Upload folder using huggingface_hub

README.md

@@ -0,0 +1,120 @@
+---
+license: mit
+library_name: chrombpnet
+tags:
+  - encode
+  - chrombpnet
+  - chromatin-accessibility
+  - DNASE
+  - t-helper
+  - 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 T-helper 17 cell (ENCSR747RGR)
+- Model: ChromBPNet
+- Assay: DNASE-seq
+- Experiment: [ENCSR747RGR](https://www.encodeproject.org/experiments/ENCSR747RGR/)
+- Model annotation: [ENCSR574LGV](https://www.encodeproject.org/annotations/ENCSR574LGV/)
+- Biosample: T-helper 17 cell (Full name: Homo sapiens T-helper 17 cell male adult (24 years))
+- Cell slim(s): CD4+-T-cell,T-cell,hematopoietic-cell,leukocyte
+- Organ slim(s): blood,bodily-fluid
+- Developmental slim(s): mesoderm,endoderm
+- System slim(s): 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.ENCSR747RGR/logfile.modelling.fold_0.ENCSR747RGR.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/ENCSR747RGR/preprocessing/bigWigs/ENCSR747RGR.bigWig",
+    "output_dir": "/oak/stanford/groups/akundaje/ziwei75/chromatin_atlas_bias/DNase_model/bias_threshold_0.8/ENCSR747RGR/fold0/",
+    "data_type": "DNASE",
+    "peaks": "/oak/stanford/groups/akundaje/ziwei75/chromatin_atlas_bias/DNase_model/bias_threshold_0.8/ENCSR747RGR/fold0/auxiliary/filtered.peaks.bed",
+    "nonpeaks": "/oak/stanford/groups/akundaje/ziwei75/chromatin_atlas_bias/DNase_model/bias_threshold_0.8/ENCSR747RGR/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/ENCSR747RGR/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/ENCSR747RGR/fold0/models/chrombpnet",
+    "chr": "chr8",
+    "pwm_width": 24,
+    "params": "/oak/stanford/groups/akundaje/ziwei75/chromatin_atlas_bias/DNase_model/bias_threshold_0.8/ENCSR747RGR/fold0/logs/chrombpnet_model_params.tsv"
+}

fold_0/logs.models.fold_0.ENCSR747RGR/logfile.modelling.fold_0.ENCSR747RGR.bias_formatting.stdout.txt

@@ -0,0 +1 @@
+Converting /oak/stanford/groups/akundaje/ziwei75/chromatin_atlas_bias/DNase_model/bias_threshold_0.8/ENCSR747RGR/fold0/models/bias_model_scaled.h5 to /oak/stanford/groups/akundaje/vhecht/chromatin-atlas-2022/DNASE/ENCSR747RGR/fold_0/new_model_format/bias_model_scaled.tar with get_new_tf_model_format.py

fold_0/logs.models.fold_0.ENCSR747RGR/logfile.modelling.fold_0.ENCSR747RGR.chrombpnet_data_params.tsv

@@ -0,0 +1,3 @@
+counts_sum_min_thresh	0.0
+counts_sum_max_thresh	9963.35
+trainings_pts_post_thresh	173757

fold_0/logs.models.fold_0.ENCSR747RGR/logfile.modelling.fold_0.ENCSR747RGR.chrombpnet_formatting.stdout.txt

@@ -0,0 +1 @@
+Converting /oak/stanford/groups/akundaje/ziwei75/chromatin_atlas_bias/DNase_model/bias_threshold_0.8/ENCSR747RGR/fold0/models/chrombpnet.h5 to /oak/stanford/groups/akundaje/vhecht/chromatin-atlas-2022/DNASE/ENCSR747RGR/fold_0/new_model_format/chrombpnet.tar with get_new_tf_model_format.py

fold_0/logs.models.fold_0.ENCSR747RGR/logfile.modelling.fold_0.ENCSR747RGR.chrombpnet_model_params.tsv

@@ -0,0 +1,9 @@
+counts_loss_weight	7.8
+filters	512
+n_dil_layers	8
+bias_model_path	/oak/stanford/groups/akundaje/ziwei75/chromatin_atlas_bias/DNase_model/bias_threshold_0.8/ENCSR747RGR/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.ENCSR747RGR/logfile.modelling.fold_0.ENCSR747RGR.chrombpnet_no_bias_formatting.stdout.txt

