Upload folder using huggingface_hub

README.md

@@ -0,0 +1,120 @@
+---
+license: mit
+library_name: chrombpnet
+tags:
+  - encode
+  - chrombpnet
+  - chromatin-accessibility
+  - DNASE
+  - heart
+  - 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 heart (ENCSR914DOH)
+- Model: ChromBPNet
+- Assay: DNASE-seq
+- Experiment: [ENCSR914DOH](https://www.encodeproject.org/experiments/ENCSR914DOH/)
+- Model annotation: [ENCSR333JBA](https://www.encodeproject.org/annotations/ENCSR333JBA/)
+- Biosample: heart (Full name: Homo sapiens heart tissue female embryo (103 days))
+- Cell slim(s): None
+- Organ slim(s): heart
+- Developmental slim(s): mesoderm
+- System slim(s): circulatory-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.ENCSR914DOH/logfile.modelling.fold_0.ENCSR914DOH.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//ENCSR914DOH//preprocessing/bigWigs/ENCSR914DOH.bigWig",
+    "output_dir": "/scratch/groups/akundaje/anusri/chromatin_atlas/DNASE/ENCSR914DOH//chrombpnet_model_feb15_fold_0/chrombpnet_model/",
+    "data_type": "DNASE",
+    "peaks": "/scratch/groups/akundaje/anusri/chromatin_atlas/DNASE/ENCSR914DOH//chrombpnet_model_feb15_fold_0/chrombpnet_model/auxiliary/ENCSR914DOH_filtered.peaks.bed",
+    "nonpeaks": "/scratch/groups/akundaje/anusri/chromatin_atlas/DNASE/ENCSR914DOH//chrombpnet_model_feb15_fold_0/chrombpnet_model/auxiliary/ENCSR914DOH_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": "ENCSR914DOH",
+    "html_prefix": "./",
+    "bias_model_path": "/scratch/groups/akundaje/anusri/chromatin_atlas/DNASE/ENCSR914DOH//chrombpnet_model_feb15_fold_0/bias_model/models/ENCSR914DOH_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/ENCSR914DOH//chrombpnet_model_feb15_fold_0/chrombpnet_model/models/ENCSR914DOH_chrombpnet",
+    "chr": "chr8",
+    "pwm_width": 24,
+    "params": "/scratch/groups/akundaje/anusri/chromatin_atlas/DNASE/ENCSR914DOH//chrombpnet_model_feb15_fold_0/chrombpnet_model/logs/ENCSR914DOH_chrombpnet_model_params.tsv"
+}

fold_0/logs.models.fold_0.ENCSR914DOH/logfile.modelling.fold_0.ENCSR914DOH.bias_formatting.stdout.txt

@@ -0,0 +1 @@
+Converting /oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/DNASE/ENCSR914DOH/failed_models_retrained/chrombpnet_model_feb15_fold_0/chrombpnet_model/models/ENCSR914DOH_bias_model_scaled.h5 to /oak/stanford/groups/akundaje/vhecht/chromatin-atlas-2022/DNASE/ENCSR914DOH/fold_0/new_model_format/bias_model_scaled.tar with get_new_tf_model_format.py

fold_0/logs.models.fold_0.ENCSR914DOH/logfile.modelling.fold_0.ENCSR914DOH.chrombpnet_data_params.tsv

@@ -0,0 +1,3 @@
+counts_sum_min_thresh	0.0
+counts_sum_max_thresh	763.09
+trainings_pts_post_thresh	166767

fold_0/logs.models.fold_0.ENCSR914DOH/logfile.modelling.fold_0.ENCSR914DOH.chrombpnet_formatting.stdout.txt

@@ -0,0 +1 @@
+Converting /oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/DNASE/ENCSR914DOH/failed_models_retrained/chrombpnet_model_feb15_fold_0/chrombpnet_model/models/ENCSR914DOH_chrombpnet.h5 to /oak/stanford/groups/akundaje/vhecht/chromatin-atlas-2022/DNASE/ENCSR914DOH/fold_0/new_model_format/chrombpnet.tar with get_new_tf_model_format.py

fold_0/logs.models.fold_0.ENCSR914DOH/logfile.modelling.fold_0.ENCSR914DOH.chrombpnet_model_params.tsv

