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 (ENCSR174JMM)
+- Model: ChromBPNet
+- Assay: DNASE-seq
+- Experiment: [ENCSR174JMM](https://www.encodeproject.org/experiments/ENCSR174JMM/)
+- Model annotation: [ENCSR294MBS](https://www.encodeproject.org/annotations/ENCSR294MBS/)
+- Biosample: heart (Full name: Homo sapiens heart tissue female embryo (117 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.ENCSR174JMM/logfile.modelling.fold_0.ENCSR174JMM.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//ENCSR174JMM//preprocessing/bigWigs/ENCSR174JMM.bigWig",
+    "output_dir": "/scratch/groups/akundaje/anusri/chromatin_atlas/DNASE/ENCSR174JMM//chrombpnet_model_feb20_fold_0/chrombpnet_model/",
+    "data_type": "DNASE",
+    "peaks": "/scratch/groups/akundaje/anusri/chromatin_atlas/DNASE/ENCSR174JMM//chrombpnet_model_feb20_fold_0/chrombpnet_model/auxiliary/ENCSR174JMM_filtered.peaks.bed",
+    "nonpeaks": "/scratch/groups/akundaje/anusri/chromatin_atlas/DNASE/ENCSR174JMM//chrombpnet_model_feb20_fold_0/chrombpnet_model/auxiliary/ENCSR174JMM_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": "ENCSR174JMM",
+    "html_prefix": "./",
+    "bias_model_path": "/scratch/groups/akundaje/anusri/chromatin_atlas/DNASE/ENCSR174JMM//chrombpnet_model_feb20_fold_0/bias_model/models/ENCSR174JMM_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/ENCSR174JMM//chrombpnet_model_feb20_fold_0/chrombpnet_model/models/ENCSR174JMM_chrombpnet",
+    "chr": "chr8",
+    "pwm_width": 24,
+    "params": "/scratch/groups/akundaje/anusri/chromatin_atlas/DNASE/ENCSR174JMM//chrombpnet_model_feb20_fold_0/chrombpnet_model/logs/ENCSR174JMM_chrombpnet_model_params.tsv"
+}

fold_0/logs.models.fold_0.ENCSR174JMM/logfile.modelling.fold_0.ENCSR174JMM.bias_formatting.stdout.txt

@@ -0,0 +1 @@
+Converting /oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/DNASE/ENCSR174JMM/failed_models_retrained/chrombpnet_model_feb20_fold_0/chrombpnet_model/models/ENCSR174JMM_bias_model_scaled.h5 to /oak/stanford/groups/akundaje/vhecht/chromatin-atlas-2022/DNASE/ENCSR174JMM/fold_0/new_model_format/bias_model_scaled.tar with get_new_tf_model_format.py

fold_0/logs.models.fold_0.ENCSR174JMM/logfile.modelling.fold_0.ENCSR174JMM.chrombpnet_data_params.tsv

@@ -0,0 +1,3 @@
+counts_sum_min_thresh	0.0
+counts_sum_max_thresh	1022.84
+trainings_pts_post_thresh	166290

fold_0/logs.models.fold_0.ENCSR174JMM/logfile.modelling.fold_0.ENCSR174JMM.chrombpnet_formatting.stdout.txt

@@ -0,0 +1 @@
+Converting /oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/DNASE/ENCSR174JMM/failed_models_retrained/chrombpnet_model_feb20_fold_0/chrombpnet_model/models/ENCSR174JMM_chrombpnet.h5 to /oak/stanford/groups/akundaje/vhecht/chromatin-atlas-2022/DNASE/ENCSR174JMM/fold_0/new_model_format/chrombpnet.tar with get_new_tf_model_format.py

fold_0/logs.models.fold_0.ENCSR174JMM/logfile.modelling.fold_0.ENCSR174JMM.chrombpnet_model_params.tsv

