Upload folder using huggingface_hub

README.md

@@ -0,0 +1,120 @@
+---
+license: mit
+library_name: chrombpnet
+tags:
+  - encode
+  - chrombpnet
+  - chromatin-accessibility
+  - ATAC
+  - 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: ATAC in heart left ventricle (ENCSR899YEP)
+- Model: ChromBPNet
+- Assay: ATAC-seq
+- Experiment: [ENCSR899YEP](https://www.encodeproject.org/experiments/ENCSR899YEP/)
+- Model annotation: [ENCSR012HQM](https://www.encodeproject.org/annotations/ENCSR012HQM/)
+- Biosample: heart left ventricle (Full name: Homo sapiens heart left ventricle tissue male adult (61 years))
+- 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.ENCSR899YEP/logfile.modelling.fold_0.ENCSR899YEP.args.json

@@ -0,0 +1,50 @@
+{
+    "cmd": "pipeline",
+    "genome": "/oak/stanford/groups/akundaje/ziwei75/atac_seq_pipeline/hg38/GRCh38_no_alt_analysis_set_GCA_000001405.15.fasta",
+    "chrom_sizes": "/oak/stanford/groups/akundaje/ziwei75/atac_seq_pipeline/hg38/GRCh38_EBV.chrom.sizes.tsv",
+    "input_bam_file": "/scratch/users/vhecht/chromatin-atlas-2022/ATAC/ENCSR899YEP/preprocessing/bigWigs/ENCSR899YEP.bigWig",
+    "input_fragment_file": null,
+    "input_tagalign_file": null,
+    "output_dir": "/scratch/users/vhecht/chromatin-atlas-2022/ATAC/ENCSR899YEP/fold_0/model_outputs",
+    "data_type": "ATAC",
+    "peaks": "/scratch/users/vhecht/chromatin-atlas-2022/ATAC/ENCSR899YEP/fold_0/model_outputs/auxiliary/filtered.peaks.bed",
+    "nonpeaks": "/scratch/users/vhecht/chromatin-atlas-2022/ATAC/ENCSR899YEP/fold_0/model_outputs/auxiliary/filtered.nonpeaks.bed",
+    "chr_fold_path": "/oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/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/users/vhecht/chrombpnet/chrombpnet/chrombpnet/training/models/chrombpnet_with_bias_model.py",
+    "file_prefix": null,
+    "html_prefix": "./",
+    "bsort": false,
+    "tmpdir": null,
+    "no_st": false,
+    "bias_model_path": "/scratch/users/vhecht/chromatin-atlas-2022/reference/ATAC/fold_0/model.bias.fold_0.ENCSR868FGK.h5",
+    "negative_sampling_ratio": 0.1,
+    "filters": 512,
+    "n_dilation_layers": 8,
+    "max_jitter": 500,
+    "batch_size": 64,
+    "output_prefix": "/scratch/users/vhecht/chromatin-atlas-2022/ATAC/ENCSR899YEP/fold_0/model_outputs/models/chrombpnet",
+    "bigwig": "/scratch/users/vhecht/chromatin-atlas-2022/ATAC/ENCSR899YEP/fold_0/model_outputs/auxiliary/data_unstranded.bw",
+    "plus_shift": null,
+    "minus_shift": null,
+    "chr": "chr8",
+    "pwm_width": 24,
+    "params": "/scratch/users/vhecht/chromatin-atlas-2022/ATAC/ENCSR899YEP/fold_0/model_outputs/logs/chrombpnet_model_params.tsv"
+}

fold_0/logs.models.fold_0.ENCSR899YEP/logfile.modelling.fold_0.ENCSR899YEP.bias_formatting.stdout.txt

@@ -0,0 +1 @@
+Converting /oak/stanford/groups/akundaje/vhecht/chromatin-atlas-2022/ATAC/ENCSR899YEP/fold_0/model_outputs/models/bias_model_scaled.h5 to /oak/stanford/groups/akundaje/vhecht/chromatin-atlas-2022/ATAC/ENCSR899YEP/fold_0/new_model_format/bias_model_scaled.tar with get_new_tf_model_format.py

fold_0/logs.models.fold_0.ENCSR899YEP/logfile.modelling.fold_0.ENCSR899YEP.chrombpnet_data_params.tsv

