From 3473263e64cbc6ed13778e3050a4e51d76685b3a Mon Sep 17 00:00:00 2001
From: Anusri Pampari
Date: Tue, 27 Aug 2024 07:06:52 -0700
Subject: [PATCH] updating logs
---
.gitignore | 2 +
logs/checkpoint/JAN_02_2023/check_nums.sh | 5 +
.../JAN_02_2023/dnase_make_average_bigwigs.sh | 57 +
.../dnase_make_average_bigwigs_profile.sh | 57 +
.../JAN_02_2023/screenlog/output1.log | 408 +++++++
.../screenlog/output_combine_deepshap.log | 326 +++++
.../output_run_train_test_making.log | 1074 +++++++++++++++++
.../output_train_test_making_bias.log | 1074 +++++++++++++++++
.../screenlog/output_zenodo_upload.log | 364 ++++++
.../JAN_02_2023/script_make_bigwig.sh | 164 +++
logs/checkpoint/JAN_02_2023/script_temp.sh | 9 +
.../JAN_20_2024/marginal_footprints/a.out | 0
.../JAN_20_2024/marginal_footprints/list.txt | 8 +
.../output/ATAC/GM12878/footprints.h5 | Bin 0 -> 62374 bytes
.../ATAC/GM12878/uncorrected_footprints.h5 | Bin 0 -> 63348 bytes
.../output/ATAC/H1ESC/footprints.h5 | Bin 0 -> 62418 bytes
.../ATAC/H1ESC/uncorrected_footprints.h5 | Bin 0 -> 63181 bytes
.../output/ATAC/HEPG2/footprints.h5 | Bin 0 -> 62436 bytes
.../ATAC/HEPG2/uncorrected_footprints.h5 | Bin 0 -> 63368 bytes
.../output/ATAC/IMR90/footprints.h5 | Bin 0 -> 62883 bytes
.../ATAC/IMR90/uncorrected_footprints.h5 | Bin 0 -> 63360 bytes
.../output/ATAC/K562/footprints.h5 | Bin 0 -> 62707 bytes
.../ATAC/K562/uncorrected_footprints.h5 | Bin 0 -> 63268 bytes
.../output/DNASE/GM12878/footprints.h5 | Bin 0 -> 63104 bytes
.../DNASE/GM12878/uncorrected_footprints.h5 | Bin 0 -> 63132 bytes
.../output/DNASE/H1ESC/footprints.h5 | Bin 0 -> 63070 bytes
.../DNASE/H1ESC/uncorrected_footprints.h5 | Bin 0 -> 63229 bytes
.../output/DNASE/HEPG2/footprints.h5 | Bin 0 -> 62897 bytes
.../DNASE/HEPG2/uncorrected_footprints.h5 | Bin 0 -> 63275 bytes
.../output/DNASE/IMR90/footprints.h5 | Bin 0 -> 63127 bytes
.../DNASE/IMR90/uncorrected_footprints.h5 | Bin 0 -> 63175 bytes
.../output/DNASE/K562/footprints.h5 | Bin 0 -> 62906 bytes
.../DNASE/K562/uncorrected_footprints.h5 | Bin 0 -> 63065 bytes
.../JAN_20_2024/marginal_footprints/script.sh | 72 ++
.../marginal_footprints/script_temp.sh | 8 +
.../JAN_20_2024/preds/bigwig_helper.py | 102 ++
.../JAN_20_2024/preds/merge_predictions.py | 217 ++++
logs/checkpoint/JAN_20_2024/preds/one_hot.py | 61 +
.../JAN_20_2024/preds/run_script.py | 49 +
logs/checkpoint/JAN_20_2024/preds/script.sh | 15 +
nautlius/cp_bias_stuff.py | 18 +
reference/script.sh | 2 +
42 files changed, 4092 insertions(+)
create mode 100644 logs/checkpoint/JAN_02_2023/check_nums.sh
create mode 100644 logs/checkpoint/JAN_02_2023/dnase_make_average_bigwigs.sh
create mode 100644 logs/checkpoint/JAN_02_2023/dnase_make_average_bigwigs_profile.sh
create mode 100644 logs/checkpoint/JAN_02_2023/screenlog/output1.log
create mode 100644 logs/checkpoint/JAN_02_2023/screenlog/output_combine_deepshap.log
create mode 100644 logs/checkpoint/JAN_02_2023/screenlog/output_run_train_test_making.log
create mode 100644 logs/checkpoint/JAN_02_2023/screenlog/output_train_test_making_bias.log
create mode 100644 logs/checkpoint/JAN_02_2023/screenlog/output_zenodo_upload.log
create mode 100644 logs/checkpoint/JAN_02_2023/script_make_bigwig.sh
create mode 100644 logs/checkpoint/JAN_02_2023/script_temp.sh
create mode 100644 logs/checkpoint/JAN_20_2024/marginal_footprints/a.out
create mode 100644 logs/checkpoint/JAN_20_2024/marginal_footprints/list.txt
create mode 100644 logs/checkpoint/JAN_20_2024/marginal_footprints/output/ATAC/GM12878/footprints.h5
create mode 100644 logs/checkpoint/JAN_20_2024/marginal_footprints/output/ATAC/GM12878/uncorrected_footprints.h5
create mode 100644 logs/checkpoint/JAN_20_2024/marginal_footprints/output/ATAC/H1ESC/footprints.h5
create mode 100644 logs/checkpoint/JAN_20_2024/marginal_footprints/output/ATAC/H1ESC/uncorrected_footprints.h5
create mode 100644 logs/checkpoint/JAN_20_2024/marginal_footprints/output/ATAC/HEPG2/footprints.h5
create mode 100644 logs/checkpoint/JAN_20_2024/marginal_footprints/output/ATAC/HEPG2/uncorrected_footprints.h5
create mode 100644 logs/checkpoint/JAN_20_2024/marginal_footprints/output/ATAC/IMR90/footprints.h5
create mode 100644 logs/checkpoint/JAN_20_2024/marginal_footprints/output/ATAC/IMR90/uncorrected_footprints.h5
create mode 100644 logs/checkpoint/JAN_20_2024/marginal_footprints/output/ATAC/K562/footprints.h5
create mode 100644 logs/checkpoint/JAN_20_2024/marginal_footprints/output/ATAC/K562/uncorrected_footprints.h5
create mode 100644 logs/checkpoint/JAN_20_2024/marginal_footprints/output/DNASE/GM12878/footprints.h5
create mode 100644 logs/checkpoint/JAN_20_2024/marginal_footprints/output/DNASE/GM12878/uncorrected_footprints.h5
create mode 100644 logs/checkpoint/JAN_20_2024/marginal_footprints/output/DNASE/H1ESC/footprints.h5
create mode 100644 logs/checkpoint/JAN_20_2024/marginal_footprints/output/DNASE/H1ESC/uncorrected_footprints.h5
create mode 100644 logs/checkpoint/JAN_20_2024/marginal_footprints/output/DNASE/HEPG2/footprints.h5
create mode 100644 logs/checkpoint/JAN_20_2024/marginal_footprints/output/DNASE/HEPG2/uncorrected_footprints.h5
create mode 100644 logs/checkpoint/JAN_20_2024/marginal_footprints/output/DNASE/IMR90/footprints.h5
create mode 100644 logs/checkpoint/JAN_20_2024/marginal_footprints/output/DNASE/IMR90/uncorrected_footprints.h5
create mode 100644 logs/checkpoint/JAN_20_2024/marginal_footprints/output/DNASE/K562/footprints.h5
create mode 100644 logs/checkpoint/JAN_20_2024/marginal_footprints/output/DNASE/K562/uncorrected_footprints.h5
create mode 100644 logs/checkpoint/JAN_20_2024/marginal_footprints/script.sh
create mode 100644 logs/checkpoint/JAN_20_2024/marginal_footprints/script_temp.sh
create mode 100644 logs/checkpoint/JAN_20_2024/preds/bigwig_helper.py
create mode 100644 logs/checkpoint/JAN_20_2024/preds/merge_predictions.py
create mode 100644 logs/checkpoint/JAN_20_2024/preds/one_hot.py
create mode 100644 logs/checkpoint/JAN_20_2024/preds/run_script.py
create mode 100644 logs/checkpoint/JAN_20_2024/preds/script.sh
create mode 100644 nautlius/cp_bias_stuff.py
diff --git a/.gitignore b/.gitignore
index a3e389f8..cdd6bebe 100644
--- a/.gitignore
+++ b/.gitignore
@@ -18,6 +18,7 @@
*.bw
*.fai
*.json
+*.tsv
# Directories #
# logs
results
@@ -28,3 +29,4 @@ old
reference
melanie_models/
melanie_bias_model.sh
+jan_5_2024/
diff --git a/logs/checkpoint/JAN_02_2023/check_nums.sh b/logs/checkpoint/JAN_02_2023/check_nums.sh
new file mode 100644
index 00000000..b932be28
--- /dev/null
+++ b/logs/checkpoint/JAN_02_2023/check_nums.sh
@@ -0,0 +1,5 @@
+wc -l /oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/chrombpnet/folds/$2/$1/preds_upload/fold_0/$1_w_bias_all_regions.bed
+zcat /oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/chrombpnet/folds/$2/$1/merge_folds_all_regions_may_05_24/$1_folds_merged.profile_scores_new_compressed.bed.gz | wc -l
+zcat /oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/chrombpnet/folds/$2/$1/merge_folds_all_regions_may_05_24/$1_folds_merged.counts_scores_new_compressed.bed.gz | wc -l
+bedtools sort -i /oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/chrombpnet/folds/$2/$1/preds_upload/fold_0/$1_w_bias_all_regions.bed | uniq | wc -l
+bedtools sort -i /oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/chrombpnet/folds/$2/$1/merge_folds_all_regions_may_05_24/$1_folds_merged.counts_scores_new_compressed.bed.gz | zcat | cut -f1,2,3 | uniq | wc -l
diff --git a/logs/checkpoint/JAN_02_2023/dnase_make_average_bigwigs.sh b/logs/checkpoint/JAN_02_2023/dnase_make_average_bigwigs.sh
