Upload folder using huggingface_hub

README.md

@@ -0,0 +1,120 @@
+---
+license: mit
+library_name: chrombpnet
+tags:
+  - encode
+  - chrombpnet
+  - chromatin-accessibility
+  - DNASE
+  - lung
+  - 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 right lung (ENCSR299INS)
+- Model: ChromBPNet
+- Assay: DNASE-seq
+- Experiment: [ENCSR299INS](https://www.encodeproject.org/experiments/ENCSR299INS/)
+- Model annotation: [ENCSR624DIU](https://www.encodeproject.org/annotations/ENCSR624DIU/)
+- Biosample: right lung (Full name: Homo sapiens right lung tissue female embryo (105 days))
+- Cell slim(s): None
+- Organ slim(s): lung
+- Developmental slim(s): endoderm
+- System slim(s): respiratory-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.ENCSR299INS/logfile.modelling.fold_0.ENCSR299INS.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/ENCSR299INS/preprocessing/bigWigs/ENCSR299INS.bigWig",
+    "output_dir": "/oak/stanford/groups/akundaje/ziwei75/chromatin_atlas_bias/DNase_model/bias_filtered/ENCSR299INS//fold0/",
+    "data_type": "DNASE",
+    "peaks": "/oak/stanford/groups/akundaje/ziwei75/chromatin_atlas_bias/DNase_model/bias_filtered/ENCSR299INS//fold0/auxiliary/filtered.peaks.bed",
+    "nonpeaks": "/oak/stanford/groups/akundaje/ziwei75/chromatin_atlas_bias/DNase_model/bias_filtered/ENCSR299INS//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/filtered_negatives_models/ENCSR299INS/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_filtered/ENCSR299INS//fold0/models/chrombpnet",
+    "chr": "chr8",
+    "pwm_width": 24,
+    "params": "/oak/stanford/groups/akundaje/ziwei75/chromatin_atlas_bias/DNase_model/bias_filtered/ENCSR299INS//fold0/logs/chrombpnet_model_params.tsv"
+}

fold_0/logs.models.fold_0.ENCSR299INS/logfile.modelling.fold_0.ENCSR299INS.bias_formatting.stdout.txt

@@ -0,0 +1 @@
+Converting /oak/stanford/groups/akundaje/ziwei75/chromatin_atlas_bias/DNase_model/bias_filtered/ENCSR299INS/fold0/models/bias_model_scaled.h5 to /oak/stanford/groups/akundaje/vhecht/chromatin-atlas-2022/DNASE/ENCSR299INS/fold_0/new_model_format/bias_model_scaled.tar with get_new_tf_model_format.py

fold_0/logs.models.fold_0.ENCSR299INS/logfile.modelling.fold_0.ENCSR299INS.chrombpnet_data_params.tsv

@@ -0,0 +1,3 @@
+counts_sum_min_thresh	0.0
+counts_sum_max_thresh	3676.26
+trainings_pts_post_thresh	170379

fold_0/logs.models.fold_0.ENCSR299INS/logfile.modelling.fold_0.ENCSR299INS.chrombpnet_formatting.stdout.txt

@@ -0,0 +1 @@
+Converting /oak/stanford/groups/akundaje/ziwei75/chromatin_atlas_bias/DNase_model/bias_filtered/ENCSR299INS/fold0/models/chrombpnet.h5 to /oak/stanford/groups/akundaje/vhecht/chromatin-atlas-2022/DNASE/ENCSR299INS/fold_0/new_model_format/chrombpnet.tar with get_new_tf_model_format.py

fold_0/logs.models.fold_0.ENCSR299INS/logfile.modelling.fold_0.ENCSR299INS.chrombpnet_model_params.tsv

@@ -0,0 +1,9 @@
+counts_loss_weight	9.5
+filters	512
+n_dil_layers	8
+bias_model_path	/oak/stanford/groups/akundaje/ziwei75/chromatin_atlas_bias/DNase_model/bias_filtered/ENCSR299INS//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.ENCSR299INS/logfile.modelling.fold_0.ENCSR299INS.chrombpnet_no_bias_formatting.stdout.txt

