Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,18 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+fold_0/model.bias_scaled.fold_0.ENCSR627UDJ.tar/variables/variables.data-00000-of-00001 filter=lfs diff=lfs merge=lfs -text
+fold_0/model.chrombpnet.fold_0.ENCSR627UDJ.tar/variables/variables.data-00000-of-00001 filter=lfs diff=lfs merge=lfs -text
+fold_0/model.chrombpnet_nobias.fold_0.ENCSR627UDJ.tar/variables/variables.data-00000-of-00001 filter=lfs diff=lfs merge=lfs -text
+fold_1/model.bias_scaled.fold_1.ENCSR627UDJ.tar/variables/variables.data-00000-of-00001 filter=lfs diff=lfs merge=lfs -text
+fold_1/model.chrombpnet.fold_1.ENCSR627UDJ.tar/variables/variables.data-00000-of-00001 filter=lfs diff=lfs merge=lfs -text
+fold_1/model.chrombpnet_nobias.fold_1.ENCSR627UDJ.tar/variables/variables.data-00000-of-00001 filter=lfs diff=lfs merge=lfs -text
+fold_2/model.bias_scaled.fold_2.ENCSR627UDJ.tar/variables/variables.data-00000-of-00001 filter=lfs diff=lfs merge=lfs -text
+fold_2/model.chrombpnet.fold_2.ENCSR627UDJ.tar/variables/variables.data-00000-of-00001 filter=lfs diff=lfs merge=lfs -text
+fold_2/model.chrombpnet_nobias.fold_2.ENCSR627UDJ.tar/variables/variables.data-00000-of-00001 filter=lfs diff=lfs merge=lfs -text
+fold_3/model.bias_scaled.fold_3.ENCSR627UDJ.tar/variables/variables.data-00000-of-00001 filter=lfs diff=lfs merge=lfs -text
+fold_3/model.chrombpnet.fold_3.ENCSR627UDJ.tar/variables/variables.data-00000-of-00001 filter=lfs diff=lfs merge=lfs -text
+fold_3/model.chrombpnet_nobias.fold_3.ENCSR627UDJ.tar/variables/variables.data-00000-of-00001 filter=lfs diff=lfs merge=lfs -text
+fold_4/model.bias_scaled.fold_4.ENCSR627UDJ.tar/variables/variables.data-00000-of-00001 filter=lfs diff=lfs merge=lfs -text
+fold_4/model.chrombpnet.fold_4.ENCSR627UDJ.tar/variables/variables.data-00000-of-00001 filter=lfs diff=lfs merge=lfs -text
+fold_4/model.chrombpnet_nobias.fold_4.ENCSR627UDJ.tar/variables/variables.data-00000-of-00001 filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,120 @@
+---
+license: mit
+library_name: chrombpnet
+tags:
+  - encode
+  - chrombpnet
+  - chromatin-accessibility
+  - DNASE
+  - 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: DNASE in T-cell (ENCSR627UDJ)
+- Model: ChromBPNet
+- Assay: DNASE-seq
+- Experiment: [ENCSR627UDJ](https://www.encodeproject.org/experiments/ENCSR627UDJ/)
+- Model annotation: [ENCSR806CDG](https://www.encodeproject.org/annotations/ENCSR806CDG/)
+- Biosample: T-cell (Full name: Homo sapiens T-cell male adult (36 years))
+- Cell slim(s): T-cell,leukocyte,hematopoietic-cell
+- Organ slim(s): bodily-fluid,blood
+- 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.ENCSR627UDJ/logfile.modelling.fold_0.ENCSR627UDJ.args.json