@@ -0,0 +1,9 @@
+counts_loss_weight	5.1
+filters	512
+n_dil_layers	8
+bias_model_path	/scratch/groups/akundaje/anusri/chromatin_atlas/DNASE/ENCSR914DOH//chrombpnet_model_feb15_fold_0/chrombpnet_model/models/ENCSR914DOH_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.ENCSR914DOH/logfile.modelling.fold_0.ENCSR914DOH.chrombpnet_no_bias_formatting.stdout.txt

@@ -0,0 +1 @@
+Converting /oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/DNASE/ENCSR914DOH/failed_models_retrained/chrombpnet_model_feb15_fold_0/chrombpnet_model/models/ENCSR914DOH_chrombpnet_nobias.h5 to /oak/stanford/groups/akundaje/vhecht/chromatin-atlas-2022/DNASE/ENCSR914DOH/fold_0/new_model_format/chrombpnet_nobias.tar with get_new_tf_model_format.py

fold_0/logs.models.fold_0.ENCSR914DOH/logfile.modelling.fold_0.ENCSR914DOH.epoch_loss.csv

@@ -0,0 +1,12 @@
+epoch,logcount_predictions_loss,logits_profile_predictions_loss,loss,val_logcount_predictions_loss,val_logits_profile_predictions_loss,val_loss
+0,4.758664131164551,232.62535095214844,256.89471435546875,1.1056981086730957,235.924072265625,241.56300354003906
+1,1.0307785272598267,227.9333953857422,233.19029235839844,0.9458255767822266,233.5879364013672,238.4116973876953
+2,0.9391119480133057,225.68251037597656,230.47198486328125,0.8881170749664307,231.50350952148438,236.03292846679688
+3,0.8753817677497864,224.30706787109375,228.77139282226562,0.9008144736289978,230.97329711914062,235.5674591064453
+4,0.8280647397041321,223.22604370117188,227.4492950439453,0.820381224155426,230.8101043701172,234.99398803710938
+5,0.7845550775527954,222.47613525390625,226.47755432128906,0.781876266002655,230.6362762451172,234.6239776611328
+6,0.7513571977615356,221.4271240234375,225.25901794433594,0.7469934225082397,230.91842651367188,234.72801208496094
+7,0.7280874252319336,220.400390625,224.11373901367188,0.946323037147522,231.24209594726562,236.068359375
+8,0.7044016718864441,219.78338623046875,223.3756866455078,0.7670829892158508,231.12635803222656,235.0384521484375
+9,0.679275393486023,218.861083984375,222.3254852294922,0.7602362036705017,231.57772827148438,235.45492553710938
+10,0.6626833081245422,217.91282653808594,221.29244995117188,0.740689754486084,232.4914093017578,236.2688751220703

fold_0/model.bias_scaled.fold_0.ENCSR914DOH.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d114a00542c678a8278e31482f0a51450856352066c5c46214dfdef4dc50c37e
+size 2691928

fold_0/model.bias_scaled.fold_0.ENCSR914DOH.tar

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1225bfe4575c96670e4c7b3013c11338d8dabd3c48aaf632a7e26c1220351ed3
+size 1198080

fold_0/model.chrombpnet.fold_0.ENCSR914DOH.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:96f5dfde883659e8c2d1b1d0ab2ded2bf966668aa38b04ab88f74062846b7669
+size 77538904

fold_0/model.chrombpnet.fold_0.ENCSR914DOH.tar

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:95a6beec420954163c502d9139c53e8a57c37570cd49eddbd9b37ba0509b290b
+size 27525120

