Upload folder using huggingface_hub

README.md

@@ -0,0 +1,120 @@
+---
+license: mit
+library_name: chrombpnet
+tags:
+  - encode
+  - chrombpnet
+  - chromatin-accessibility
+  - DNASE
+  - renal
+  - 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 renal cortex interstitium (ENCSR254AGA)
+- Model: ChromBPNet
+- Assay: DNASE-seq
+- Experiment: [ENCSR254AGA](https://www.encodeproject.org/experiments/ENCSR254AGA/)
+- Model annotation: [ENCSR615RQE](https://www.encodeproject.org/annotations/ENCSR615RQE/)
+- Biosample: renal cortex interstitium (Full name: Homo sapiens renal cortex interstitium tissue male embryo (91 days))
+- Cell slim(s): None
+- Organ slim(s): kidney
+- Developmental slim(s): mesoderm
+- System slim(s): excretory-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.ENCSR254AGA/logfile.modelling.fold_0.ENCSR254AGA.args.json

@@ -0,0 +1,42 @@
+{
+    "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",
+    "bigwig": "/oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/DNASE/ENCSR254AGA/preprocessing/bigWigs/ENCSR254AGA.bigWig",
+    "output_dir": "/oak/stanford/groups/akundaje/ziwei75/chromatin_atlas_bias/DNase_model/bias_threshold_0.8/ENCSR254AGA/fold0/",
+    "data_type": "DNASE",
+    "peaks": "/oak/stanford/groups/akundaje/ziwei75/chromatin_atlas_bias/DNase_model/bias_threshold_0.8/ENCSR254AGA/fold0/auxiliary/filtered.peaks.bed",
+    "nonpeaks": "/oak/stanford/groups/akundaje/ziwei75/chromatin_atlas_bias/DNase_model/bias_threshold_0.8/ENCSR254AGA/fold0/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/groups/akundaje/ziwei75/anaconda3/envs/chrombpnet/lib/python3.8/site-packages/chrombpnet/training/models/chrombpnet_with_bias_model.py",
+    "file_prefix": null,
+    "html_prefix": "./",
+    "bias_model_path": "/oak/stanford/groups/akundaje/ziwei75/chromatin_atlas_bias/DNase_bias_model/bias_threshold_0.8/ENCSR254AGA/models/bias.h5",
+    "negative_sampling_ratio": 0.1,
+    "filters": 512,
+    "n_dilation_layers": 8,
+    "max_jitter": 500,
+    "batch_size": 64,
+    "output_prefix": "/oak/stanford/groups/akundaje/ziwei75/chromatin_atlas_bias/DNase_model/bias_threshold_0.8/ENCSR254AGA/fold0/models/chrombpnet",
+    "chr": "chr8",
+    "pwm_width": 24,
+    "params": "/oak/stanford/groups/akundaje/ziwei75/chromatin_atlas_bias/DNase_model/bias_threshold_0.8/ENCSR254AGA/fold0/logs/chrombpnet_model_params.tsv"
+}

fold_0/logs.models.fold_0.ENCSR254AGA/logfile.modelling.fold_0.ENCSR254AGA.bias_formatting.stdout.txt

@@ -0,0 +1 @@
+Converting /oak/stanford/groups/akundaje/ziwei75/chromatin_atlas_bias/DNase_model/bias_threshold_0.8/ENCSR254AGA/fold0/models/bias_model_scaled.h5 to /oak/stanford/groups/akundaje/vhecht/chromatin-atlas-2022/DNASE/ENCSR254AGA/fold_0/new_model_format/bias_model_scaled.tar with get_new_tf_model_format.py

fold_0/logs.models.fold_0.ENCSR254AGA/logfile.modelling.fold_0.ENCSR254AGA.chrombpnet_data_params.tsv

@@ -0,0 +1,3 @@
+counts_sum_min_thresh	0.0
+counts_sum_max_thresh	914.0
+trainings_pts_post_thresh	170822

fold_0/logs.models.fold_0.ENCSR254AGA/logfile.modelling.fold_0.ENCSR254AGA.chrombpnet_formatting.stdout.txt

