Upload folder using huggingface_hub

README.md

@@ -0,0 +1,120 @@
+---
+license: mit
+library_name: chrombpnet
+tags:
+  - encode
+  - chrombpnet
+  - chromatin-accessibility
+  - DNASE
+  - limb
+  - 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 hindlimb muscle (ENCSR385AMY)
+- Model: ChromBPNet
+- Assay: DNASE-seq
+- Experiment: [ENCSR385AMY](https://www.encodeproject.org/experiments/ENCSR385AMY/)
+- Model annotation: [ENCSR003PKQ](https://www.encodeproject.org/annotations/ENCSR003PKQ/)
+- Biosample: hindlimb muscle (Full name: Homo sapiens hindlimb muscle tissue male embryo (120 days))
+- Cell slim(s): None
+- Organ slim(s): musculature-of-body,limb
+- Developmental slim(s): mesoderm
+- System slim(s): musculature
+- 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.ENCSR385AMY/logfile.modelling.fold_0.ENCSR385AMY.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/ENCSR385AMY/preprocessing/bigWigs/ENCSR385AMY.bigWig",
+    "output_dir": "/oak/stanford/groups/akundaje/ziwei75/chromatin_atlas_bias/DNase_model/bias_filtered/ENCSR385AMY//fold0/",
+    "data_type": "DNASE",
+    "peaks": "/oak/stanford/groups/akundaje/ziwei75/chromatin_atlas_bias/DNase_model/bias_filtered/ENCSR385AMY//fold0/auxiliary/filtered.peaks.bed",
+    "nonpeaks": "/oak/stanford/groups/akundaje/ziwei75/chromatin_atlas_bias/DNase_model/bias_filtered/ENCSR385AMY//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/ENCSR385AMY/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/ENCSR385AMY//fold0/models/chrombpnet",
+    "chr": "chr8",
+    "pwm_width": 24,
+    "params": "/oak/stanford/groups/akundaje/ziwei75/chromatin_atlas_bias/DNase_model/bias_filtered/ENCSR385AMY//fold0/logs/chrombpnet_model_params.tsv"
+}

fold_0/logs.models.fold_0.ENCSR385AMY/logfile.modelling.fold_0.ENCSR385AMY.bias_formatting.stdout.txt

@@ -0,0 +1 @@
+Converting /oak/stanford/groups/akundaje/ziwei75/chromatin_atlas_bias/DNase_model/bias_filtered/ENCSR385AMY/fold0/models/bias_model_scaled.h5 to /oak/stanford/groups/akundaje/vhecht/chromatin-atlas-2022/DNASE/ENCSR385AMY/fold_0/new_model_format/bias_model_scaled.tar with get_new_tf_model_format.py

fold_0/logs.models.fold_0.ENCSR385AMY/logfile.modelling.fold_0.ENCSR385AMY.chrombpnet_data_params.tsv

@@ -0,0 +1,3 @@
+counts_sum_min_thresh	0.0
+counts_sum_max_thresh	5132.92
+trainings_pts_post_thresh	171261

fold_0/logs.models.fold_0.ENCSR385AMY/logfile.modelling.fold_0.ENCSR385AMY.chrombpnet_formatting.stdout.txt

@@ -0,0 +1 @@
+Converting /oak/stanford/groups/akundaje/ziwei75/chromatin_atlas_bias/DNase_model/bias_filtered/ENCSR385AMY/fold0/models/chrombpnet.h5 to /oak/stanford/groups/akundaje/vhecht/chromatin-atlas-2022/DNASE/ENCSR385AMY/fold_0/new_model_format/chrombpnet.tar with get_new_tf_model_format.py

fold_0/logs.models.fold_0.ENCSR385AMY/logfile.modelling.fold_0.ENCSR385AMY.chrombpnet_model_params.tsv

@@ -0,0 +1,9 @@
+counts_loss_weight	12.2
+filters	512
+n_dil_layers	8
+bias_model_path	/oak/stanford/groups/akundaje/ziwei75/chromatin_atlas_bias/DNase_model/bias_filtered/ENCSR385AMY//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.ENCSR385AMY/logfile.modelling.fold_0.ENCSR385AMY.chrombpnet_no_bias_formatting.stdout.txt

