Upload folder using huggingface_hub

README.md

@@ -0,0 +1,120 @@
+---
+license: mit
+library_name: chrombpnet
+tags:
+  - encode
+  - chrombpnet
+  - chromatin-accessibility
+  - DNASE
+  - kidney
+  - 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 kidney (ENCSR871APX)
+- Model: ChromBPNet
+- Assay: DNASE-seq
+- Experiment: [ENCSR871APX](https://www.encodeproject.org/experiments/ENCSR871APX/)
+- Model annotation: [ENCSR132IOD](https://www.encodeproject.org/annotations/ENCSR132IOD/)
+- Biosample: right kidney (Full name: Homo sapiens right kidney tissue female embryo (147 days))
+- Cell slim(s): None
+- Organ slim(s): kidney
+- Developmental slim(s): mesoderm
+- System slim(s): excretory-system
+- Assembly: hg38
+
+## Directory structure
+- `fold_0`: Model of 5-fold cross-validation: Fold 0
+    - `model.chrombpnet.fold_0.encid.h5`: full chrombpnet model that combines both bias and corrected model in .h5 format
+    - `model.chrombpnet_nobias.fold_0.encid.h5`: bias-corrected accessibility model in .h5 format (Use for all biological discovery)
+    - `model.bias_scaled.fold_0.encid.h5`: bias model in .h5 format
+    - `model.chrombpnet.fold_0.encid.tar`: full chrombpnet model that combines both bias and  corrected model in SavedModel format. After being untarred, it results in a directory named "chrombpnet".
+    - `model.chrombpnet_nobias.fold_0.encid.tar`: bias-corrected accessibility model in SavedModel format (Use for all biological discovery). After being untarred, it results in a directory named "chrombpnet_wo_bias".
+    - `model.bias_scaled.fold_0.encid.tar`: bias model in SavedModel format. After being untarred, it results in a directory named "bias_model_scaled".
+    - `logs.models.fold_0.encid`: folder containing log files for training models
+- `fold_1`: Model of 5-fold coss-validation: Fold 1
+- `fold_2`: Model of 5-fold cross-validation: Fold 2
+- `fold_3`: Model of 5-fold cross-validation: Fold 3
+- `fold_4`: Model of 5-fold cross-validation: Fold 4
+
+# Instructions
+## 1. Pseudocode for loading models in .h5 format 
+
+(1) Use the code in python after appropriately defining `model_in_h5_format` and `inputs`. \
+(2) `inputs` is a one hot encoded sequence of shape (N,2114,4). Here N corresponds to the 
+number of tested sequences, 2114 is the input sequence length and 4 corresponds to [A,C,G,T].
+
+```python
+import tensorflow as tf
+from tensorflow.keras.utils import get_custom_objects
+from tensorflow.keras.models import load_model
+
+custom_objects={"tf": tf}
+get_custom_objects().update(custom_objects)
+
+model=load_model(model_in_h5_format,compile=False)
+outputs = model(inputs)
+```
+
+The list `outputs` consists of two elements. The first element has a shape of (N, 1000) and
+contains logit predictions for a 1000-base-pair output. The second element, with a shape of
+(N, 1), contains logcount predictions. To transform these predictions into per-base signals, 
+follow the provided pseudo code lines below.
+
+```python
+import numpy as np
+
+def softmax(x, temp=1):
+    norm_x = x - np.mean(x,axis=1, keepdims=True)
+    return np.exp(temp*norm_x)/np.sum(np.exp(temp*norm_x), axis=1, keepdims=True)
+    
+predictions = softmax(outputs[0]) * (np.exp(outputs[1])-1)
+```
+
+## 2. Pseudocode for loading models in .tar format
+
+(1) First untar the directory as follows `tar -xvf model.tar`. \
+(2) Use the code below in python after appropriately defining `model_dir_untared` and `inputs`. \
+(3) `inputs` is a one hot encoded sequence of shape (N,2114,4). Here N corresponds to the number
+of tested sequences, 2114 is the input sequence length and 4 corresponds to ACGT.
+
+Reference: https://www.tensorflow.org/api_docs/python/tf/saved_model/load
+
+```python
+import tensorflow as tf
+
+model = tf.saved_model.load('model_dir_untared')
+outputs = model.signatures['serving_default'](**{'sequence':inputs.astype('float32')})
+```
+
+The variable `outputs` represents a dictionary containing two key-value pairs. The first key
+is `logits_profile_predictions`, holding a value with a shape of (N, 1000). This value corresponds
+to logit predictions for a 1000-base-pair output. The second key, named `logcount_predictions``, 
+is associated with a value of shape (N, 1), representing logcount predictions. To transform these
+predictions into per-base signals, utilize the provided pseudo code lines mentioned below.
+
+```python
+import numpy as np
+def softmax(x, temp=1):
+    norm_x = x - np.mean(x,axis=1, keepdims=True)
+    return np.exp(temp*norm_x)/np.sum(np.exp(temp*norm_x), axis=1, keepdims=True)
+    
+predictions = softmax(outputs["logits_profile_predictions"]) * (np.exp(outputs["logcount_predictions"])-1)
+```
+
+## Docker image to load and use the models
+- https://hub.docker.com/r/kundajelab/chrombpnet-atlas/ (tag:v1)
+
+## Code for ChromBPNet
+- https://github.com/kundajelab/chrombpnet/
+
+# License & citation
+External data users may freely download, analyze and publish results based on any ENCODE data without restrictions.
+
+Released under the [ENCODE data-use policy](https://www.encodeproject.org/about/data-use-policy/). Please cite the ENCODE Project Consortium and the model software: [ChromBPNet](https://github.com/kundajelab/chrombpnet) (Pampari et al., bioRxiv 2024).

