Upload folder using huggingface_hub

README.md

@@ -0,0 +1,120 @@
+---
+license: mit
+library_name: chrombpnet
+tags:
+  - encode
+  - chrombpnet
+  - chromatin-accessibility
+  - DNASE
+  - thymus
+  - 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 thymus (ENCSR682PKY)
+- Model: ChromBPNet
+- Assay: DNASE-seq
+- Experiment: [ENCSR682PKY](https://www.encodeproject.org/experiments/ENCSR682PKY/)
+- Model annotation: [ENCSR108MFV](https://www.encodeproject.org/annotations/ENCSR108MFV/)
+- Biosample: thymus (Full name: Homo sapiens thymus tissue female embryo)
+- Cell slim(s): None
+- Organ slim(s): endocrine-gland,thymus,immune-organ
+- Developmental slim(s): mesoderm,endoderm
+- System slim(s): endocrine-system,immune-system
+- Assembly: hg38
+
+## Directory structure
+- `fold_0`: Model of 5-fold cross-validation: Fold 0
+    - `model.chrombpnet.fold_0.encid.h5`: full chrombpnet model that combines both bias and corrected model in .h5 format
+    - `model.chrombpnet_nobias.fold_0.encid.h5`: bias-corrected accessibility model in .h5 format (Use for all biological discovery)
+    - `model.bias_scaled.fold_0.encid.h5`: bias model in .h5 format
+    - `model.chrombpnet.fold_0.encid.tar`: full chrombpnet model that combines both bias and  corrected model in SavedModel format. After being untarred, it results in a directory named "chrombpnet".
+    - `model.chrombpnet_nobias.fold_0.encid.tar`: bias-corrected accessibility model in SavedModel format (Use for all biological discovery). After being untarred, it results in a directory named "chrombpnet_wo_bias".
+    - `model.bias_scaled.fold_0.encid.tar`: bias model in SavedModel format. After being untarred, it results in a directory named "bias_model_scaled".
+    - `logs.models.fold_0.encid`: folder containing log files for training models
+- `fold_1`: Model of 5-fold coss-validation: Fold 1
+- `fold_2`: Model of 5-fold cross-validation: Fold 2
+- `fold_3`: Model of 5-fold cross-validation: Fold 3
+- `fold_4`: Model of 5-fold cross-validation: Fold 4
+
+# Instructions
+## 1. Pseudocode for loading models in .h5 format 
+
+(1) Use the code in python after appropriately defining `model_in_h5_format` and `inputs`. \
+(2) `inputs` is a one hot encoded sequence of shape (N,2114,4). Here N corresponds to the 
+number of tested sequences, 2114 is the input sequence length and 4 corresponds to [A,C,G,T].
+
+```python
+import tensorflow as tf
+from tensorflow.keras.utils import get_custom_objects
+from tensorflow.keras.models import load_model
+
+custom_objects={"tf": tf}
+get_custom_objects().update(custom_objects)
+
+model=load_model(model_in_h5_format,compile=False)
+outputs = model(inputs)
+```
+
+The list `outputs` consists of two elements. The first element has a shape of (N, 1000) and
+contains logit predictions for a 1000-base-pair output. The second element, with a shape of
+(N, 1), contains logcount predictions. To transform these predictions into per-base signals, 
+follow the provided pseudo code lines below.
+
+```python
+import numpy as np
+
+def softmax(x, temp=1):
+    norm_x = x - np.mean(x,axis=1, keepdims=True)
+    return np.exp(temp*norm_x)/np.sum(np.exp(temp*norm_x), axis=1, keepdims=True)
+    
+predictions = softmax(outputs[0]) * (np.exp(outputs[1])-1)
+```
+
+## 2. Pseudocode for loading models in .tar format
+
+(1) First untar the directory as follows `tar -xvf model.tar`. \
+(2) Use the code below in python after appropriately defining `model_dir_untared` and `inputs`. \
+(3) `inputs` is a one hot encoded sequence of shape (N,2114,4). Here N corresponds to the number
+of tested sequences, 2114 is the input sequence length and 4 corresponds to ACGT.
+
+Reference: https://www.tensorflow.org/api_docs/python/tf/saved_model/load
+
+```python
+import tensorflow as tf
+
+model = tf.saved_model.load('model_dir_untared')
+outputs = model.signatures['serving_default'](**{'sequence':inputs.astype('float32')})
+```
+
+The variable `outputs` represents a dictionary containing two key-value pairs. The first key
+is `logits_profile_predictions`, holding a value with a shape of (N, 1000). This value corresponds
+to logit predictions for a 1000-base-pair output. The second key, named `logcount_predictions``, 
+is associated with a value of shape (N, 1), representing logcount predictions. To transform these
+predictions into per-base signals, utilize the provided pseudo code lines mentioned below.
+
+```python
+import numpy as np
+def softmax(x, temp=1):
+    norm_x = x - np.mean(x,axis=1, keepdims=True)
+    return np.exp(temp*norm_x)/np.sum(np.exp(temp*norm_x), axis=1, keepdims=True)
+    
+predictions = softmax(outputs["logits_profile_predictions"]) * (np.exp(outputs["logcount_predictions"])-1)
+```
+
+## Docker image to load and use the models
+- https://hub.docker.com/r/kundajelab/chrombpnet-atlas/ (tag:v1)
+
+## Code for ChromBPNet
+- https://github.com/kundajelab/chrombpnet/
+
+# License & citation
+External data users may freely download, analyze and publish results based on any ENCODE data without restrictions.
+
+Released under the [ENCODE data-use policy](https://www.encodeproject.org/about/data-use-policy/). Please cite the ENCODE Project Consortium and the model software: [ChromBPNet](https://github.com/kundajelab/chrombpnet) (Pampari et al., bioRxiv 2024).