@@ -0,0 +1 @@
+Converting /oak/stanford/groups/akundaje/ziwei75/chromatin_atlas_bias/DNase_model/bias_filtered/ENCSR385AMY/fold0/models/chrombpnet_nobias.h5 to /oak/stanford/groups/akundaje/vhecht/chromatin-atlas-2022/DNASE/ENCSR385AMY/fold_0/new_model_format/chrombpnet_nobias.tar with get_new_tf_model_format.py

fold_0/logs.models.fold_0.ENCSR385AMY/logfile.modelling.fold_0.ENCSR385AMY.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
+0,1.9770828485488892,522.44189453125,546.5613403320312,0.878165602684021,507.1616516113281,517.8751831054688
+1,0.8748293519020081,495.7141418457031,506.3877258300781,0.8365785479545593,494.6370849609375,504.8434143066406
+2,0.7963923811912537,488.0716552734375,497.7874755859375,0.7952279448509216,495.7333984375,505.435302734375
+3,0.7414178848266602,483.43304443359375,492.4776611328125,0.6943086385726929,493.35467529296875,501.82525634765625
+4,0.7072145342826843,479.7239685058594,488.3514404296875,0.6661702990531921,493.9805603027344,502.1078186035156
+5,0.6854123473167419,476.93798828125,485.2994689941406,0.699362576007843,490.8526611328125,499.38507080078125
+6,0.6538832783699036,474.883056640625,482.8609619140625,0.6603286862373352,494.6324768066406,502.688720703125
+7,0.6392768621444702,472.5515441894531,480.3503112792969,0.7141312956809998,491.0947265625,499.80706787109375
+8,0.626732349395752,470.98797607421875,478.634033203125,0.6582152843475342,495.2186584472656,503.2485656738281
+9,0.6128236651420593,469.64739990234375,477.1233215332031,0.6511006355285645,499.6353454589844,507.57879638671875
+10,0.5974838137626648,468.0060119628906,475.29583740234375,0.6157989501953125,502.32843017578125,509.84100341796875

fold_0/model.bias_scaled.fold_0.ENCSR385AMY.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0ae27f76e5091e7c278af748a2124c76346ddf0bb165c95e7a451cb4f6094be8
+size 2691928

fold_0/model.bias_scaled.fold_0.ENCSR385AMY.tar

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:81db4ee3e3fa5b5be725dbc90440517ba8f598afea84a2ee7664c0dfe0bfd490
+size 1198080

fold_0/model.chrombpnet.fold_0.ENCSR385AMY.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b323c74ba6355fa98766f0695d90b4a75fe263cb588535ddc09563cd64d972c7
+size 77538952

fold_0/model.chrombpnet.fold_0.ENCSR385AMY.tar

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:268d0b12a78c1834d7b71bd50b2a56ea8dd22eb1a74a1644d7f325d55fbc2f7b
+size 27525120

fold_0/model.chrombpnet_nobias.fold_0.ENCSR385AMY.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4791a15cdd32113d43f0af0db2e58252028f8fc1bf0285ac9d0a508298a7d151
+size 25582648

fold_0/model.chrombpnet_nobias.fold_0.ENCSR385AMY.tar

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1a829c2c39cc0062507d9d8650df8211c146ff340fd15c246422e71051ca0d54
+size 26060800

fold_1/logs.models.fold_1.ENCSR385AMY/logfile.modelling.fold_1.ENCSR385AMY.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/ENCSR385AMY/preprocessing/bigWigs/ENCSR385AMY.bigWig",
+    "input_fragment_file": null,
+    "input_tagalign_file": null,
+    "output_dir": "/oak/stanford/groups/akundaje/vhecht/chromatin_atlas_bias_corrected/DNASE_model/ENCSR385AMY/fold_1",
+    "data_type": "DNASE",
+    "peaks": "/oak/stanford/groups/akundaje/vhecht/chromatin_atlas_bias_corrected/DNASE_model/ENCSR385AMY/fold_1/auxiliary/filtered.peaks.bed",
+    "nonpeaks": "/oak/stanford/groups/akundaje/vhecht/chromatin_atlas_bias_corrected/DNASE_model/ENCSR385AMY/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/ENCSR385AMY/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/ENCSR385AMY/fold_1/models/chrombpnet",
+    "bigwig": "/oak/stanford/groups/akundaje/vhecht/chromatin_atlas_bias_corrected/DNASE_model/ENCSR385AMY/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/ENCSR385AMY/fold_1/logs/chrombpnet_model_params.tsv"
+}

fold_1/logs.models.fold_1.ENCSR385AMY/logfile.modelling.fold_1.ENCSR385AMY.bias_formatting.stdout.txt