fold_0/logs.models.fold_0.ENCSR871APX/logfile.modelling.fold_0.ENCSR871APX.args.json

@@ -0,0 +1,45 @@
+{
+    "cmd": "pipeline",
+    "genome": "/scratch/groups/akundaje/anusri/chromatin_atlas/reference//hg38.genome.fa",
+    "chrom_sizes": "/scratch/groups/akundaje/anusri/chromatin_atlas/reference//chrom.sizes",
+    "input_bam_file": null,
+    "input_fragment_file": null,
+    "input_tagalign_file": null,
+    "bigwig": "/oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/DNASE//ENCSR871APX//preprocessing/bigWigs/ENCSR871APX.bigWig",
+    "output_dir": "/scratch/groups/akundaje/anusri/chromatin_atlas/DNASE/ENCSR871APX//chrombpnet_model_feb22_fold_0/chrombpnet_model/",
+    "data_type": "DNASE",
+    "peaks": "/scratch/groups/akundaje/anusri/chromatin_atlas/DNASE/ENCSR871APX//chrombpnet_model_feb22_fold_0/chrombpnet_model/auxiliary/ENCSR871APX_filtered.peaks.bed",
+    "nonpeaks": "/scratch/groups/akundaje/anusri/chromatin_atlas/DNASE/ENCSR871APX//chrombpnet_model_feb22_fold_0/chrombpnet_model/auxiliary/ENCSR871APX_filtered.nonpeaks.bed",
+    "chr_fold_path": "/scratch/groups/akundaje/anusri/chromatin_atlas/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/anusri/simg/chrombpnet_latest/chrombpnet/chrombpnet/training/models/chrombpnet_with_bias_model.py",
+    "file_prefix": "ENCSR871APX",
+    "html_prefix": "./",
+    "bias_model_path": "/scratch/groups/akundaje/anusri/chromatin_atlas/DNASE/ENCSR871APX//chrombpnet_model_feb22_fold_0/bias_model/models/ENCSR871APX_bias.h5",
+    "negative_sampling_ratio": 0.1,
+    "filters": 512,
+    "n_dilation_layers": 8,
+    "max_jitter": 500,
+    "batch_size": 64,
+    "output_prefix": "/scratch/groups/akundaje/anusri/chromatin_atlas/DNASE/ENCSR871APX//chrombpnet_model_feb22_fold_0/chrombpnet_model/models/ENCSR871APX_chrombpnet",
+    "chr": "chr8",
+    "pwm_width": 24,
+    "params": "/scratch/groups/akundaje/anusri/chromatin_atlas/DNASE/ENCSR871APX//chrombpnet_model_feb22_fold_0/chrombpnet_model/logs/ENCSR871APX_chrombpnet_model_params.tsv"
+}

fold_0/logs.models.fold_0.ENCSR871APX/logfile.modelling.fold_0.ENCSR871APX.bias_formatting.stdout.txt