fold_0/logs.models.fold_0.ENCSR682PKY/logfile.modelling.fold_0.ENCSR682PKY.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/ENCSR682PKY/preprocessing/bigWigs/ENCSR682PKY.bigWig",
+    "output_dir": "/oak/stanford/groups/akundaje/ziwei75/chromatin_atlas_bias/DNase_model/bias_threshold_0.8/ENCSR682PKY/fold0/",
+    "data_type": "DNASE",
+    "peaks": "/oak/stanford/groups/akundaje/ziwei75/chromatin_atlas_bias/DNase_model/bias_threshold_0.8/ENCSR682PKY/fold0/auxiliary/filtered.peaks.bed",
+    "nonpeaks": "/oak/stanford/groups/akundaje/ziwei75/chromatin_atlas_bias/DNase_model/bias_threshold_0.8/ENCSR682PKY/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/ENCSR682PKY/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/ENCSR682PKY/fold0/models/chrombpnet",
+    "chr": "chr8",
+    "pwm_width": 24,
+    "params": "/oak/stanford/groups/akundaje/ziwei75/chromatin_atlas_bias/DNase_model/bias_threshold_0.8/ENCSR682PKY/fold0/logs/chrombpnet_model_params.tsv"
+}

fold_0/logs.models.fold_0.ENCSR682PKY/logfile.modelling.fold_0.ENCSR682PKY.bias_formatting.stdout.txt

@@ -0,0 +1 @@
+Converting /oak/stanford/groups/akundaje/ziwei75/chromatin_atlas_bias/DNase_model/bias_threshold_0.8/ENCSR682PKY/fold0/models/bias_model_scaled.h5 to /oak/stanford/groups/akundaje/vhecht/chromatin-atlas-2022/DNASE/ENCSR682PKY/fold_0/new_model_format/bias_model_scaled.tar with get_new_tf_model_format.py

fold_0/logs.models.fold_0.ENCSR682PKY/logfile.modelling.fold_0.ENCSR682PKY.chrombpnet_data_params.tsv