fold_0/model.chrombpnet_nobias.fold_0.ENCSR914DOH.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:33d8e12313ab309296a1e6899342cc9e5856ff64ba96c8bff1cd40a6ac9fe47c
+size 25582648

fold_0/model.chrombpnet_nobias.fold_0.ENCSR914DOH.tar

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ce80f2838be15c0d5170552e4acc8723fd717cbd77f9700c49a3731a41bc8e92
+size 26060800

fold_1/logs.models.fold_1.ENCSR914DOH/logfile.modelling.fold_1.ENCSR914DOH.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//ENCSR914DOH//preprocessing/bigWigs/ENCSR914DOH.bigWig",
+    "output_dir": "/scratch/groups/akundaje/anusri/chromatin_atlas/DNASE/ENCSR914DOH//chrombpnet_model_feb15_fold_1/chrombpnet_model/",
+    "data_type": "DNASE",
+    "peaks": "/scratch/groups/akundaje/anusri/chromatin_atlas/DNASE/ENCSR914DOH//chrombpnet_model_feb15_fold_1/chrombpnet_model/auxiliary/ENCSR914DOH_filtered.peaks.bed",
+    "nonpeaks": "/scratch/groups/akundaje/anusri/chromatin_atlas/DNASE/ENCSR914DOH//chrombpnet_model_feb15_fold_1/chrombpnet_model/auxiliary/ENCSR914DOH_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": "ENCSR914DOH",
+    "html_prefix": "./",
+    "bias_model_path": "/scratch/groups/akundaje/anusri/chromatin_atlas/DNASE/ENCSR914DOH//chrombpnet_model_feb15_fold_0/bias_model/models/ENCSR914DOH_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/ENCSR914DOH//chrombpnet_model_feb15_fold_1/chrombpnet_model/models/ENCSR914DOH_chrombpnet",
+    "chr": "chr12",
+    "pwm_width": 24,
+    "params": "/scratch/groups/akundaje/anusri/chromatin_atlas/DNASE/ENCSR914DOH//chrombpnet_model_feb15_fold_1/chrombpnet_model/logs/ENCSR914DOH_chrombpnet_model_params.tsv"
+}

fold_1/logs.models.fold_1.ENCSR914DOH/logfile.modelling.fold_1.ENCSR914DOH.bias_formatting.stdout.txt

@@ -0,0 +1 @@
+Converting /oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/DNASE/ENCSR914DOH/failed_models_retrained/chrombpnet_model_feb15_fold_1/chrombpnet_model/models/ENCSR914DOH_bias_model_scaled.h5 to /oak/stanford/groups/akundaje/vhecht/chromatin-atlas-2022/DNASE/ENCSR914DOH/fold_1/new_model_format/bias_model_scaled.tar with get_new_tf_model_format.py

fold_1/logs.models.fold_1.ENCSR914DOH/logfile.modelling.fold_1.ENCSR914DOH.chrombpnet_data_params.tsv

@@ -0,0 +1,3 @@
+counts_sum_min_thresh	0.0
+counts_sum_max_thresh	771.18
+trainings_pts_post_thresh	173299

fold_1/logs.models.fold_1.ENCSR914DOH/logfile.modelling.fold_1.ENCSR914DOH.chrombpnet_formatting.stdout.txt

@@ -0,0 +1 @@
+Converting /oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/DNASE/ENCSR914DOH/failed_models_retrained/chrombpnet_model_feb15_fold_1/chrombpnet_model/models/ENCSR914DOH_chrombpnet.h5 to /oak/stanford/groups/akundaje/vhecht/chromatin-atlas-2022/DNASE/ENCSR914DOH/fold_1/new_model_format/chrombpnet.tar with get_new_tf_model_format.py

fold_1/logs.models.fold_1.ENCSR914DOH/logfile.modelling.fold_1.ENCSR914DOH.chrombpnet_model_params.tsv