@@ -0,0 +1 @@
+Converting /oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/DNASE/ENCSR871APX/failed_models_retrained/chrombpnet_model_feb22_fold_0/chrombpnet_model/models/ENCSR871APX_bias_model_scaled.h5 to /oak/stanford/groups/akundaje/vhecht/chromatin-atlas-2022/DNASE/ENCSR871APX/fold_0/new_model_format/bias_model_scaled.tar with get_new_tf_model_format.py

fold_0/logs.models.fold_0.ENCSR871APX/logfile.modelling.fold_0.ENCSR871APX.chrombpnet_data_params.tsv

@@ -0,0 +1,3 @@
+counts_sum_min_thresh	0.0
+counts_sum_max_thresh	1697.58
+trainings_pts_post_thresh	171376

fold_0/logs.models.fold_0.ENCSR871APX/logfile.modelling.fold_0.ENCSR871APX.chrombpnet_formatting.stdout.txt

@@ -0,0 +1 @@
+Converting /oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/DNASE/ENCSR871APX/failed_models_retrained/chrombpnet_model_feb22_fold_0/chrombpnet_model/models/ENCSR871APX_chrombpnet.h5 to /oak/stanford/groups/akundaje/vhecht/chromatin-atlas-2022/DNASE/ENCSR871APX/fold_0/new_model_format/chrombpnet.tar with get_new_tf_model_format.py

fold_0/logs.models.fold_0.ENCSR871APX/logfile.modelling.fold_0.ENCSR871APX.chrombpnet_model_params.tsv

@@ -0,0 +1,9 @@
+counts_loss_weight	5.1
+filters	512
+n_dil_layers	8
+bias_model_path	/scratch/groups/akundaje/anusri/chromatin_atlas/DNASE/ENCSR871APX//chrombpnet_model_feb22_fold_0/chrombpnet_model/models/ENCSR871APX_bias_model_scaled.h5
+inputlen	2114
+outputlen	1000
+max_jitter	500
+chr_fold_path	/scratch/groups/akundaje/anusri/chromatin_atlas/splits/fold_0.json
+negative_sampling_ratio	0.1

fold_0/logs.models.fold_0.ENCSR871APX/logfile.modelling.fold_0.ENCSR871APX.chrombpnet_no_bias_formatting.stdout.txt

@@ -0,0 +1 @@
+Converting /oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/DNASE/ENCSR871APX/failed_models_retrained/chrombpnet_model_feb22_fold_0/chrombpnet_model/models/ENCSR871APX_chrombpnet_nobias.h5 to /oak/stanford/groups/akundaje/vhecht/chromatin-atlas-2022/DNASE/ENCSR871APX/fold_0/new_model_format/chrombpnet_nobias.tar with get_new_tf_model_format.py