@@ -0,0 +1 @@
+Converting /oak/stanford/groups/akundaje/ziwei75/chromatin_atlas_bias/DNase_model/bias_threshold_0.8/ENCSR747RGR/fold0/models/chrombpnet_nobias.h5 to /oak/stanford/groups/akundaje/vhecht/chromatin-atlas-2022/DNASE/ENCSR747RGR/fold_0/new_model_format/chrombpnet_nobias.tar with get_new_tf_model_format.py

fold_0/logs.models.fold_0.ENCSR747RGR/logfile.modelling.fold_0.ENCSR747RGR.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
+0,1.2925502061843872,476.6384582519531,486.7205810546875,0.4294416904449463,431.2535095214844,434.6031188964844
+1,0.5352932810783386,451.863037109375,456.0387878417969,0.45682692527770996,425.0539855957031,428.6171569824219
+2,0.4859892725944519,444.9548034667969,448.74609375,0.3626110255718231,425.84814453125,428.6766052246094
+3,0.4524414837360382,439.6213073730469,443.1501770019531,0.378993958234787,422.3098449707031,425.2662353515625
+4,0.4285624325275421,436.01678466796875,439.3597412109375,0.33006447553634644,422.6611328125,425.2357482910156
+5,0.41444140672683716,433.268310546875,436.5014953613281,0.36236363649368286,422.8913269042969,425.71771240234375
+6,0.39992377161979675,430.8200988769531,433.9391174316406,0.3692809045314789,424.0606689453125,426.94085693359375
+7,0.38863733410835266,428.5807800292969,431.6125183105469,0.3141239881515503,422.0132751464844,424.46307373046875
+8,0.38134220242500305,426.0995788574219,429.07391357421875,0.3198069930076599,422.2647399902344,424.7591552734375
+9,0.3720634877681732,424.5972595214844,427.4991149902344,0.3165786862373352,424.0127868652344,426.4820556640625
+10,0.361735075712204,423.5448913574219,426.3665771484375,0.3096660077571869,418.9152526855469,421.3306884765625
+11,0.3543407917022705,421.8152770996094,424.5791931152344,0.32018914818763733,424.8943176269531,427.3915710449219
+12,0.35100626945495605,421.1789855957031,423.9172058105469,0.29908287525177,424.5084228515625,426.84112548828125
+13,0.34578362107276917,419.78436279296875,422.4811706542969,0.30651435256004333,427.3683166503906,429.75909423828125
+14,0.3420630693435669,418.90252685546875,421.5713806152344,0.3546304702758789,424.3857116699219,427.1517333984375
+15,0.33758506178855896,419.447265625,422.0801086425781,0.3054017722606659,422.9700012207031,425.35186767578125

fold_0/model.bias_scaled.fold_0.ENCSR747RGR.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e4214b808e3326a31391a17ce0a58202185d31498003f152c461681fbd59a420
+size 2691928

fold_0/model.bias_scaled.fold_0.ENCSR747RGR.tar

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e4fed28a80c5e1f81c9963ed938d23009c0c8940f9c7e7e7ed05dba0212574e9
+size 1198080

fold_0/model.chrombpnet.fold_0.ENCSR747RGR.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9dcb24ab7954289b812d530fa3ab1b346afe295ebaca4c1a360d4c94dcd94d6d
+size 77538952

fold_0/model.chrombpnet.fold_0.ENCSR747RGR.tar

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fcd8c39e8e13bc73ede0b5512e0b155d1bb581b63cf885ea1c62c3cb1f32c534
+size 27525120

fold_0/model.chrombpnet_nobias.fold_0.ENCSR747RGR.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:104dce7751c5039ea18eac0bb3b86fc03cb7d7e8fde76acb5f4297c9fd8d009d
+size 25582648

fold_0/model.chrombpnet_nobias.fold_0.ENCSR747RGR.tar

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4d6edf30b068cda133bb3ecb3c6a289791d3ace670c5a5c9e91263e5fb3c4172
+size 26060800