@@ -0,0 +1,45 @@
+{
+    "cmd": "pipeline",
+    "genome": "/scratch/groups/akundaje/anusri/chromatin_atlas/reference//hg38.genome.fa",
+    "chrom_sizes": "/scratch/groups/akundaje/anusri/chromatin_atlas/reference//chrom.sizes",
+    "input_bam_file": null,
+    "input_fragment_file": null,
+    "input_tagalign_file": null,
+    "bigwig": "/oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/DNASE//ENCSR627UDJ//preprocessing/bigWigs/ENCSR627UDJ.bigWig",
+    "output_dir": "/scratch/groups/akundaje/anusri/chromatin_atlas/DNASE/ENCSR627UDJ//chrombpnet_model_feb15_fold_0/chrombpnet_model/",
+    "data_type": "DNASE",
+    "peaks": "/scratch/groups/akundaje/anusri/chromatin_atlas/DNASE/ENCSR627UDJ//chrombpnet_model_feb15_fold_0/chrombpnet_model/auxiliary/ENCSR627UDJ_filtered.peaks.bed",
+    "nonpeaks": "/scratch/groups/akundaje/anusri/chromatin_atlas/DNASE/ENCSR627UDJ//chrombpnet_model_feb15_fold_0/chrombpnet_model/auxiliary/ENCSR627UDJ_filtered.nonpeaks.bed",
+    "chr_fold_path": "/scratch/groups/akundaje/anusri/chromatin_atlas/splits/fold_0.json",
+    "outlier_threshold": 0.9999,
+    "ATAC_ref_path": null,
+    "DNASE_ref_path": null,
+    "num_samples": 10000,
+    "inputlen": 2114,
+    "outputlen": 1000,
+    "seed": 1234,
+    "epochs": 50,
+    "early_stop": 5,
+    "learning_rate": 0.001,
+    "trackables": [
+        "logcount_predictions_loss",
+        "loss",
+        "logits_profile_predictions_loss",
+        "val_logcount_predictions_loss",
+        "val_loss",
+        "val_logits_profile_predictions_loss"
+    ],
+    "architecture_from_file": "/home/groups/akundaje/anusri/simg/chrombpnet_latest/chrombpnet/chrombpnet/training/models/chrombpnet_with_bias_model.py",
+    "file_prefix": "ENCSR627UDJ",
+    "html_prefix": "./",
+    "bias_model_path": "/scratch/groups/akundaje/anusri/chromatin_atlas/DNASE/ENCSR627UDJ//chrombpnet_model_feb15_fold_0/bias_model/models/ENCSR627UDJ_bias.h5",
+    "negative_sampling_ratio": 0.1,
+    "filters": 512,
+    "n_dilation_layers": 8,
+    "max_jitter": 500,
+    "batch_size": 64,
+    "output_prefix": "/scratch/groups/akundaje/anusri/chromatin_atlas/DNASE/ENCSR627UDJ//chrombpnet_model_feb15_fold_0/chrombpnet_model/models/ENCSR627UDJ_chrombpnet",
+    "chr": "chr8",
+    "pwm_width": 24,
+    "params": "/scratch/groups/akundaje/anusri/chromatin_atlas/DNASE/ENCSR627UDJ//chrombpnet_model_feb15_fold_0/chrombpnet_model/logs/ENCSR627UDJ_chrombpnet_model_params.tsv"
+}

fold_0/logs.models.fold_0.ENCSR627UDJ/logfile.modelling.fold_0.ENCSR627UDJ.bias_formatting.stdout.txt

@@ -0,0 +1 @@
+Converting /oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/DNASE/ENCSR627UDJ/failed_models_retrained/chrombpnet_model_feb15_fold_0/chrombpnet_model/models/ENCSR627UDJ_bias_model_scaled.h5 to /oak/stanford/groups/akundaje/vhecht/chromatin-atlas-2022/DNASE/ENCSR627UDJ/fold_0/new_model_format/bias_model_scaled.tar with get_new_tf_model_format.py

fold_0/logs.models.fold_0.ENCSR627UDJ/logfile.modelling.fold_0.ENCSR627UDJ.chrombpnet_data_params.tsv

@@ -0,0 +1,3 @@
+counts_sum_min_thresh	0.0
+counts_sum_max_thresh	4220.37
+trainings_pts_post_thresh	146455

fold_0/logs.models.fold_0.ENCSR627UDJ/logfile.modelling.fold_0.ENCSR627UDJ.chrombpnet_formatting.stdout.txt

@@ -0,0 +1 @@
+Converting /oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/DNASE/ENCSR627UDJ/failed_models_retrained/chrombpnet_model_feb15_fold_0/chrombpnet_model/models/ENCSR627UDJ_chrombpnet.h5 to /oak/stanford/groups/akundaje/vhecht/chromatin-atlas-2022/DNASE/ENCSR627UDJ/fold_0/new_model_format/chrombpnet.tar with get_new_tf_model_format.py

fold_0/logs.models.fold_0.ENCSR627UDJ/logfile.modelling.fold_0.ENCSR627UDJ.chrombpnet_model_params.tsv