@@ -0,0 +1,3 @@
+counts_sum_min_thresh	0.0
+counts_sum_max_thresh	2068.0
+trainings_pts_post_thresh	106759

fold_0/logs.models.fold_0.ENCSR899YEP/logfile.modelling.fold_0.ENCSR899YEP.chrombpnet_formatting.stdout.txt

@@ -0,0 +1 @@
+Converting /oak/stanford/groups/akundaje/vhecht/chromatin-atlas-2022/ATAC/ENCSR899YEP/fold_0/model_outputs/models/chrombpnet.h5 to /oak/stanford/groups/akundaje/vhecht/chromatin-atlas-2022/ATAC/ENCSR899YEP/fold_0/new_model_format/chrombpnet.tar with get_new_tf_model_format.py

fold_0/logs.models.fold_0.ENCSR899YEP/logfile.modelling.fold_0.ENCSR899YEP.chrombpnet_model_params.tsv

@@ -0,0 +1,9 @@
+counts_loss_weight	9.5
+filters	512
+n_dil_layers	8
+bias_model_path	/scratch/users/vhecht/chromatin-atlas-2022/ATAC/ENCSR899YEP/fold_0/model_outputs/models/bias_model_scaled.h5
+inputlen	2114
+outputlen	1000
+max_jitter	500
+chr_fold_path	/oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/splits/fold_0.json
+negative_sampling_ratio	0.1

fold_0/logs.models.fold_0.ENCSR899YEP/logfile.modelling.fold_0.ENCSR899YEP.chrombpnet_no_bias_formatting.stdout.txt

@@ -0,0 +1 @@
+Converting /oak/stanford/groups/akundaje/vhecht/chromatin-atlas-2022/ATAC/ENCSR899YEP/fold_0/model_outputs/models/chrombpnet_nobias.h5 to /oak/stanford/groups/akundaje/vhecht/chromatin-atlas-2022/ATAC/ENCSR899YEP/fold_0/new_model_format/chrombpnet_nobias.tar with get_new_tf_model_format.py

fold_0/logs.models.fold_0.ENCSR899YEP/logfile.modelling.fold_0.ENCSR899YEP.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
+0,2.0021190643310547,258.0376892089844,277.0578918457031,0.7169472575187683,253.4816436767578,260.2926025390625
+1,0.6505547165870667,249.5293731689453,255.70982360839844,0.6923624873161316,248.72140502929688,255.29884338378906
+2,0.6026322841644287,245.4470672607422,251.17193603515625,0.588131308555603,246.51953125,252.1067657470703
+3,0.5678892731666565,243.7018280029297,249.09683227539062,0.5820415616035461,245.5370635986328,251.06637573242188
+4,0.5530826449394226,242.35789489746094,247.61209106445312,0.5534594058990479,245.19876098632812,250.4567108154297
+5,0.5265135169029236,240.66357421875,245.66537475585938,0.5029644966125488,244.90188598632812,249.6800079345703
+6,0.5073981881141663,239.53131103515625,244.3517608642578,0.48743730783462524,244.35635375976562,248.98687744140625
+7,0.48263660073280334,238.63890075683594,243.22415161132812,0.49665144085884094,244.7334442138672,249.45156860351562
+8,0.46985769271850586,237.2386474609375,241.7020263671875,0.46367141604423523,244.60858154296875,249.01348876953125
+9,0.450512558221817,236.3290557861328,240.6087646484375,0.47512272000312805,245.15841674804688,249.6721649169922
+10,0.4326127767562866,235.0797882080078,239.18954467773438,0.5456013679504395,244.93946838378906,250.1226043701172
+11,0.4166698455810547,234.4572296142578,238.41543579101562,0.5107725262641907,245.2526397705078,250.10513305664062

fold_0/model.bias_scaled.fold_0.ENCSR899YEP.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0336c0216dffd1274d3b74849938354eaa9f171a383aef324a572247d4b10d0b
+size 2691928