@@ -0,0 +1,3 @@
+counts_sum_min_thresh	0.0
+counts_sum_max_thresh	2035.96
+trainings_pts_post_thresh	105848

fold_0/logs.models.fold_0.ENCSR682PKY/logfile.modelling.fold_0.ENCSR682PKY.chrombpnet_formatting.stdout.txt

@@ -0,0 +1 @@
+Converting /oak/stanford/groups/akundaje/ziwei75/chromatin_atlas_bias/DNase_model/bias_threshold_0.8/ENCSR682PKY/fold0/models/chrombpnet.h5 to /oak/stanford/groups/akundaje/vhecht/chromatin-atlas-2022/DNASE/ENCSR682PKY/fold_0/new_model_format/chrombpnet.tar with get_new_tf_model_format.py

fold_0/logs.models.fold_0.ENCSR682PKY/logfile.modelling.fold_0.ENCSR682PKY.chrombpnet_model_params.tsv

@@ -0,0 +1,9 @@
+counts_loss_weight	4.0
+filters	512
+n_dil_layers	8
+bias_model_path	/oak/stanford/groups/akundaje/ziwei75/chromatin_atlas_bias/DNase_model/bias_threshold_0.8/ENCSR682PKY/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.ENCSR682PKY/logfile.modelling.fold_0.ENCSR682PKY.chrombpnet_no_bias_formatting.stdout.txt

@@ -0,0 +1 @@
+Converting /oak/stanford/groups/akundaje/ziwei75/chromatin_atlas_bias/DNase_model/bias_threshold_0.8/ENCSR682PKY/fold0/models/chrombpnet_nobias.h5 to /oak/stanford/groups/akundaje/vhecht/chromatin-atlas-2022/DNASE/ENCSR682PKY/fold_0/new_model_format/chrombpnet_nobias.tar with get_new_tf_model_format.py

fold_0/logs.models.fold_0.ENCSR682PKY/logfile.modelling.fold_0.ENCSR682PKY.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
+0,2.493856430053711,247.874267578125,257.8495178222656,0.9028163552284241,232.27870178222656,235.8899383544922
+1,0.9491434693336487,234.030029296875,237.82656860351562,0.8455594182014465,226.5965576171875,229.97874450683594
+2,0.8676550984382629,229.9627227783203,233.433349609375,0.77589350938797,227.2081756591797,230.31161499023438
+3,0.797684371471405,227.9213409423828,231.11204528808594,0.6940566301345825,225.9148712158203,228.69107055664062
+4,0.7577353119850159,225.96826171875,228.9993438720703,0.7422990798950195,225.55422973632812,228.5235137939453
+5,0.7253113985061646,224.9037628173828,227.80462646484375,0.6657625436782837,224.8573760986328,227.5203094482422
+6,0.7080032825469971,223.01646423339844,225.8482666015625,0.6466060876846313,224.67910766601562,227.26551818847656
+7,0.6708201766014099,221.28167724609375,223.9649658203125,0.618523120880127,223.40245056152344,225.87661743164062
+8,0.6454801559448242,220.3433074951172,222.92526245117188,0.6524143815040588,225.33108520507812,227.94088745117188
+9,0.6316117644309998,218.75384521484375,221.28021240234375,0.6460595726966858,225.3179168701172,227.90237426757812
+10,0.6140193939208984,217.99240112304688,220.44879150390625,0.6362847089767456,224.23992919921875,226.78501892089844
+11,0.5961651802062988,217.26898193359375,219.65370178222656,0.6204438209533691,225.86940002441406,228.35116577148438
+12,0.5851977467536926,215.7010955810547,218.0419921875,0.6177035570144653,225.69371032714844,228.16461181640625