@@ -0,0 +1,9 @@
+counts_loss_weight	4.2
+filters	512
+n_dil_layers	8
+bias_model_path	/scratch/groups/akundaje/anusri/chromatin_atlas/DNASE/ENCSR174JMM//chrombpnet_model_feb20_fold_0/chrombpnet_model/models/ENCSR174JMM_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.ENCSR174JMM/logfile.modelling.fold_0.ENCSR174JMM.chrombpnet_no_bias_formatting.stdout.txt

@@ -0,0 +1 @@
+Converting /oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/DNASE/ENCSR174JMM/failed_models_retrained/chrombpnet_model_feb20_fold_0/chrombpnet_model/models/ENCSR174JMM_chrombpnet_nobias.h5 to /oak/stanford/groups/akundaje/vhecht/chromatin-atlas-2022/DNASE/ENCSR174JMM/fold_0/new_model_format/chrombpnet_nobias.tar with get_new_tf_model_format.py

fold_0/logs.models.fold_0.ENCSR174JMM/logfile.modelling.fold_0.ENCSR174JMM.epoch_loss.csv

@@ -0,0 +1,10 @@
+epoch,logcount_predictions_loss,logits_profile_predictions_loss,loss,val_logcount_predictions_loss,val_logits_profile_predictions_loss,val_loss
+0,1.739310383796692,218.46751403808594,225.7726287841797,0.958078145980835,223.1644287109375,227.1883544921875
+1,0.9454631209373474,212.42506408691406,216.39633178710938,0.862903356552124,221.0325469970703,224.65667724609375
+2,0.8785760998725891,210.6996307373047,214.38926696777344,0.8210712671279907,220.25244140625,223.7008514404297
+3,0.8254299759864807,209.4208221435547,212.8874053955078,0.8092076778411865,218.64154052734375,222.0402069091797
+4,0.7897056341171265,208.3110809326172,211.62786865234375,0.9490761756896973,220.46974182128906,224.4557342529297
+5,0.7678460478782654,207.39276123046875,210.61795043945312,0.7645962834358215,220.90728759765625,224.11863708496094
+6,0.7391471266746521,206.4008026123047,209.5050506591797,0.888036847114563,220.7837677001953,224.51336669921875
+7,0.7172517776489258,205.80943298339844,208.82122802734375,0.7384932041168213,220.6656494140625,223.76730346679688
+8,0.6889055371284485,204.71531677246094,207.60848999023438,0.773732602596283,221.01284790039062,224.26260375976562

fold_0/model.bias_scaled.fold_0.ENCSR174JMM.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:772880d014fdcf23810dadef92968d1b7c9984af3df86802126cec2e0251e026
+size 2691928

fold_0/model.bias_scaled.fold_0.ENCSR174JMM.tar

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:852b76a3146f50a62fb6bb123b70b16597f684df93fb57331f3c46b87f8fd534
+size 1198080

fold_0/model.chrombpnet.fold_0.ENCSR174JMM.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ea0c189d9c0ddcd297d2fff9d19038f85032dc00598bd2f7c40ad6b227099254
+size 77538904

fold_0/model.chrombpnet.fold_0.ENCSR174JMM.tar

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bd8bef5ecf9d86f19b424cf6a950389d9ceade66a69fd825e54d607d3d234093
+size 27525120

fold_0/model.chrombpnet_nobias.fold_0.ENCSR174JMM.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cdb161233d4ac390a4c46717c88e777ccba00171a0f950d448806e4fb69a82ba
+size 25582648

fold_0/model.chrombpnet_nobias.fold_0.ENCSR174JMM.tar

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:099cae35758ee575395ad5ea81119ca6d53cc7a20e83ee36606a396ae5afd19e
+size 26060800