@@ -0,0 +1 @@
+Converting /oak/stanford/groups/akundaje/ziwei75/chromatin_atlas_bias/DNase_model/bias_filtered/ENCSR299INS/fold0/models/chrombpnet_nobias.h5 to /oak/stanford/groups/akundaje/vhecht/chromatin-atlas-2022/DNASE/ENCSR299INS/fold_0/new_model_format/chrombpnet_nobias.tar with get_new_tf_model_format.py

fold_0/logs.models.fold_0.ENCSR299INS/logfile.modelling.fold_0.ENCSR299INS.epoch_loss.csv

@@ -0,0 +1,13 @@
+epoch,logcount_predictions_loss,logits_profile_predictions_loss,loss,val_logcount_predictions_loss,val_logits_profile_predictions_loss,val_loss
+0,2.0044658184051514,407.354736328125,426.3971252441406,0.9529058337211609,398.51287841796875,407.5654296875
+1,0.8849955201148987,389.9696350097656,398.37774658203125,1.1361018419265747,395.7605895996094,406.55316162109375
+2,0.8066031336784363,384.7595520019531,392.42218017578125,0.8313305974006653,390.3385009765625,398.2359924316406
+3,0.7663715481758118,380.7339172363281,388.014892578125,0.7918302416801453,392.9501647949219,400.4725646972656
+4,0.7251124382019043,377.6830139160156,384.5717468261719,0.8197651505470276,387.8530578613281,395.6410217285156
+5,0.7022647261619568,375.9962158203125,382.66845703125,0.7162261009216309,390.8121032714844,397.6163635253906
+6,0.6790509819984436,373.4618835449219,379.9122619628906,0.6764617562294006,387.75860595703125,394.18487548828125
+7,0.6564476490020752,372.357421875,378.5939025878906,0.668582022190094,389.3092346191406,395.6607971191406
+8,0.6424672603607178,370.6844177246094,376.78778076171875,0.7020719647407532,388.42291259765625,395.0923156738281
+9,0.6232390999794006,369.3633117675781,375.2829895019531,0.6605405807495117,389.7886657714844,396.0639953613281
+10,0.6009427309036255,367.9281311035156,373.63739013671875,0.6732273101806641,391.5409851074219,397.9365234375
+11,0.5924471020698547,367.50811767578125,373.1361083984375,0.6665859818458557,390.54559326171875,396.8782653808594

fold_0/model.bias_scaled.fold_0.ENCSR299INS.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bb3fd1d75c216990e03c7fe7ea217035be856b225c9dbaf586fd284533368d95
+size 2691928

fold_0/model.bias_scaled.fold_0.ENCSR299INS.tar

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8c54a98e971c01fa8d211d7822b982ddeefa790a37c56de2b9d4058dad05c866
+size 1198080

fold_0/model.chrombpnet.fold_0.ENCSR299INS.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:38abaadd3a5ea0028ccee0cf5b69b32a63ab167b88f8c71018c156468e9af81a
+size 77538952

fold_0/model.chrombpnet.fold_0.ENCSR299INS.tar

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aedf09a90838d2cfac50cb8680de65595fe1c2921d3d4047df3b64464fbe0d4e
+size 27525120

fold_0/model.chrombpnet_nobias.fold_0.ENCSR299INS.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4924ade223c54bce85923c309bf79a9d3f4c0d101216224c8fa10eee395bd725
+size 25582648

fold_0/model.chrombpnet_nobias.fold_0.ENCSR299INS.tar

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:afd6cb1babcedfcc4badcb29c8b489ef55333201906af1e274d7c8f6319add9c
+size 26060800

fold_1/logs.models.fold_1.ENCSR299INS/logfile.modelling.fold_1.ENCSR299INS.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/ENCSR299INS/preprocessing/bigWigs/ENCSR299INS.bigWig",
+    "input_fragment_file": null,
+    "input_tagalign_file": null,
+    "output_dir": "/oak/stanford/groups/akundaje/vhecht/chromatin_atlas_bias_corrected/DNASE_model/ENCSR299INS/fold_1",
+    "data_type": "DNASE",
+    "peaks": "/oak/stanford/groups/akundaje/vhecht/chromatin_atlas_bias_corrected/DNASE_model/ENCSR299INS/fold_1/auxiliary/filtered.peaks.bed",
+    "nonpeaks": "/oak/stanford/groups/akundaje/vhecht/chromatin_atlas_bias_corrected/DNASE_model/ENCSR299INS/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/filtered_negatives_models/ENCSR299INS/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/ENCSR299INS/fold_1/models/chrombpnet",
+    "bigwig": "/oak/stanford/groups/akundaje/vhecht/chromatin_atlas_bias_corrected/DNASE_model/ENCSR299INS/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/ENCSR299INS/fold_1/logs/chrombpnet_model_params.tsv"
+}