@@ -0,0 +1 @@
+Converting /oak/stanford/groups/akundaje/ziwei75/chromatin_atlas_bias/DNase_model/bias_threshold_0.8/ENCSR254AGA/fold0/models/chrombpnet.h5 to /oak/stanford/groups/akundaje/vhecht/chromatin-atlas-2022/DNASE/ENCSR254AGA/fold_0/new_model_format/chrombpnet.tar with get_new_tf_model_format.py

fold_0/logs.models.fold_0.ENCSR254AGA/logfile.modelling.fold_0.ENCSR254AGA.chrombpnet_model_params.tsv

@@ -0,0 +1,9 @@
+counts_loss_weight	2.4
+filters	512
+n_dil_layers	8
+bias_model_path	/oak/stanford/groups/akundaje/ziwei75/chromatin_atlas_bias/DNase_model/bias_threshold_0.8/ENCSR254AGA/fold0/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.ENCSR254AGA/logfile.modelling.fold_0.ENCSR254AGA.chrombpnet_no_bias_formatting.stdout.txt

@@ -0,0 +1 @@
+Converting /oak/stanford/groups/akundaje/ziwei75/chromatin_atlas_bias/DNase_model/bias_threshold_0.8/ENCSR254AGA/fold0/models/chrombpnet_nobias.h5 to /oak/stanford/groups/akundaje/vhecht/chromatin-atlas-2022/DNASE/ENCSR254AGA/fold_0/new_model_format/chrombpnet_nobias.tar with get_new_tf_model_format.py

fold_0/logs.models.fold_0.ENCSR254AGA/logfile.modelling.fold_0.ENCSR254AGA.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
+0,1.902961254119873,138.38705444335938,142.95436096191406,0.5538715720176697,135.0886993408203,136.41795349121094
+1,0.5703755021095276,134.32676696777344,135.69558715820312,0.4649643003940582,133.5932159423828,134.70916748046875
+2,0.5104778409004211,132.8687744140625,134.09393310546875,0.4494793713092804,133.12672424316406,134.2055206298828
+3,0.47242823243141174,132.0067138671875,133.14036560058594,0.41981711983680725,132.0454864501953,133.0531005859375
+4,0.4488910436630249,131.50747680664062,132.58482360839844,0.3989710211753845,131.10733032226562,132.06483459472656
+5,0.43310028314590454,130.76754760742188,131.80699157714844,0.38727524876594543,131.54025268554688,132.46974182128906
+6,0.4177314043045044,130.33636474609375,131.3390350341797,0.4135650396347046,132.06593322753906,133.0584716796875
+7,0.4096055030822754,130.025634765625,131.00863647460938,0.4228832423686981,131.3567352294922,132.37171936035156
+8,0.3931267261505127,129.82278442382812,130.76629638671875,0.39444372057914734,131.45233154296875,132.3989715576172
+9,0.38768672943115234,129.3135223388672,130.2439727783203,0.36791157722473145,132.2118377685547,133.09487915039062

fold_0/model.bias_scaled.fold_0.ENCSR254AGA.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e6734f3e3edf026922071a9bde84d2cca3b15588794a21a0c1c6f3db52327152
+size 2691928

fold_0/model.bias_scaled.fold_0.ENCSR254AGA.tar

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b5aaa8ceb7f49b7e208846e44b118a600564b6c4e14b11f620163b29adee2e2d
+size 1198080

fold_0/model.chrombpnet.fold_0.ENCSR254AGA.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2a2357690a64476a60bd14a6582b4f00ee8ba4817f3d04eb6b2695a16872b113
+size 77538952

fold_0/model.chrombpnet.fold_0.ENCSR254AGA.tar

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:795f69f9564fe2ac1ca587c20cdc602e6f77c1eb0f3683a1d1005eafd6a93347
+size 27525120

fold_0/model.chrombpnet_nobias.fold_0.ENCSR254AGA.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e8cc07f6a6146fc4a5ea736a7369f5a0f0552b2967b2c8a8ed440e1b733ffc0a
+size 25582648