fold_1/logs.models.fold_1.ENCSR174JMM/logfile.modelling.fold_1.ENCSR174JMM.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//ENCSR174JMM//preprocessing/bigWigs/ENCSR174JMM.bigWig",
+    "output_dir": "/scratch/groups/akundaje/anusri/chromatin_atlas/DNASE/ENCSR174JMM//chrombpnet_model_feb20_fold_1/chrombpnet_model/",
+    "data_type": "DNASE",
+    "peaks": "/scratch/groups/akundaje/anusri/chromatin_atlas/DNASE/ENCSR174JMM//chrombpnet_model_feb20_fold_1/chrombpnet_model/auxiliary/ENCSR174JMM_filtered.peaks.bed",
+    "nonpeaks": "/scratch/groups/akundaje/anusri/chromatin_atlas/DNASE/ENCSR174JMM//chrombpnet_model_feb20_fold_1/chrombpnet_model/auxiliary/ENCSR174JMM_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": "ENCSR174JMM",
+    "html_prefix": "./",
+    "bias_model_path": "/scratch/groups/akundaje/anusri/chromatin_atlas/DNASE/ENCSR174JMM//chrombpnet_model_feb20_fold_0/bias_model/models/ENCSR174JMM_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/ENCSR174JMM//chrombpnet_model_feb20_fold_1/chrombpnet_model/models/ENCSR174JMM_chrombpnet",
+    "chr": "chr12",
+    "pwm_width": 24,
+    "params": "/scratch/groups/akundaje/anusri/chromatin_atlas/DNASE/ENCSR174JMM//chrombpnet_model_feb20_fold_1/chrombpnet_model/logs/ENCSR174JMM_chrombpnet_model_params.tsv"
+}

fold_1/logs.models.fold_1.ENCSR174JMM/logfile.modelling.fold_1.ENCSR174JMM.bias_formatting.stdout.txt

@@ -0,0 +1 @@
+Converting /oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/DNASE/ENCSR174JMM/failed_models_retrained/chrombpnet_model_feb20_fold_1/chrombpnet_model/models/ENCSR174JMM_bias_model_scaled.h5 to /oak/stanford/groups/akundaje/vhecht/chromatin-atlas-2022/DNASE/ENCSR174JMM/fold_1/new_model_format/bias_model_scaled.tar with get_new_tf_model_format.py

fold_1/logs.models.fold_1.ENCSR174JMM/logfile.modelling.fold_1.ENCSR174JMM.chrombpnet_data_params.tsv

@@ -0,0 +1,3 @@
+counts_sum_min_thresh	0.0
+counts_sum_max_thresh	1026.0
+trainings_pts_post_thresh	172417

fold_1/logs.models.fold_1.ENCSR174JMM/logfile.modelling.fold_1.ENCSR174JMM.chrombpnet_formatting.stdout.txt

@@ -0,0 +1 @@
+Converting /oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/DNASE/ENCSR174JMM/failed_models_retrained/chrombpnet_model_feb20_fold_1/chrombpnet_model/models/ENCSR174JMM_chrombpnet.h5 to /oak/stanford/groups/akundaje/vhecht/chromatin-atlas-2022/DNASE/ENCSR174JMM/fold_1/new_model_format/chrombpnet.tar with get_new_tf_model_format.py

fold_1/logs.models.fold_1.ENCSR174JMM/logfile.modelling.fold_1.ENCSR174JMM.chrombpnet_model_params.tsv

@@ -0,0 +1,9 @@
+counts_loss_weight	4.3
+filters	512
+n_dil_layers	8
+bias_model_path	/scratch/groups/akundaje/anusri/chromatin_atlas/DNASE/ENCSR174JMM//chrombpnet_model_feb20_fold_1/chrombpnet_model/models/ENCSR174JMM_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.ENCSR174JMM/logfile.modelling.fold_1.ENCSR174JMM.chrombpnet_no_bias_formatting.stdout.txt