@@ -0,0 +1,9 @@
+counts_loss_weight	5.2
+filters	512
+n_dil_layers	8
+bias_model_path	/scratch/groups/akundaje/anusri/chromatin_atlas/DNASE/ENCSR914DOH//chrombpnet_model_feb15_fold_1/chrombpnet_model/models/ENCSR914DOH_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.ENCSR914DOH/logfile.modelling.fold_1.ENCSR914DOH.chrombpnet_no_bias_formatting.stdout.txt

@@ -0,0 +1 @@
+Converting /oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/DNASE/ENCSR914DOH/failed_models_retrained/chrombpnet_model_feb15_fold_1/chrombpnet_model/models/ENCSR914DOH_chrombpnet_nobias.h5 to /oak/stanford/groups/akundaje/vhecht/chromatin-atlas-2022/DNASE/ENCSR914DOH/fold_1/new_model_format/chrombpnet_nobias.tar with get_new_tf_model_format.py

fold_1/logs.models.fold_1.ENCSR914DOH/logfile.modelling.fold_1.ENCSR914DOH.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
+0,3.2841439247131348,232.7257843017578,249.80328369140625,1.0238242149353027,259.044677734375,264.36834716796875
+1,0.9895934462547302,227.76510620117188,232.9115447998047,1.0175542831420898,256.11474609375,261.40594482421875
+2,0.9054428339004517,225.89248657226562,230.6006622314453,0.8527833223342896,255.8607940673828,260.295166015625
+3,0.8556702136993408,224.62841796875,229.07763671875,0.8105573654174805,254.42872619628906,258.643798828125
+4,0.8006834983825684,223.92201232910156,228.08541870117188,1.1057566404342651,254.09674072265625,259.84686279296875
+5,0.7712125778198242,223.07015991210938,227.08074951171875,0.7427418231964111,254.27468872070312,258.13702392578125
+6,0.7327189445495605,221.9873046875,225.7976531982422,0.7154141664505005,253.92987060546875,257.65008544921875
+7,0.7122138738632202,221.0009002685547,224.70431518554688,0.8441315293312073,254.45863342285156,258.8482360839844
+8,0.6860426068305969,220.4830322265625,224.05052185058594,0.7084928154945374,255.31053161621094,258.9945373535156
+9,0.6634119749069214,219.70484924316406,223.15455627441406,0.6968827247619629,255.54168701171875,259.16534423828125
+10,0.6497734189033508,218.3824005126953,221.76092529296875,0.6987376809120178,256.558349609375,260.19171142578125
+11,0.6313955783843994,217.924072265625,221.20718383789062,0.6970866918563843,256.472412109375,260.09747314453125

fold_1/model.bias_scaled.fold_1.ENCSR914DOH.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:198c67058efb89a521576ae42c0115ce185b1b697913d6f82115133f8fc89f1f
+size 2691928

fold_1/model.bias_scaled.fold_1.ENCSR914DOH.tar

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:482a1e909c8a2d70d00ae64531d521c65389d546d584147f0f32e98e6fa97540
+size 1198080

fold_1/model.chrombpnet.fold_1.ENCSR914DOH.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ffe9f5415e0787342e7411faa593a10203408f6d39d0b667bbec30901494ac01
+size 77538904

fold_1/model.chrombpnet.fold_1.ENCSR914DOH.tar

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:95c0d0474fe5c2b15f337e4f1523b67f524925c6fadaf767ed576fced3251f4f
+size 27525120

fold_1/model.chrombpnet_nobias.fold_1.ENCSR914DOH.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d933fd82501b7cbdbf84c56ffe985d2ca5e21b1b81bf05e503e1473e6f02b56e
+size 25582648

fold_1/model.chrombpnet_nobias.fold_1.ENCSR914DOH.tar

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:12b2d924b972a939cd5cd8979689f6fc3485738b3cb5a048278c75120bc787c6
+size 26060800