@@ -0,0 +1,9 @@
+counts_loss_weight	1.7
+filters	512
+n_dil_layers	8
+bias_model_path	/scratch/groups/akundaje/anusri/chromatin_atlas/DNASE/ENCSR627UDJ//chrombpnet_model_feb15_fold_0/chrombpnet_model/models/ENCSR627UDJ_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.ENCSR627UDJ/logfile.modelling.fold_0.ENCSR627UDJ.chrombpnet_no_bias_formatting.stdout.txt

@@ -0,0 +1 @@
+Converting /oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/DNASE/ENCSR627UDJ/failed_models_retrained/chrombpnet_model_feb15_fold_0/chrombpnet_model/models/ENCSR627UDJ_chrombpnet_nobias.h5 to /oak/stanford/groups/akundaje/vhecht/chromatin-atlas-2022/DNASE/ENCSR627UDJ/fold_0/new_model_format/chrombpnet_nobias.tar with get_new_tf_model_format.py

fold_0/logs.models.fold_0.ENCSR627UDJ/logfile.modelling.fold_0.ENCSR627UDJ.epoch_loss.csv

@@ -0,0 +1,19 @@
+epoch,logcount_predictions_loss,logits_profile_predictions_loss,loss,val_logcount_predictions_loss,val_logits_profile_predictions_loss,val_loss
+0,0.9895820617675781,146.00006103515625,147.68228149414062,0.583143413066864,131.5310821533203,132.52249145507812
+1,0.6674968600273132,139.0525360107422,140.187255859375,0.5199884176254272,128.28216552734375,129.1660919189453
+2,0.5800759196281433,135.62864685058594,136.61465454101562,0.43020331859588623,127.33728790283203,128.068603515625
+3,0.5252796411514282,133.75625610351562,134.64926147460938,0.46785202622413635,125.80829620361328,126.60359954833984
+4,0.4996189475059509,132.62574768066406,133.47496032714844,0.3915397524833679,125.12403869628906,125.78958129882812
+5,0.4893253743648529,131.82640075683594,132.65847778320312,0.38885191082954407,125.57927703857422,126.24029541015625
+6,0.46705663204193115,131.0092010498047,131.80320739746094,0.38208144903182983,125.25164794921875,125.90118408203125
+7,0.45954811573028564,130.32447814941406,131.10565185546875,0.3688335716724396,124.96236419677734,125.58940887451172
+8,0.4413752555847168,129.75411987304688,130.50436401367188,0.4245743155479431,125.59444427490234,126.31620025634766
+9,0.42841461300849915,129.29893493652344,130.02743530273438,0.44212305545806885,124.91888427734375,125.67062377929688
+10,0.4203205704689026,129.06993103027344,129.7843475341797,0.37497663497924805,125.38601684570312,126.02342987060547
+11,0.41941529512405396,128.38523864746094,129.098388671875,0.4006596803665161,125.92906188964844,126.61016845703125
+12,0.41313114762306213,127.99708557128906,128.69927978515625,0.3535228371620178,124.42587280273438,125.02688598632812
+13,0.4051046669483185,127.73643493652344,128.4251251220703,0.393800288438797,125.38741302490234,126.05687713623047
+14,0.40862908959388733,128.04063415527344,128.7352294921875,0.35500285029411316,125.92372131347656,126.52716064453125
+15,0.3937455117702484,127.45276641845703,128.12229919433594,0.36118653416633606,124.95207214355469,125.56607818603516
+16,0.38787296414375305,127.42994689941406,128.08949279785156,0.3610517382621765,124.74005889892578,125.35385131835938
+17,0.3873811364173889,127.27168273925781,127.93016052246094,0.3658977448940277,124.50116729736328,125.1231918334961

fold_0/model.bias_scaled.fold_0.ENCSR627UDJ.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8b49aa4607c44b1fa44d196149742512689761f87ee8eb5e0908fc1339aeb04d
+size 2691928

fold_0/model.bias_scaled.fold_0.ENCSR627UDJ.tar/keras_metadata.pb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bf03080435e97ceaf819923c48ce2acde74d094371880a79e44141b267548eed
+size 32946

fold_0/model.bias_scaled.fold_0.ENCSR627UDJ.tar/saved_model.pb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4086baa1e3c62ff25642424fc6d21a96ea0cc655ae97cb912c3fa732920a5ffa
+size 267277

fold_0/model.bias_scaled.fold_0.ENCSR627UDJ.tar/variables/variables.data-00000-of-00001