fold_0/model.chrombpnet_nobias.fold_0.ENCSR254AGA.tar

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b56d7699017ec21424c2396b059021ee87db02f88e1aecbd55f20eca70cd35fd
+size 26060800

fold_1/logs.models.fold_1.ENCSR254AGA/logfile.modelling.fold_1.ENCSR254AGA.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": "/oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/DNASE/ENCSR254AGA/preprocessing/bigWigs/ENCSR254AGA.bigWig",
+    "input_fragment_file": null,
+    "input_tagalign_file": null,
+    "output_dir": "/oak/stanford/groups/akundaje/vhecht/chromatin_atlas_bias_corrected/DNASE_model/ENCSR254AGA/fold_1",
+    "data_type": "DNASE",
+    "peaks": "/oak/stanford/groups/akundaje/vhecht/chromatin_atlas_bias_corrected/DNASE_model/ENCSR254AGA/fold_1/auxiliary/filtered.peaks.bed",
+    "nonpeaks": "/oak/stanford/groups/akundaje/vhecht/chromatin_atlas_bias_corrected/DNASE_model/ENCSR254AGA/fold_1/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": "/oak/stanford/groups/akundaje/ziwei75/chromatin_atlas_bias/DNase_bias_model/bias_threshold_0.8/ENCSR254AGA/models/bias.h5",
+    "negative_sampling_ratio": 0.1,
+    "filters": 512,
+    "n_dilation_layers": 8,
+    "max_jitter": 500,
+    "batch_size": 64,
+    "output_prefix": "/oak/stanford/groups/akundaje/vhecht/chromatin_atlas_bias_corrected/DNASE_model/ENCSR254AGA/fold_1/models/chrombpnet",
+    "bigwig": "/oak/stanford/groups/akundaje/vhecht/chromatin_atlas_bias_corrected/DNASE_model/ENCSR254AGA/fold_1/auxiliary/data_unstranded.bw",
+    "plus_shift": null,
+    "minus_shift": null,
+    "chr": "chr12",
+    "pwm_width": 24,
+    "params": "/oak/stanford/groups/akundaje/vhecht/chromatin_atlas_bias_corrected/DNASE_model/ENCSR254AGA/fold_1/logs/chrombpnet_model_params.tsv"
+}

fold_1/logs.models.fold_1.ENCSR254AGA/logfile.modelling.fold_1.ENCSR254AGA.bias_formatting.stdout.txt

@@ -0,0 +1 @@
+Converting /oak/stanford/groups/akundaje/vhecht/chromatin_atlas_bias_corrected/DNASE_model/ENCSR254AGA/fold_1/models/bias_model_scaled.h5 to /oak/stanford/groups/akundaje/vhecht/chromatin-atlas-2022/DNASE/ENCSR254AGA/fold_1/new_model_format/bias_model_scaled.tar with get_new_tf_model_format.py

fold_1/logs.models.fold_1.ENCSR254AGA/logfile.modelling.fold_1.ENCSR254AGA.chrombpnet_data_params.tsv

@@ -0,0 +1,3 @@
+counts_sum_min_thresh	0.0
+counts_sum_max_thresh	939.47
+trainings_pts_post_thresh	172536

fold_1/logs.models.fold_1.ENCSR254AGA/logfile.modelling.fold_1.ENCSR254AGA.chrombpnet_formatting.stdout.txt

@@ -0,0 +1 @@
+Converting /oak/stanford/groups/akundaje/vhecht/chromatin_atlas_bias_corrected/DNASE_model/ENCSR254AGA/fold_1/models/chrombpnet.h5 to /oak/stanford/groups/akundaje/vhecht/chromatin-atlas-2022/DNASE/ENCSR254AGA/fold_1/new_model_format/chrombpnet.tar with get_new_tf_model_format.py

fold_1/logs.models.fold_1.ENCSR254AGA/logfile.modelling.fold_1.ENCSR254AGA.chrombpnet_model_params.tsv