fold_1/logs.models.fold_1.ENCSR299INS/logfile.modelling.fold_1.ENCSR299INS.bias_formatting.stdout.txt

@@ -0,0 +1 @@
+Converting /oak/stanford/groups/akundaje/vhecht/chromatin_atlas_bias_corrected/DNASE_model/ENCSR299INS/fold_1/models/bias_model_scaled.h5 to /oak/stanford/groups/akundaje/vhecht/chromatin-atlas-2022/DNASE/ENCSR299INS/fold_1/new_model_format/bias_model_scaled.tar with get_new_tf_model_format.py

fold_1/logs.models.fold_1.ENCSR299INS/logfile.modelling.fold_1.ENCSR299INS.chrombpnet_data_params.tsv

@@ -0,0 +1,3 @@
+counts_sum_min_thresh	0.0
+counts_sum_max_thresh	3674.96
+trainings_pts_post_thresh	173714

fold_1/logs.models.fold_1.ENCSR299INS/logfile.modelling.fold_1.ENCSR299INS.chrombpnet_formatting.stdout.txt

@@ -0,0 +1 @@
+Converting /oak/stanford/groups/akundaje/vhecht/chromatin_atlas_bias_corrected/DNASE_model/ENCSR299INS/fold_1/models/chrombpnet.h5 to /oak/stanford/groups/akundaje/vhecht/chromatin-atlas-2022/DNASE/ENCSR299INS/fold_1/new_model_format/chrombpnet.tar with get_new_tf_model_format.py

fold_1/logs.models.fold_1.ENCSR299INS/logfile.modelling.fold_1.ENCSR299INS.chrombpnet_model_params.tsv

@@ -0,0 +1,9 @@
+counts_loss_weight	9.5
+filters	512
+n_dil_layers	8
+bias_model_path	/oak/stanford/groups/akundaje/vhecht/chromatin_atlas_bias_corrected/DNASE_model/ENCSR299INS/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.ENCSR299INS/logfile.modelling.fold_1.ENCSR299INS.chrombpnet_no_bias_formatting.stdout.txt

@@ -0,0 +1 @@
+Converting /oak/stanford/groups/akundaje/vhecht/chromatin_atlas_bias_corrected/DNASE_model/ENCSR299INS/fold_1/models/chrombpnet_nobias.h5 to /oak/stanford/groups/akundaje/vhecht/chromatin-atlas-2022/DNASE/ENCSR299INS/fold_1/new_model_format/chrombpnet_nobias.tar with get_new_tf_model_format.py

fold_1/logs.models.fold_1.ENCSR299INS/logfile.modelling.fold_1.ENCSR299INS.epoch_loss.csv

@@ -0,0 +1,14 @@
+epoch,logcount_predictions_loss,logits_profile_predictions_loss,loss,val_logcount_predictions_loss,val_logits_profile_predictions_loss,val_loss
+0,3.2694215774536133,409.2376403808594,440.2969970703125,0.9868219494819641,469.99365234375,479.3683166503906
+1,0.9503605961799622,390.123291015625,399.1513366699219,0.8648077845573425,461.8839416503906,470.09979248046875
+2,0.8720584511756897,385.47650146484375,393.7609558105469,0.7773147225379944,453.6208801269531,461.00531005859375
+3,0.8111585974693298,381.357177734375,389.0633544921875,0.8067960143089294,451.7127380371094,459.3771667480469
+4,0.7706909775733948,378.433837890625,385.7557067871094,0.7877694368362427,452.0272216796875,459.5110778808594
+5,0.7349733114242554,376.091796875,383.07354736328125,0.7630680799484253,446.8045654296875,454.05364990234375
+6,0.7126445770263672,373.64923095703125,380.4194641113281,0.6809223294258118,448.08837890625,454.55731201171875
+7,0.6709076762199402,371.0446472167969,377.4185791015625,0.7001804113388062,445.9004211425781,452.55218505859375
+8,0.6556457877159119,369.6400451660156,375.86834716796875,0.8752992749214172,449.5173034667969,457.8324890136719
+9,0.6364076733589172,367.7270812988281,373.77337646484375,0.6667841076850891,447.5584411621094,453.892333984375
+10,0.6103054285049438,366.1277770996094,371.9261779785156,0.6531592011451721,450.1517639160156,456.3570556640625
+11,0.5994511246681213,365.58477783203125,371.2799072265625,0.6658178567886353,449.4888610839844,455.8144226074219
+12,0.5784355998039246,364.2674255371094,369.76214599609375,0.6734664440155029,448.2718505859375,454.6698303222656