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:64a445a37559381197e09408d086a14bf61363692f3ae576d17bcfb5bc287da6
+size 882550

fold_0/model.chrombpnet.fold_0.ENCSR627UDJ.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:02c6d0d4fc552d947d4942e77afbfa33d30fa2de84bb5e362c081aeec61db2e8
+size 77538904

fold_0/model.chrombpnet.fold_0.ENCSR627UDJ.tar/keras_metadata.pb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c22c4530e1dbffe1f5aa36633482921869fbba65e9531eec1d3bc1353fc6f3eb
+size 136809

fold_0/model.chrombpnet.fold_0.ENCSR627UDJ.tar/saved_model.pb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8bddfc250d542afd2777a125755a3d312640cf635e1c5115ee27ba223994ebad
+size 958726

fold_0/model.chrombpnet.fold_0.ENCSR627UDJ.tar/variables/variables.data-00000-of-00001

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:52593bb9ba00f90649c58d910aafd60684d2a2ed77e570c015a86bcff2296aeb
+size 26415899

fold_0/model.chrombpnet_nobias.fold_0.ENCSR627UDJ.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ed8f5c7e19da06557dd99885386f9785b68051f285d6091c48bfa40ac8335d6a
+size 25582648

fold_0/model.chrombpnet_nobias.fold_0.ENCSR627UDJ.tar/keras_metadata.pb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e3414d53705260cdd80f7a6c30a5457b7ed495394a3f243abf90239d125be736
+size 53915

fold_0/model.chrombpnet_nobias.fold_0.ENCSR627UDJ.tar/saved_model.pb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3cf82e94c50badd69ec5aff3655d797f290d17f4848d905447395cf70d4c65d5
+size 460921

fold_0/model.chrombpnet_nobias.fold_0.ENCSR627UDJ.tar/variables/variables.data-00000-of-00001

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bd1613752a605d082b8f1fb15f7bce81635282dc0fb03eb6acc8d71c86a58fe5
+size 25531097

fold_1/logs.models.fold_1.ENCSR627UDJ/logfile.modelling.fold_1.ENCSR627UDJ.args.json

@@ -0,0 +1,45 @@
+{
+    "cmd": "train",
+    "genome": "/scratch/groups/akundaje/anusri/chromatin_atlas/reference//hg38.genome.fa",
+    "chrom_sizes": "/scratch/groups/akundaje/anusri/chromatin_atlas/reference//chrom.sizes",
+    "input_bam_file": null,
+    "input_fragment_file": null,
+    "input_tagalign_file": null,
+    "bigwig": "/oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/DNASE//ENCSR627UDJ//preprocessing/bigWigs/ENCSR627UDJ.bigWig",
+    "output_dir": "/scratch/groups/akundaje/anusri/chromatin_atlas/DNASE/ENCSR627UDJ//chrombpnet_model_feb15_fold_1/chrombpnet_model/",
+    "data_type": "DNASE",
+    "peaks": "/scratch/groups/akundaje/anusri/chromatin_atlas/DNASE/ENCSR627UDJ//chrombpnet_model_feb15_fold_1/chrombpnet_model/auxiliary/ENCSR627UDJ_filtered.peaks.bed",
+    "nonpeaks": "/scratch/groups/akundaje/anusri/chromatin_atlas/DNASE/ENCSR627UDJ//chrombpnet_model_feb15_fold_1/chrombpnet_model/auxiliary/ENCSR627UDJ_filtered.nonpeaks.bed",
+    "chr_fold_path": "/scratch/groups/akundaje/anusri/chromatin_atlas/splits/fold_1.json",
+    "outlier_threshold": 0.9999,
+    "ATAC_ref_path": null,
+    "DNASE_ref_path": null,
+    "num_samples": 10000,
+    "inputlen": 2114,
+    "outputlen": 1000,
+    "seed": 1234,
+    "epochs": 50,
+    "early_stop": 5,
+    "learning_rate": 0.001,
+    "trackables": [
+        "logcount_predictions_loss",
+        "loss",
+        "logits_profile_predictions_loss",
+        "val_logcount_predictions_loss",
+        "val_loss",
+        "val_logits_profile_predictions_loss"
+    ],
+    "architecture_from_file": "/home/groups/akundaje/anusri/simg/chrombpnet_latest/chrombpnet/chrombpnet/training/models/chrombpnet_with_bias_model.py",
+    "file_prefix": "ENCSR627UDJ",
+    "html_prefix": "./",
+    "bias_model_path": "/scratch/groups/akundaje/anusri/chromatin_atlas/DNASE/ENCSR627UDJ//chrombpnet_model_feb15_fold_0/bias_model/models/ENCSR627UDJ_bias.h5",
+    "negative_sampling_ratio": 0.1,
+    "filters": 512,
+    "n_dilation_layers": 8,
+    "max_jitter": 500,
+    "batch_size": 64,
+    "output_prefix": "/scratch/groups/akundaje/anusri/chromatin_atlas/DNASE/ENCSR627UDJ//chrombpnet_model_feb15_fold_1/chrombpnet_model/models/ENCSR627UDJ_chrombpnet",
+    "chr": "chr12",
+    "pwm_width": 24,
+    "params": "/scratch/groups/akundaje/anusri/chromatin_atlas/DNASE/ENCSR627UDJ//chrombpnet_model_feb15_fold_1/chrombpnet_model/logs/ENCSR627UDJ_chrombpnet_model_params.tsv"
+}