fold_1/logs.models.fold_1.ENCSR747RGR/logfile.modelling.fold_1.ENCSR747RGR.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/ENCSR747RGR/preprocessing/bigWigs/ENCSR747RGR.bigWig",
+    "input_fragment_file": null,
+    "input_tagalign_file": null,
+    "output_dir": "/oak/stanford/groups/akundaje/vhecht/chromatin_atlas_bias_corrected/DNASE_model/ENCSR747RGR/fold_1",
+    "data_type": "DNASE",
+    "peaks": "/oak/stanford/groups/akundaje/vhecht/chromatin_atlas_bias_corrected/DNASE_model/ENCSR747RGR/fold_1/auxiliary/filtered.peaks.bed",
+    "nonpeaks": "/oak/stanford/groups/akundaje/vhecht/chromatin_atlas_bias_corrected/DNASE_model/ENCSR747RGR/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/ENCSR747RGR/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/ENCSR747RGR/fold_1/models/chrombpnet",
+    "bigwig": "/oak/stanford/groups/akundaje/vhecht/chromatin_atlas_bias_corrected/DNASE_model/ENCSR747RGR/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/ENCSR747RGR/fold_1/logs/chrombpnet_model_params.tsv"
+}

fold_1/logs.models.fold_1.ENCSR747RGR/logfile.modelling.fold_1.ENCSR747RGR.bias_formatting.stdout.txt

@@ -0,0 +1 @@
+Converting /oak/stanford/groups/akundaje/vhecht/chromatin_atlas_bias_corrected/DNASE_model/ENCSR747RGR/fold_1/models/bias_model_scaled.h5 to /oak/stanford/groups/akundaje/vhecht/chromatin-atlas-2022/DNASE/ENCSR747RGR/fold_1/new_model_format/bias_model_scaled.tar with get_new_tf_model_format.py

fold_1/logs.models.fold_1.ENCSR747RGR/logfile.modelling.fold_1.ENCSR747RGR.chrombpnet_data_params.tsv

@@ -0,0 +1,3 @@
+counts_sum_min_thresh	0.0
+counts_sum_max_thresh	9751.94
+trainings_pts_post_thresh	173968

fold_1/logs.models.fold_1.ENCSR747RGR/logfile.modelling.fold_1.ENCSR747RGR.chrombpnet_formatting.stdout.txt

@@ -0,0 +1 @@
+Converting /oak/stanford/groups/akundaje/vhecht/chromatin_atlas_bias_corrected/DNASE_model/ENCSR747RGR/fold_1/models/chrombpnet.h5 to /oak/stanford/groups/akundaje/vhecht/chromatin-atlas-2022/DNASE/ENCSR747RGR/fold_1/new_model_format/chrombpnet.tar with get_new_tf_model_format.py

fold_1/logs.models.fold_1.ENCSR747RGR/logfile.modelling.fold_1.ENCSR747RGR.chrombpnet_model_params.tsv

@@ -0,0 +1,9 @@
+counts_loss_weight	7.8
+filters	512
+n_dil_layers	8
+bias_model_path	/oak/stanford/groups/akundaje/vhecht/chromatin_atlas_bias_corrected/DNASE_model/ENCSR747RGR/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.ENCSR747RGR/logfile.modelling.fold_1.ENCSR747RGR.chrombpnet_no_bias_formatting.stdout.txt

@@ -0,0 +1 @@
+Converting /oak/stanford/groups/akundaje/vhecht/chromatin_atlas_bias_corrected/DNASE_model/ENCSR747RGR/fold_1/models/chrombpnet_nobias.h5 to /oak/stanford/groups/akundaje/vhecht/chromatin-atlas-2022/DNASE/ENCSR747RGR/fold_1/new_model_format/chrombpnet_nobias.tar with get_new_tf_model_format.py