@@ -0,0 +1 @@
+Converting /oak/stanford/groups/akundaje/vhecht/chromatin_atlas_bias_corrected/DNASE_model/ENCSR385AMY/fold_1/models/bias_model_scaled.h5 to /oak/stanford/groups/akundaje/vhecht/chromatin-atlas-2022/DNASE/ENCSR385AMY/fold_1/new_model_format/bias_model_scaled.tar with get_new_tf_model_format.py

fold_1/logs.models.fold_1.ENCSR385AMY/logfile.modelling.fold_1.ENCSR385AMY.chrombpnet_data_params.tsv

@@ -0,0 +1,3 @@
+counts_sum_min_thresh	0.0
+counts_sum_max_thresh	5143.72
+trainings_pts_post_thresh	173979

fold_1/logs.models.fold_1.ENCSR385AMY/logfile.modelling.fold_1.ENCSR385AMY.chrombpnet_formatting.stdout.txt

@@ -0,0 +1 @@
+Converting /oak/stanford/groups/akundaje/vhecht/chromatin_atlas_bias_corrected/DNASE_model/ENCSR385AMY/fold_1/models/chrombpnet.h5 to /oak/stanford/groups/akundaje/vhecht/chromatin-atlas-2022/DNASE/ENCSR385AMY/fold_1/new_model_format/chrombpnet.tar with get_new_tf_model_format.py

fold_1/logs.models.fold_1.ENCSR385AMY/logfile.modelling.fold_1.ENCSR385AMY.chrombpnet_model_params.tsv

@@ -0,0 +1,9 @@
+counts_loss_weight	12.2
+filters	512
+n_dil_layers	8
+bias_model_path	/oak/stanford/groups/akundaje/vhecht/chromatin_atlas_bias_corrected/DNASE_model/ENCSR385AMY/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.ENCSR385AMY/logfile.modelling.fold_1.ENCSR385AMY.chrombpnet_no_bias_formatting.stdout.txt

@@ -0,0 +1 @@
+Converting /oak/stanford/groups/akundaje/vhecht/chromatin_atlas_bias_corrected/DNASE_model/ENCSR385AMY/fold_1/models/chrombpnet_nobias.h5 to /oak/stanford/groups/akundaje/vhecht/chromatin-atlas-2022/DNASE/ENCSR385AMY/fold_1/new_model_format/chrombpnet_nobias.tar with get_new_tf_model_format.py

fold_1/logs.models.fold_1.ENCSR385AMY/logfile.modelling.fold_1.ENCSR385AMY.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
+0,2.424912214279175,529.6612548828125,559.24462890625,0.9572994709014893,602.5901489257812,614.2691650390625
+1,0.9195420145988464,498.1009521484375,509.3187255859375,0.8413581848144531,579.21533203125,589.4797973632812
+2,0.8402743339538574,488.75689697265625,499.00860595703125,0.7647204995155334,576.4014282226562,585.73095703125
+3,0.7942594289779663,483.0146484375,492.7039489746094,0.7088714838027954,566.425048828125,575.0730590820312
+4,0.7513942718505859,479.6485595703125,488.8154296875,0.6680809259414673,567.3887329101562,575.5392456054688
+5,0.7172863483428955,476.3273620605469,485.07843017578125,0.646342933177948,566.6307373046875,574.515869140625
+6,0.6939284801483154,472.8807067871094,481.3465576171875,0.6559173464775085,569.8682861328125,577.8707275390625
+7,0.6707106828689575,470.9489440917969,479.1319885253906,0.6465588808059692,567.7783813476562,575.6661987304688
+8,0.6497904658317566,468.7471618652344,476.6751403808594,0.6884491443634033,565.8653564453125,574.2647705078125
+9,0.638763427734375,466.5169982910156,474.31011962890625,0.6580843329429626,569.990966796875,578.0197143554688
+10,0.6197393536567688,465.3634948730469,472.9242858886719,0.6305816173553467,570.5250244140625,578.2179565429688
+11,0.6102444529533386,463.60302734375,471.0477600097656,0.7974913120269775,573.4833984375,583.2124633789062
+12,0.5966919660568237,462.4775695800781,469.7580871582031,0.6064395308494568,568.424072265625,575.82275390625
+13,0.590790867805481,460.1824951171875,467.390869140625,0.6153243780136108,570.3412475585938,577.8485107421875