fold_0/model.bias_scaled.fold_0.ENCSR682PKY.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a4047958ed064c6c3a232cad863fbcc626837317885b696ea016b35843edcbb2
+size 2691928

fold_0/model.bias_scaled.fold_0.ENCSR682PKY.tar

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4c7b5a9d04b5990bd99b6addedc650cb48a4e6cced91fe0eeb48479db7f00d0a
+size 1198080

fold_0/model.chrombpnet.fold_0.ENCSR682PKY.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b59ce7163be0a2cd74d04d27d420126aa4ab31cfc482cb9362bcb7edf38ee0e4
+size 77538952

fold_0/model.chrombpnet.fold_0.ENCSR682PKY.tar

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8025748b46fcda2f0894d36ff50bd7c8f93fdea48819ecdba4057012bc7adf2e
+size 27525120

fold_0/model.chrombpnet_nobias.fold_0.ENCSR682PKY.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3554dbf26cd964b6584df57ab4fbd02d627a0576c7804641287954b6d94d8c58
+size 25582648

fold_0/model.chrombpnet_nobias.fold_0.ENCSR682PKY.tar

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:05d9ad2f043d3e48df01a6e73e59792b2959495f70414f2dcb88fde7ba605326
+size 26060800

fold_1/logs.models.fold_1.ENCSR682PKY/logfile.modelling.fold_1.ENCSR682PKY.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/ENCSR682PKY/preprocessing/bigWigs/ENCSR682PKY.bigWig",
+    "input_fragment_file": null,
+    "input_tagalign_file": null,
+    "output_dir": "/oak/stanford/groups/akundaje/vhecht/chromatin_atlas_bias_corrected/DNASE_model/ENCSR682PKY/fold_1",
+    "data_type": "DNASE",
+    "peaks": "/oak/stanford/groups/akundaje/vhecht/chromatin_atlas_bias_corrected/DNASE_model/ENCSR682PKY/fold_1/auxiliary/filtered.peaks.bed",
+    "nonpeaks": "/oak/stanford/groups/akundaje/vhecht/chromatin_atlas_bias_corrected/DNASE_model/ENCSR682PKY/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/ENCSR682PKY/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/ENCSR682PKY/fold_1/models/chrombpnet",
+    "bigwig": "/oak/stanford/groups/akundaje/vhecht/chromatin_atlas_bias_corrected/DNASE_model/ENCSR682PKY/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/ENCSR682PKY/fold_1/logs/chrombpnet_model_params.tsv"
+}

fold_1/logs.models.fold_1.ENCSR682PKY/logfile.modelling.fold_1.ENCSR682PKY.bias_formatting.stdout.txt

@@ -0,0 +1 @@
+Converting /oak/stanford/groups/akundaje/vhecht/chromatin_atlas_bias_corrected/DNASE_model/ENCSR682PKY/fold_1/models/bias_model_scaled.h5 to /oak/stanford/groups/akundaje/vhecht/chromatin-atlas-2022/DNASE/ENCSR682PKY/fold_1/new_model_format/bias_model_scaled.tar with get_new_tf_model_format.py

fold_1/logs.models.fold_1.ENCSR682PKY/logfile.modelling.fold_1.ENCSR682PKY.chrombpnet_data_params.tsv

@@ -0,0 +1,3 @@
+counts_sum_min_thresh	0.0
+counts_sum_max_thresh	2022.76
+trainings_pts_post_thresh	109364

fold_1/logs.models.fold_1.ENCSR682PKY/logfile.modelling.fold_1.ENCSR682PKY.chrombpnet_formatting.stdout.txt

@@ -0,0 +1 @@
+Converting /oak/stanford/groups/akundaje/vhecht/chromatin_atlas_bias_corrected/DNASE_model/ENCSR682PKY/fold_1/models/chrombpnet.h5 to /oak/stanford/groups/akundaje/vhecht/chromatin-atlas-2022/DNASE/ENCSR682PKY/fold_1/new_model_format/chrombpnet.tar with get_new_tf_model_format.py

fold_1/logs.models.fold_1.ENCSR682PKY/logfile.modelling.fold_1.ENCSR682PKY.chrombpnet_model_params.tsv