fold_2/logs.models.fold_2.ENCSR914DOH/logfile.modelling.fold_2.ENCSR914DOH.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//ENCSR914DOH//preprocessing/bigWigs/ENCSR914DOH.bigWig",
+    "output_dir": "/scratch/groups/akundaje/anusri/chromatin_atlas/DNASE/ENCSR914DOH//chrombpnet_model_feb15_fold_2/chrombpnet_model/",
+    "data_type": "DNASE",
+    "peaks": "/scratch/groups/akundaje/anusri/chromatin_atlas/DNASE/ENCSR914DOH//chrombpnet_model_feb15_fold_2/chrombpnet_model/auxiliary/ENCSR914DOH_filtered.peaks.bed",
+    "nonpeaks": "/scratch/groups/akundaje/anusri/chromatin_atlas/DNASE/ENCSR914DOH//chrombpnet_model_feb15_fold_2/chrombpnet_model/auxiliary/ENCSR914DOH_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": "ENCSR914DOH",
+    "html_prefix": "./",
+    "bias_model_path": "/scratch/groups/akundaje/anusri/chromatin_atlas/DNASE/ENCSR914DOH//chrombpnet_model_feb15_fold_0/bias_model/models/ENCSR914DOH_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/ENCSR914DOH//chrombpnet_model_feb15_fold_2/chrombpnet_model/models/ENCSR914DOH_chrombpnet",
+    "chr": "chr22",
+    "pwm_width": 24,
+    "params": "/scratch/groups/akundaje/anusri/chromatin_atlas/DNASE/ENCSR914DOH//chrombpnet_model_feb15_fold_2/chrombpnet_model/logs/ENCSR914DOH_chrombpnet_model_params.tsv"
+}

fold_2/logs.models.fold_2.ENCSR914DOH/logfile.modelling.fold_2.ENCSR914DOH.bias_formatting.stdout.txt

@@ -0,0 +1 @@
+Converting /oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/DNASE/ENCSR914DOH/failed_models_retrained/chrombpnet_model_feb15_fold_2/chrombpnet_model/models/ENCSR914DOH_bias_model_scaled.h5 to /oak/stanford/groups/akundaje/vhecht/chromatin-atlas-2022/DNASE/ENCSR914DOH/fold_2/new_model_format/bias_model_scaled.tar with get_new_tf_model_format.py

fold_2/logs.models.fold_2.ENCSR914DOH/logfile.modelling.fold_2.ENCSR914DOH.chrombpnet_data_params.tsv

@@ -0,0 +1,3 @@
+counts_sum_min_thresh	0.0
+counts_sum_max_thresh	765.81
+trainings_pts_post_thresh	175514

fold_2/logs.models.fold_2.ENCSR914DOH/logfile.modelling.fold_2.ENCSR914DOH.chrombpnet_formatting.stdout.txt

@@ -0,0 +1 @@
+Converting /oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/DNASE/ENCSR914DOH/failed_models_retrained/chrombpnet_model_feb15_fold_2/chrombpnet_model/models/ENCSR914DOH_chrombpnet.h5 to /oak/stanford/groups/akundaje/vhecht/chromatin-atlas-2022/DNASE/ENCSR914DOH/fold_2/new_model_format/chrombpnet.tar with get_new_tf_model_format.py

fold_2/logs.models.fold_2.ENCSR914DOH/logfile.modelling.fold_2.ENCSR914DOH.chrombpnet_model_params.tsv

@@ -0,0 +1,9 @@
+counts_loss_weight	5.1
+filters	512
+n_dil_layers	8
+bias_model_path	/scratch/groups/akundaje/anusri/chromatin_atlas/DNASE/ENCSR914DOH//chrombpnet_model_feb15_fold_2/chrombpnet_model/models/ENCSR914DOH_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.ENCSR914DOH/logfile.modelling.fold_2.ENCSR914DOH.chrombpnet_no_bias_formatting.stdout.txt