@@ -0,0 +1 @@
+Converting /oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/DNASE/ENCSR174JMM/failed_models_retrained/chrombpnet_model_feb20_fold_1/chrombpnet_model/models/ENCSR174JMM_chrombpnet_nobias.h5 to /oak/stanford/groups/akundaje/vhecht/chromatin-atlas-2022/DNASE/ENCSR174JMM/fold_1/new_model_format/chrombpnet_nobias.tar with get_new_tf_model_format.py

fold_1/logs.models.fold_1.ENCSR174JMM/logfile.modelling.fold_1.ENCSR174JMM.epoch_loss.csv

@@ -0,0 +1,13 @@
+epoch,logcount_predictions_loss,logits_profile_predictions_loss,loss,val_logcount_predictions_loss,val_logits_profile_predictions_loss,val_loss
+0,5.212784767150879,219.67538452148438,242.09030151367188,1.0697938203811646,251.89706420898438,256.4969787597656
+1,1.0219366550445557,213.76296997070312,218.15724182128906,1.0482327938079834,247.68568420410156,252.19302368164062
+2,0.9537290930747986,211.638916015625,215.73992919921875,1.208980679512024,246.39285278320312,251.5914764404297
+3,0.8987663984298706,210.9284210205078,214.79270935058594,0.8369583487510681,245.48329162597656,249.08226013183594
+4,0.8555904030799866,209.9145965576172,213.59329223632812,0.8304556012153625,244.68260192871094,248.25347900390625
+5,0.8210099339485168,209.12509155273438,212.6555633544922,0.8108441233634949,244.8659210205078,248.3525390625
+6,0.7869173884391785,208.1915283203125,211.5751190185547,0.783132791519165,244.31178283691406,247.67935180664062
+7,0.7550934553146362,207.49488830566406,210.74200439453125,1.2138056755065918,244.14010620117188,249.35952758789062
+8,0.737208366394043,206.3842010498047,209.55465698242188,0.7379584312438965,245.1006317138672,248.2740478515625
+9,0.709071934223175,205.74339294433594,208.79225158691406,0.8271404504776001,245.91769409179688,249.47467041015625
+10,0.6879807114601135,204.485107421875,207.44366455078125,0.815724790096283,246.7330780029297,250.24082946777344
+11,0.6690319776535034,204.0198974609375,206.89706420898438,0.781477689743042,246.77011108398438,250.13027954101562

fold_1/model.bias_scaled.fold_1.ENCSR174JMM.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:47b74c24859929d68f56c8b932da8646eb66feaea01e9ff877182da9338fa804
+size 2691928

fold_1/model.bias_scaled.fold_1.ENCSR174JMM.tar

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e2662cddda3c6fa6384cfb1fd69629cebb1cb6a980d64028605e46e14cea435a
+size 1198080

fold_1/model.chrombpnet.fold_1.ENCSR174JMM.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ca2bad4eb8332e44f3bc89aef20c7894336b213aea7739076aaaf59780e4417b
+size 77538904

fold_1/model.chrombpnet.fold_1.ENCSR174JMM.tar

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:283f226f0679693e8eb6a39a85ff104487a67516862e8693fa95d3fda8c1f89f
+size 27525120

fold_1/model.chrombpnet_nobias.fold_1.ENCSR174JMM.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5fe8309ad33c4773ef1e70dd97291668f8d7b55de5dfdea707a5fb39de877bb7
+size 25582648

fold_1/model.chrombpnet_nobias.fold_1.ENCSR174JMM.tar

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:99572639f7a7f227814480209d812c1c717a3d9cea63fc2b27fcedb52773a68b
+size 26060800