fold_1/model.bias_scaled.fold_1.ENCSR385AMY.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6e1b7c91434c16ce25406b1c134ef9a2428b83222806eb9f37f98b8eb1ef03a0
+size 2691928

fold_1/model.bias_scaled.fold_1.ENCSR385AMY.tar

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0668e8cb1932dbc4918c86494b7cec4bd69fab72513d7a2cb239516b6c36b85a
+size 1198080

fold_1/model.chrombpnet.fold_1.ENCSR385AMY.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4bbd35af3ab0259db2452d2b8e6626cc0bec9053e493168b4b0166719a80a30f
+size 77538840

fold_1/model.chrombpnet.fold_1.ENCSR385AMY.tar

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2ad05ee8f5cbd864e07461beb728673eea7db3b5f44e37db34ac891b7801b5db
+size 27525120

fold_1/model.chrombpnet_nobias.fold_1.ENCSR385AMY.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:590fe49e7fa86985110edd60c7dfe6aecbada2561e4b4a32d5a1178ec6849f41
+size 25582648

fold_1/model.chrombpnet_nobias.fold_1.ENCSR385AMY.tar

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bd9b7a16df3f10d04922820be12dfb2de5618542a8fed64b9e34084e1808da71
+size 26060800

fold_2/logs.models.fold_2.ENCSR385AMY/logfile.modelling.fold_2.ENCSR385AMY.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/ENCSR385AMY/preprocessing/bigWigs/ENCSR385AMY.bigWig",
+    "input_fragment_file": null,
+    "input_tagalign_file": null,
+    "output_dir": "/oak/stanford/groups/akundaje/vhecht/chromatin_atlas_bias_corrected/DNASE_model/ENCSR385AMY/fold_2",
+    "data_type": "DNASE",
+    "peaks": "/oak/stanford/groups/akundaje/vhecht/chromatin_atlas_bias_corrected/DNASE_model/ENCSR385AMY/fold_2/auxiliary/filtered.peaks.bed",
+    "nonpeaks": "/oak/stanford/groups/akundaje/vhecht/chromatin_atlas_bias_corrected/DNASE_model/ENCSR385AMY/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/ENCSR385AMY/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/ENCSR385AMY/fold_2/models/chrombpnet",
+    "bigwig": "/oak/stanford/groups/akundaje/vhecht/chromatin_atlas_bias_corrected/DNASE_model/ENCSR385AMY/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/ENCSR385AMY/fold_2/logs/chrombpnet_model_params.tsv"
+}

fold_2/logs.models.fold_2.ENCSR385AMY/logfile.modelling.fold_2.ENCSR385AMY.bias_formatting.stdout.txt

@@ -0,0 +1 @@
+Converting /oak/stanford/groups/akundaje/vhecht/chromatin_atlas_bias_corrected/DNASE_model/ENCSR385AMY/fold_2/models/bias_model_scaled.h5 to /oak/stanford/groups/akundaje/vhecht/chromatin-atlas-2022/DNASE/ENCSR385AMY/fold_2/new_model_format/bias_model_scaled.tar with get_new_tf_model_format.py

fold_2/logs.models.fold_2.ENCSR385AMY/logfile.modelling.fold_2.ENCSR385AMY.chrombpnet_data_params.tsv

@@ -0,0 +1,3 @@
+counts_sum_min_thresh	0.0
+counts_sum_max_thresh	5126.81
+trainings_pts_post_thresh	178753

fold_2/logs.models.fold_2.ENCSR385AMY/logfile.modelling.fold_2.ENCSR385AMY.chrombpnet_formatting.stdout.txt