fold_1/model.bias_scaled.fold_1.ENCSR299INS.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1c3a2bf37e86def7b6c9c63bf21165c14f54e23ba4ab18b3541af54b4f2ebea9
+size 2691928

fold_1/model.bias_scaled.fold_1.ENCSR299INS.tar

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5c90dbe77428186e63c3938566102e37c3ce9efb922616eea7f05ca856c2c91f
+size 1198080

fold_1/model.chrombpnet.fold_1.ENCSR299INS.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7b6316ba770a3ea4f20f8478841bd62fe28efa6c49914f35197c38825751c4c1
+size 77538840

fold_1/model.chrombpnet.fold_1.ENCSR299INS.tar

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fb6562510163a065355c9c1ecf478b23e2b2cabceb1f2024d0c66f84d8ae896b
+size 27525120

fold_1/model.chrombpnet_nobias.fold_1.ENCSR299INS.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cb03130ddaf894ce588df94207dc93eb676569c2b9ba43a73133d4965c4beeaf
+size 25582648

fold_1/model.chrombpnet_nobias.fold_1.ENCSR299INS.tar

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1d294088367196599c9382b2c94b1a4423e5fbdd36fbc830eb4ceedaee21fe99
+size 26060800

fold_2/logs.models.fold_2.ENCSR299INS/logfile.modelling.fold_2.ENCSR299INS.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/ENCSR299INS/preprocessing/bigWigs/ENCSR299INS.bigWig",
+    "input_fragment_file": null,
+    "input_tagalign_file": null,
+    "output_dir": "/oak/stanford/groups/akundaje/vhecht/chromatin_atlas_bias_corrected/DNASE_model/ENCSR299INS/fold_2",
+    "data_type": "DNASE",
+    "peaks": "/oak/stanford/groups/akundaje/vhecht/chromatin_atlas_bias_corrected/DNASE_model/ENCSR299INS/fold_2/auxiliary/filtered.peaks.bed",
+    "nonpeaks": "/oak/stanford/groups/akundaje/vhecht/chromatin_atlas_bias_corrected/DNASE_model/ENCSR299INS/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/filtered_negatives_models/ENCSR299INS/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/ENCSR299INS/fold_2/models/chrombpnet",
+    "bigwig": "/oak/stanford/groups/akundaje/vhecht/chromatin_atlas_bias_corrected/DNASE_model/ENCSR299INS/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/ENCSR299INS/fold_2/logs/chrombpnet_model_params.tsv"
+}

fold_2/logs.models.fold_2.ENCSR299INS/logfile.modelling.fold_2.ENCSR299INS.bias_formatting.stdout.txt

@@ -0,0 +1 @@
+Converting /oak/stanford/groups/akundaje/vhecht/chromatin_atlas_bias_corrected/DNASE_model/ENCSR299INS/fold_2/models/bias_model_scaled.h5 to /oak/stanford/groups/akundaje/vhecht/chromatin-atlas-2022/DNASE/ENCSR299INS/fold_2/new_model_format/bias_model_scaled.tar with get_new_tf_model_format.py

fold_2/logs.models.fold_2.ENCSR299INS/logfile.modelling.fold_2.ENCSR299INS.chrombpnet_data_params.tsv