fold_0/logs.models.fold_0.ENCSR871APX/logfile.modelling.fold_0.ENCSR871APX.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
+0,2.0337893962860107,234.23770141601562,244.60977172851562,0.5834267735481262,230.37353515625,233.3489532470703
+1,0.5720600485801697,228.03683471679688,230.95445251464844,0.5348910093307495,228.36563110351562,231.0935516357422
+2,0.5203266739845276,226.06210327148438,228.7155303955078,0.5115373730659485,227.40298461914062,230.01181030273438
+3,0.49313241243362427,224.8061065673828,227.32119750976562,0.46285706758499146,226.7898406982422,229.15048217773438
+4,0.4671780467033386,224.03448486328125,226.4169158935547,0.4194790720939636,226.75282287597656,228.89208984375
+5,0.44377565383911133,223.14669799804688,225.40940856933594,0.4411715865135193,226.44729614257812,228.6971893310547
+6,0.42485615611076355,222.20138549804688,224.36822509765625,0.40463152527809143,224.2241973876953,226.28797912597656
+7,0.415470153093338,221.3678436279297,223.48672485351562,0.43943989276885986,225.45362854003906,227.69468688964844
+8,0.40160322189331055,220.7429656982422,222.79090881347656,0.4125784635543823,227.16583251953125,229.27000427246094
+9,0.389480322599411,220.26914978027344,222.25540161132812,0.39712923765182495,226.19293212890625,228.2183837890625
+10,0.3810652792453766,219.59765625,221.5409698486328,0.4016355276107788,225.6121063232422,227.66050720214844
+11,0.37579068541526794,218.7931365966797,220.70947265625,0.39375489950180054,226.5655059814453,228.57373046875

fold_0/model.bias_scaled.fold_0.ENCSR871APX.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b78409a46046f0afc6952a9b0f92c57ed7fd1320f6e5f55c5a7ff266953d06d7
+size 2691928

fold_0/model.bias_scaled.fold_0.ENCSR871APX.tar

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6b662296a8119c66f1eb9d3483de837a4134d601d8db01ffad6f39e6d0faf323
+size 1198080

fold_0/model.chrombpnet.fold_0.ENCSR871APX.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f487b2f63cad4c9da984bdbdcf9205b7ca02e7e0b297de533582394b10a222cd
+size 77538904

fold_0/model.chrombpnet.fold_0.ENCSR871APX.tar

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5a28199e2856d66ebb79fb8caa7f4f7fd52aec83fa41e1c2d01be005ab1b0f5c
+size 27525120

fold_0/model.chrombpnet_nobias.fold_0.ENCSR871APX.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:51cb6b3e4bec8f2ee81d5dabe4e40a6de50dac16cb3766ed5bc89703ac301b15
+size 25582648

fold_0/model.chrombpnet_nobias.fold_0.ENCSR871APX.tar

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:19ab2ffed6a866e4f2899e39cfad31e5dd11ff478744e681bb216bb016ed8ac7
+size 26060800

fold_1/logs.models.fold_1.ENCSR871APX/logfile.modelling.fold_1.ENCSR871APX.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/ENCSR871APX/preprocessing/bigWigs/ENCSR871APX.bigWig",
+    "input_fragment_file": null,
+    "input_tagalign_file": null,
+    "output_dir": "/oak/stanford/groups/akundaje/vhecht/chromatin_atlas_bias_corrected/DNASE_model/ENCSR871APX/fold_1",
+    "data_type": "DNASE",
+    "peaks": "/oak/stanford/groups/akundaje/vhecht/chromatin_atlas_bias_corrected/DNASE_model/ENCSR871APX/fold_1/auxiliary/filtered.peaks.bed",
+    "nonpeaks": "/oak/stanford/groups/akundaje/vhecht/chromatin_atlas_bias_corrected/DNASE_model/ENCSR871APX/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/projects/chromatin-atlas-2022/DNASE/ENCSR871APX/failed_models_retrained/chrombpnet_model_feb22_fold_0/bias_model/models/ENCSR871APX_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/ENCSR871APX/fold_1/models/chrombpnet",
+    "bigwig": "/oak/stanford/groups/akundaje/vhecht/chromatin_atlas_bias_corrected/DNASE_model/ENCSR871APX/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/ENCSR871APX/fold_1/logs/chrombpnet_model_params.tsv"
+}

fold_1/logs.models.fold_1.ENCSR871APX/logfile.modelling.fold_1.ENCSR871APX.bias_formatting.stdout.txt