@@ -0,0 +1,9 @@
+counts_loss_weight	2.4
+filters	512
+n_dil_layers	8
+bias_model_path	/oak/stanford/groups/akundaje/vhecht/chromatin_atlas_bias_corrected/DNASE_model/ENCSR254AGA/fold_1/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.ENCSR254AGA/logfile.modelling.fold_1.ENCSR254AGA.chrombpnet_no_bias_formatting.stdout.txt

@@ -0,0 +1 @@
+Converting /oak/stanford/groups/akundaje/vhecht/chromatin_atlas_bias_corrected/DNASE_model/ENCSR254AGA/fold_1/models/chrombpnet_nobias.h5 to /oak/stanford/groups/akundaje/vhecht/chromatin-atlas-2022/DNASE/ENCSR254AGA/fold_1/new_model_format/chrombpnet_nobias.tar with get_new_tf_model_format.py

fold_1/logs.models.fold_1.ENCSR254AGA/logfile.modelling.fold_1.ENCSR254AGA.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
+0,1.6824519634246826,137.96839904785156,142.00628662109375,0.7053110003471375,155.8767852783203,157.5694580078125
+1,0.5556705594062805,133.5326385498047,134.8662567138672,0.5240889191627502,152.99200439453125,154.24989318847656
+2,0.5008152723312378,132.07754516601562,133.27914428710938,0.5887712836265564,152.75735473632812,154.17039489746094
+3,0.47066348791122437,131.239990234375,132.36956787109375,0.4652869701385498,152.20823669433594,153.32484436035156
+4,0.44413480162620544,130.67735290527344,131.7432098388672,0.44860878586769104,151.92782592773438,153.00453186035156
+5,0.42705732583999634,130.25572204589844,131.28076171875,0.7384540438652039,151.3441619873047,153.1164093017578
+6,0.41467851400375366,129.7061767578125,130.701416015625,0.43060290813446045,151.40191650390625,152.43544006347656
+7,0.4035803973674774,129.4392547607422,130.4080047607422,0.43455156683921814,152.3099365234375,153.35293579101562
+8,0.39358776807785034,129.07781982421875,130.0224151611328,0.44809070229530334,152.3264617919922,153.4019317626953
+9,0.3851829171180725,128.5650177001953,129.4894561767578,0.43557503819465637,151.65359497070312,152.6988525390625
+10,0.3805426061153412,128.35804748535156,129.27145385742188,0.41008996963500977,152.23153686523438,153.21592712402344
+11,0.3737695813179016,127.9769287109375,128.8740234375,0.40351876616477966,152.21420288085938,153.18263244628906

fold_1/model.bias_scaled.fold_1.ENCSR254AGA.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:49d59088803627d3ebd0a95d62d5577b1dc0979959fa90541a56bf886982af66
+size 2691928

fold_1/model.bias_scaled.fold_1.ENCSR254AGA.tar

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:548a7f37b29813735521f842ced827a80cad024746f3c4ce17009ee7c1a9d20f
+size 1198080

fold_1/model.chrombpnet.fold_1.ENCSR254AGA.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:992b302bb9bdad9fa42924d557eede466f1a8a27b88add8bc659a732730f5cdf
+size 77538840

fold_1/model.chrombpnet.fold_1.ENCSR254AGA.tar

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:25ee3d23c2be97f837cb2a71e1899c27a78511c1b707054bbe952993df576409
+size 27525120

fold_1/model.chrombpnet_nobias.fold_1.ENCSR254AGA.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b811e6d3672a1f634568a2b4758232e225bb17611267b5cb518a7f2b9f666ffc
+size 25582648

fold_1/model.chrombpnet_nobias.fold_1.ENCSR254AGA.tar

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c9e6b4664e333ca56343494c0619aa6c56d0143b30453ab5f430d9a74e47a315
+size 26060800