fold_0/model.bias_scaled.fold_0.ENCSR899YEP.tar

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eabb27a6f089ebafa8ebe2d9c0da3f35115a319c9c9b212edceade1b60a82135
+size 1198080

fold_0/model.chrombpnet.fold_0.ENCSR899YEP.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:806ba40d0d4cfd66bfc8656977e46cf50b760ce3838eee406e1b81f7b9466389
+size 77538896

fold_0/model.chrombpnet.fold_0.ENCSR899YEP.tar

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aa0638650869f364114b829fb6f992ed228a904e8853c2fef7572b746ae603c2
+size 27535360

fold_0/model.chrombpnet_nobias.fold_0.ENCSR899YEP.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bbb5cecc2a44587e475a33b0130f622e6edd153434de0ec5f8008ea2b1390bcf
+size 25582648

fold_0/model.chrombpnet_nobias.fold_0.ENCSR899YEP.tar

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aeac7175ecb31926b6d6dd7a362980c9af0ec47532b2a8a28e1600c0b8b3e5c8
+size 26060800

fold_1/logs.models.fold_1.ENCSR899YEP/logfile.modelling.fold_1.ENCSR899YEP.args.json

@@ -0,0 +1,50 @@
+{
+    "cmd": "pipeline",
+    "genome": "/oak/stanford/groups/akundaje/ziwei75/atac_seq_pipeline/hg38/GRCh38_no_alt_analysis_set_GCA_000001405.15.fasta",
+    "chrom_sizes": "/oak/stanford/groups/akundaje/ziwei75/atac_seq_pipeline/hg38/GRCh38_EBV.chrom.sizes.tsv",
+    "input_bam_file": "/scratch/users/vhecht/chromatin-atlas-2022/ATAC/ENCSR899YEP/preprocessing/bigWigs/ENCSR899YEP.bigWig",
+    "input_fragment_file": null,
+    "input_tagalign_file": null,
+    "output_dir": "/scratch/users/vhecht/chromatin-atlas-2022/ATAC/ENCSR899YEP/fold_1/model_outputs",
+    "data_type": "ATAC",
+    "peaks": "/scratch/users/vhecht/chromatin-atlas-2022/ATAC/ENCSR899YEP/fold_1/model_outputs/auxiliary/filtered.peaks.bed",
+    "nonpeaks": "/scratch/users/vhecht/chromatin-atlas-2022/ATAC/ENCSR899YEP/fold_1/model_outputs/auxiliary/filtered.nonpeaks.bed",
+    "chr_fold_path": "/oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/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/users/vhecht/chrombpnet/chrombpnet/chrombpnet/training/models/chrombpnet_with_bias_model.py",
+    "file_prefix": null,
+    "html_prefix": "./",
+    "bsort": false,
+    "tmpdir": null,
+    "no_st": false,
+    "bias_model_path": "/scratch/users/vhecht/chromatin-atlas-2022/reference/ATAC/fold_0/model.bias.fold_0.ENCSR868FGK.h5",
+    "negative_sampling_ratio": 0.1,
+    "filters": 512,
+    "n_dilation_layers": 8,
+    "max_jitter": 500,
+    "batch_size": 64,
+    "output_prefix": "/scratch/users/vhecht/chromatin-atlas-2022/ATAC/ENCSR899YEP/fold_1/model_outputs/models/chrombpnet",
+    "bigwig": "/scratch/users/vhecht/chromatin-atlas-2022/ATAC/ENCSR899YEP/fold_1/model_outputs/auxiliary/data_unstranded.bw",
+    "plus_shift": null,
+    "minus_shift": null,
+    "chr": "chr12",
+    "pwm_width": 24,
+    "params": "/scratch/users/vhecht/chromatin-atlas-2022/ATAC/ENCSR899YEP/fold_1/model_outputs/logs/chrombpnet_model_params.tsv"
+}

fold_1/logs.models.fold_1.ENCSR899YEP/logfile.modelling.fold_1.ENCSR899YEP.bias_formatting.stdout.txt