@@ -0,0 +1 @@
+Converting /oak/stanford/groups/akundaje/vhecht/chromatin_atlas_bias_corrected/DNASE_model/ENCSR871APX/fold_1/models/bias_model_scaled.h5 to /oak/stanford/groups/akundaje/vhecht/chromatin-atlas-2022/DNASE/ENCSR871APX/fold_1/new_model_format/bias_model_scaled.tar with get_new_tf_model_format.py

fold_1/logs.models.fold_1.ENCSR871APX/logfile.modelling.fold_1.ENCSR871APX.chrombpnet_data_params.tsv

@@ -0,0 +1,3 @@
+counts_sum_min_thresh	0.0
+counts_sum_max_thresh	1692.9
+trainings_pts_post_thresh	173788

fold_1/logs.models.fold_1.ENCSR871APX/logfile.modelling.fold_1.ENCSR871APX.chrombpnet_formatting.stdout.txt

@@ -0,0 +1 @@
+Converting /oak/stanford/groups/akundaje/vhecht/chromatin_atlas_bias_corrected/DNASE_model/ENCSR871APX/fold_1/models/chrombpnet.h5 to /oak/stanford/groups/akundaje/vhecht/chromatin-atlas-2022/DNASE/ENCSR871APX/fold_1/new_model_format/chrombpnet.tar with get_new_tf_model_format.py

fold_1/logs.models.fold_1.ENCSR871APX/logfile.modelling.fold_1.ENCSR871APX.chrombpnet_model_params.tsv

@@ -0,0 +1,9 @@
+counts_loss_weight	5.1
+filters	512
+n_dil_layers	8
+bias_model_path	/oak/stanford/groups/akundaje/vhecht/chromatin_atlas_bias_corrected/DNASE_model/ENCSR871APX/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.ENCSR871APX/logfile.modelling.fold_1.ENCSR871APX.chrombpnet_no_bias_formatting.stdout.txt

@@ -0,0 +1 @@
+Converting /oak/stanford/groups/akundaje/vhecht/chromatin_atlas_bias_corrected/DNASE_model/ENCSR871APX/fold_1/models/chrombpnet_nobias.h5 to /oak/stanford/groups/akundaje/vhecht/chromatin-atlas-2022/DNASE/ENCSR871APX/fold_1/new_model_format/chrombpnet_nobias.tar with get_new_tf_model_format.py

fold_1/logs.models.fold_1.ENCSR871APX/logfile.modelling.fold_1.ENCSR871APX.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
+0,2.2415997982025146,233.67678833007812,245.10870361328125,0.8924901485443115,262.8577575683594,267.4094543457031
+1,0.5764709711074829,226.69320678710938,229.63348388671875,0.8072852492332458,261.04888916015625,265.16607666015625
+2,0.5299411416053772,225.2480926513672,227.95101928710938,0.49726641178131104,260.31982421875,262.8558654785156
+3,0.49545150995254517,223.59165954589844,226.11830139160156,0.4776497483253479,259.8454895019531,262.2817687988281
+4,0.46709638833999634,222.59291076660156,224.97511291503906,0.4777815341949463,257.163330078125,259.599853515625
+5,0.450275719165802,221.70069885253906,223.9971923828125,0.54720538854599,257.6120300292969,260.4027404785156
+6,0.43315568566322327,221.1971893310547,223.40594482421875,0.43259093165397644,257.962890625,260.1691589355469
+7,0.4233977496623993,220.11761474609375,222.2767333984375,0.42515280842781067,257.0703430175781,259.238525390625
+8,0.407671183347702,219.89964294433594,221.97862243652344,0.4217776954174042,258.3819885253906,260.5330810546875
+9,0.39629265666007996,219.03091430664062,221.05218505859375,0.4240971505641937,257.80267333984375,259.9656066894531
+10,0.38893428444862366,218.24501037597656,220.2287139892578,0.426658570766449,258.16778564453125,260.34356689453125
+11,0.3778766095638275,217.92727661132812,219.85401916503906,0.4118932783603668,258.9065246582031,261.0069885253906
+12,0.3714500665664673,217.14988708496094,219.04443359375,0.4221433997154236,258.66595458984375,260.8189392089844