@@ -0,0 +1 @@
+Converting /oak/stanford/groups/akundaje/vhecht/chromatin_atlas_bias_corrected/DNASE_model/ENCSR385AMY/fold_2/models/chrombpnet.h5 to /oak/stanford/groups/akundaje/vhecht/chromatin-atlas-2022/DNASE/ENCSR385AMY/fold_2/new_model_format/chrombpnet.tar with get_new_tf_model_format.py

fold_2/logs.models.fold_2.ENCSR385AMY/logfile.modelling.fold_2.ENCSR385AMY.chrombpnet_model_params.tsv

@@ -0,0 +1,9 @@
+counts_loss_weight	12.2
+filters	512
+n_dil_layers	8
+bias_model_path	/oak/stanford/groups/akundaje/vhecht/chromatin_atlas_bias_corrected/DNASE_model/ENCSR385AMY/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.ENCSR385AMY/logfile.modelling.fold_2.ENCSR385AMY.chrombpnet_no_bias_formatting.stdout.txt

@@ -0,0 +1 @@
+Converting /oak/stanford/groups/akundaje/vhecht/chromatin_atlas_bias_corrected/DNASE_model/ENCSR385AMY/fold_2/models/chrombpnet_nobias.h5 to /oak/stanford/groups/akundaje/vhecht/chromatin-atlas-2022/DNASE/ENCSR385AMY/fold_2/new_model_format/chrombpnet_nobias.tar with get_new_tf_model_format.py

fold_2/logs.models.fold_2.ENCSR385AMY/logfile.modelling.fold_2.ENCSR385AMY.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
+0,2.771857500076294,536.7540283203125,570.571044921875,0.9925419092178345,533.5272216796875,545.6359252929688
+1,0.9409024119377136,502.71185302734375,514.1902465820312,0.812254786491394,519.439208984375,529.348876953125
+2,0.8516588807106018,493.65301513671875,504.0433654785156,0.8800976276397705,517.45556640625,528.192626953125
+3,0.7830417156219482,488.1264953613281,497.6792297363281,1.090691089630127,515.3241577148438,528.630615234375
+4,0.7456042170524597,483.96575927734375,493.06182861328125,0.7167993783950806,504.13275146484375,512.8778076171875
+5,0.7080942392349243,480.1345520019531,488.7730712890625,0.7253450751304626,503.6178283691406,512.4674072265625
+6,0.6795583367347717,478.2273864746094,486.5172424316406,0.7077139019966125,507.39202880859375,516.026123046875
+7,0.6550350785255432,474.9714050292969,482.9627685546875,0.7205138802528381,502.78802490234375,511.5780334472656
+8,0.6312917470932007,473.41387939453125,481.115478515625,0.6696923971176147,506.3115234375,514.481689453125
+9,0.6226451992988586,470.5510559082031,478.1474609375,0.6414923071861267,504.35382080078125,512.1802368164062
+10,0.6068309545516968,469.2301940917969,476.63287353515625,0.6340993642807007,505.0211181640625,512.7572021484375
+11,0.5914859175682068,467.615234375,474.8310241699219,0.6398987770080566,506.36077880859375,514.1672973632812
+12,0.5783110857009888,465.83984375,472.8951110839844,0.6854179501533508,506.67529296875,515.0374755859375

fold_2/model.bias_scaled.fold_2.ENCSR385AMY.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:455ff2f8cabfe7d734b473857bfccc3a765a25eb8659ca03d6084d1d5622d9ca
+size 2691928

fold_2/model.bias_scaled.fold_2.ENCSR385AMY.tar

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7f4b97d0cd2e444a1f12e97b9da6e4db2b4a88fb675ab2c5550ce3dd5f9457a8
+size 1198080

fold_2/model.chrombpnet.fold_2.ENCSR385AMY.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:125751b1a8478345c73d935d3d3cbb5e1aa8aaa09d026dd29dcda2b86a1a261c
+size 77538840

fold_2/model.chrombpnet.fold_2.ENCSR385AMY.tar

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0be2ccceeb5f5573a47e30efaab7239fbecae9ea1d64ba43bdede86e952b881a
+size 27525120