@@ -0,0 +1 @@
+Converting /oak/stanford/groups/akundaje/vhecht/chromatin-atlas-2022/ATAC/ENCSR899YEP/fold_1/model_outputs/models/bias_model_scaled.h5 to /oak/stanford/groups/akundaje/vhecht/chromatin-atlas-2022/ATAC/ENCSR899YEP/fold_1/new_model_format/bias_model_scaled.tar with get_new_tf_model_format.py

fold_1/logs.models.fold_1.ENCSR899YEP/logfile.modelling.fold_1.ENCSR899YEP.chrombpnet_data_params.tsv

@@ -0,0 +1,3 @@
+counts_sum_min_thresh	0.0
+counts_sum_max_thresh	2004.94
+trainings_pts_post_thresh	109923

fold_1/logs.models.fold_1.ENCSR899YEP/logfile.modelling.fold_1.ENCSR899YEP.chrombpnet_formatting.stdout.txt

@@ -0,0 +1 @@
+Converting /oak/stanford/groups/akundaje/vhecht/chromatin-atlas-2022/ATAC/ENCSR899YEP/fold_1/model_outputs/models/chrombpnet.h5 to /oak/stanford/groups/akundaje/vhecht/chromatin-atlas-2022/ATAC/ENCSR899YEP/fold_1/new_model_format/chrombpnet.tar with get_new_tf_model_format.py

fold_1/logs.models.fold_1.ENCSR899YEP/logfile.modelling.fold_1.ENCSR899YEP.chrombpnet_model_params.tsv

@@ -0,0 +1,9 @@
+counts_loss_weight	9.5
+filters	512
+n_dil_layers	8
+bias_model_path	/scratch/users/vhecht/chromatin-atlas-2022/ATAC/ENCSR899YEP/fold_1/model_outputs/models/bias_model_scaled.h5
+inputlen	2114
+outputlen	1000
+max_jitter	500
+chr_fold_path	/oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/splits/fold_1.json
+negative_sampling_ratio	0.1

fold_1/logs.models.fold_1.ENCSR899YEP/logfile.modelling.fold_1.ENCSR899YEP.chrombpnet_no_bias_formatting.stdout.txt

@@ -0,0 +1 @@
+Converting /oak/stanford/groups/akundaje/vhecht/chromatin-atlas-2022/ATAC/ENCSR899YEP/fold_1/model_outputs/models/chrombpnet_nobias.h5 to /oak/stanford/groups/akundaje/vhecht/chromatin-atlas-2022/ATAC/ENCSR899YEP/fold_1/new_model_format/chrombpnet_nobias.tar with get_new_tf_model_format.py

fold_1/logs.models.fold_1.ENCSR899YEP/logfile.modelling.fold_1.ENCSR899YEP.epoch_loss.csv

@@ -0,0 +1,15 @@
+epoch,logcount_predictions_loss,logits_profile_predictions_loss,loss,val_logcount_predictions_loss,val_logits_profile_predictions_loss,val_loss
+0,4.041744232177734,256.1143493652344,294.5113525390625,0.8140014410018921,285.880615234375,293.61358642578125
+1,0.6754552721977234,248.78028869628906,255.1970977783203,0.6206655502319336,279.36480712890625,285.2611389160156
+2,0.6256240010261536,244.1838836669922,250.1275177001953,0.5698261260986328,276.7046203613281,282.1180725097656
+3,0.5921037793159485,242.0550079345703,247.68032836914062,0.5283814668655396,275.8813781738281,280.9011535644531
+4,0.563994824886322,240.47434997558594,245.83206176757812,0.6867856383323669,274.13671875,280.66131591796875
+5,0.5379528403282166,239.51222229003906,244.62261962890625,0.5309303402900696,274.1097717285156,279.15362548828125
+6,0.5234211087226868,238.40121459960938,243.37368774414062,0.5086278915405273,273.42950439453125,278.261474609375
+7,0.5083741545677185,237.4552459716797,242.2848358154297,0.47515809535980225,272.83843994140625,277.3524475097656
+8,0.4834263026714325,236.422607421875,241.0153045654297,0.4650522470474243,272.8792419433594,277.29718017578125
+9,0.4715595841407776,235.21456909179688,239.6942138671875,0.4770828187465668,273.06500244140625,277.5973205566406
+10,0.45167362689971924,234.1383514404297,238.42929077148438,0.45819172263145447,273.36920166015625,277.72198486328125
+11,0.4347181022167206,233.15863037109375,237.28851318359375,0.4646589159965515,273.3661193847656,277.7803649902344
+12,0.41833576560020447,232.37103271484375,236.34524536132812,0.4550204873085022,273.9077453613281,278.2305603027344
+13,0.40368473529815674,231.74998474121094,235.58506774902344,0.48180264234542847,274.0463562011719,278.6233825683594