new file mode 100644
index 00000000..f489543d
--- /dev/null
+++ b/logs/checkpoint/JAN_02_2023/dnase_make_average_bigwigs.sh
@@ -0,0 +1,57 @@
+oakdir="/oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/chrombpnet/folds/DNASE/"
+celltype="HEPG2"
+zcat $oakdir/$celltype/merge_folds_new/$celltype"_folds_merged.counts_scores_new_compressed.bed" > $oakdir/$celltype/merge_folds_new/$celltype"_folds_merged.counts_scores_new_compressed.unzip.bed"
+wc -l $oakdir/$celltype/merge_folds_new/$celltype"_folds_merged.counts_scores_new_compressed.unzip.bed"
+python /mnt/lab_data2/anusri/chrombpnet/src/evaluation/make_bigwigs/importance_hdf5_to_bigwig.py \
+ -h5 $oakdir/$celltype/merge_folds_new/$celltype"_folds_merged.counts_scores_new_compressed.h5" \
+ -r $oakdir/$celltype/merge_folds_new/$celltype"_folds_merged.counts_scores_new_compressed.unzip.bed" \
+ -c /mnt/lab_data2/anusri/chrombpnet/reference/chrom.sizes \
+ -o $oakdir/$celltype/merge_folds_new/$celltype"_folds_merged.counts_scores.bw" \
+ -s $oakdir/$celltype/merge_folds_new/$celltype"_folds_merged.counts_scores.stat" \
+ -t 1
+
+celltype="K562"
+zcat $oakdir/$celltype/merge_folds_new/$celltype"_folds_merged.counts_scores_new_compressed.bed" > $oakdir/$celltype/merge_folds_new/$celltype"_folds_merged.counts_scores_new_compressed.unzip.bed"
+wc -l $oakdir/$celltype/merge_folds_new/$celltype"_folds_merged.counts_scores_new_compressed.unzip.bed"
+python /mnt/lab_data2/anusri/chrombpnet/src/evaluation/make_bigwigs/importance_hdf5_to_bigwig.py \
+ -h5 $oakdir/$celltype/merge_folds_new/$celltype"_folds_merged.counts_scores_new_compressed.h5" \
+ -r $oakdir/$celltype/merge_folds_new/$celltype"_folds_merged.counts_scores_new_compressed.unzip.bed" \
+ -c /mnt/lab_data2/anusri/chrombpnet/reference/chrom.sizes \
+ -o $oakdir/$celltype/merge_folds_new/$celltype"_folds_merged.counts_scores.bw" \
+ -s $oakdir/$celltype/merge_folds_new/$celltype"_folds_merged.counts_scores.stat" \
+ -t 1
+
+celltype="GM12878"
+zcat $oakdir/$celltype/merge_folds_new/$celltype"_folds_merged.counts_scores_new_compressed.bed" > $oakdir/$celltype/merge_folds_new/$celltype"_folds_merged.counts_scores_new_compressed.unzip.bed"
+wc -l $oakdir/$celltype/merge_folds_new/$celltype"_folds_merged.counts_scores_new_compressed.unzip.bed"
+python /mnt/lab_data2/anusri/chrombpnet/src/evaluation/make_bigwigs/importance_hdf5_to_bigwig.py \
+ -h5 $oakdir/$celltype/merge_folds_new/$celltype"_folds_merged.counts_scores_new_compressed.h5" \
+ -r $oakdir/$celltype/merge_folds_new/$celltype"_folds_merged.counts_scores_new_compressed.unzip.bed" \
+ -c /mnt/lab_data2/anusri/chrombpnet/reference/chrom.sizes \
+ -o $oakdir/$celltype/merge_folds_new/$celltype"_folds_merged.counts_scores.bw" \
+ -s $oakdir/$celltype/merge_folds_new/$celltype"_folds_merged.counts_scores.stat" \
+ -t 1
+
+
+celltype="IMR90"
+zcat $oakdir/$celltype/merge_folds_new/$celltype"_folds_merged.counts_scores_new_compressed.bed" > $oakdir/$celltype/merge_folds_new/$celltype"_folds_merged.counts_scores_new_compressed.unzip.bed"
+wc -l $oakdir/$celltype/merge_folds_new/$celltype"_folds_merged.counts_scores_new_compressed.unzip.bed"
+python /mnt/lab_data2/anusri/chrombpnet/src/evaluation/make_bigwigs/importance_hdf5_to_bigwig.py \
+ -h5 $oakdir/$celltype/merge_folds_new/$celltype"_folds_merged.counts_scores_new_compressed.h5" \
+ -r $oakdir/$celltype/merge_folds_new/$celltype"_folds_merged.counts_scores_new_compressed.unzip.bed" \
+ -c /mnt/lab_data2/anusri/chrombpnet/reference/chrom.sizes \
+ -o $oakdir/$celltype/merge_folds_new/$celltype"_folds_merged.counts_scores.bw" \
+ -s $oakdir/$celltype/merge_folds_new/$celltype"_folds_merged.counts_scores.stat" \
+ -t 1
+
+
+celltype="H1ESC"
+zcat $oakdir/$celltype/merge_folds_new/$celltype"_folds_merged.counts_scores_new_compressed.bed" > $oakdir/$celltype/merge_folds_new/$celltype"_folds_merged.counts_scores_new_compressed.unzip.bed"
+wc -l $oakdir/$celltype/merge_folds_new/$celltype"_folds_merged.counts_scores_new_compressed.unzip.bed"
+python /mnt/lab_data2/anusri/chrombpnet/src/evaluation/make_bigwigs/importance_hdf5_to_bigwig.py \
+ -h5 $oakdir/$celltype/merge_folds_new/$celltype"_folds_merged.counts_scores_new_compressed.h5" \
+ -r $oakdir/$celltype/merge_folds_new/$celltype"_folds_merged.counts_scores_new_compressed.unzip.bed" \
+ -c /mnt/lab_data2/anusri/chrombpnet/reference/chrom.sizes \
+ -o $oakdir/$celltype/merge_folds_new/$celltype"_folds_merged.counts_scores.bw" \
+ -s $oakdir/$celltype/merge_folds_new/$celltype"_folds_merged.counts_scores.stat" \
+ -t 1
diff --git a/logs/checkpoint/JAN_02_2023/dnase_make_average_bigwigs_profile.sh b/logs/checkpoint/JAN_02_2023/dnase_make_average_bigwigs_profile.sh
new file mode 100644
index 00000000..98923925
--- /dev/null
+++ b/logs/checkpoint/JAN_02_2023/dnase_make_average_bigwigs_profile.sh
@@ -0,0 +1,57 @@
+oakdir="/oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/chrombpnet/folds/DNASE/"
+celltype="HEPG2"
+zcat $oakdir/$celltype/merge_folds_new/$celltype"_folds_merged.profile_scores_new_compressed.bed" > $oakdir/$celltype/merge_folds_new/$celltype"_folds_merged.profile_scores_new_compressed.unzip.bed"
+wc -l $oakdir/$celltype/merge_folds_new/$celltype"_folds_merged.profile_scores_new_compressed.unzip.bed"
+python /mnt/lab_data2/anusri/chrombpnet/src/evaluation/make_bigwigs/importance_hdf5_to_bigwig.py \
+ -h5 $oakdir/$celltype/merge_folds_new/$celltype"_folds_merged.profile_scores_new_compressed.h5" \
+ -r $oakdir/$celltype/merge_folds_new/$celltype"_folds_merged.profile_scores_new_compressed.unzip.bed" \
+ -c /mnt/lab_data2/anusri/chrombpnet/reference/chrom.sizes \
+ -o $oakdir/$celltype/merge_folds_new/$celltype"_folds_merged.profile_scores.bw" \
+ -s $oakdir/$celltype/merge_folds_new/$celltype"_folds_merged.profile_scores.stat" \
+ -t 1
+
+celltype="K562"
+zcat $oakdir/$celltype/merge_folds_new/$celltype"_folds_merged.profile_scores_new_compressed.bed" > $oakdir/$celltype/merge_folds_new/$celltype"_folds_merged.profile_scores_new_compressed.unzip.bed"
+wc -l $oakdir/$celltype/merge_folds_new/$celltype"_folds_merged.profile_scores_new_compressed.unzip.bed"
+python /mnt/lab_data2/anusri/chrombpnet/src/evaluation/make_bigwigs/importance_hdf5_to_bigwig.py \
+ -h5 $oakdir/$celltype/merge_folds_new/$celltype"_folds_merged.profile_scores_new_compressed.h5" \
+ -r $oakdir/$celltype/merge_folds_new/$celltype"_folds_merged.profile_scores_new_compressed.unzip.bed" \
+ -c /mnt/lab_data2/anusri/chrombpnet/reference/chrom.sizes \
+ -o $oakdir/$celltype/merge_folds_new/$celltype"_folds_merged.profile_scores.bw" \
+ -s $oakdir/$celltype/merge_folds_new/$celltype"_folds_merged.profile_scores.stat" \
+ -t 1
+
+celltype="GM12878"
+zcat $oakdir/$celltype/merge_folds_new/$celltype"_folds_merged.profile_scores_new_compressed.bed" > $oakdir/$celltype/merge_folds_new/$celltype"_folds_merged.profile_scores_new_compressed.unzip.bed"
+wc -l $oakdir/$celltype/merge_folds_new/$celltype"_folds_merged.profile_scores_new_compressed.unzip.bed"
+python /mnt/lab_data2/anusri/chrombpnet/src/evaluation/make_bigwigs/importance_hdf5_to_bigwig.py \
+ -h5 $oakdir/$celltype/merge_folds_new/$celltype"_folds_merged.profile_scores_new_compressed.h5" \
+ -r $oakdir/$celltype/merge_folds_new/$celltype"_folds_merged.profile_scores_new_compressed.unzip.bed" \
+ -c /mnt/lab_data2/anusri/chrombpnet/reference/chrom.sizes \
+ -o $oakdir/$celltype/merge_folds_new/$celltype"_folds_merged.profile_scores.bw" \