fold_1/logs.models.fold_1.ENCSR627UDJ/logfile.modelling.fold_1.ENCSR627UDJ.bias_formatting.stdout.txt

@@ -0,0 +1 @@
+Converting /oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/DNASE/ENCSR627UDJ/failed_models_retrained/chrombpnet_model_feb15_fold_1/chrombpnet_model/models/ENCSR627UDJ_bias_model_scaled.h5 to /oak/stanford/groups/akundaje/vhecht/chromatin-atlas-2022/DNASE/ENCSR627UDJ/fold_1/new_model_format/bias_model_scaled.tar with get_new_tf_model_format.py

fold_1/logs.models.fold_1.ENCSR627UDJ/logfile.modelling.fold_1.ENCSR627UDJ.chrombpnet_data_params.tsv

@@ -0,0 +1,3 @@
+counts_sum_min_thresh	0.0
+counts_sum_max_thresh	4586.31
+trainings_pts_post_thresh	149372

fold_1/logs.models.fold_1.ENCSR627UDJ/logfile.modelling.fold_1.ENCSR627UDJ.chrombpnet_formatting.stdout.txt

@@ -0,0 +1 @@
+Converting /oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/DNASE/ENCSR627UDJ/failed_models_retrained/chrombpnet_model_feb15_fold_1/chrombpnet_model/models/ENCSR627UDJ_chrombpnet.h5 to /oak/stanford/groups/akundaje/vhecht/chromatin-atlas-2022/DNASE/ENCSR627UDJ/fold_1/new_model_format/chrombpnet.tar with get_new_tf_model_format.py

fold_1/logs.models.fold_1.ENCSR627UDJ/logfile.modelling.fold_1.ENCSR627UDJ.chrombpnet_model_params.tsv

@@ -0,0 +1,9 @@
+counts_loss_weight	1.7
+filters	512
+n_dil_layers	8
+bias_model_path	/scratch/groups/akundaje/anusri/chromatin_atlas/DNASE/ENCSR627UDJ//chrombpnet_model_feb15_fold_1/chrombpnet_model/models/ENCSR627UDJ_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.ENCSR627UDJ/logfile.modelling.fold_1.ENCSR627UDJ.chrombpnet_no_bias_formatting.stdout.txt