fold_1/model.bias_scaled.fold_1.ENCSR899YEP.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:21e9f618ec3cacb18933d3cf59ffdc3932263d70ecf4890e3b79133368c3ec8e
+size 2691928

fold_1/model.bias_scaled.fold_1.ENCSR899YEP.tar

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:44595983c2543834a5e70d48eacaa1b8ee971e445e8f7a8730f16354cb46baa8
+size 1198080

fold_1/model.chrombpnet.fold_1.ENCSR899YEP.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:74b4937ab95ccd7cade7958bd03d5e48ac7c0601c26a77732bbe68b58665ea29
+size 77538896

fold_1/model.chrombpnet.fold_1.ENCSR899YEP.tar

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3b301791af7de6ec4263f49efd89a51c8193826ea76b43425160e0124d105e7f
+size 27535360

fold_1/model.chrombpnet_nobias.fold_1.ENCSR899YEP.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9b276d79a0f5e1f0a25689b8b34f948e06f69a861e7ca7c48b36c9f565c7fed7
+size 25582648

fold_1/model.chrombpnet_nobias.fold_1.ENCSR899YEP.tar

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ea7b0d175fe2819dc172e81eb74d8952b912c8bb6f4ad1a2aec7105ca27c33a5
+size 26060800

fold_2/logs.models.fold_2.ENCSR899YEP/logfile.modelling.fold_2.ENCSR899YEP.args.json

@@ -0,0 +1,50 @@
+{
+    "cmd": "pipeline",
+    "genome": "/oak/stanford/groups/akundaje/ziwei75/atac_seq_pipeline/hg38/GRCh38_no_alt_analysis_set_GCA_000001405.15.fasta",
+    "chrom_sizes": "/oak/stanford/groups/akundaje/ziwei75/atac_seq_pipeline/hg38/GRCh38_EBV.chrom.sizes.tsv",
+    "input_bam_file": "/scratch/users/vhecht/chromatin-atlas-2022/ATAC/ENCSR899YEP/preprocessing/bigWigs/ENCSR899YEP.bigWig",
+    "input_fragment_file": null,
+    "input_tagalign_file": null,
+    "output_dir": "/scratch/users/vhecht/chromatin-atlas-2022/ATAC/ENCSR899YEP/fold_2/model_outputs",
+    "data_type": "ATAC",
+    "peaks": "/scratch/users/vhecht/chromatin-atlas-2022/ATAC/ENCSR899YEP/fold_2/model_outputs/auxiliary/filtered.peaks.bed",
+    "nonpeaks": "/scratch/users/vhecht/chromatin-atlas-2022/ATAC/ENCSR899YEP/fold_2/model_outputs/auxiliary/filtered.nonpeaks.bed",
+    "chr_fold_path": "/oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/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/users/vhecht/chrombpnet/chrombpnet/chrombpnet/training/models/chrombpnet_with_bias_model.py",
+    "file_prefix": null,
+    "html_prefix": "./",
+    "bsort": false,
+    "tmpdir": null,
+    "no_st": false,
+    "bias_model_path": "/scratch/users/vhecht/chromatin-atlas-2022/reference/ATAC/fold_0/model.bias.fold_0.ENCSR868FGK.h5",
+    "negative_sampling_ratio": 0.1,
+    "filters": 512,
+    "n_dilation_layers": 8,
+    "max_jitter": 500,
+    "batch_size": 64,
+    "output_prefix": "/scratch/users/vhecht/chromatin-atlas-2022/ATAC/ENCSR899YEP/fold_2/model_outputs/models/chrombpnet",
+    "bigwig": "/scratch/users/vhecht/chromatin-atlas-2022/ATAC/ENCSR899YEP/fold_2/model_outputs/auxiliary/data_unstranded.bw",
+    "plus_shift": null,
+    "minus_shift": null,
+    "chr": "chr22",
+    "pwm_width": 24,
+    "params": "/scratch/users/vhecht/chromatin-atlas-2022/ATAC/ENCSR899YEP/fold_2/model_outputs/logs/chrombpnet_model_params.tsv"
+}