+ -s $oakdir/$celltype/merge_folds_new/$celltype"_folds_merged.profile_scores.stat" \
+ -t 1
+
+
+celltype="IMR90"
+zcat $oakdir/$celltype/merge_folds_new/$celltype"_folds_merged.profile_scores_new_compressed.bed" > $oakdir/$celltype/merge_folds_new/$celltype"_folds_merged.profile_scores_new_compressed.unzip.bed"
+wc -l $oakdir/$celltype/merge_folds_new/$celltype"_folds_merged.profile_scores_new_compressed.unzip.bed"
+python /mnt/lab_data2/anusri/chrombpnet/src/evaluation/make_bigwigs/importance_hdf5_to_bigwig.py \
+ -h5 $oakdir/$celltype/merge_folds_new/$celltype"_folds_merged.profile_scores_new_compressed.h5" \
+ -r $oakdir/$celltype/merge_folds_new/$celltype"_folds_merged.profile_scores_new_compressed.unzip.bed" \
+ -c /mnt/lab_data2/anusri/chrombpnet/reference/chrom.sizes \
+ -o $oakdir/$celltype/merge_folds_new/$celltype"_folds_merged.profile_scores.bw" \
+ -s $oakdir/$celltype/merge_folds_new/$celltype"_folds_merged.profile_scores.stat" \
+ -t 1
+
+
+celltype="H1ESC"
+zcat $oakdir/$celltype/merge_folds_new/$celltype"_folds_merged.profile_scores_new_compressed.bed" > $oakdir/$celltype/merge_folds_new/$celltype"_folds_merged.profile_scores_new_compressed.unzip.bed"
+wc -l $oakdir/$celltype/merge_folds_new/$celltype"_folds_merged.profile_scores_new_compressed.unzip.bed"
+python /mnt/lab_data2/anusri/chrombpnet/src/evaluation/make_bigwigs/importance_hdf5_to_bigwig.py \
+ -h5 $oakdir/$celltype/merge_folds_new/$celltype"_folds_merged.profile_scores_new_compressed.h5" \
+ -r $oakdir/$celltype/merge_folds_new/$celltype"_folds_merged.profile_scores_new_compressed.unzip.bed" \
+ -c /mnt/lab_data2/anusri/chrombpnet/reference/chrom.sizes \
+ -o $oakdir/$celltype/merge_folds_new/$celltype"_folds_merged.profile_scores.bw" \
+ -s $oakdir/$celltype/merge_folds_new/$celltype"_folds_merged.profile_scores.stat" \
+ -t 1
diff --git a/logs/checkpoint/JAN_02_2023/screenlog/output1.log b/logs/checkpoint/JAN_02_2023/screenlog/output1.log
new file mode 100644
index 00000000..839611d7
--- /dev/null
+++ b/logs/checkpoint/JAN_02_2023/screenlog/output1.log
@@ -0,0 +1,408 @@
+ -s /oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/chrombpnet/folds/$dtty/$cellty/interpret_upload/average_preds/$cellty"_folds_merged".profile_sc
+ores_new_compressed.stats \
+
+cellty=GM12878_new
+dtty=DNASE
+python /mnt/lab_data2/anusri/chrombpnet/src/evaluation/make_bigwigs/importance_hdf5_to_bigwig.py \
+ -h5 /oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/chrombpnet/folds/$dtty/$cellty/merge_folds_all_regions_jun_11_24/$cellty"_folds_merged".profil
+e_scores_new_compressed.h5 \
+ -r /oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/chrombpnet/folds/$dtty/$cellty/merge_folds_all_regions_jun_11_24/$cellty"_folds_merged".profile
+_scores_new_compressed.bed.gz \
+ -c /mnt/lab_data2/anusri/chrombpnet/reference/chrom.sizes \
+ -o /oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/chrombpnet/folds/$dtty/$cellty/interpret_upload/average_preds/$cellty"_folds_merged".profile_sc
+ores_new_compressed.bw \
+ -s /oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/chrombpnet/folds/$dtty/$cellty/interpret_upload/average_preds/$cellty"_folds_merged".profile_sc
+ores_new_compressed.stats \
+
+
+
+cellty=IMR90
+dtty=ATAC
+python /mnt/lab_data2/anusri/chrombpnet/src/evaluation/make_bigwigs/importance_hdf5_to_bigwig.py \
+ -h5 /oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/chrombpnet/folds/$dtty/$cellty/merge_folds_all_regions_jun_11_24/$cellty"_folds_merged".counts
+_scores_new_compressed.h5 \
+ -r /oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/chrombpnet/folds/$dtty/$cellty/merge_folds_all_regions_jun_11_24/$cellty"_folds_merged".counts_
+scores_new_compressed.bed.gz \
+ -c /mnt/lab_data2/anusri/chrombpnet/reference/chrom.sizes \
+ -o /oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/chrombpnet/folds/$dtty/$cellty/interpret_upload/average_preds/$cellty"_folds_merged".counts_sco
+res_new_compressed.bw \
+ -s /oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/chrombpnet/folds/$dtty/$cellty/interpret_upload/average_preds/$cellty"_folds_merged".counts_sco
+res_new_compressed.stats \
+
+cellty=GM12878
+dtty=ATAC
+python /mnt/lab_data2/anusri/chrombpnet/src/evaluation/make_bigwigs/importance_hdf5_to_bigwig.py \
+ -h5 /oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/chrombpnet/folds/$dtty/$cellty/merge_folds_all_regions_jun_11_24/$cellty"_folds_merged".counts
+_scores_new_compressed.h5 \
+ -r /oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/chrombpnet/folds/$dtty/$cellty/merge_folds_all_regions_jun_11_24/$cellty"_folds_merged".counts_
+scores_new_compressed.bed.gz \
+ -c /mnt/lab_data2/anusri/chrombpnet/reference/chrom.sizes \
+ -o /oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/chrombpnet/folds/$dtty/$cellty/interpret_upload/average_preds/$cellty"_folds_merged".counts_sco
+res_new_compressed.bw \
+ -s /oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/chrombpnet/folds/$dtty/$cellty/interpret_upload/average_preds/$cellty"_folds_merged".counts_sco
+res_new_compressed.stats \
+
+cellty=H1ESC
+dtty=ATAC
+python /mnt/lab_data2/anusri/chrombpnet/src/evaluation/make_bigwigs/importance_hdf5_to_bigwig.py \
+ -h5 /oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/chrombpnet/folds/$dtty/$cellty/merge_folds_all_regions_jun_11_24/$cellty"_folds_merged".counts
+_scores_new_compressed.h5 \
+ -r /oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/chrombpnet/folds/$dtty/$cellty/merge_folds_all_regions_jun_11_24/$cellty"_folds_merged".counts_
+scores_new_compressed.bed.gz \
+ -c /mnt/lab_data2/anusri/chrombpnet/reference/chrom.sizes \
+ -o /oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/chrombpnet/folds/$dtty/$cellty/interpret_upload/average_preds/$cellty"_folds_merged".counts_sco
+res_new_compressed.bw \
+ -s /oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/chrombpnet/folds/$dtty/$cellty/interpret_upload/average_preds/$cellty"_folds_merged".counts_sco
+res_new_compressed.stats \
+
+cellty=IMR90_new
+dtty=DNASE
+python /mnt/lab_data2/anusri/chrombpnet/src/evaluation/make_bigwigs/importance_hdf5_to_bigwig.py \
+ -h5 /oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/chrombpnet/folds/$dtty/$cellty/merge_folds_all_regions_jun_11_24/$cellty"_folds_merged".counts
+_scores_new_compressed.h5 \
+ -r /oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/chrombpnet/folds/$dtty/$cellty/merge_folds_all_regions_jun_11_24/$cellty"_folds_merged".counts_
+scores_new_compressed.bed.gz \
+ -c /mnt/lab_data2/anusri/chrombpnet/reference/chrom.sizes \
+ -o /oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/chrombpnet/folds/$dtty/$cellty/interpret_upload/average_preds/$cellty"_folds_merged".counts_sco
+res_new_compressed.bw \
+
+
+(base) anusri@brahma:/mnt/lab_data2/anusri/chrombpnet/logs/checkpoint/JAN_02_2023$ nano script_make_bigwig.sh
+
+
+#merge_folds_all_regions_may_05_24/$cellty"_folds_merged".counts_scores_new_compressed.bw
+
+# cellty=IMR90
+# dtty=ATAC
+# python /mnt/lab_data2/anusri/chrombpnet/src/evaluation/make_bigwigs/importance_hdf5_to_bigwig.py \
+# -h5 /oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/chrombpnet/folds/$dtty/$cellty/merge_folds_all_regions_may_05_24/$cellty"_folds_merged".profil
+e_scores_new_compressed.h5 \
+# -r /oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/chrombpnet/folds/$dtty/$cellty/merge_folds_all_regions_may_05_24/$cellty"_folds_merged".profile
+_scores_new_compressed.bed.gz \
+# -c /mnt/lab_data2/anusri/chrombpnet/reference/chrom.sizes \