@@ -0,0 +1,9 @@
+counts_loss_weight	4.0
+filters	512
+n_dil_layers	8
+bias_model_path	/oak/stanford/groups/akundaje/vhecht/chromatin_atlas_bias_corrected/DNASE_model/ENCSR682PKY/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.ENCSR682PKY/logfile.modelling.fold_1.ENCSR682PKY.chrombpnet_no_bias_formatting.stdout.txt

@@ -0,0 +1 @@
+Converting /oak/stanford/groups/akundaje/vhecht/chromatin_atlas_bias_corrected/DNASE_model/ENCSR682PKY/fold_1/models/chrombpnet_nobias.h5 to /oak/stanford/groups/akundaje/vhecht/chromatin-atlas-2022/DNASE/ENCSR682PKY/fold_1/new_model_format/chrombpnet_nobias.tar with get_new_tf_model_format.py

fold_1/logs.models.fold_1.ENCSR682PKY/logfile.modelling.fold_1.ENCSR682PKY.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
+0,5.757243633270264,246.6372833251953,269.66607666015625,1.1074268817901611,284.9434814453125,289.37310791015625
+1,1.0046288967132568,232.80621337890625,236.82492065429688,0.965516209602356,278.9366149902344,282.798583984375
+2,0.8869020342826843,228.62942504882812,232.1771697998047,0.9578444957733154,274.4176025390625,278.2489013671875
+3,0.8353527784347534,226.58363342285156,229.92544555664062,0.8509908318519592,273.3754577636719,276.7794494628906
+4,0.7830361127853394,224.15809631347656,227.2899627685547,0.7628027200698853,272.9508056640625,276.00201416015625
+5,0.7565289735794067,223.4295654296875,226.4554901123047,0.7442036867141724,269.68792724609375,272.664794921875
+6,0.730538010597229,221.8185272216797,224.7407989501953,0.7998101115226746,271.0401306152344,274.2391662597656
+7,0.6977428793907166,220.4678955078125,223.2590789794922,0.7017690539360046,268.6153869628906,271.4224548339844
+8,0.6681365370750427,219.4599609375,222.13291931152344,0.6844648122787476,271.05401611328125,273.79193115234375
+9,0.6496052742004395,217.98974609375,220.5880584716797,0.8210148811340332,268.26275634765625,271.5466613769531
+10,0.6314457058906555,217.0505828857422,219.57603454589844,0.6888963580131531,269.40264892578125,272.158203125
+11,0.6129534840583801,215.91079711914062,218.36231994628906,0.6856677532196045,270.983642578125,273.7262878417969
+12,0.6019126772880554,214.32339477539062,216.73126220703125,0.9168003797531128,270.6571960449219,274.3243408203125

fold_1/model.bias_scaled.fold_1.ENCSR682PKY.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:813479eb23b984bc55c006d3700c18175b10775f5c02d3384d6760d106f45d23
+size 2691928

fold_1/model.bias_scaled.fold_1.ENCSR682PKY.tar

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2661358fa6a0e0e16296a05a819261c652d0901157f402186564794c26e837be
+size 1198080

fold_1/model.chrombpnet.fold_1.ENCSR682PKY.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eba5fc3fa5c08cfe95e23955e5aa8cfb160ce59ced8026b6d920b95f7f77fa3c
+size 77538840

fold_1/model.chrombpnet.fold_1.ENCSR682PKY.tar

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c6f28d262057a0dc8bdd092d618ecdabb45c4b044d98516e29e49d53db44386f
+size 27525120

fold_1/model.chrombpnet_nobias.fold_1.ENCSR682PKY.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9596949cdf92e025bf68d38a4d3ee034ac4914cdb64425fe85dbb3cb8c08db6f
+size 25582648