@@ -0,0 +1,3 @@
+counts_sum_min_thresh	0.0
+counts_sum_max_thresh	3844.95
+trainings_pts_post_thresh	178710

fold_2/logs.models.fold_2.ENCSR299INS/logfile.modelling.fold_2.ENCSR299INS.chrombpnet_formatting.stdout.txt

@@ -0,0 +1 @@
+Converting /oak/stanford/groups/akundaje/vhecht/chromatin_atlas_bias_corrected/DNASE_model/ENCSR299INS/fold_2/models/chrombpnet.h5 to /oak/stanford/groups/akundaje/vhecht/chromatin-atlas-2022/DNASE/ENCSR299INS/fold_2/new_model_format/chrombpnet.tar with get_new_tf_model_format.py

fold_2/logs.models.fold_2.ENCSR299INS/logfile.modelling.fold_2.ENCSR299INS.chrombpnet_model_params.tsv

@@ -0,0 +1,9 @@
+counts_loss_weight	9.5
+filters	512
+n_dil_layers	8
+bias_model_path	/oak/stanford/groups/akundaje/vhecht/chromatin_atlas_bias_corrected/DNASE_model/ENCSR299INS/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.ENCSR299INS/logfile.modelling.fold_2.ENCSR299INS.chrombpnet_no_bias_formatting.stdout.txt

@@ -0,0 +1 @@
+Converting /oak/stanford/groups/akundaje/vhecht/chromatin_atlas_bias_corrected/DNASE_model/ENCSR299INS/fold_2/models/chrombpnet_nobias.h5 to /oak/stanford/groups/akundaje/vhecht/chromatin-atlas-2022/DNASE/ENCSR299INS/fold_2/new_model_format/chrombpnet_nobias.tar with get_new_tf_model_format.py

fold_2/logs.models.fold_2.ENCSR299INS/logfile.modelling.fold_2.ENCSR299INS.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
+0,1.7862237691879272,407.2773132324219,424.2464904785156,1.1235997676849365,416.4328308105469,427.10699462890625
+1,0.8818398714065552,389.2347106933594,397.6127624511719,0.8678457736968994,409.98333740234375,418.22772216796875
+2,0.8129622340202332,384.37109375,392.09417724609375,0.766974687576294,406.9416198730469,414.2275390625
+3,0.7657344341278076,380.72113037109375,387.9958190917969,0.7531278729438782,405.29754638671875,412.452392578125
+4,0.7268348336219788,377.8879089355469,384.79296875,0.751449465751648,401.8074645996094,408.946044921875
+5,0.6981989741325378,375.72412109375,382.3564758300781,0.7057041525840759,403.2260437011719,409.9308776855469
+6,0.6657394170761108,373.5740966796875,379.8984069824219,0.7069109678268433,402.4052429199219,409.12109375
+7,0.6454981565475464,371.9115295410156,378.0442199707031,0.7584488391876221,401.1718444824219,408.3770751953125
+8,0.630329966545105,370.33526611328125,376.3243713378906,0.7100486755371094,405.9042053222656,412.64990234375
+9,0.614305317401886,368.9599609375,374.7961120605469,0.7212152481079102,403.25750732421875,410.1092529296875
+10,0.5967612862586975,368.1210632324219,373.7904357910156,0.7654650807380676,403.8367004394531,411.10858154296875
+11,0.5818486213684082,367.17529296875,372.70294189453125,0.7088703513145447,402.21929931640625,408.9534912109375
+12,0.5659429430961609,365.7784423828125,371.1546936035156,0.6798276305198669,403.7816162109375,410.24005126953125

fold_2/model.bias_scaled.fold_2.ENCSR299INS.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:89d4ded3f54fa93d8b3fee81239c126ec7ace6e50dd01c1913892f97a9e6e75c
+size 2691928

fold_2/model.bias_scaled.fold_2.ENCSR299INS.tar

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9ea245357c78fd23a2ff44b629d1dbd4ee568d2d0353340272f50304ba38a0bd
+size 1198080

fold_2/model.chrombpnet.fold_2.ENCSR299INS.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8c5e0fc99fd85b418e54d4d8ed56622998c9421d241564485989a2ff3d1f7941
+size 77538840

fold_2/model.chrombpnet.fold_2.ENCSR299INS.tar

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9dc29bd224385e5102774222e08de3a93a5121602f6263f694896007494a59a0
+size 27525120