+# -o /oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/chrombpnet/folds/$dtty/$cellty/interpret_upload/average_preds/$cellty"_folds_merged".profile_sc
+ores_new_compressed.bw \
+# -s /oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/chrombpnet/folds/$dtty/$cellty/interpret_upload/average_preds/$cellty"_folds_merged".profile_sc
+ores_new_compressed.stats \
+#
+# cellty=GM12878
+# dtty=ATAC
+# python /mnt/lab_data2/anusri/chrombpnet/src/evaluation/make_bigwigs/importance_hdf5_to_bigwig.py \
+# -h5 /oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/chrombpnet/folds/$dtty/$cellty/merge_folds_all_regions_may_05_24/$cellty"_folds_merged".profil
+e_scores_new_compressed.h5 \
+# -r /oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/chrombpnet/folds/$dtty/$cellty/merge_folds_all_regions_may_05_24/$cellty"_folds_merged".profile
+_scores_new_compressed.bed.gz \
+# -c /mnt/lab_data2/anusri/chrombpnet/reference/chrom.sizes \
+# -o /oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/chrombpnet/folds/$dtty/$cellty/interpret_upload/average_preds/$cellty"_folds_merged".profile_sc
+ores_new_compressed.bw \
+# -s /oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/chrombpnet/folds/$dtty/$cellty/interpret_upload/average_preds/$cellty"_folds_merged".profile_sc
+ores_new_compressed.stats \
+#
+# cellty=H1ESC
+# dtty=ATAC
+# python /mnt/lab_data2/anusri/chrombpnet/src/evaluation/make_bigwigs/importance_hdf5_to_bigwig.py \
+# -h5 /oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/chrombpnet/folds/$dtty/$cellty/merge_folds_all_regions_may_05_24/$cellty"_folds_merged".profil
+e_scores_new_compressed.h5 \
+# -r /oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/chrombpnet/folds/$dtty/$cellty/merge_folds_all_regions_may_05_24/$cellty"_folds_merged".profile
+_scores_new_compressed.bed.gz \
+# -c /mnt/lab_data2/anusri/chrombpnet/reference/chrom.sizes \
+# -o /oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/chrombpnet/folds/$dtty/$cellty/interpret_upload/average_preds/$cellty"_folds_merged".profile_sc
+ores_new_compressed.bw \
+# -s /oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/chrombpnet/folds/$dtty/$cellty/interpret_upload/average_preds/$cellty"_folds_merged".profile_sc
+ores_new_compressed.stats \
+
+cellty=IMR90_new
+dtty=DNASE
+python /mnt/lab_data2/anusri/chrombpnet/src/evaluation/make_bigwigs/importance_hdf5_to_bigwig.py \
+ -h5 /oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/chrombpnet/folds/$dtty/$cellty/merge_folds_all_regions_jun_11_24/$cellty"_folds_merged".profil
+e_scores_new_compressed.h5 \
+ -r /oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/chrombpnet/folds/$dtty/$cellty/merge_folds_all_regions_jun_11_24/$cellty"_folds_merged".profile
+_scores_new_compressed.bed.gz \
+ -c /mnt/lab_data2/anusri/chrombpnet/reference/chrom.sizes \
+ -o /oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/chrombpnet/folds/$dtty/$cellty/interpret_upload/average_preds/$cellty"_folds_merged".profile_sc
+ores_new_compressed.bw \
+ -s /oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/chrombpnet/folds/$dtty/$cellty/interpret_upload/average_preds/$cellty"_folds_merged".profile_sc
+ores_new_compressed.stats \
+
+cellty=H1ESC_new
+dtty=DNASE
+python /mnt/lab_data2/anusri/chrombpnet/src/evaluation/make_bigwigs/importance_hdf5_to_bigwig.py \
+ -h5 /oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/chrombpnet/folds/$dtty/$cellty/merge_folds_all_regions_jun_11_24/$cellty"_folds_merged".profil
+e_scores_new_compressed.h5 \
+ -r /oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/chrombpnet/folds/$dtty/$cellty/merge_folds_all_regions_jun_11_24/$cellty"_folds_merged".profile
+_scores_new_compressed.bed.gz \
+ -c /mnt/lab_data2/anusri/chrombpnet/reference/chrom.sizes \
+ -o /oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/chrombpnet/folds/$dtty/$cellty/interpret_upload/average_preds/$cellty"_folds_merged".profile_sc
+ores_new_compressed.bw \
+ -s /oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/chrombpnet/folds/$dtty/$cellty/interpret_upload/average_preds/$cellty"_folds_merged".profile_sc
+ores_new_compressed.stats \
+
+cellty=GM12878_new
+dtty=DNASE
+python /mnt/lab_data2/anusri/chrombpnet/src/evaluation/make_bigwigs/importance_hdf5_to_bigwig.py \
+ -h5 /oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/chrombpnet/folds/$dtty/$cellty/merge_folds_all_regions_jun_11_24/$cellty"_folds_merged".profil
+e_scores_new_compressed.h5 \
+ -r /oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/chrombpnet/folds/$dtty/$cellty/merge_folds_all_regions_jun_11_24/$cellty"_folds_merged".profile
+_scores_new_compressed.bed.gz \
+ -c /mnt/lab_data2/anusri/chrombpnet/reference/chrom.sizes \
+ -o /oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/chrombpnet/folds/$dtty/$cellty/interpret_upload/average_preds/$cellty"_folds_merged".profile_sc
+ores_new_compressed.bw \
+ -s /oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/chrombpnet/folds/$dtty/$cellty/interpret_upload/average_preds/$cellty"_folds_merged".profile_sc
+ores_new_compressed.stats \
+
+
+
+# cellty=IMR90
+# dtty=ATAC
+# python /mnt/lab_data2/anusri/chrombpnet/src/evaluation/make_bigwigs/importance_hdf5_to_bigwig.py \
+# -h5 /oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/chrombpnet/folds/$dtty/$cellty/merge_folds_all_regions_may_05_24/$cellty"_folds_merged".counts
+_scores_new_compressed.h5 \
+# -r /oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/chrombpnet/folds/$dtty/$cellty/merge_folds_all_regions_may_05_24/$cellty"_folds_merged".counts_
+scores_new_compressed.bed.gz \
+# -c /mnt/lab_data2/anusri/chrombpnet/reference/chrom.sizes \
+# -o /oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/chrombpnet/folds/$dtty/$cellty/interpret_upload/average_preds/$cellty"_folds_merged".counts_sco
+res_new_compressed.bw \
+# -s /oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/chrombpnet/folds/$dtty/$cellty/interpret_upload/average_preds/$cellty"_folds_merged".counts_sco
+res_new_compressed.stats \
+#
+# cellty=GM12878
+# dtty=ATAC
+# python /mnt/lab_data2/anusri/chrombpnet/src/evaluation/make_bigwigs/importance_hdf5_to_bigwig.py \
+# -h5 /oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/chrombpnet/folds/$dtty/$cellty/merge_folds_all_regions_may_05_24/$cellty"_folds_merged".counts
+_scores_new_compressed.h5 \
+# -r /oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/chrombpnet/folds/$dtty/$cellty/merge_folds_all_regions_may_05_24/$cellty"_folds_merged".counts_
+scores_new_compressed.bed.gz \
+# -c /mnt/lab_data2/anusri/chrombpnet/reference/chrom.sizes \
+# -o /oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/chrombpnet/folds/$dtty/$cellty/interpret_upload/average_preds/$cellty"_folds_merged".counts_sco
+res_new_compressed.bw \
+# -s /oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/chrombpnet/folds/$dtty/$cellty/interpret_upload/average_preds/$cellty"_folds_merged".counts_sco
+res_new_compressed.stats \
+#
+# cellty=H1ESC
+# dtty=ATAC
+# python /mnt/lab_data2/anusri/chrombpnet/src/evaluation/make_bigwigs/importance_hdf5_to_bigwig.py \
+# -h5 /oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/chrombpnet/folds/$dtty/$cellty/merge_folds_all_regions_may_05_24/$cellty"_folds_merged".counts
+_scores_new_compressed.h5 \
+# -r /oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/chrombpnet/folds/$dtty/$cellty/merge_folds_all_regions_may_05_24/$cellty"_folds_merged".counts_
+scores_new_compressed.bed.gz \