fold_2/logs.models.fold_2.ENCSR254AGA/logfile.modelling.fold_2.ENCSR254AGA.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": "/oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/DNASE/ENCSR254AGA/preprocessing/bigWigs/ENCSR254AGA.bigWig",
+    "input_fragment_file": null,
+    "input_tagalign_file": null,
+    "output_dir": "/oak/stanford/groups/akundaje/vhecht/chromatin_atlas_bias_corrected/DNASE_model/ENCSR254AGA/fold_2",
+    "data_type": "DNASE",
+    "peaks": "/oak/stanford/groups/akundaje/vhecht/chromatin_atlas_bias_corrected/DNASE_model/ENCSR254AGA/fold_2/auxiliary/filtered.peaks.bed",
+    "nonpeaks": "/oak/stanford/groups/akundaje/vhecht/chromatin_atlas_bias_corrected/DNASE_model/ENCSR254AGA/fold_2/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": "/oak/stanford/groups/akundaje/ziwei75/chromatin_atlas_bias/DNase_bias_model/bias_threshold_0.8/ENCSR254AGA/models/bias.h5",
+    "negative_sampling_ratio": 0.1,
+    "filters": 512,
+    "n_dilation_layers": 8,
+    "max_jitter": 500,
+    "batch_size": 64,
+    "output_prefix": "/oak/stanford/groups/akundaje/vhecht/chromatin_atlas_bias_corrected/DNASE_model/ENCSR254AGA/fold_2/models/chrombpnet",
+    "bigwig": "/oak/stanford/groups/akundaje/vhecht/chromatin_atlas_bias_corrected/DNASE_model/ENCSR254AGA/fold_2/auxiliary/data_unstranded.bw",
+    "plus_shift": null,
+    "minus_shift": null,
+    "chr": "chr22",
+    "pwm_width": 24,
+    "params": "/oak/stanford/groups/akundaje/vhecht/chromatin_atlas_bias_corrected/DNASE_model/ENCSR254AGA/fold_2/logs/chrombpnet_model_params.tsv"
+}

fold_2/logs.models.fold_2.ENCSR254AGA/logfile.modelling.fold_2.ENCSR254AGA.bias_formatting.stdout.txt

@@ -0,0 +1 @@
+Converting /oak/stanford/groups/akundaje/vhecht/chromatin_atlas_bias_corrected/DNASE_model/ENCSR254AGA/fold_2/models/bias_model_scaled.h5 to /oak/stanford/groups/akundaje/vhecht/chromatin-atlas-2022/DNASE/ENCSR254AGA/fold_2/new_model_format/bias_model_scaled.tar with get_new_tf_model_format.py

fold_2/logs.models.fold_2.ENCSR254AGA/logfile.modelling.fold_2.ENCSR254AGA.chrombpnet_data_params.tsv

@@ -0,0 +1,3 @@
+counts_sum_min_thresh	0.0
+counts_sum_max_thresh	945.8
+trainings_pts_post_thresh	176849

fold_2/logs.models.fold_2.ENCSR254AGA/logfile.modelling.fold_2.ENCSR254AGA.chrombpnet_formatting.stdout.txt

@@ -0,0 +1 @@
+Converting /oak/stanford/groups/akundaje/vhecht/chromatin_atlas_bias_corrected/DNASE_model/ENCSR254AGA/fold_2/models/chrombpnet.h5 to /oak/stanford/groups/akundaje/vhecht/chromatin-atlas-2022/DNASE/ENCSR254AGA/fold_2/new_model_format/chrombpnet.tar with get_new_tf_model_format.py

fold_2/logs.models.fold_2.ENCSR254AGA/logfile.modelling.fold_2.ENCSR254AGA.chrombpnet_model_params.tsv

@@ -0,0 +1,9 @@
+counts_loss_weight	2.4
+filters	512
+n_dil_layers	8
+bias_model_path	/oak/stanford/groups/akundaje/vhecht/chromatin_atlas_bias_corrected/DNASE_model/ENCSR254AGA/fold_2/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.ENCSR254AGA/logfile.modelling.fold_2.ENCSR254AGA.chrombpnet_no_bias_formatting.stdout.txt