fold_2/model.chrombpnet_nobias.fold_2.ENCSR299INS.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2d5c8e3f55afa3c09c16cc409074ee1c3290b691b10b950fd719356fa59225fd
+size 25582648

fold_2/model.chrombpnet_nobias.fold_2.ENCSR299INS.tar

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1e00d6292821a6b08c4cc24d5fe591760db517681cb36685bfc5b7edc8cc2a85
+size 26060800

fold_3/logs.models.fold_3.ENCSR299INS/logfile.modelling.fold_3.ENCSR299INS.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/ENCSR299INS/preprocessing/bigWigs/ENCSR299INS.bigWig",
+    "input_fragment_file": null,
+    "input_tagalign_file": null,
+    "output_dir": "/oak/stanford/groups/akundaje/vhecht/chromatin_atlas_bias_corrected/DNASE_model/ENCSR299INS/fold_3",
+    "data_type": "DNASE",
+    "peaks": "/oak/stanford/groups/akundaje/vhecht/chromatin_atlas_bias_corrected/DNASE_model/ENCSR299INS/fold_3/auxiliary/filtered.peaks.bed",
+    "nonpeaks": "/oak/stanford/groups/akundaje/vhecht/chromatin_atlas_bias_corrected/DNASE_model/ENCSR299INS/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/filtered_negatives_models/ENCSR299INS/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/ENCSR299INS/fold_3/models/chrombpnet",
+    "bigwig": "/oak/stanford/groups/akundaje/vhecht/chromatin_atlas_bias_corrected/DNASE_model/ENCSR299INS/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/ENCSR299INS/fold_3/logs/chrombpnet_model_params.tsv"
+}

fold_3/logs.models.fold_3.ENCSR299INS/logfile.modelling.fold_3.ENCSR299INS.bias_formatting.stdout.txt

@@ -0,0 +1 @@
+Converting /oak/stanford/groups/akundaje/vhecht/chromatin_atlas_bias_corrected/DNASE_model/ENCSR299INS/fold_3/models/bias_model_scaled.h5 to /oak/stanford/groups/akundaje/vhecht/chromatin-atlas-2022/DNASE/ENCSR299INS/fold_3/new_model_format/bias_model_scaled.tar with get_new_tf_model_format.py

fold_3/logs.models.fold_3.ENCSR299INS/logfile.modelling.fold_3.ENCSR299INS.chrombpnet_data_params.tsv

@@ -0,0 +1,3 @@
+counts_sum_min_thresh	0.0
+counts_sum_max_thresh	3877.97
+trainings_pts_post_thresh	172456

fold_3/logs.models.fold_3.ENCSR299INS/logfile.modelling.fold_3.ENCSR299INS.chrombpnet_formatting.stdout.txt

@@ -0,0 +1 @@
+Converting /oak/stanford/groups/akundaje/vhecht/chromatin_atlas_bias_corrected/DNASE_model/ENCSR299INS/fold_3/models/chrombpnet.h5 to /oak/stanford/groups/akundaje/vhecht/chromatin-atlas-2022/DNASE/ENCSR299INS/fold_3/new_model_format/chrombpnet.tar with get_new_tf_model_format.py

fold_3/logs.models.fold_3.ENCSR299INS/logfile.modelling.fold_3.ENCSR299INS.chrombpnet_model_params.tsv

@@ -0,0 +1,9 @@
+counts_loss_weight	9.6
+filters	512
+n_dil_layers	8
+bias_model_path	/oak/stanford/groups/akundaje/vhecht/chromatin_atlas_bias_corrected/DNASE_model/ENCSR299INS/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.ENCSR299INS/logfile.modelling.fold_3.ENCSR299INS.chrombpnet_no_bias_formatting.stdout.txt

@@ -0,0 +1 @@
+Converting /oak/stanford/groups/akundaje/vhecht/chromatin_atlas_bias_corrected/DNASE_model/ENCSR299INS/fold_3/models/chrombpnet_nobias.h5 to /oak/stanford/groups/akundaje/vhecht/chromatin-atlas-2022/DNASE/ENCSR299INS/fold_3/new_model_format/chrombpnet_nobias.tar with get_new_tf_model_format.py