fold_1/model.chrombpnet_nobias.fold_1.ENCSR682PKY.tar

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:38eb3303d5ae8880c9afa1b96dde2ea639d7ced434079893de5e696395f8279f
+size 26060800

fold_2/logs.models.fold_2.ENCSR682PKY/logfile.modelling.fold_2.ENCSR682PKY.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/ENCSR682PKY/preprocessing/bigWigs/ENCSR682PKY.bigWig",
+    "input_fragment_file": null,
+    "input_tagalign_file": null,
+    "output_dir": "/oak/stanford/groups/akundaje/vhecht/chromatin_atlas_bias_corrected/DNASE_model/ENCSR682PKY/fold_2",
+    "data_type": "DNASE",
+    "peaks": "/oak/stanford/groups/akundaje/vhecht/chromatin_atlas_bias_corrected/DNASE_model/ENCSR682PKY/fold_2/auxiliary/filtered.peaks.bed",
+    "nonpeaks": "/oak/stanford/groups/akundaje/vhecht/chromatin_atlas_bias_corrected/DNASE_model/ENCSR682PKY/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/ENCSR682PKY/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/ENCSR682PKY/fold_2/models/chrombpnet",
+    "bigwig": "/oak/stanford/groups/akundaje/vhecht/chromatin_atlas_bias_corrected/DNASE_model/ENCSR682PKY/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/ENCSR682PKY/fold_2/logs/chrombpnet_model_params.tsv"
+}

fold_2/logs.models.fold_2.ENCSR682PKY/logfile.modelling.fold_2.ENCSR682PKY.bias_formatting.stdout.txt

@@ -0,0 +1 @@
+Converting /oak/stanford/groups/akundaje/vhecht/chromatin_atlas_bias_corrected/DNASE_model/ENCSR682PKY/fold_2/models/bias_model_scaled.h5 to /oak/stanford/groups/akundaje/vhecht/chromatin-atlas-2022/DNASE/ENCSR682PKY/fold_2/new_model_format/bias_model_scaled.tar with get_new_tf_model_format.py

fold_2/logs.models.fold_2.ENCSR682PKY/logfile.modelling.fold_2.ENCSR682PKY.chrombpnet_data_params.tsv

@@ -0,0 +1,3 @@
+counts_sum_min_thresh	0.0
+counts_sum_max_thresh	2018.64
+trainings_pts_post_thresh	112500

fold_2/logs.models.fold_2.ENCSR682PKY/logfile.modelling.fold_2.ENCSR682PKY.chrombpnet_formatting.stdout.txt

@@ -0,0 +1 @@
+Converting /oak/stanford/groups/akundaje/vhecht/chromatin_atlas_bias_corrected/DNASE_model/ENCSR682PKY/fold_2/models/chrombpnet.h5 to /oak/stanford/groups/akundaje/vhecht/chromatin-atlas-2022/DNASE/ENCSR682PKY/fold_2/new_model_format/chrombpnet.tar with get_new_tf_model_format.py

fold_2/logs.models.fold_2.ENCSR682PKY/logfile.modelling.fold_2.ENCSR682PKY.chrombpnet_model_params.tsv

@@ -0,0 +1,9 @@
+counts_loss_weight	4.0
+filters	512
+n_dil_layers	8
+bias_model_path	/oak/stanford/groups/akundaje/vhecht/chromatin_atlas_bias_corrected/DNASE_model/ENCSR682PKY/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.ENCSR682PKY/logfile.modelling.fold_2.ENCSR682PKY.chrombpnet_no_bias_formatting.stdout.txt