@@ -0,0 +1 @@
+Converting /oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/DNASE/ENCSR914DOH/failed_models_retrained/chrombpnet_model_feb15_fold_2/chrombpnet_model/models/ENCSR914DOH_chrombpnet_nobias.h5 to /oak/stanford/groups/akundaje/vhecht/chromatin-atlas-2022/DNASE/ENCSR914DOH/fold_2/new_model_format/chrombpnet_nobias.tar with get_new_tf_model_format.py

fold_2/logs.models.fold_2.ENCSR914DOH/logfile.modelling.fold_2.ENCSR914DOH.epoch_loss.csv

@@ -0,0 +1,11 @@
+epoch,logcount_predictions_loss,logits_profile_predictions_loss,loss,val_logcount_predictions_loss,val_logits_profile_predictions_loss,val_loss
+0,5.475602149963379,232.40011596679688,260.3256530761719,0.9718027710914612,238.9605255126953,243.91677856445312
+1,0.9816336035728455,227.54246520996094,232.54873657226562,0.8893459439277649,236.1734161376953,240.70896911621094
+2,0.9096200466156006,225.59938049316406,230.23837280273438,0.8370091319084167,236.14794921875,240.4166259765625
+3,0.8537629246711731,224.62722778320312,228.98153686523438,0.8298797011375427,233.8291778564453,238.06161499023438
+4,0.8126247525215149,223.7384490966797,227.8822021484375,0.7848828434944153,232.85020446777344,236.8531036376953
+5,0.7756116390228271,222.88043212890625,226.83651733398438,0.9245596528053284,233.47021484375,238.1856689453125
+6,0.7383350729942322,221.89193725585938,225.65736389160156,0.7557170987129211,233.81832885742188,237.6725311279297
+7,0.7185662984848022,221.1320343017578,224.7962188720703,0.7241970896720886,233.91580200195312,237.6092529296875
+8,0.6941832900047302,220.10743713378906,223.64788818359375,0.7563595175743103,233.8511962890625,237.70864868164062
+9,0.6727387309074402,219.4416961669922,222.87274169921875,0.7255550026893616,235.54296875,239.2432098388672

fold_2/model.bias_scaled.fold_2.ENCSR914DOH.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d6cad9eced2d8e9595728a25a9d600059fbffa1177ea1fbd8db1b4e218dac9e2
+size 2691928

fold_2/model.bias_scaled.fold_2.ENCSR914DOH.tar

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ef5e178ac4266f17150a2a5533e9600d39de6b4a113c0011fc08fb05af6fe09e
+size 1198080

fold_2/model.chrombpnet.fold_2.ENCSR914DOH.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bd75e3ca8f2cc20c8f16574902d6570beb0088a99fb2d43c7c6dc7e3680624f2
+size 77538904

fold_2/model.chrombpnet.fold_2.ENCSR914DOH.tar

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9dc5bf089b801d22ae1668387eb9f268352e94b6f8de0719c18d85aace475a96
+size 27525120

fold_2/model.chrombpnet_nobias.fold_2.ENCSR914DOH.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8abd2d3650b4e5f78b775fc1aa50e9e6c48f6bfb334ffa51613d4b9a30376def
+size 25582648

fold_2/model.chrombpnet_nobias.fold_2.ENCSR914DOH.tar

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ca517e5a6cfa6d9224351166827f949f4dfe514a5eb5291f16c7a11420fcb112
+size 26060800