fold_1/model.bias_scaled.fold_1.ENCSR871APX.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5e81ce8200fa23900065fcbce20b3d776b08b8a3c75e96a03d19376545728d53
+size 2691928

fold_1/model.bias_scaled.fold_1.ENCSR871APX.tar

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0b5b2528c855e5f761499e8a114835a90967b1039a706b4008676b39b864172f
+size 1198080

fold_1/model.chrombpnet.fold_1.ENCSR871APX.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:93fdb49f0dfba4d70bb753bacb0c43e64d331e8d3926ac850cafee1e3d69e66f
+size 77538840

fold_1/model.chrombpnet.fold_1.ENCSR871APX.tar

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2c22f1736cb2ba0b04a2fe8deeb63934d6158864030955d6fa89c920e98f02ad
+size 27525120

fold_1/model.chrombpnet_nobias.fold_1.ENCSR871APX.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4a2fcdfeddb9467a1270cd77695ac5ca43611b0115b5195d67925201b46b4e00
+size 25582648

fold_1/model.chrombpnet_nobias.fold_1.ENCSR871APX.tar

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:62b664574c02cffa57c6fa069564b6e70a8ea235bf5281bc9415dcf512571ae8
+size 26060800

fold_2/logs.models.fold_2.ENCSR871APX/logfile.modelling.fold_2.ENCSR871APX.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/ENCSR871APX/preprocessing/bigWigs/ENCSR871APX.bigWig",
+    "input_fragment_file": null,
+    "input_tagalign_file": null,
+    "output_dir": "/oak/stanford/groups/akundaje/vhecht/chromatin_atlas_bias_corrected/DNASE_model/ENCSR871APX/fold_2",
+    "data_type": "DNASE",
+    "peaks": "/oak/stanford/groups/akundaje/vhecht/chromatin_atlas_bias_corrected/DNASE_model/ENCSR871APX/fold_2/auxiliary/filtered.peaks.bed",
+    "nonpeaks": "/oak/stanford/groups/akundaje/vhecht/chromatin_atlas_bias_corrected/DNASE_model/ENCSR871APX/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/projects/chromatin-atlas-2022/DNASE/ENCSR871APX/failed_models_retrained/chrombpnet_model_feb22_fold_0/bias_model/models/ENCSR871APX_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/ENCSR871APX/fold_2/models/chrombpnet",
+    "bigwig": "/oak/stanford/groups/akundaje/vhecht/chromatin_atlas_bias_corrected/DNASE_model/ENCSR871APX/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/ENCSR871APX/fold_2/logs/chrombpnet_model_params.tsv"
+}

fold_2/logs.models.fold_2.ENCSR871APX/logfile.modelling.fold_2.ENCSR871APX.bias_formatting.stdout.txt

@@ -0,0 +1 @@
+Converting /oak/stanford/groups/akundaje/vhecht/chromatin_atlas_bias_corrected/DNASE_model/ENCSR871APX/fold_2/models/bias_model_scaled.h5 to /oak/stanford/groups/akundaje/vhecht/chromatin-atlas-2022/DNASE/ENCSR871APX/fold_2/new_model_format/bias_model_scaled.tar with get_new_tf_model_format.py

fold_2/logs.models.fold_2.ENCSR871APX/logfile.modelling.fold_2.ENCSR871APX.chrombpnet_data_params.tsv

@@ -0,0 +1,3 @@
+counts_sum_min_thresh	0.0
+counts_sum_max_thresh	1655.46
+trainings_pts_post_thresh	177871

fold_2/logs.models.fold_2.ENCSR871APX/logfile.modelling.fold_2.ENCSR871APX.chrombpnet_formatting.stdout.txt

@@ -0,0 +1 @@
+Converting /oak/stanford/groups/akundaje/vhecht/chromatin_atlas_bias_corrected/DNASE_model/ENCSR871APX/fold_2/models/chrombpnet.h5 to /oak/stanford/groups/akundaje/vhecht/chromatin-atlas-2022/DNASE/ENCSR871APX/fold_2/new_model_format/chrombpnet.tar with get_new_tf_model_format.py

fold_2/logs.models.fold_2.ENCSR871APX/logfile.modelling.fold_2.ENCSR871APX.chrombpnet_model_params.tsv