fold_2/logs.models.fold_2.ENCSR899YEP/logfile.modelling.fold_2.ENCSR899YEP.bias_formatting.stdout.txt

@@ -0,0 +1 @@
+Converting /oak/stanford/groups/akundaje/vhecht/chromatin-atlas-2022/ATAC/ENCSR899YEP/fold_2/model_outputs/models/bias_model_scaled.h5 to /oak/stanford/groups/akundaje/vhecht/chromatin-atlas-2022/ATAC/ENCSR899YEP/fold_2/new_model_format/bias_model_scaled.tar with get_new_tf_model_format.py

fold_2/logs.models.fold_2.ENCSR899YEP/logfile.modelling.fold_2.ENCSR899YEP.chrombpnet_data_params.tsv

@@ -0,0 +1,3 @@
+counts_sum_min_thresh	0.0
+counts_sum_max_thresh	2055.05
+trainings_pts_post_thresh	112695

fold_2/logs.models.fold_2.ENCSR899YEP/logfile.modelling.fold_2.ENCSR899YEP.chrombpnet_formatting.stdout.txt

@@ -0,0 +1 @@
+Converting /oak/stanford/groups/akundaje/vhecht/chromatin-atlas-2022/ATAC/ENCSR899YEP/fold_2/model_outputs/models/chrombpnet.h5 to /oak/stanford/groups/akundaje/vhecht/chromatin-atlas-2022/ATAC/ENCSR899YEP/fold_2/new_model_format/chrombpnet.tar with get_new_tf_model_format.py

fold_2/logs.models.fold_2.ENCSR899YEP/logfile.modelling.fold_2.ENCSR899YEP.chrombpnet_model_params.tsv

@@ -0,0 +1,9 @@
+counts_loss_weight	9.5
+filters	512
+n_dil_layers	8
+bias_model_path	/scratch/users/vhecht/chromatin-atlas-2022/ATAC/ENCSR899YEP/fold_2/model_outputs/models/bias_model_scaled.h5
+inputlen	2114
+outputlen	1000
+max_jitter	500
+chr_fold_path	/oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/splits/fold_2.json
+negative_sampling_ratio	0.1

fold_2/logs.models.fold_2.ENCSR899YEP/logfile.modelling.fold_2.ENCSR899YEP.chrombpnet_no_bias_formatting.stdout.txt

@@ -0,0 +1 @@
+Converting /oak/stanford/groups/akundaje/vhecht/chromatin-atlas-2022/ATAC/ENCSR899YEP/fold_2/model_outputs/models/chrombpnet_nobias.h5 to /oak/stanford/groups/akundaje/vhecht/chromatin-atlas-2022/ATAC/ENCSR899YEP/fold_2/new_model_format/chrombpnet_nobias.tar with get_new_tf_model_format.py

fold_2/logs.models.fold_2.ENCSR899YEP/logfile.modelling.fold_2.ENCSR899YEP.epoch_loss.csv