@@ -0,0 +1 @@
+Converting /oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/DNASE/ENCSR627UDJ/failed_models_retrained/chrombpnet_model_feb15_fold_1/chrombpnet_model/models/ENCSR627UDJ_chrombpnet_nobias.h5 to /oak/stanford/groups/akundaje/vhecht/chromatin-atlas-2022/DNASE/ENCSR627UDJ/fold_1/new_model_format/chrombpnet_nobias.tar with get_new_tf_model_format.py

fold_1/logs.models.fold_1.ENCSR627UDJ/logfile.modelling.fold_1.ENCSR627UDJ.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
+0,1.933280110359192,145.362060546875,148.6482696533203,1.0987399816513062,177.65025329589844,179.51795959472656
+1,0.7729538083076477,138.51681518554688,139.8311004638672,1.0232205390930176,170.95529174804688,172.69464111328125
+2,0.6410585641860962,135.8238067626953,136.91351318359375,0.7143363356590271,170.13143920898438,171.34584045410156
+3,0.5623558163642883,133.8951873779297,134.85122680664062,0.7024086117744446,166.50320434570312,167.69723510742188
+4,0.5174820423126221,132.54617309570312,133.42593383789062,0.6120665073394775,168.5902557373047,169.63075256347656
+5,0.49552711844444275,131.92486572265625,132.76719665527344,0.6225351095199585,165.6868896484375,166.74513244628906
+6,0.4797850251197815,131.0008544921875,131.8166046142578,0.9209599494934082,168.15744018554688,169.7229461669922
+7,0.464979887008667,130.35186767578125,131.1423797607422,0.5260078310966492,165.2237548828125,166.11798095703125
+8,0.4527904987335205,129.7759246826172,130.5458221435547,0.5199325680732727,165.4796142578125,166.3634033203125
+9,0.4383392035961151,129.05438232421875,129.7994842529297,0.5101093053817749,165.70216369628906,166.56951904296875
+10,0.43170079588890076,128.63961791992188,129.37364196777344,0.5037223696708679,164.5777130126953,165.43408203125
+11,0.42347046732902527,128.41990661621094,129.13987731933594,0.5061619281768799,164.76968383789062,165.6301727294922
+12,0.41901952028274536,127.7149658203125,128.42726135253906,0.49932587146759033,166.08042907714844,166.92926025390625
+13,0.40646639466285706,127.47030639648438,128.1611785888672,0.5070534348487854,165.22164916992188,166.0836944580078
+14,0.4001356065273285,127.60198211669922,128.2822723388672,0.4965253472328186,164.8624267578125,165.70635986328125
+15,0.39702463150024414,127.04399108886719,127.71882629394531,0.5111998319625854,167.48727416992188,168.35643005371094

fold_1/model.bias_scaled.fold_1.ENCSR627UDJ.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1c9a4e38fb76e940476e5c61163ad4bafafeb539781157594a64f332e853450a
+size 2691928

fold_1/model.bias_scaled.fold_1.ENCSR627UDJ.tar/keras_metadata.pb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bf03080435e97ceaf819923c48ce2acde74d094371880a79e44141b267548eed
+size 32946

fold_1/model.bias_scaled.fold_1.ENCSR627UDJ.tar/saved_model.pb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4086baa1e3c62ff25642424fc6d21a96ea0cc655ae97cb912c3fa732920a5ffa
+size 267277

fold_1/model.bias_scaled.fold_1.ENCSR627UDJ.tar/variables/variables.data-00000-of-00001

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:58fdcc855fff5b1c7e51bb46f72864a0e9ae203cea19d1b3554b4d7f029c0390
+size 882550

fold_1/model.chrombpnet.fold_1.ENCSR627UDJ.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0445a22cbfa87baaff51c95b2ae7d0910c26a4acd6fe5f1d98bdb72671df6fc0
+size 77538904

fold_1/model.chrombpnet.fold_1.ENCSR627UDJ.tar/keras_metadata.pb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c22c4530e1dbffe1f5aa36633482921869fbba65e9531eec1d3bc1353fc6f3eb
+size 136809

fold_1/model.chrombpnet.fold_1.ENCSR627UDJ.tar/saved_model.pb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8bddfc250d542afd2777a125755a3d312640cf635e1c5115ee27ba223994ebad
+size 958726

fold_1/model.chrombpnet.fold_1.ENCSR627UDJ.tar/variables/variables.data-00000-of-00001