@@ -0,0 +1 @@
+Converting /oak/stanford/groups/akundaje/vhecht/chromatin_atlas_bias_corrected/DNASE_model/ENCSR254AGA/fold_2/models/chrombpnet_nobias.h5 to /oak/stanford/groups/akundaje/vhecht/chromatin-atlas-2022/DNASE/ENCSR254AGA/fold_2/new_model_format/chrombpnet_nobias.tar with get_new_tf_model_format.py

fold_2/logs.models.fold_2.ENCSR254AGA/logfile.modelling.fold_2.ENCSR254AGA.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
+0,3.1766700744628906,138.4324951171875,146.05674743652344,0.566170334815979,139.7108612060547,141.0697021484375
+1,0.5633323788642883,134.33778381347656,135.6897430419922,0.5370769500732422,138.82383728027344,140.11277770996094
+2,0.5151906609535217,133.1587677001953,134.395263671875,0.46407750248908997,137.30799865722656,138.42181396484375
+3,0.4800666272640228,132.45347595214844,133.60557556152344,0.4802955985069275,137.04701232910156,138.19970703125
+4,0.4536423087120056,131.7532501220703,132.8419189453125,0.45376577973365784,137.2599334716797,138.34896850585938
+5,0.4346008002758026,131.09234619140625,132.13563537597656,0.4576334059238434,136.3784942626953,137.47686767578125
+6,0.42215487360954285,130.71490478515625,131.72793579101562,0.4621153175830841,136.28492736816406,137.39395141601562
+7,0.40907707810401917,130.41842651367188,131.4002227783203,0.414143443107605,136.66004943847656,137.654052734375
+8,0.39958158135414124,129.99720764160156,130.95639038085938,0.3997040390968323,136.1973114013672,137.15658569335938
+9,0.3913962244987488,129.59353637695312,130.53289794921875,0.40381184220314026,136.78518676757812,137.7543182373047
+10,0.38513052463531494,129.2222137451172,130.14637756347656,0.39148271083831787,137.03822326660156,137.977783203125
+11,0.37607091665267944,128.85806274414062,129.76072692871094,0.39238274097442627,136.94235229492188,137.8840789794922
+12,0.36931273341178894,128.62716674804688,129.513427734375,0.4039476811885834,136.8325958251953,137.80215454101562
+13,0.36632758378982544,128.3108673095703,129.190185546875,0.38459670543670654,137.24868774414062,138.17172241210938

fold_2/model.bias_scaled.fold_2.ENCSR254AGA.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:004cc43160ee8cf14ddaa4f1a5430b2f33e8dafa55ee308282408f354a1884e3
+size 2691928

fold_2/model.bias_scaled.fold_2.ENCSR254AGA.tar

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aa39a50793698d90bed4927eaaa33eacb0a4741c6bd345323255f172ad199c9c
+size 1198080

fold_2/model.chrombpnet.fold_2.ENCSR254AGA.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:45fdd39579f75159824f097625ef77294cef298b4cfd90532d3a3547f279bc8d
+size 77538840

fold_2/model.chrombpnet.fold_2.ENCSR254AGA.tar

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e4d031b63690f255d645bc3f99a05ddf71e16d1f66e44da7e52fb3d678474e1c
+size 27525120

fold_2/model.chrombpnet_nobias.fold_2.ENCSR254AGA.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cbb4f207935d0f0064e28cd2a23ff10f03ce1edba126828c250af19ebe03d4ee
+size 25582648

fold_2/model.chrombpnet_nobias.fold_2.ENCSR254AGA.tar

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d0ca685ba1d989081a56bae1776544945ea03df7f862402f2f075d088ee90f86
+size 26060800