@@ -0,0 +1,9 @@
+counts_loss_weight	5.1
+filters	512
+n_dil_layers	8
+bias_model_path	/oak/stanford/groups/akundaje/vhecht/chromatin_atlas_bias_corrected/DNASE_model/ENCSR871APX/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.ENCSR871APX/logfile.modelling.fold_2.ENCSR871APX.chrombpnet_no_bias_formatting.stdout.txt

@@ -0,0 +1 @@
+Converting /oak/stanford/groups/akundaje/vhecht/chromatin_atlas_bias_corrected/DNASE_model/ENCSR871APX/fold_2/models/chrombpnet_nobias.h5 to /oak/stanford/groups/akundaje/vhecht/chromatin-atlas-2022/DNASE/ENCSR871APX/fold_2/new_model_format/chrombpnet_nobias.tar with get_new_tf_model_format.py

fold_2/logs.models.fold_2.ENCSR871APX/logfile.modelling.fold_2.ENCSR871APX.epoch_loss.csv

@@ -0,0 +1,13 @@
+epoch,logcount_predictions_loss,logits_profile_predictions_loss,loss,val_logcount_predictions_loss,val_logits_profile_predictions_loss,val_loss
+0,1.1824023723602295,233.4678192138672,239.49818420410156,0.5728767514228821,235.6623077392578,238.58412170410156
+1,0.547116219997406,227.25038146972656,230.04074096679688,0.4960409998893738,234.24600219726562,236.77589416503906
+2,0.49931231141090393,224.88690185546875,227.4334259033203,0.48394283652305603,232.6641387939453,235.13229370117188
+3,0.4720722734928131,223.77767944335938,226.18508911132812,0.4430365562438965,232.80892944335938,235.0684356689453
+4,0.4510393440723419,222.98089599609375,225.28102111816406,0.4423811733722687,232.22474670410156,234.48086547851562
+5,0.4331496059894562,221.76559448242188,223.97479248046875,0.5198537111282349,230.9480438232422,233.5992889404297
+6,0.41452938318252563,221.41175842285156,223.52650451660156,0.41947901248931885,230.8816375732422,233.02101135253906
+7,0.4063046872615814,220.17478942871094,222.24697875976562,0.43850141763687134,232.71104431152344,234.94749450683594
+8,0.39459216594696045,219.68194580078125,221.69424438476562,0.4086454212665558,232.53883361816406,234.6229248046875
+9,0.38618797063827515,219.10061645507812,221.07009887695312,0.40499386191368103,231.83901977539062,233.9044647216797
+10,0.37697169184684753,218.28256225585938,220.205078125,0.4034346640110016,232.81546020507812,234.87301635742188
+11,0.3741559386253357,217.98037719726562,219.88839721679688,0.48910170793533325,233.41998291015625,235.91455078125

fold_2/model.bias_scaled.fold_2.ENCSR871APX.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9fc89440918292a5f128e79c2fed881f030367b6c82a07dbdbc6baf836a77a3b
+size 2691928

fold_2/model.bias_scaled.fold_2.ENCSR871APX.tar

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6fabd319e88628d0d94043aa9a1ed6534ad70f9d0561623e269f7eec4c6d9f07
+size 1198080

fold_2/model.chrombpnet.fold_2.ENCSR871APX.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2630c341c64bf300d015e041dc4c9d147a24e24dec66a71f80f423f204938d18
+size 77538840

fold_2/model.chrombpnet.fold_2.ENCSR871APX.tar

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:df08a383ea579ba048696f64243c4594a2a0cf6225cb7f79fce7803968083cf7
+size 27525120

fold_2/model.chrombpnet_nobias.fold_2.ENCSR871APX.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e82245a13ff2d001635b334e5944e31f81760188a77d7a1fb229885efc3479f9
+size 25582648