fold_1/logs.models.fold_1.ENCSR747RGR/logfile.modelling.fold_1.ENCSR747RGR.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
+0,3.7711069583892822,480.6839599609375,510.0984191894531,0.7879485487937927,547.7022705078125,553.8485717773438
+1,0.6594530344009399,448.0424499511719,453.18603515625,0.5513231158256531,539.3137817382812,543.6138916015625
+2,0.560219943523407,440.9747314453125,445.3450622558594,0.46474093198776245,534.0152587890625,537.6401977539062
+3,0.4975387156009674,436.14080810546875,440.0209045410156,0.4062459170818329,524.9202880859375,528.0890502929688
+4,0.4712754189968109,432.4747619628906,436.15032958984375,0.42598170042037964,530.467041015625,533.7894897460938
+5,0.44882047176361084,430.4147033691406,433.91552734375,0.4134954810142517,524.7543334960938,527.9801025390625
+6,0.43344801664352417,426.4465026855469,429.8276062011719,0.37123462557792664,528.8552856445312,531.7514038085938
+7,0.4171842932701111,424.7765197753906,428.03118896484375,0.3919215500354767,525.1603393554688,528.217041015625
+8,0.40570130944252014,422.2950134277344,425.4590759277344,0.3614274561405182,522.188720703125,525.0076904296875
+9,0.3925134241580963,420.2323303222656,423.2934265136719,0.410776823759079,530.5012817382812,533.705078125
+10,0.38815590739250183,418.2417297363281,421.2699890136719,0.3603891134262085,528.347412109375,531.1580200195312
+11,0.37885594367980957,416.6837158203125,419.6383972167969,0.34876853227615356,528.2662963867188,530.9865112304688
+12,0.3678433895111084,413.7152404785156,416.5838623046875,0.34933850169181824,524.81005859375,527.5347290039062
+13,0.3646697402000427,414.4666442871094,417.31103515625,0.34141674637794495,524.5057983398438,527.169189453125

fold_1/model.bias_scaled.fold_1.ENCSR747RGR.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3f905888e9c27a748aa8e86698ce4ed7ca3011729c185e342e3bc74e586098b7
+size 2691928

fold_1/model.bias_scaled.fold_1.ENCSR747RGR.tar

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:18d03cf4748909478c6b5ff1e6043a48823c33fb126d8d6760d1ca4531c552ac
+size 1198080

fold_1/model.chrombpnet.fold_1.ENCSR747RGR.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:86954745f9062283efdd19550aa2bc2e916a91274fe1b684d7990ad9fe070bcd
+size 77538840

fold_1/model.chrombpnet.fold_1.ENCSR747RGR.tar

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:addd2869e97fc27f297313f4979f1f759e5e20cc7b6aa1ce4a69846ee51f8dd3
+size 27525120

fold_1/model.chrombpnet_nobias.fold_1.ENCSR747RGR.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f3f14e5fa626e51471e59c7ec7db439c139106eb08bb861ec6a54a21036fab26
+size 25582648

fold_1/model.chrombpnet_nobias.fold_1.ENCSR747RGR.tar

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ce555ddfda017e0e9873d47f14c391bd3a0a7274d6465463073e97ff756a4316
+size 26060800

fold_2/logs.models.fold_2.ENCSR747RGR/logfile.modelling.fold_2.ENCSR747RGR.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/ENCSR747RGR/preprocessing/bigWigs/ENCSR747RGR.bigWig",
+    "input_fragment_file": null,
+    "input_tagalign_file": null,
+    "output_dir": "/oak/stanford/groups/akundaje/vhecht/chromatin_atlas_bias_corrected/DNASE_model/ENCSR747RGR/fold_2",
+    "data_type": "DNASE",
+    "peaks": "/oak/stanford/groups/akundaje/vhecht/chromatin_atlas_bias_corrected/DNASE_model/ENCSR747RGR/fold_2/auxiliary/filtered.peaks.bed",
+    "nonpeaks": "/oak/stanford/groups/akundaje/vhecht/chromatin_atlas_bias_corrected/DNASE_model/ENCSR747RGR/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/ENCSR747RGR/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/ENCSR747RGR/fold_2/models/chrombpnet",
+    "bigwig": "/oak/stanford/groups/akundaje/vhecht/chromatin_atlas_bias_corrected/DNASE_model/ENCSR747RGR/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/ENCSR747RGR/fold_2/logs/chrombpnet_model_params.tsv"
+}

fold_2/logs.models.fold_2.ENCSR747RGR/logfile.modelling.fold_2.ENCSR747RGR.bias_formatting.stdout.txt

@@ -0,0 +1 @@
+Converting /oak/stanford/groups/akundaje/vhecht/chromatin_atlas_bias_corrected/DNASE_model/ENCSR747RGR/fold_2/models/bias_model_scaled.h5 to /oak/stanford/groups/akundaje/vhecht/chromatin-atlas-2022/DNASE/ENCSR747RGR/fold_2/new_model_format/bias_model_scaled.tar with get_new_tf_model_format.py

fold_2/logs.models.fold_2.ENCSR747RGR/logfile.modelling.fold_2.ENCSR747RGR.chrombpnet_data_params.tsv