+# -c /mnt/lab_data2/anusri/chrombpnet/reference/chrom.sizes \
+# -o /oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/chrombpnet/folds/$dtty/$cellty/interpret_upload/average_preds/$cellty"_folds_merged".counts_sco
+res_new_compressed.bw \
+# -s /oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/chrombpnet/folds/$dtty/$cellty/interpret_upload/average_preds/$cellty"_folds_merged".counts_sco
+res_new_compressed.stats \
+
+cellty=IMR90_new
+dtty=DNASE
+python /mnt/lab_data2/anusri/chrombpnet/src/evaluation/make_bigwigs/importance_hdf5_to_bigwig.py \
+ -h5 /oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/chrombpnet/folds/$dtty/$cellty/merge_folds_all_regions_jun_11_24/$cellty"_folds_merged".counts
+_scores_new_compressed.h5 \
+ -r /oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/chrombpnet/folds/$dtty/$cellty/merge_folds_all_regions_jun_11_24/$cellty"_folds_merged".counts_
+scores_new_compressed.bed.gz \
+ -c /mnt/lab_data2/anusri/chrombpnet/reference/chrom.sizes \
+ -o /oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/chrombpnet/folds/$dtty/$cellty/interpret_upload/average_preds/$cellty"_folds_merged".counts_sco
+res_new_compressed.bw \
+ -s /oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/chrombpnet/folds/$dtty/$cellty/interpret_upload/average_preds/$cellty"_folds_merged".counts_sco
+res_new_compressed.stats \
+ GNU nano 6.2 script_make_bigwig.sh
+
+
+cellty=H1ESC_new
+dtty=DNASE
+python /mnt/lab_data2/anusri/chrombpnet/src/evaluation/make_bigwigs/importance_hdf5_to_bigwig.py \
+ -h5 /oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/chrombpnet/folds/$dtty/$cellty/merge_folds_all_regions_jun_11_24/$cellty"_folds_merged".counts
+_scores_new_compressed.h5 \
+ -r /oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/chrombpnet/folds/$dtty/$cellty/merge_folds_all_regions_jun_11_24/$cellty"_folds_merged".counts_
+scores_new_compressed.bed.gz \
+ -c /mnt/lab_data2/anusri/chrombpnet/reference/chrom.sizes \
+ -o /oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/chrombpnet/folds/$dtty/$cellty/interpret_upload/average_preds/$cellty"_folds_merged".counts_sco
+res_new_compressed.bw \
+ -s /oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/chrombpnet/folds/$dtty/$cellty/interpret_upload/average_preds/$cellty"_folds_merged".counts_sco
+res_new_compressed.stats \
+
+cellty=GM12878_new
+dtty=DNASE
+python /mnt/lab_data2/anusri/chrombpnet/src/evaluation/make_bigwigs/importance_hdf5_to_bigwig.py \
+ -h5 /oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/chrombpnet/folds/$dtty/$cellty/merge_folds_all_regions_jun_11_24/$cellty"_folds_merged".counts
+_scores_new_compressed.h5 \
+ -r /oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/chrombpnet/folds/$dtty/$cellty/merge_folds_all_regions_jun_11_24/$cellty"_folds_merged".counts_
+scores_new_compressed.bed.gz \
+ -c /mnt/lab_data2/anusri/chrombpnet/reference/chrom.sizes \
+ -o /oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/chrombpnet/folds/$dtty/$cellty/interpret_upload/average_preds/$cellty"_folds_merged".counts_sco
+res_new_compressed.bw \
+ -s /oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/chrombpnet/folds/$dtty/$cellty/interpret_upload/average_preds/$cellty"_folds_merged".counts_sco
+res_new_compressed.stats \
+
+
+#python /mnt/lab_data2/anusri/chrombpnet/src/evaluation/make_bigwigs/importance_hdf5_to_bigwig.py \
+# -h5 /oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/chrombpnet/folds/DNASE/HEPG2/merge_folds_new_may_05_24/HEPG2_folds_merged.counts_scores_new_co
+mpressed.h5 \
+# -r /mnt/lab_data2/anusri/chrombpnet/results/chrombpnet/hepg2.merged.atac.dnase.peaks.bed \
+# -c /mnt/lab_data2/anusri/chrombpnet/reference/chrom.sizes \
+# -o /oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/chrombpnet/folds/DNASE/HEPG2/interpret_upload/average_preds/HEPG2_folds_merged.counts_scores.bw
+ \
+# -s /oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/chrombpnet/folds/DNASE/HEPG2/interpret_upload/average_preds/HEPG2_folds_merged.counts_scores.st
+ats \
+
+#python /mnt/lab_data2/anusri/chrombpnet/src/evaluation/make_bigwigs/importance_hdf5_to_bigwig.py \
+# -h5 /oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/chrombpnet/folds/DNASE/K562/merge_folds_new_may_05_24/K562_folds_merged.counts_scores_new_comp
+ressed.h5 \
+# -r /mnt/lab_data2/anusri/chrombpnet/results/chrombpnet/k562.merged.atac.dnase.peaks.bed \
+# -c /mnt/lab_data2/anusri/chrombpnet/reference/chrom.sizes \
+# -o /oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/chrombpnet/folds/DNASE/K562/interpret_upload/average_preds/K562_folds_merged.counts_scores.bw
+\
+# -s /oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/chrombpnet/folds/DNASE/K562/interpret_upload/average_preds/K562_folds_merged.counts_scores.stat
+s \
+
+
+#python /mnt/lab_data2/anusri/chrombpnet/src/evaluation/make_bigwigs/importance_hdf5_to_bigwig.py \
+# -h5 /oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/chrombpnet/folds/ATAC/HEPG2/merge_folds_new_may_05_24/HEPG2_folds_merged.profile_scores_new_co
+mpressed.h5 \
+# -r /mnt/lab_data2/anusri/chrombpnet/results/chrombpnet/hepg2.merged.atac.dnase.peaks.bed \
+# -c /mnt/lab_data2/anusri/chrombpnet/reference/chrom.sizes \
+# -o /oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/chrombpnet/folds/ATAC/HEPG2/interpret_upload/average_preds/HEPG2_folds_merged.profile_scores.bw
+ \
+# -s /oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/chrombpnet/folds/ATAC/HEPG2/interpret_upload/average_preds/HEPG2_folds_merged.profile_scores.st
+ats \
+
+#python /mnt/lab_data2/anusri/chrombpnet/src/evaluation/make_bigwigs/importance_hdf5_to_bigwig.py \
+# -h5 /oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/chrombpnet/folds/ATAC/K562/merge_folds_new_may_05_24/K562_folds_merged.profile_scores_new_comp
+ressed.h5 \
+# -r /mnt/lab_data2/anusri/chrombpnet/results/chrombpnet/k562.merged.atac.dnase.peaks.bed \
+# -c /mnt/lab_data2/anusri/chrombpnet/reference/chrom.sizes \
+# -o /oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/chrombpnet/folds/ATAC/K562/interpret_upload/average_preds/K562_folds_merged.profile_scores.bw
+\
+# -s /oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/chrombpnet/folds/ATAC/K562/interpret_upload/average_preds/K562_folds_merged.profile_scores.stat
+s \
+
+
+
+
+
+
+
+
+
+
+(base) anusri@brahma:/mnt/lab_data2/anusri/chrombpnet/logs/checkpoint/JAN_02_2023$ bash script_make_bigwig.sh
+Namespace(chrom_sizes='/mnt/lab_data2/anusri/chrombpnet/reference/chrom.sizes', debug_chr=None, hdf5='/oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/chro
+mbpnet/folds/DNASE/IMR90_new/merge_folds_all_regions_jun_11_24/IMR90_new_folds_merged.profile_scores_new_compressed.h5', outfile='/oak/stanford/groups/akundaje/projec
+ts/chromatin-atlas-2022/chrombpnet/folds/DNASE/IMR90_new/interpret_upload/average_preds/IMR90_new_folds_merged.profile_scores_new_compressed.bw', outstats='/oak/stanf
+ord/groups/akundaje/projects/chromatin-atlas-2022/chrombpnet/folds/DNASE/IMR90_new/interpret_upload/average_preds/IMR90_new_folds_merged.profile_scores_new_compressed
+.stats', regions='/oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/chrombpnet/folds/DNASE/IMR90_new/merge_folds_all_regions_jun_11_24/IMR90_new_folds_merge
+d.profile_scores_new_compressed.bed.gz', tqdm=0)
+/mnt/lab_data2/anusri/chrombpnet/src/evaluation/make_bigwigs/importance_hdf5_to_bigwig.py:26: DtypeWarning: Columns (4,6,7,8) have mixed types.Specify dtype option on
+ import or set low_memory=False.