@@ -0,0 +1 @@
+Converting /oak/stanford/groups/akundaje/vhecht/chromatin_atlas_bias_corrected/DNASE_model/ENCSR682PKY/fold_2/models/chrombpnet_nobias.h5 to /oak/stanford/groups/akundaje/vhecht/chromatin-atlas-2022/DNASE/ENCSR682PKY/fold_2/new_model_format/chrombpnet_nobias.tar with get_new_tf_model_format.py

fold_2/logs.models.fold_2.ENCSR682PKY/logfile.modelling.fold_2.ENCSR682PKY.epoch_loss.csv

@@ -0,0 +1,17 @@
+epoch,logcount_predictions_loss,logits_profile_predictions_loss,loss,val_logcount_predictions_loss,val_logits_profile_predictions_loss,val_loss
+0,3.9792816638946533,248.86593627929688,264.7831726074219,1.1090081930160522,241.9507598876953,246.38673400878906
+1,0.9807172417640686,234.70040893554688,238.6234130859375,0.9526723027229309,238.0480499267578,241.85874938964844
+2,0.872150719165802,230.38575744628906,233.8743133544922,0.8508355617523193,232.91893005371094,236.32215881347656
+3,0.8133458495140076,228.11392211914062,231.3672332763672,0.7448890209197998,231.56187438964844,234.54144287109375
+4,0.7686431407928467,225.88877868652344,228.96331787109375,0.714899480342865,230.9652557373047,233.82493591308594
+5,0.7358021140098572,224.57485961914062,227.51832580566406,0.8165582418441772,231.0918426513672,234.35797119140625
+6,0.7156357169151306,223.2484588623047,226.1109161376953,0.6847951412200928,232.97564697265625,235.71484375
+7,0.6797231435775757,221.91859436035156,224.63726806640625,0.7696481943130493,231.33493041992188,234.4134063720703
+8,0.6611118316650391,220.7906951904297,223.43490600585938,0.6730247735977173,230.85597229003906,233.5480499267578
+9,0.640509843826294,219.28802490234375,221.84996032714844,0.6671070456504822,232.3447723388672,235.01315307617188
+10,0.6202687621116638,218.12548828125,220.60665893554688,0.7084334492683411,229.4847412109375,232.3184356689453
+11,0.5974528789520264,217.45594787597656,219.84596252441406,0.6885644197463989,231.89993286132812,234.65406799316406
+12,0.5838879346847534,216.31817626953125,218.65379333496094,0.7170962691307068,232.2521514892578,235.12039184570312
+13,0.5681493878364563,215.217529296875,217.48974609375,0.6712817549705505,233.8170166015625,236.50198364257812
+14,0.5531471967697144,214.30877685546875,216.5213165283203,0.6664986610412598,234.77505493164062,237.44094848632812
+15,0.548395574092865,213.58201599121094,215.77545166015625,0.6408520936965942,235.62850952148438,238.19192504882812

fold_2/model.bias_scaled.fold_2.ENCSR682PKY.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:44f7ca4556be3e133413b903371a4701db5ef128b3c24fe444576abdfd4a7130
+size 2691928

fold_2/model.bias_scaled.fold_2.ENCSR682PKY.tar

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:49a48de44b6dcaddf119ee7ffe0fb1fd696149b29e927a4fdbadd1feceac456b
+size 1198080

fold_2/model.chrombpnet.fold_2.ENCSR682PKY.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:454daa3ea05bfed52788b82202ec4020cd1082e955648f3814b5590df94a4e2d
+size 77538840

fold_2/model.chrombpnet.fold_2.ENCSR682PKY.tar

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2420d302dd529f190420190dc18717a3172b1d32fcf25bbefca6b460a9912433
+size 27525120

fold_2/model.chrombpnet_nobias.fold_2.ENCSR682PKY.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:24b8b1f04fbff9956c2cfe41f0cd8753067bb6553f3eb4808a165929ebf297bd
+size 25582648

fold_2/model.chrombpnet_nobias.fold_2.ENCSR682PKY.tar

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bc8dbaac03d1512fc0a9b3f25c73608a4c4c9ec77e1d921c962307c1e7cd97b8
+size 26060800