@@ -0,0 +1,16 @@
+epoch,logcount_predictions_loss,logits_profile_predictions_loss,loss,val_logcount_predictions_loss,val_logits_profile_predictions_loss,val_loss
+0,11.027467727661133,258.5550842285156,363.3155822753906,0.7704501152038574,266.51336669921875,273.83258056640625
+1,0.6904276013374329,253.36436462402344,259.9234924316406,0.6096286773681641,262.62432861328125,268.4158020019531
+2,0.6367142796516418,248.0735626220703,254.12213134765625,0.5690073370933533,257.8022155761719,263.207763671875
+3,0.5998712182044983,245.20480346679688,250.90377807617188,0.561165452003479,255.8964385986328,261.2276306152344
+4,0.5723211765289307,242.98468017578125,248.4215087890625,0.557995617389679,254.925537109375,260.22650146484375
+5,0.555833637714386,242.1770477294922,247.4572296142578,0.5192469954490662,255.1828155517578,260.11566162109375
+6,0.5282469987869263,241.04953002929688,246.0677490234375,0.5011784434318542,253.9118194580078,258.6730041503906
+7,0.5161895751953125,240.19070434570312,245.09420776367188,0.4947833716869354,253.8499755859375,258.55029296875
+8,0.48972246050834656,239.0466766357422,243.69883728027344,0.4887935519218445,253.4617156982422,258.1053466796875
+9,0.4795531928539276,237.78700256347656,242.3428955078125,0.4807133376598358,253.26834106445312,257.83514404296875
+10,0.4591781795024872,237.0266876220703,241.38900756835938,0.4723987877368927,253.44435119628906,257.9322509765625
+11,0.4492177367210388,236.0106201171875,240.27828979492188,0.4748114347457886,253.3712921142578,257.8819885253906
+12,0.4293331205844879,235.214599609375,239.29306030273438,0.47300806641578674,253.4503173828125,257.9439392089844
+13,0.4238801598548889,234.50035095214844,238.527099609375,0.46653127670288086,253.94691467285156,258.3788146972656
+14,0.4040709435939789,233.6136474609375,237.4523162841797,0.491685688495636,254.20640563964844,258.87744140625

fold_2/model.bias_scaled.fold_2.ENCSR899YEP.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:75df2e78d2f42f56301871c461a4d6d0ffcf842c88a1e03989197fce75f408df
+size 2691928

fold_2/model.bias_scaled.fold_2.ENCSR899YEP.tar

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e73c0b521169a7e7bf7e6931405f761621eca483d5bda0ceda1dbf7f5de81ebc
+size 1198080

fold_2/model.chrombpnet.fold_2.ENCSR899YEP.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b5bb5aeafab0323b9d64077130adf163cc99d9ce16a00b0eabc7a792301b6382
+size 77538896

fold_2/model.chrombpnet.fold_2.ENCSR899YEP.tar

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5ee34176af8c7b98a0b024d1326ed46c2e181b8b8fb23208b640e292cb567c7b
+size 27535360

fold_2/model.chrombpnet_nobias.fold_2.ENCSR899YEP.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:489879895601f341767acc925ad7609cbdeb065be6e7b9671d9c0241a45d3d85
+size 25582648

fold_2/model.chrombpnet_nobias.fold_2.ENCSR899YEP.tar

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5f07bcd8f202995ea8d27f0324e1ad0842d21889c4f57462072465439d796080
+size 26060800

fold_3/logs.models.fold_3.ENCSR899YEP/logfile.modelling.fold_3.ENCSR899YEP.args.json

