.ENCSR841LHT.chrombpnet_no_bias_formatting.stdout.txt

@@ -0,0 +1 @@
+Converting /oak/stanford/groups/akundaje/vhecht/chromatin-atlas-2022/ATAC/ENCSR841LHT/chrombpnet_model_feb15_fold_3/chrombpnet_wo_bias.h5 to /oak/stanford/groups/akundaje/vhecht/chromatin-atlas-2022/ATAC/ENCSR841LHT/fold_3/new_model_format/chrombpnet_nobias.tar with get_new_tf_model_format.py