+ regions = bigwig_helper.get_regions(args.regions, SEQLEN)
+Namespace(chrom_sizes='/mnt/lab_data2/anusri/chrombpnet/reference/chrom.sizes', debug_chr=None, hdf5='/oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/chro
+mbpnet/folds/DNASE/H1ESC_new/merge_folds_all_regions_jun_11_24/H1ESC_new_folds_merged.profile_scores_new_compressed.h5', outfile='/oak/stanford/groups/akundaje/projec
+ts/chromatin-atlas-2022/chrombpnet/folds/DNASE/H1ESC_new/interpret_upload/average_preds/H1ESC_new_folds_merged.profile_scores_new_compressed.bw', outstats='/oak/stanf
+ord/groups/akundaje/projects/chromatin-atlas-2022/chrombpnet/folds/DNASE/H1ESC_new/interpret_upload/average_preds/H1ESC_new_folds_merged.profile_scores_new_compressed
+.stats', regions='/oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/chrombpnet/folds/DNASE/H1ESC_new/merge_folds_all_regions_jun_11_24/H1ESC_new_folds_merge
+d.profile_scores_new_compressed.bed.gz', tqdm=0)
+/mnt/lab_data2/anusri/chrombpnet/src/evaluation/make_bigwigs/importance_hdf5_to_bigwig.py:26: DtypeWarning: Columns (4,6,7,8) have mixed types.Specify dtype option on
+ import or set low_memory=False.
+ regions = bigwig_helper.get_regions(args.regions, SEQLEN)
+Namespace(chrom_sizes='/mnt/lab_data2/anusri/chrombpnet/reference/chrom.sizes', debug_chr=None, hdf5='/oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/chro
+mbpnet/folds/DNASE/GM12878_new/merge_folds_all_regions_jun_11_24/GM12878_new_folds_merged.profile_scores_new_compressed.h5', outfile='/oak/stanford/groups/akundaje/pr
+ojects/chromatin-atlas-2022/chrombpnet/folds/DNASE/GM12878_new/interpret_upload/average_preds/GM12878_new_folds_merged.profile_scores_new_compressed.bw', outstats='/o
+ak/stanford/groups/akundaje/projects/chromatin-atlas-2022/chrombpnet/folds/DNASE/GM12878_new/interpret_upload/average_preds/GM12878_new_folds_merged.profile_scores_ne
+w_compressed.stats', regions='/oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/chrombpnet/folds/DNASE/GM12878_new/merge_folds_all_regions_jun_11_24/GM12878
+_new_folds_merged.profile_scores_new_compressed.bed.gz', tqdm=0)
+/mnt/lab_data2/anusri/chrombpnet/src/evaluation/make_bigwigs/importance_hdf5_to_bigwig.py:26: DtypeWarning: Columns (4,6,7,8) have mixed types.Specify dtype option on
+ import or set low_memory=False.
+ regions = bigwig_helper.get_regions(args.regions, SEQLEN)
+Namespace(chrom_sizes='/mnt/lab_data2/anusri/chrombpnet/reference/chrom.sizes', debug_chr=None, hdf5='/oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/chro
+mbpnet/folds/DNASE/IMR90_new/merge_folds_all_regions_jun_11_24/IMR90_new_folds_merged.counts_scores_new_compressed.h5', outfile='/oak/stanford/groups/akundaje/project
+s/chromatin-atlas-2022/chrombpnet/folds/DNASE/IMR90_new/interpret_upload/average_preds/IMR90_new_folds_merged.counts_scores_new_compressed.bw', outstats='/oak/stanfor
+d/groups/akundaje/projects/chromatin-atlas-2022/chrombpnet/folds/DNASE/IMR90_new/interpret_upload/average_preds/IMR90_new_folds_merged.counts_scores_new_compressed.st
+ats', regions='/oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/chrombpnet/folds/DNASE/IMR90_new/merge_folds_all_regions_jun_11_24/IMR90_new_folds_merged.c
+ounts_scores_new_compressed.bed.gz', tqdm=0)
+/mnt/lab_data2/anusri/chrombpnet/src/evaluation/make_bigwigs/importance_hdf5_to_bigwig.py:26: DtypeWarning: Columns (4,6,7,8) have mixed types.Specify dtype option on
+ import or set low_memory=False.
+ regions = bigwig_helper.get_regions(args.regions, SEQLEN)
+Namespace(chrom_sizes='/mnt/lab_data2/anusri/chrombpnet/reference/chrom.sizes', debug_chr=None, hdf5='/oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/chro
+mbpnet/folds/DNASE/H1ESC_new/merge_folds_all_regions_jun_11_24/H1ESC_new_folds_merged.counts_scores_new_compressed.h5', outfile='/oak/stanford/groups/akundaje/project
+s/chromatin-atlas-2022/chrombpnet/folds/DNASE/H1ESC_new/interpret_upload/average_preds/H1ESC_new_folds_merged.counts_scores_new_compressed.bw', outstats='/oak/stanfor
+d/groups/akundaje/projects/chromatin-atlas-2022/chrombpnet/folds/DNASE/H1ESC_new/interpret_upload/average_preds/H1ESC_new_folds_merged.counts_scores_new_compressed.st
+ats', regions='/oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/chrombpnet/folds/DNASE/H1ESC_new/merge_folds_all_regions_jun_11_24/H1ESC_new_folds_merged.c
+ounts_scores_new_compressed.bed.gz', tqdm=0)
+/mnt/lab_data2/anusri/chrombpnet/src/evaluation/make_bigwigs/importance_hdf5_to_bigwig.py:26: DtypeWarning: Columns (4,6,7,8) have mixed types.Specify dtype option on
+ import or set low_memory=False.
+ regions = bigwig_helper.get_regions(args.regions, SEQLEN)
+Namespace(chrom_sizes='/mnt/lab_data2/anusri/chrombpnet/reference/chrom.sizes', debug_chr=None, hdf5='/oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/chro
+mbpnet/folds/DNASE/GM12878_new/merge_folds_all_regions_jun_11_24/GM12878_new_folds_merged.counts_scores_new_compressed.h5', outfile='/oak/stanford/groups/akundaje/pro
+jects/chromatin-atlas-2022/chrombpnet/folds/DNASE/GM12878_new/interpret_upload/average_preds/GM12878_new_folds_merged.counts_scores_new_compressed.bw', outstats='/oak
+/stanford/groups/akundaje/projects/chromatin-atlas-2022/chrombpnet/folds/DNASE/GM12878_new/interpret_upload/average_preds/GM12878_new_folds_merged.counts_scores_new_c
+ompressed.stats', regions='/oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/chrombpnet/folds/DNASE/GM12878_new/merge_folds_all_regions_jun_11_24/GM12878_ne
+w_folds_merged.counts_scores_new_compressed.bed.gz', tqdm=0)
+/mnt/lab_data2/anusri/chrombpnet/src/evaluation/make_bigwigs/importance_hdf5_to_bigwig.py:26: DtypeWarning: Columns (4,6,7,8) have mixed types.Specify dtype option on
+ import or set low_memory=False.