fold_3/logs.models.fold_3.ENCSR914DOH/logfile.modelling.fold_3.ENCSR914DOH.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//ENCSR914DOH//preprocessing/bigWigs/ENCSR914DOH.bigWig",
+    "output_dir": "/scratch/groups/akundaje/anusri/chromatin_atlas/DNASE/ENCSR914DOH//chrombpnet_model_feb15_fold_3/chrombpnet_model/",
+    "data_type": "DNASE",
+    "peaks": "/scratch/groups/akundaje/anusri/chromatin_atlas/DNASE/ENCSR914DOH//chrombpnet_model_feb15_fold_3/chrombpnet_model/auxiliary/ENCSR914DOH_filtered.peaks.bed",
+    "nonpeaks": "/scratch/groups/akundaje/anusri/chromatin_atlas/DNASE/ENCSR914DOH//chrombpnet_model_feb15_fold_3/chrombpnet_model/auxiliary/ENCSR914DOH_filtered.nonpeaks.bed",
+    "chr_fold_path": "/scratch/groups/akundaje/anusri/chromatin_atlas/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/groups/akundaje/anusri/simg/chrombpnet_latest/chrombpnet/chrombpnet/training/models/chrombpnet_with_bias_model.py",
+    "file_prefix": "ENCSR914DOH",
+    "html_prefix": "./",
+    "bias_model_path": "/scratch/groups/akundaje/anusri/chromatin_atlas/DNASE/ENCSR914DOH//chrombpnet_model_feb15_fold_0/bias_model/models/ENCSR914DOH_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/ENCSR914DOH//chrombpnet_model_feb15_fold_3/chrombpnet_model/models/ENCSR914DOH_chrombpnet",
+    "chr": "chr6",
+    "pwm_width": 24,
+    "params": "/scratch/groups/akundaje/anusri/chromatin_atlas/DNASE/ENCSR914DOH//chrombpnet_model_feb15_fold_3/chrombpnet_model/logs/ENCSR914DOH_chrombpnet_model_params.tsv"
+}

fold_3/logs.models.fold_3.ENCSR914DOH/logfile.modelling.fold_3.ENCSR914DOH.bias_formatting.stdout.txt

@@ -0,0 +1 @@
+Converting /oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/DNASE/ENCSR914DOH/failed_models_retrained/chrombpnet_model_feb15_fold_3/chrombpnet_model/models/ENCSR914DOH_bias_model_scaled.h5 to /oak/stanford/groups/akundaje/vhecht/chromatin-atlas-2022/DNASE/ENCSR914DOH/fold_3/new_model_format/bias_model_scaled.tar with get_new_tf_model_format.py

fold_3/logs.models.fold_3.ENCSR914DOH/logfile.modelling.fold_3.ENCSR914DOH.chrombpnet_data_params.tsv

@@ -0,0 +1,3 @@
+counts_sum_min_thresh	0.0
+counts_sum_max_thresh	771.4
+trainings_pts_post_thresh	172312

fold_3/logs.models.fold_3.ENCSR914DOH/logfile.modelling.fold_3.ENCSR914DOH.chrombpnet_formatting.stdout.txt

@@ -0,0 +1 @@
+Converting /oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/DNASE/ENCSR914DOH/failed_models_retrained/chrombpnet_model_feb15_fold_3/chrombpnet_model/models/ENCSR914DOH_chrombpnet.h5 to /oak/stanford/groups/akundaje/vhecht/chromatin-atlas-2022/DNASE/ENCSR914DOH/fold_3/new_model_format/chrombpnet.tar with get_new_tf_model_format.py

fold_3/logs.models.fold_3.ENCSR914DOH/logfile.modelling.fold_3.ENCSR914DOH.chrombpnet_model_params.tsv

@@ -0,0 +1,9 @@
+counts_loss_weight	5.2
+filters	512
+n_dil_layers	8
+bias_model_path	/scratch/groups/akundaje/anusri/chromatin_atlas/DNASE/ENCSR914DOH//chrombpnet_model_feb15_fold_3/chrombpnet_model/models/ENCSR914DOH_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.ENCSR914DOH/logfile.modelling.fold_3.ENCSR914DOH.chrombpnet_no_bias_formatting.stdout.txt

@@ -0,0 +1 @@
+Converting /oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/DNASE/ENCSR914DOH/failed_models_retrained/chrombpnet_model_feb15_fold_3/chrombpnet_model/models/ENCSR914DOH_chrombpnet_nobias.h5 to /oak/stanford/groups/akundaje/vhecht/chromatin-atlas-2022/DNASE/ENCSR914DOH/fold_3/new_model_format/chrombpnet_nobias.tar with get_new_tf_model_format.py