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1e1fe1c9fbea63016e67a3b82e9bf3bb5c7218051609c4538f201b87388e8cb3
+size 26415899

fold_1/model.chrombpnet_nobias.fold_1.ENCSR627UDJ.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2c03049cb4a1929cb3470d479fd38b16e1885a783c5a2246b69417270896ec6e
+size 25582648

fold_1/model.chrombpnet_nobias.fold_1.ENCSR627UDJ.tar/keras_metadata.pb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e3414d53705260cdd80f7a6c30a5457b7ed495394a3f243abf90239d125be736
+size 53915

fold_1/model.chrombpnet_nobias.fold_1.ENCSR627UDJ.tar/saved_model.pb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3cf82e94c50badd69ec5aff3655d797f290d17f4848d905447395cf70d4c65d5
+size 460921

fold_1/model.chrombpnet_nobias.fold_1.ENCSR627UDJ.tar/variables/variables.data-00000-of-00001

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9a73ad9718fa03d1c5390d658842aac806f09b3244608ca5f6c515a41043ab88
+size 25531097

fold_2/logs.models.fold_2.ENCSR627UDJ/logfile.modelling.fold_2.ENCSR627UDJ.args.json

@@ -0,0 +1,45 @@
+{
+    "cmd": "train",
+    "genome": "/scratch/groups/akundaje/anusri/chromatin_atlas/reference//hg38.genome.fa",
+    "chrom_sizes": "/scratch/groups/akundaje/anusri/chromatin_atlas/reference//chrom.sizes",
+    "input_bam_file": null,
+    "input_fragment_file": null,
+    "input_tagalign_file": null,
+    "bigwig": "/oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/DNASE//ENCSR627UDJ//preprocessing/bigWigs/ENCSR627UDJ.bigWig",
+    "output_dir": "/scratch/groups/akundaje/anusri/chromatin_atlas/DNASE/ENCSR627UDJ//chrombpnet_model_feb15_fold_2/chrombpnet_model/",
+    "data_type": "DNASE",
+    "peaks": "/scratch/groups/akundaje/anusri/chromatin_atlas/DNASE/ENCSR627UDJ//chrombpnet_model_feb15_fold_2/chrombpnet_model/auxiliary/ENCSR627UDJ_filtered.peaks.bed",
+    "nonpeaks": "/scratch/groups/akundaje/anusri/chromatin_atlas/DNASE/ENCSR627UDJ//chrombpnet_model_feb15_fold_2/chrombpnet_model/auxiliary/ENCSR627UDJ_filtered.nonpeaks.bed",
+    "chr_fold_path": "/scratch/groups/akundaje/anusri/chromatin_atlas/splits/fold_2.json",
+    "outlier_threshold": 0.9999,
+    "ATAC_ref_path": null,
+    "DNASE_ref_path": null,
+    "num_samples": 10000,
+    "inputlen": 2114,
+    "outputlen": 1000,
+    "seed": 1234,
+    "epochs": 50,
+    "early_stop": 5,
+    "learning_rate": 0.001,
+    "trackables": [
+        "logcount_predictions_loss",
+        "loss",
+        "logits_profile_predictions_loss",
+        "val_logcount_predictions_loss",
+        "val_loss",
+        "val_logits_profile_predictions_loss"
+    ],
+    "architecture_from_file": "/home/groups/akundaje/anusri/simg/chrombpnet_latest/chrombpnet/chrombpnet/training/models/chrombpnet_with_bias_model.py",
+    "file_prefix": "ENCSR627UDJ",
+    "html_prefix": "./",
+    "bias_model_path": "/scratch/groups/akundaje/anusri/chromatin_atlas/DNASE/ENCSR627UDJ//chrombpnet_model_feb15_fold_0/bias_model/models/ENCSR627UDJ_bias.h5",
+    "negative_sampling_ratio": 0.1,
+    "filters": 512,
+    "n_dilation_layers": 8,
+    "max_jitter": 500,
+    "batch_size": 64,
+    "output_prefix": "/scratch/groups/akundaje/anusri/chromatin_atlas/DNASE/ENCSR627UDJ//chrombpnet_model_feb15_fold_2/chrombpnet_model/models/ENCSR627UDJ_chrombpnet",
+    "chr": "chr22",
+    "pwm_width": 24,
+    "params": "/scratch/groups/akundaje/anusri/chromatin_atlas/DNASE/ENCSR627UDJ//chrombpnet_model_feb15_fold_2/chrombpnet_model/logs/ENCSR627UDJ_chrombpnet_model_params.tsv"
+}