@@ -0,0 +1,3 @@
+counts_sum_min_thresh	0.0
+counts_sum_max_thresh	10669.31
+trainings_pts_post_thresh	181459

fold_2/logs.models.fold_2.ENCSR747RGR/logfile.modelling.fold_2.ENCSR747RGR.chrombpnet_formatting.stdout.txt

@@ -0,0 +1 @@
+Converting /oak/stanford/groups/akundaje/vhecht/chromatin_atlas_bias_corrected/DNASE_model/ENCSR747RGR/fold_2/models/chrombpnet.h5 to /oak/stanford/groups/akundaje/vhecht/chromatin-atlas-2022/DNASE/ENCSR747RGR/fold_2/new_model_format/chrombpnet.tar with get_new_tf_model_format.py

fold_2/logs.models.fold_2.ENCSR747RGR/logfile.modelling.fold_2.ENCSR747RGR.chrombpnet_model_params.tsv

@@ -0,0 +1,9 @@
+counts_loss_weight	7.8
+filters	512
+n_dil_layers	8
+bias_model_path	/oak/stanford/groups/akundaje/vhecht/chromatin_atlas_bias_corrected/DNASE_model/ENCSR747RGR/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.ENCSR747RGR/logfile.modelling.fold_2.ENCSR747RGR.chrombpnet_no_bias_formatting.stdout.txt

@@ -0,0 +1 @@
+Converting /oak/stanford/groups/akundaje/vhecht/chromatin_atlas_bias_corrected/DNASE_model/ENCSR747RGR/fold_2/models/chrombpnet_nobias.h5 to /oak/stanford/groups/akundaje/vhecht/chromatin-atlas-2022/DNASE/ENCSR747RGR/fold_2/new_model_format/chrombpnet_nobias.tar with get_new_tf_model_format.py

fold_2/logs.models.fold_2.ENCSR747RGR/logfile.modelling.fold_2.ENCSR747RGR.epoch_loss.csv

@@ -0,0 +1,12 @@
+epoch,logcount_predictions_loss,logits_profile_predictions_loss,loss,val_logcount_predictions_loss,val_logits_profile_predictions_loss,val_loss
+0,1.2453484535217285,473.9410400390625,483.6549377441406,0.4798350930213928,471.947509765625,475.69024658203125
+1,0.5229969024658203,446.8885803222656,450.96771240234375,0.5552623271942139,462.8897399902344,467.22076416015625
+2,0.4717894494533539,440.27630615234375,443.9562683105469,0.41866472363471985,456.68341064453125,459.94891357421875
+3,0.44981998205184937,435.8316345214844,439.3396301269531,0.38544532656669617,459.2462463378906,462.2528076171875
+4,0.4214244484901428,432.0452575683594,435.33184814453125,0.3733065128326416,458.7150573730469,461.6264343261719
+5,0.40587395429611206,428.7069091796875,431.87249755859375,0.4115147888660431,456.66204833984375,459.8719177246094
+6,0.38925597071647644,427.6155700683594,430.65167236328125,0.4359162449836731,461.0498962402344,464.44976806640625
+7,0.38452690839767456,424.5883483886719,427.587158203125,0.37431904673576355,462.58441162109375,465.5041809082031
+8,0.3722810447216034,423.2230529785156,426.1265869140625,0.42660751938819885,460.01373291015625,463.3412170410156
+9,0.365249365568161,420.97186279296875,423.821044921875,0.35803380608558655,464.0509033203125,466.8438415527344
+10,0.3589780330657959,420.3593444824219,423.15960693359375,0.3665141463279724,463.1448669433594,466.0039978027344

fold_2/model.bias_scaled.fold_2.ENCSR747RGR.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ccdfc2b7293b95f5bf2725b884d825b593332915b2130fbe66515d9e5d9000cf
+size 2691928

fold_2/model.bias_scaled.fold_2.ENCSR747RGR.tar

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:788022f462994dc2377b794c3b8c126b5cd6a46c46b39dd91ee70c4b417aff6b
+size 1198080

fold_2/model.chrombpnet.fold_2.ENCSR747RGR.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c9e27369c9cb1f5141ab48a4a5a301f0c97a2bea77e350ce06fb08c779442a8e
+size 77538840