+ regions = bigwig_helper.get_regions(args.regions, SEQLEN)
+Namespace(chrom_sizes='/mnt/lab_data2/anusri/chrombpnet/reference/chrom.sizes', debug_chr=None, hdf5='/oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/chro
+mbpnet/folds/DNASE/HEPG2/merge_folds_all_regions_jun_11_24/HEPG2_folds_merged.counts_scores_new_compressed.h5', outfile='/oak/stanford/groups/akundaje/projects/chroma
+tin-atlas-2022/chrombpnet/folds/DNASE/HEPG2/interpret_upload/average_preds/HEPG2_folds_merged.counts_scores.bw', outstats='/oak/stanford/groups/akundaje/projects/chro
+matin-atlas-2022/chrombpnet/folds/DNASE/HEPG2/interpret_upload/average_preds/HEPG2_folds_merged.counts_scores.stats', regions='/oak/stanford/groups/akundaje/projects/
+chromatin-atlas-2022/chrombpnet/folds/DNASE/HEPG2/merge_folds_all_regions_jun_11_24/HEPG2_folds_merged.counts_scores_new_compressed.bed.gz', tqdm=0)
+/mnt/lab_data2/anusri/chrombpnet/src/evaluation/make_bigwigs/importance_hdf5_to_bigwig.py:26: DtypeWarning: Columns (4,6,7,8) have mixed types.Specify dtype option on
+ import or set low_memory=False.
+ regions = bigwig_helper.get_regions(args.regions, SEQLEN)
+Namespace(chrom_sizes='/mnt/lab_data2/anusri/chrombpnet/reference/chrom.sizes', debug_chr=None, hdf5='/oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/chro
+mbpnet/folds/DNASE/HEPG2/merge_folds_all_regions_jun_11_24/HEPG2_folds_merged.profile_scores_new_compressed.h5', outfile='/oak/stanford/groups/akundaje/projects/chrom
+atin-atlas-2022/chrombpnet/folds/DNASE/HEPG2/interpret_upload/average_preds/HEPG2_folds_merged.profile_scores.bw', outstats='/oak/stanford/groups/akundaje/projects/ch
+romatin-atlas-2022/chrombpnet/folds/DNASE/HEPG2/interpret_upload/average_preds/HEPG2_folds_merged.profile_scores.stats', regions='/oak/stanford/groups/akundaje/projec
+ts/chromatin-atlas-2022/chrombpnet/folds/DNASE/HEPG2/merge_folds_all_regions_jun_11_24/HEPG2_folds_merged.profile_scores_new_compressed.bed.gz', tqdm=0)
+/mnt/lab_data2/anusri/chrombpnet/src/evaluation/make_bigwigs/importance_hdf5_to_bigwig.py:26: DtypeWarning: Columns (4,6,7,8) have mixed types.Specify dtype option on
+ import or set low_memory=False.
+ regions = bigwig_helper.get_regions(args.regions, SEQLEN)
+(base) anusri@brahma:/mnt/lab_data2/anusri/chrombpnet/logs/checkpoint/JAN_02_2023$ bash script_make_bigwig.sh
+Namespace(chrom_sizes='/mnt/lab_data2/anusri/chrombpnet/reference/chrom.sizes', debug_chr=None, hdf5='/oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/chro
+mbpnet/folds/DNASE/K562/merge_folds_all_regions_jun_11_24/K562_folds_merged.counts_scores_new_compressed.h5', outfile='/oak/stanford/groups/akundaje/projects/chromati
+n-atlas-2022/chrombpnet/folds/DNASE/K562/interpret_upload/average_preds/K562_folds_merged.counts_scores.bw', outstats='/oak/stanford/groups/akundaje/projects/chromati
+n-atlas-2022/chrombpnet/folds/DNASE/K562/interpret_upload/average_preds/K562_folds_merged.counts_scores.stats', regions='/oak/stanford/groups/akundaje/projects/chroma
+tin-atlas-2022/chrombpnet/folds/DNASE/K562/merge_folds_all_regions_jun_11_24/K562_folds_merged.profile_scores_new_compressed.bed.gz', tqdm=0)
+/mnt/lab_data2/anusri/chrombpnet/src/evaluation/make_bigwigs/importance_hdf5_to_bigwig.py:26: DtypeWarning: Columns (4,6,7,8) have mixed types.Specify dtype option on
+ import or set low_memory=False.
+ regions = bigwig_helper.get_regions(args.regions, SEQLEN)
+Namespace(chrom_sizes='/mnt/lab_data2/anusri/chrombpnet/reference/chrom.sizes', debug_chr=None, hdf5='/oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/chro
+mbpnet/folds/DNASE/K562/merge_folds_all_regions_jun_11_24/K562_folds_merged.profile_scores_new_compressed.h5', outfile='/oak/stanford/groups/akundaje/projects/chromat
+in-atlas-2022/chrombpnet/folds/DNASE/K562/interpret_upload/average_preds/K562_folds_merged.profile_scores.bw', outstats='/oak/stanford/groups/akundaje/projects/chroma
+tin-atlas-2022/chrombpnet/folds/DNASE/K562/interpret_upload/average_preds/K562_folds_merged.profile_scores.stats', regions='/oak/stanford/groups/akundaje/projects/chr
+omatin-atlas-2022/chrombpnet/folds/DNASE/K562/merge_folds_all_regions_jun_11_24/K562_folds_merged.profile_scores_new_compressed.bed.gz', tqdm=0)
+^[[B^[[B^[[B^[[B^[[B^[[B^[[B^[[B^[[B^[[B^[[B^[[B^[[B^[[B^[[B^[[B^[[B^[[B^[[B^[[B^[[B^[[B^[[B^[[B^[[B^[[B^[[B^[[B^[[B^[[B^[[B^[[B^[[B^[[B^[[B/mnt/lab_data2/anusri/chro
+mbpnet/src/evaluation/make_bigwigs/importance_hdf5_to_bigwig.py:26: DtypeWarning: Columns (4,6,7,8) have mixed types.Specify dtype option on import or set low_memory=
+False.
+ regions = bigwig_helper.get_regions(args.regions, SEQLEN)
+(base) anusri@brahma:/mnt/lab_data2/anusri/chrombpnet/logs/checkpoint/JAN_02_2023$ mkdir screenlog
+(base) anusri@brahma:/mnt/lab_data2/anusri/chrombpnet/logs/checkpoint/JAN_02_2023$ hardcopy -h screenlog/out1.txt
+bash: hardcopy: command not found
+(base) anusri@brahma:/mnt/lab_data2/anusri/chrombpnet/logs/checkpoint/JAN_02_2023$ screen hardcopy -h screenlog/out1.txt
+(base) anusri@brahma:/mnt/lab_data2/anusri/chrombpnet/logs/checkpoint/JAN_02_2023$
+(base) anusri@brahma:/mnt/lab_data2/anusri/chrombpnet/logs/checkpoint/JAN_02_2023$
+(base) anusri@brahma:/mnt/lab_data2/anusri/chrombpnet/logs/checkpoint/JAN_02_2023$ screen -ls
+There are screens on:
+ 3740381.pts-62.brahma (08/06/2024 06:03:37 PM) (Attached)
+ 3644261.pts-56.brahma (07/31/2024 03:44:41 PM) (Detached)
+ 2370989.pts-34.brahma (05/24/2024 12:27:02 PM) (Detached)
+ 2293758.pts-34.brahma (05/20/2024 04:17:07 PM) (Detached)
+ 1995284.pts-40.brahma (05/12/2024 08:32:42 PM) (Detached)
+ 1897790.pts-34.brahma (05/08/2024 05:10:48 PM) (Detached)
+ 1864976.pts-35.brahma (05/07/2024 10:22:08 PM) (Detached)
+ 1824483.pts-36.brahma (05/07/2024 03:57:21 PM) (Detached)
+ 1789131.pts-1.brahma (05/05/2024 11:57:03 PM) (Detached)
+ 1788878.pts-1.brahma (05/05/2024 11:46:21 PM) (Detached)
+ 1766561.backup_lab_data_3 (05/04/2024 01:31:01 PM) (Detached)
+ 1753443.backup_lab_data2 (05/03/2024 05:09:13 PM) (Detached)
+ 1753280.backup_home (05/03/2024 05:06:46 PM) (Detached)
+ 936016.pts-8.brahma (04/21/2024 01:12:59 AM) (Detached)
+ 860877.pts-17.brahma (04/19/2024 04:50:50 PM) (Detached)
+ 860533.pts-17.brahma (04/19/2024 04:49:52 PM) (Detached)
+ 860064.pts-8.brahma (04/19/2024 04:44:45 PM) (Detached)
+ 859980.pts-8.brahma (04/19/2024 04:44:35 PM) (Detached)
+ 408994.pts-8.brahma (04/09/2024 03:19:03 PM) (Detached)
+ 292942.pts-8.brahma (04/08/2024 06:35:59 PM) (Detached)
+ 285213.pts-8.brahma (04/08/2024 06:07:50 PM) (Detached)
+ 162710.pts-8.brahma (04/02/2024 06:24:51 PM) (Detached)
+ 137607.pts-8.brahma (04/02/2024 11:51:24 AM) (Detached)
+ 102542.pts-4.brahma (02/19/2024 05:20:30 PM) (Detached)
+24 Sockets in /run/screen/S-anusri.