fold_2/model.chrombpnet_nobias.fold_2.ENCSR871APX.tar

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fa99faaa0599695508c559695bf89d840ef4d8e78c10bd477229c6f9579f9adc
+size 26060800

fold_3/logs.models.fold_3.ENCSR871APX/logfile.modelling.fold_3.ENCSR871APX.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/ENCSR871APX/preprocessing/bigWigs/ENCSR871APX.bigWig",
+    "input_fragment_file": null,
+    "input_tagalign_file": null,
+    "output_dir": "/oak/stanford/groups/akundaje/vhecht/chromatin_atlas_bias_corrected/DNASE_model/ENCSR871APX/fold_3",
+    "data_type": "DNASE",
+    "peaks": "/oak/stanford/groups/akundaje/vhecht/chromatin_atlas_bias_corrected/DNASE_model/ENCSR871APX/fold_3/auxiliary/filtered.peaks.bed",
+    "nonpeaks": "/oak/stanford/groups/akundaje/vhecht/chromatin_atlas_bias_corrected/DNASE_model/ENCSR871APX/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/projects/chromatin-atlas-2022/DNASE/ENCSR871APX/failed_models_retrained/chrombpnet_model_feb22_fold_0/bias_model/models/ENCSR871APX_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/ENCSR871APX/fold_3/models/chrombpnet",
+    "bigwig": "/oak/stanford/groups/akundaje/vhecht/chromatin_atlas_bias_corrected/DNASE_model/ENCSR871APX/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/ENCSR871APX/fold_3/logs/chrombpnet_model_params.tsv"
+}

fold_3/logs.models.fold_3.ENCSR871APX/logfile.modelling.fold_3.ENCSR871APX.bias_formatting.stdout.txt

@@ -0,0 +1 @@
+Converting /oak/stanford/groups/akundaje/vhecht/chromatin_atlas_bias_corrected/DNASE_model/ENCSR871APX/fold_3/models/bias_model_scaled.h5 to /oak/stanford/groups/akundaje/vhecht/chromatin-atlas-2022/DNASE/ENCSR871APX/fold_3/new_model_format/bias_model_scaled.tar with get_new_tf_model_format.py

fold_3/logs.models.fold_3.ENCSR871APX/logfile.modelling.fold_3.ENCSR871APX.chrombpnet_data_params.tsv

@@ -0,0 +1,3 @@
+counts_sum_min_thresh	0.0
+counts_sum_max_thresh	1711.0
+trainings_pts_post_thresh	171925

fold_3/logs.models.fold_3.ENCSR871APX/logfile.modelling.fold_3.ENCSR871APX.chrombpnet_formatting.stdout.txt

@@ -0,0 +1 @@
+Converting /oak/stanford/groups/akundaje/vhecht/chromatin_atlas_bias_corrected/DNASE_model/ENCSR871APX/fold_3/models/chrombpnet.h5 to /oak/stanford/groups/akundaje/vhecht/chromatin-atlas-2022/DNASE/ENCSR871APX/fold_3/new_model_format/chrombpnet.tar with get_new_tf_model_format.py

fold_3/logs.models.fold_3.ENCSR871APX/logfile.modelling.fold_3.ENCSR871APX.chrombpnet_model_params.tsv

@@ -0,0 +1,9 @@
+counts_loss_weight	5.1
+filters	512
+n_dil_layers	8
+bias_model_path	/oak/stanford/groups/akundaje/vhecht/chromatin_atlas_bias_corrected/DNASE_model/ENCSR871APX/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.ENCSR871APX/logfile.modelling.fold_3.ENCSR871APX.chrombpnet_no_bias_formatting.stdout.txt

@@ -0,0 +1 @@
+Converting /oak/stanford/groups/akundaje/vhecht/chromatin_atlas_bias_corrected/DNASE_model/ENCSR871APX/fold_3/models/chrombpnet_nobias.h5 to /oak/stanford/groups/akundaje/vhecht/chromatin-atlas-2022/DNASE/ENCSR871APX/fold_3/new_model_format/chrombpnet_nobias.tar with get_new_tf_model_format.py