fold_3/logs.models.fold_3.ENCSR682PKY/logfile.modelling.fold_3.ENCSR682PKY.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/ENCSR682PKY/preprocessing/bigWigs/ENCSR682PKY.bigWig",
+    "input_fragment_file": null,
+    "input_tagalign_file": null,
+    "output_dir": "/oak/stanford/groups/akundaje/vhecht/chromatin_atlas_bias_corrected/DNASE_model/ENCSR682PKY/fold_3",
+    "data_type": "DNASE",
+    "peaks": "/oak/stanford/groups/akundaje/vhecht/chromatin_atlas_bias_corrected/DNASE_model/ENCSR682PKY/fold_3/auxiliary/filtered.peaks.bed",
+    "nonpeaks": "/oak/stanford/groups/akundaje/vhecht/chromatin_atlas_bias_corrected/DNASE_model/ENCSR682PKY/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/ENCSR682PKY/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/ENCSR682PKY/fold_3/models/chrombpnet",
+    "bigwig": "/oak/stanford/groups/akundaje/vhecht/chromatin_atlas_bias_corrected/DNASE_model/ENCSR682PKY/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/ENCSR682PKY/fold_3/logs/chrombpnet_model_params.tsv"
+}

fold_3/logs.models.fold_3.ENCSR682PKY/logfile.modelling.fold_3.ENCSR682PKY.bias_formatting.stdout.txt

@@ -0,0 +1 @@
+Converting /oak/stanford/groups/akundaje/vhecht/chromatin_atlas_bias_corrected/DNASE_model/ENCSR682PKY/fold_3/models/bias_model_scaled.h5 to /oak/stanford/groups/akundaje/vhecht/chromatin-atlas-2022/DNASE/ENCSR682PKY/fold_3/new_model_format/bias_model_scaled.tar with get_new_tf_model_format.py

fold_3/logs.models.fold_3.ENCSR682PKY/logfile.modelling.fold_3.ENCSR682PKY.chrombpnet_data_params.tsv

@@ -0,0 +1,3 @@
+counts_sum_min_thresh	0.0
+counts_sum_max_thresh	2013.19
+trainings_pts_post_thresh	108519

fold_3/logs.models.fold_3.ENCSR682PKY/logfile.modelling.fold_3.ENCSR682PKY.chrombpnet_formatting.stdout.txt

@@ -0,0 +1 @@
+Converting /oak/stanford/groups/akundaje/vhecht/chromatin_atlas_bias_corrected/DNASE_model/ENCSR682PKY/fold_3/models/chrombpnet.h5 to /oak/stanford/groups/akundaje/vhecht/chromatin-atlas-2022/DNASE/ENCSR682PKY/fold_3/new_model_format/chrombpnet.tar with get_new_tf_model_format.py

fold_3/logs.models.fold_3.ENCSR682PKY/logfile.modelling.fold_3.ENCSR682PKY.chrombpnet_model_params.tsv

@@ -0,0 +1,9 @@
+counts_loss_weight	4.0
+filters	512
+n_dil_layers	8
+bias_model_path	/oak/stanford/groups/akundaje/vhecht/chromatin_atlas_bias_corrected/DNASE_model/ENCSR682PKY/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.ENCSR682PKY/logfile.modelling.fold_3.ENCSR682PKY.chrombpnet_no_bias_formatting.stdout.txt

@@ -0,0 +1 @@
+Converting /oak/stanford/groups/akundaje/vhecht/chromatin_atlas_bias_corrected/DNASE_model/ENCSR682PKY/fold_3/models/chrombpnet_nobias.h5 to /oak/stanford/groups/akundaje/vhecht/chromatin-atlas-2022/DNASE/ENCSR682PKY/fold_3/new_model_format/chrombpnet_nobias.tar with get_new_tf_model_format.py