@@ -0,0 +1,50 @@
+{
+    "cmd": "pipeline",
+    "genome": "/oak/stanford/groups/akundaje/ziwei75/atac_seq_pipeline/hg38/GRCh38_no_alt_analysis_set_GCA_000001405.15.fasta",
+    "chrom_sizes": "/oak/stanford/groups/akundaje/ziwei75/atac_seq_pipeline/hg38/GRCh38_EBV.chrom.sizes.tsv",
+    "input_bam_file": "/scratch/users/vhecht/chromatin-atlas-2022/ATAC/ENCSR899YEP/preprocessing/bigWigs/ENCSR899YEP.bigWig",
+    "input_fragment_file": null,
+    "input_tagalign_file": null,
+    "output_dir": "/scratch/users/vhecht/chromatin-atlas-2022/ATAC/ENCSR899YEP/fold_3/model_outputs",
+    "data_type": "ATAC",
+    "peaks": "/scratch/users/vhecht/chromatin-atlas-2022/ATAC/ENCSR899YEP/fold_3/model_outputs/auxiliary/filtered.peaks.bed",
+    "nonpeaks": "/scratch/users/vhecht/chromatin-atlas-2022/ATAC/ENCSR899YEP/fold_3/model_outputs/auxiliary/filtered.nonpeaks.bed",
+    "chr_fold_path": "/oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/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/users/vhecht/chrombpnet/chrombpnet/chrombpnet/training/models/chrombpnet_with_bias_model.py",
+    "file_prefix": null,
+    "html_prefix": "./",
+    "bsort": false,
+    "tmpdir": null,
+    "no_st": false,
+    "bias_model_path": "/scratch/users/vhecht/chromatin-atlas-2022/reference/ATAC/fold_0/model.bias.fold_0.ENCSR868FGK.h5",
+    "negative_sampling_ratio": 0.1,
+    "filters": 512,
+    "n_dilation_layers": 8,
+    "max_jitter": 500,
+    "batch_size": 64,
+    "output_prefix": "/scratch/users/vhecht/chromatin-atlas-2022/ATAC/ENCSR899YEP/fold_3/model_outputs/models/chrombpnet",
+    "bigwig": "/scratch/users/vhecht/chromatin-atlas-2022/ATAC/ENCSR899YEP/fold_3/model_outputs/auxiliary/data_unstranded.bw",
+    "plus_shift": null,
+    "minus_shift": null,
+    "chr": "chr6",
+    "pwm_width": 24,
+    "params": "/scratch/users/vhecht/chromatin-atlas-2022/ATAC/ENCSR899YEP/fold_3/model_outputs/logs/chrombpnet_model_params.tsv"
+}

fold_3/logs.models.fold_3.ENCSR899YEP/logfile.modelling.fold_3.ENCSR899YEP.bias_formatting.stdout.txt

@@ -0,0 +1 @@
+Converting /oak/stanford/groups/akundaje/vhecht/chromatin-atlas-2022/ATAC/ENCSR899YEP/fold_3/model_outputs/models/bias_model_scaled.h5 to /oak/stanford/groups/akundaje/vhecht/chromatin-atlas-2022/ATAC/ENCSR899YEP/fold_3/new_model_format/bias_model_scaled.tar with get_new_tf_model_format.py

fold_3/logs.models.fold_3.ENCSR899YEP/logfile.modelling.fold_3.ENCSR899YEP.chrombpnet_data_params.tsv

@@ -0,0 +1,3 @@
+counts_sum_min_thresh	0.0
+counts_sum_max_thresh	2068.04
+trainings_pts_post_thresh	109374

fold_3/logs.models.fold_3.ENCSR899YEP/logfile.modelling.fold_3.ENCSR899YEP.chrombpnet_formatting.stdout.txt

@@ -0,0 +1 @@
+Converting /oak/stanford/groups/akundaje/vhecht/chromatin-atlas-2022/ATAC/ENCSR899YEP/fold_3/model_outputs/models/chrombpnet.h5 to /oak/stanford/groups/akundaje/vhecht/chromatin-atlas-2022/ATAC/ENCSR899YEP/fold_3/new_model_format/chrombpnet.tar with get_new_tf_model_format.py

fold_3/logs.models.fold_3.ENCSR899YEP/logfile.modelling.fold_3.ENCSR899YEP.chrombpnet_model_params.tsv

@@ -0,0 +1,9 @@
+counts_loss_weight	9.5
+filters	512
+n_dil_layers	8
+bias_model_path	/scratch/users/vhecht/chromatin-atlas-2022/ATAC/ENCSR899YEP/fold_3/model_outputs/models/bias_model_scaled.h5
+inputlen	2114
+outputlen	1000
+max_jitter	500
+chr_fold_path	/oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/splits/fold_3.json
+negative_sampling_ratio	0.1

fold_3/logs.models.fold_3.ENCSR899YEP/logfile.modelling.fold_3.ENCSR899YEP.chrombpnet_no_bias_formatting.stdout.txt

@@ -0,0 +1 @@
+Converting /oak/stanford/groups/akundaje/vhecht/chromatin-atlas-2022/ATAC/ENCSR899YEP/fold_3/model_outputs/models/chrombpnet_nobias.h5 to /oak/stanford/groups/akundaje/vhecht/chromatin-atlas-2022/ATAC/ENCSR899YEP/fold_3/new_model_format/chrombpnet_nobias.tar with get_new_tf_model_format.py