fold_2/logs.models.fold_2.ENCSR174JMM/logfile.modelling.fold_2.ENCSR174JMM.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//ENCSR174JMM//preprocessing/bigWigs/ENCSR174JMM.bigWig",
+    "output_dir": "/scratch/groups/akundaje/anusri/chromatin_atlas/DNASE/ENCSR174JMM//chrombpnet_model_feb20_fold_2/chrombpnet_model/",
+    "data_type": "DNASE",
+    "peaks": "/scratch/groups/akundaje/anusri/chromatin_atlas/DNASE/ENCSR174JMM//chrombpnet_model_feb20_fold_2/chrombpnet_model/auxiliary/ENCSR174JMM_filtered.peaks.bed",
+    "nonpeaks": "/scratch/groups/akundaje/anusri/chromatin_atlas/DNASE/ENCSR174JMM//chrombpnet_model_feb20_fold_2/chrombpnet_model/auxiliary/ENCSR174JMM_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": "ENCSR174JMM",
+    "html_prefix": "./",
+    "bias_model_path": "/scratch/groups/akundaje/anusri/chromatin_atlas/DNASE/ENCSR174JMM//chrombpnet_model_feb20_fold_0/bias_model/models/ENCSR174JMM_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/ENCSR174JMM//chrombpnet_model_feb20_fold_2/chrombpnet_model/models/ENCSR174JMM_chrombpnet",
+    "chr": "chr22",
+    "pwm_width": 24,
+    "params": "/scratch/groups/akundaje/anusri/chromatin_atlas/DNASE/ENCSR174JMM//chrombpnet_model_feb20_fold_2/chrombpnet_model/logs/ENCSR174JMM_chrombpnet_model_params.tsv"
+}

fold_2/logs.models.fold_2.ENCSR174JMM/logfile.modelling.fold_2.ENCSR174JMM.bias_formatting.stdout.txt

@@ -0,0 +1 @@
+Converting /oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/DNASE/ENCSR174JMM/failed_models_retrained/chrombpnet_model_feb20_fold_2/chrombpnet_model/models/ENCSR174JMM_bias_model_scaled.h5 to /oak/stanford/groups/akundaje/vhecht/chromatin-atlas-2022/DNASE/ENCSR174JMM/fold_2/new_model_format/bias_model_scaled.tar with get_new_tf_model_format.py

fold_2/logs.models.fold_2.ENCSR174JMM/logfile.modelling.fold_2.ENCSR174JMM.chrombpnet_data_params.tsv

@@ -0,0 +1,3 @@
+counts_sum_min_thresh	0.0
+counts_sum_max_thresh	1026.0
+trainings_pts_post_thresh	174177

fold_2/logs.models.fold_2.ENCSR174JMM/logfile.modelling.fold_2.ENCSR174JMM.chrombpnet_formatting.stdout.txt

@@ -0,0 +1 @@
+Converting /oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/DNASE/ENCSR174JMM/failed_models_retrained/chrombpnet_model_feb20_fold_2/chrombpnet_model/models/ENCSR174JMM_chrombpnet.h5 to /oak/stanford/groups/akundaje/vhecht/chromatin-atlas-2022/DNASE/ENCSR174JMM/fold_2/new_model_format/chrombpnet.tar with get_new_tf_model_format.py

fold_2/logs.models.fold_2.ENCSR174JMM/logfile.modelling.fold_2.ENCSR174JMM.chrombpnet_model_params.tsv

@@ -0,0 +1,9 @@
+counts_loss_weight	4.2
+filters	512
+n_dil_layers	8
+bias_model_path	/scratch/groups/akundaje/anusri/chromatin_atlas/DNASE/ENCSR174JMM//chrombpnet_model_feb20_fold_2/chrombpnet_model/models/ENCSR174JMM_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.ENCSR174JMM/logfile.modelling.fold_2.ENCSR174JMM.chrombpnet_no_bias_formatting.stdout.txt

@@ -0,0 +1 @@
+Converting /oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/DNASE/ENCSR174JMM/failed_models_retrained/chrombpnet_model_feb20_fold_2/chrombpnet_model/models/ENCSR174JMM_chrombpnet_nobias.h5 to /oak/stanford/groups/akundaje/vhecht/chromatin-atlas-2022/DNASE/ENCSR174JMM/fold_2/new_model_format/chrombpnet_nobias.tar with get_new_tf_model_format.py

fold_2/logs.models.fold_2.ENCSR174JMM/logfile.modelling.fold_2.ENCSR174JMM.epoch_loss.csv