fold_2/model.chrombpnet.fold_2.ENCSR747RGR.tar

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b29bc7636b4a04dc0b768a9b870e4940eb15cf0d459d98ea193693c1ca425495
+size 27525120

fold_2/model.chrombpnet_nobias.fold_2.ENCSR747RGR.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a6a805881135a6091fde6b5d4768072da521603231b332dbedc55a7d27c49595
+size 25582648

fold_2/model.chrombpnet_nobias.fold_2.ENCSR747RGR.tar

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:06e62cccbdc7459546d56c82717138c252df81246137be195847207d9ce32b15
+size 26060800

fold_3/logs.models.fold_3.ENCSR747RGR/logfile.modelling.fold_3.ENCSR747RGR.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/ENCSR747RGR/preprocessing/bigWigs/ENCSR747RGR.bigWig",
+    "input_fragment_file": null,
+    "input_tagalign_file": null,
+    "output_dir": "/oak/stanford/groups/akundaje/vhecht/chromatin_atlas_bias_corrected/DNASE_model/ENCSR747RGR/fold_3",
+    "data_type": "DNASE",
+    "peaks": "/oak/stanford/groups/akundaje/vhecht/chromatin_atlas_bias_corrected/DNASE_model/ENCSR747RGR/fold_3/auxiliary/filtered.peaks.bed",
+    "nonpeaks": "/oak/stanford/groups/akundaje/vhecht/chromatin_atlas_bias_corrected/DNASE_model/ENCSR747RGR/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/ENCSR747RGR/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/ENCSR747RGR/fold_3/models/chrombpnet",
+    "bigwig": "/oak/stanford/groups/akundaje/vhecht/chromatin_atlas_bias_corrected/DNASE_model/ENCSR747RGR/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/ENCSR747RGR/fold_3/logs/chrombpnet_model_params.tsv"
+}

fold_3/logs.models.fold_3.ENCSR747RGR/logfile.modelling.fold_3.ENCSR747RGR.bias_formatting.stdout.txt

@@ -0,0 +1 @@
+Converting /oak/stanford/groups/akundaje/vhecht/chromatin_atlas_bias_corrected/DNASE_model/ENCSR747RGR/fold_3/models/bias_model_scaled.h5 to /oak/stanford/groups/akundaje/vhecht/chromatin-atlas-2022/DNASE/ENCSR747RGR/fold_3/new_model_format/bias_model_scaled.tar with get_new_tf_model_format.py

fold_3/logs.models.fold_3.ENCSR747RGR/logfile.modelling.fold_3.ENCSR747RGR.chrombpnet_data_params.tsv

@@ -0,0 +1,3 @@
+counts_sum_min_thresh	0.0
+counts_sum_max_thresh	10694.34
+trainings_pts_post_thresh	170556

fold_3/logs.models.fold_3.ENCSR747RGR/logfile.modelling.fold_3.ENCSR747RGR.chrombpnet_formatting.stdout.txt

@@ -0,0 +1 @@
+Converting /oak/stanford/groups/akundaje/vhecht/chromatin_atlas_bias_corrected/DNASE_model/ENCSR747RGR/fold_3/models/chrombpnet.h5 to /oak/stanford/groups/akundaje/vhecht/chromatin-atlas-2022/DNASE/ENCSR747RGR/fold_3/new_model_format/chrombpnet.tar with get_new_tf_model_format.py

fold_3/logs.models.fold_3.ENCSR747RGR/logfile.modelling.fold_3.ENCSR747RGR.chrombpnet_model_params.tsv

@@ -0,0 +1,9 @@
+counts_loss_weight	7.8
+filters	512
+n_dil_layers	8
+bias_model_path	/oak/stanford/groups/akundaje/vhecht/chromatin_atlas_bias_corrected/DNASE_model/ENCSR747RGR/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.ENCSR747RGR/logfile.modelling.fold_3.ENCSR747RGR.chrombpnet_no_bias_formatting.stdout.txt

@@ -0,0 +1 @@
+Converting /oak/stanford/groups/akundaje/vhecht/chromatin_atlas_bias_corrected/DNASE_model/ENCSR747RGR/fold_3/models/chrombpnet_nobias.h5 to /oak/stanford/groups/akundaje/vhecht/chromatin-atlas-2022/DNASE/ENCSR747RGR/fold_3/new_model_format/chrombpnet_nobias.tar with get_new_tf_model_format.py