fold_2/model.chrombpnet_nobias.fold_2.ENCSR385AMY.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:10a5c6281c1c277dbedb37f9fc54f365ffda3e925e254bb07751dbf6d1a44f67
+size 25582648

fold_2/model.chrombpnet_nobias.fold_2.ENCSR385AMY.tar

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:82be39ad5c702144940f5ee0f11891fd0f93233dc37452e6a98057d351e93eef
+size 26060800

fold_3/logs.models.fold_3.ENCSR385AMY/logfile.modelling.fold_3.ENCSR385AMY.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/ENCSR385AMY/preprocessing/bigWigs/ENCSR385AMY.bigWig",
+    "input_fragment_file": null,
+    "input_tagalign_file": null,
+    "output_dir": "/oak/stanford/groups/akundaje/vhecht/chromatin_atlas_bias_corrected/DNASE_model/ENCSR385AMY/fold_3",
+    "data_type": "DNASE",
+    "peaks": "/oak/stanford/groups/akundaje/vhecht/chromatin_atlas_bias_corrected/DNASE_model/ENCSR385AMY/fold_3/auxiliary/filtered.peaks.bed",
+    "nonpeaks": "/oak/stanford/groups/akundaje/vhecht/chromatin_atlas_bias_corrected/DNASE_model/ENCSR385AMY/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/ENCSR385AMY/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/ENCSR385AMY/fold_3/models/chrombpnet",
+    "bigwig": "/oak/stanford/groups/akundaje/vhecht/chromatin_atlas_bias_corrected/DNASE_model/ENCSR385AMY/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/ENCSR385AMY/fold_3/logs/chrombpnet_model_params.tsv"
+}

fold_3/logs.models.fold_3.ENCSR385AMY/logfile.modelling.fold_3.ENCSR385AMY.bias_formatting.stdout.txt

@@ -0,0 +1 @@
+Converting /oak/stanford/groups/akundaje/vhecht/chromatin_atlas_bias_corrected/DNASE_model/ENCSR385AMY/fold_3/models/bias_model_scaled.h5 to /oak/stanford/groups/akundaje/vhecht/chromatin-atlas-2022/DNASE/ENCSR385AMY/fold_3/new_model_format/bias_model_scaled.tar with get_new_tf_model_format.py

fold_3/logs.models.fold_3.ENCSR385AMY/logfile.modelling.fold_3.ENCSR385AMY.chrombpnet_data_params.tsv

@@ -0,0 +1,3 @@
+counts_sum_min_thresh	0.0
+counts_sum_max_thresh	5257.42
+trainings_pts_post_thresh	171787

fold_3/logs.models.fold_3.ENCSR385AMY/logfile.modelling.fold_3.ENCSR385AMY.chrombpnet_formatting.stdout.txt

@@ -0,0 +1 @@
+Converting /oak/stanford/groups/akundaje/vhecht/chromatin_atlas_bias_corrected/DNASE_model/ENCSR385AMY/fold_3/models/chrombpnet.h5 to /oak/stanford/groups/akundaje/vhecht/chromatin-atlas-2022/DNASE/ENCSR385AMY/fold_3/new_model_format/chrombpnet.tar with get_new_tf_model_format.py

fold_3/logs.models.fold_3.ENCSR385AMY/logfile.modelling.fold_3.ENCSR385AMY.chrombpnet_model_params.tsv

@@ -0,0 +1,9 @@
+counts_loss_weight	12.2
+filters	512
+n_dil_layers	8
+bias_model_path	/oak/stanford/groups/akundaje/vhecht/chromatin_atlas_bias_corrected/DNASE_model/ENCSR385AMY/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.ENCSR385AMY/logfile.modelling.fold_3.ENCSR385AMY.chrombpnet_no_bias_formatting.stdout.txt

@@ -0,0 +1 @@
+Converting /oak/stanford/groups/akundaje/vhecht/chromatin_atlas_bias_corrected/DNASE_model/ENCSR385AMY/fold_3/models/chrombpnet_nobias.h5 to /oak/stanford/groups/akundaje/vhecht/chromatin-atlas-2022/DNASE/ENCSR385AMY/fold_3/new_model_format/chrombpnet_nobias.tar with get_new_tf_model_format.py