@@ -0,0 +1,14 @@
+epoch,logcount_predictions_loss,logits_profile_predictions_loss,loss,val_logcount_predictions_loss,val_logits_profile_predictions_loss,val_loss
+0,3.2939577102661133,219.87925720214844,233.71353149414062,1.0121169090270996,228.99185180664062,233.24276733398438
+1,0.9990509748458862,213.72210693359375,217.9176483154297,1.0597175359725952,227.46141052246094,231.9122314453125
+2,0.9287854433059692,212.54116821289062,216.44166564941406,0.8688495755195618,226.93190002441406,230.58103942871094
+3,0.8784216046333313,211.18505859375,214.87440490722656,1.0381478071212769,226.1006317138672,230.46066284179688
+4,0.8306057453155518,210.3565673828125,213.84494018554688,0.8293235898017883,224.87339782714844,228.35647583007812
+5,0.794233500957489,209.46568298339844,212.8014678955078,0.8237383365631104,224.5413360595703,228.00096130371094
+6,0.7668898105621338,208.3589324951172,211.5798797607422,0.7848847508430481,226.085205078125,229.3817901611328
+7,0.7340294122695923,207.5372314453125,210.62022399902344,0.7692262530326843,224.27032470703125,227.50108337402344
+8,0.7184649109840393,206.78115844726562,209.79859924316406,0.7820616364479065,225.90748596191406,229.1922149658203
+9,0.6990591883659363,206.08558654785156,209.021240234375,0.8958181738853455,226.49075317382812,230.25302124023438
+10,0.67610102891922,205.35292053222656,208.19264221191406,0.8026173710823059,226.42141723632812,229.7923583984375
+11,0.6589606404304504,204.6306915283203,207.3982696533203,0.9952027797698975,226.95213317871094,231.13204956054688
+12,0.6359161138534546,203.55287170410156,206.22369384765625,0.7531552314758301,226.93927001953125,230.10244750976562

fold_2/model.bias_scaled.fold_2.ENCSR174JMM.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d3b8b7a6227376e3c44c8e428cf61d6d23f34ea27174a8ebd9d985fe64099107
+size 2691928

fold_2/model.bias_scaled.fold_2.ENCSR174JMM.tar

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c93b9f4b3999bf38cc036e4272d3da1b27cf92a076030127663f23c1062bb0fe
+size 1198080

fold_2/model.chrombpnet.fold_2.ENCSR174JMM.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:002fbbfb40778d8bd31801811f6741216646e1a4dde028590bb4e65677a636c4
+size 77538904

fold_2/model.chrombpnet.fold_2.ENCSR174JMM.tar

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5cddaab258c6d90809376001b0482938696c0c6907ac6bf461ec8e1cfbb4daf9
+size 27525120

fold_2/model.chrombpnet_nobias.fold_2.ENCSR174JMM.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e67f0fdaeb16418a939ef16b2d4922b6acab4f9ac41cd2ef082defacadcb5a7c
+size 25582648

fold_2/model.chrombpnet_nobias.fold_2.ENCSR174JMM.tar

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f234b049c63b9305e5caa257fce4f38238e0cfd57f8c19ba627b78e9567de5ca
+size 26060800