fold_3/logs.models.fold_3.ENCSR254AGA/logfile.modelling.fold_3.ENCSR254AGA.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": "/oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/DNASE/ENCSR254AGA/preprocessing/bigWigs/ENCSR254AGA.bigWig",
+    "input_fragment_file": null,
+    "input_tagalign_file": null,
+    "output_dir": "/oak/stanford/groups/akundaje/vhecht/chromatin_atlas_bias_corrected/DNASE_model/ENCSR254AGA/fold_3",
+    "data_type": "DNASE",
+    "peaks": "/oak/stanford/groups/akundaje/vhecht/chromatin_atlas_bias_corrected/DNASE_model/ENCSR254AGA/fold_3/auxiliary/filtered.peaks.bed",
+    "nonpeaks": "/oak/stanford/groups/akundaje/vhecht/chromatin_atlas_bias_corrected/DNASE_model/ENCSR254AGA/fold_3/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": "/oak/stanford/groups/akundaje/ziwei75/chromatin_atlas_bias/DNase_bias_model/bias_threshold_0.8/ENCSR254AGA/models/bias.h5",
+    "negative_sampling_ratio": 0.1,
+    "filters": 512,
+    "n_dilation_layers": 8,
+    "max_jitter": 500,
+    "batch_size": 64,
+    "output_prefix": "/oak/stanford/groups/akundaje/vhecht/chromatin_atlas_bias_corrected/DNASE_model/ENCSR254AGA/fold_3/models/chrombpnet",
+    "bigwig": "/oak/stanford/groups/akundaje/vhecht/chromatin_atlas_bias_corrected/DNASE_model/ENCSR254AGA/fold_3/auxiliary/data_unstranded.bw",
+    "plus_shift": null,
+    "minus_shift": null,
+    "chr": "chr6",
+    "pwm_width": 24,
+    "params": "/oak/stanford/groups/akundaje/vhecht/chromatin_atlas_bias_corrected/DNASE_model/ENCSR254AGA/fold_3/logs/chrombpnet_model_params.tsv"
+}

fold_3/logs.models.fold_3.ENCSR254AGA/logfile.modelling.fold_3.ENCSR254AGA.bias_formatting.stdout.txt

@@ -0,0 +1 @@
+Converting /oak/stanford/groups/akundaje/vhecht/chromatin_atlas_bias_corrected/DNASE_model/ENCSR254AGA/fold_3/models/bias_model_scaled.h5 to /oak/stanford/groups/akundaje/vhecht/chromatin-atlas-2022/DNASE/ENCSR254AGA/fold_3/new_model_format/bias_model_scaled.tar with get_new_tf_model_format.py

fold_3/logs.models.fold_3.ENCSR254AGA/logfile.modelling.fold_3.ENCSR254AGA.chrombpnet_data_params.tsv

@@ -0,0 +1,3 @@
+counts_sum_min_thresh	0.0
+counts_sum_max_thresh	968.3
+trainings_pts_post_thresh	171292

fold_3/logs.models.fold_3.ENCSR254AGA/logfile.modelling.fold_3.ENCSR254AGA.chrombpnet_formatting.stdout.txt

@@ -0,0 +1 @@
+Converting /oak/stanford/groups/akundaje/vhecht/chromatin_atlas_bias_corrected/DNASE_model/ENCSR254AGA/fold_3/models/chrombpnet.h5 to /oak/stanford/groups/akundaje/vhecht/chromatin-atlas-2022/DNASE/ENCSR254AGA/fold_3/new_model_format/chrombpnet.tar with get_new_tf_model_format.py

fold_3/logs.models.fold_3.ENCSR254AGA/logfile.modelling.fold_3.ENCSR254AGA.chrombpnet_model_params.tsv

@@ -0,0 +1,9 @@
+counts_loss_weight	2.4
+filters	512
+n_dil_layers	8
+bias_model_path	/oak/stanford/groups/akundaje/vhecht/chromatin_atlas_bias_corrected/DNASE_model/ENCSR254AGA/fold_3/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.ENCSR254AGA/logfile.modelling.fold_3.ENCSR254AGA.chrombpnet_no_bias_formatting.stdout.txt

@@ -0,0 +1 @@
+Converting /oak/stanford/groups/akundaje/vhecht/chromatin_atlas_bias_corrected/DNASE_model/ENCSR254AGA/fold_3/models/chrombpnet_nobias.h5 to /oak/stanford/groups/akundaje/vhecht/chromatin-atlas-2022/DNASE/ENCSR254AGA/fold_3/new_model_format/chrombpnet_nobias.tar with get_new_tf_model_format.py