fold_3/logs.models.fold_3.ENCSR174JMM/logfile.modelling.fold_3.ENCSR174JMM.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//ENCSR174JMM//preprocessing/bigWigs/ENCSR174JMM.bigWig",
+    "output_dir": "/scratch/groups/akundaje/anusri/chromatin_atlas/DNASE/ENCSR174JMM//chrombpnet_model_feb20_fold_3/chrombpnet_model/",
+    "data_type": "DNASE",
+    "peaks": "/scratch/groups/akundaje/anusri/chromatin_atlas/DNASE/ENCSR174JMM//chrombpnet_model_feb20_fold_3/chrombpnet_model/auxiliary/ENCSR174JMM_filtered.peaks.bed",
+    "nonpeaks": "/scratch/groups/akundaje/anusri/chromatin_atlas/DNASE/ENCSR174JMM//chrombpnet_model_feb20_fold_3/chrombpnet_model/auxiliary/ENCSR174JMM_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": "ENCSR174JMM",
+    "html_prefix": "./",
+    "bias_model_path": "/scratch/groups/akundaje/anusri/chromatin_atlas/DNASE/ENCSR174JMM//chrombpnet_model_feb20_fold_0/bias_model/models/ENCSR174JMM_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/ENCSR174JMM//chrombpnet_model_feb20_fold_3/chrombpnet_model/models/ENCSR174JMM_chrombpnet",
+    "chr": "chr6",
+    "pwm_width": 24,
+    "params": "/scratch/groups/akundaje/anusri/chromatin_atlas/DNASE/ENCSR174JMM//chrombpnet_model_feb20_fold_3/chrombpnet_model/logs/ENCSR174JMM_chrombpnet_model_params.tsv"
+}

fold_3/logs.models.fold_3.ENCSR174JMM/logfile.modelling.fold_3.ENCSR174JMM.bias_formatting.stdout.txt

@@ -0,0 +1 @@
+Converting /oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/DNASE/ENCSR174JMM/failed_models_retrained/chrombpnet_model_feb20_fold_3/chrombpnet_model/models/ENCSR174JMM_bias_model_scaled.h5 to /oak/stanford/groups/akundaje/vhecht/chromatin-atlas-2022/DNASE/ENCSR174JMM/fold_3/new_model_format/bias_model_scaled.tar with get_new_tf_model_format.py

fold_3/logs.models.fold_3.ENCSR174JMM/logfile.modelling.fold_3.ENCSR174JMM.chrombpnet_data_params.tsv

@@ -0,0 +1,3 @@
+counts_sum_min_thresh	0.0
+counts_sum_max_thresh	1034.0
+trainings_pts_post_thresh	170649

fold_3/logs.models.fold_3.ENCSR174JMM/logfile.modelling.fold_3.ENCSR174JMM.chrombpnet_formatting.stdout.txt

@@ -0,0 +1 @@
+Converting /oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/DNASE/ENCSR174JMM/failed_models_retrained/chrombpnet_model_feb20_fold_3/chrombpnet_model/models/ENCSR174JMM_chrombpnet.h5 to /oak/stanford/groups/akundaje/vhecht/chromatin-atlas-2022/DNASE/ENCSR174JMM/fold_3/new_model_format/chrombpnet.tar with get_new_tf_model_format.py

fold_3/logs.models.fold_3.ENCSR174JMM/logfile.modelling.fold_3.ENCSR174JMM.chrombpnet_model_params.tsv

@@ -0,0 +1,9 @@
+counts_loss_weight	4.3
+filters	512
+n_dil_layers	8
+bias_model_path	/scratch/groups/akundaje/anusri/chromatin_atlas/DNASE/ENCSR174JMM//chrombpnet_model_feb20_fold_3/chrombpnet_model/models/ENCSR174JMM_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.ENCSR174JMM/logfile.modelling.fold_3.ENCSR174JMM.chrombpnet_no_bias_formatting.stdout.txt

@@ -0,0 +1 @@
+Converting /oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/DNASE/ENCSR174JMM/failed_models_retrained/chrombpnet_model_feb20_fold_3/chrombpnet_model/models/ENCSR174JMM_chrombpnet_nobias.h5 to /oak/stanford/groups/akundaje/vhecht/chromatin-atlas-2022/DNASE/ENCSR174JMM/fold_3/new_model_format/chrombpnet_nobias.tar with get_new_tf_model_format.py