+(base) anusri@brahma:/mnt/lab_data2/anusri/chrombpnet/logs/checkpoint/JAN_02_2023$
diff --git a/logs/checkpoint/JAN_02_2023/screenlog/output_combine_deepshap.log b/logs/checkpoint/JAN_02_2023/screenlog/output_combine_deepshap.log
new file mode 100644
index 00000000..d4e73eeb
--- /dev/null
+++ b/logs/checkpoint/JAN_02_2023/screenlog/output_combine_deepshap.log
@@ -0,0 +1,326 @@
+(base) anusri@brahma:/mnt/lab_data2/anusri/chrombpnet/logs/checkpoint/JAN_02_2023$ nano combine_deepshap.py
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+import pandas as pd
+import os
+import deepdish as dd
+import numpy as np
+from tqdm import tqdm
+
+#data = pd.read_csv("model_dir_atac.csv",header=None)
+#ddtpe="ATAC"
+#ddtpen=ddtpe+"_PE"
+#cell_types=["HEPG2", "K562", "GM12878", "H1ESC", "IMR90"]
+#cell_types=[ "H1ESC", "IMR90"]
+#cell_types=["K562", "GM12878", "H1ESC", "IMR90", "HEPG2"]
+#cell_types=["IMR90"]
+#itype="counts"
+
+#data = pd.read_csv("model_dir_dnase.csv",header=None)
+data = pd.read_csv("v1/model_dir_dnase_v2_interpret.csv",header=None)
+ddtpe="DNASE"
+ddtpen=ddtpe+"_SE"
+#ddtpen=ddtpe+"_SE"
+#cell_types=["HEPG2", "K562", "GM12878", "H1ESC", "IMR90"]
+#cell_types=["K562", "GM12878", "H1ESC", "IMR90", "HEPG2"]
+#cell_types=["HEPG2", "K562"]
+#cell_types=["K562"]
+#cell_types=["GM12878", "IMR90"]
+#cell_types=["GM12878_new", "IMR90_new", "H1ESC_new"]
+cell_types=["GM12878", "IMR90", "H1ESC"]
+#cell_types=[ "IMR90"]
+itype="counts"
+
+
+
+#data = pd.read_csv("model_dir_dnase.csv",header=None)
+
+
+NARROWPEAK_SCHEMA = ["chr", "start", "end", "1", "2", "3", "4", "5", "6", "summit"]
+
+def filter_regions_to_peaks(bed_of_interest, merged, scores):
+
+ output_prefix="/oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/chrombpnet/folds/"+ddtpe+"/"+cell_type+"/merge_folds_new_may_05_24_atac/in_peaks"
+
+ boi = bed_of_interest[["chr", "start", "end", "summit"]].to_numpy().tolist()
+ merged_val = merged[[0,1,2,9]].to_numpy().tolist()
+
+ indices=[]
+ dups = []
+ #for i, val in enumerate(tqdm(merged_val)):
+ for i, val in enumerate(merged_val):
+ if val in boi:
+ if val not in dups:
+ indices.append(i)
+ dups.append(val)
+
+ print(len(indices))
+ print(len(merged_val))
+ print(len(boi))
+ #assert(len(indices)==len(boi))
+ merged.iloc[indices].to_csv(output_prefix+"."+itype+".interpreted_regions.bed", header=False, index=False, sep="\t")
+
+ sub_scores = {
+ 'raw': {'seq': scores['raw']['seq'][indices]},
+ 'shap': {'seq': scores['shap']['seq'][indices]},
+ 'projected_shap': {'seq': scores['projected_shap']['seq'][indices]}
+ }
+
+ print(sub_scores['raw']['seq'].shape)
+
+ dd.io.save(output_prefix+"."+itype+"_scores_new_compressed.h5",
+ sub_scores,
+ compression='blosc')
+
+
+for cell_type in cell_types:
+ ndata = data[data[1]==cell_type].reset_index()
+ cell_type = cell_type+"_new"
+ bed_of_interest = pd.read_csv("/mnt/lab_data2/anusri/chrombpnet/results/chrombpnet/"+ddtpen+"/"+cell_type+"/data/peaks_no_blacklist.bed", sep="\t", header=No>
+ one_hots=None
+ for i,r in ndata.iterrows():
+ print(i,r[2])
+
+ beds_path = os.path.join(r[2],"chrombpnet_model/interpret/full_"+cell_type+".interpreted_regions_"+itype+".bed")
+ if os.path.exists(beds_path):
+ beds = pd.read_csv(beds_path, sep="\t", header=None)
+ elif os.path.exists(os.path.join(r[2],"chrombpnet_model/interpret/merged."+cell_type+".interpreted_regions.bed")):
+ beds_path = os.path.join(r[2],"chrombpnet_model/interpret/merged."+cell_type+".interpreted_regions.bed")
+ beds = pd.read_csv(beds_path, sep="\t", header=None)
+ else:
+ beds_path = os.path.join(r[2],"interpret/merged."+cell_type+".interpreted_regions.bed")
+ beds = pd.read_csv(beds_path, sep="\t", header=None)
+
+ print(beds.head())
+ beds["key"] = beds[0] + "_" + beds[1].astype(str) + "_" + beds[2].astype(str) + "_" + + beds[9].astype(str)
+
+ ppath = os.path.join(r[2],"chrombpnet_model/interpret/full_"+cell_type+"."+itype+"_scores_new_compressed.h5")
+ if os.path.exists(ppath):
+ scores = dd.io.load(ppath)
+ elif os.path.exists(os.path.join(r[2],"interpret/merged."+cell_type+"."+itype+"_scores_new_compressed.h5")):
+ ppath = os.path.join(r[2],"interpret/merged."+cell_type+"."+itype+"_scores_new_compressed.h5")
+ scores = dd.io.load(ppath)
+ else:
+ ppath = os.path.join(r[2],"chrombpnet_model/interpret/full_"+cell_type+"."+itype+"_scores_new_compressed.h5")
+ scores = dd.io.load(ppath)
+
+ if i == 0 :
+ output = scores['shap']['seq']
+ shapez = output.shape
+ init_beds = beds
+ print(scores.keys())
+ #raw = scores['raw']['seq']
+ if 'raw' in scores:
+ if one_hots is None:
+ one_hots = scores['raw']['seq']
+ print("one hots found")
+ else:
+ print(len(indices))
+ print(len(merged_val))
+ print(len(boi))
+ #assert(len(indices)==len(boi))
+ merged.iloc[indices].to_csv(output_prefix+"."+itype+".interpreted_regions.bed", header=False, index=False, sep="\t")
+
+ sub_scores = {
+ 'raw': {'seq': scores['raw']['seq'][indices]},
+ 'shap': {'seq': scores['shap']['seq'][indices]},
+ 'projected_shap': {'seq': scores['projected_shap']['seq'][indices]}
+ GNU nano 6.2 combine_deepshap.py *
+
+#data = pd.read_csv("model_dir_dnase.csv",header=None)
+data = pd.read_csv("v1/model_dir_dnase_v2_interpret.csv",header=None)
+ddtpe="DNASE"
+ddtpen=ddtpe+"_SE"
+#ddtpen=ddtpe+"_SE"
+#cell_types=["HEPG2", "K562", "GM12878", "H1ESC", "IMR90"]
+#cell_types=["K562", "GM12878", "H1ESC", "IMR90", "HEPG2"]
+#cell_types=["HEPG2", "K562"]
+#cell_types=["K562"]
+#cell_types=["GM12878", "IMR90"]
+#cell_types=["GM12878_new", "IMR90_new", "H1ESC_new"]
+cell_types=["GM12878", "IMR90", "H1ESC"]
+#cell_types=[ "IMR90"]
+itype="counts"
+
+
+
+#data = pd.read_csv("model_dir_dnase.csv",header=None)
+
+
+NARROWPEAK_SCHEMA = ["chr", "start", "end", "1", "2", "3", "4", "5", "6", "summit"]
+
+def filter_regions_to_peaks(bed_of_interest, merged, scores):
+
+ output_prefix="/oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/chrombpnet/folds/"+ddtpe+"/"+cell_type+"/merge_folds_new_may_05_24_atac/in_peaks"
+
+ boi = bed_of_interest[["chr", "start", "end", "summit"]].to_numpy().tolist()
+ merged_val = merged[[0,1,2,9]].to_numpy().tolist()
+
+ indices=[]
+ dups = []
+ #for i, val in enumerate(tqdm(merged_val)):
+ for i, val in enumerate(merged_val):
+ if val in boi:
+ if val not in dups:
+ indices.append(i)
+ dups.append(val)
+
+ print(len(indices))
+ print(len(merged_val))
+ print(len(boi))
+ #assert(len(indices)==len(boi))
+ merged.iloc[indices].to_csv(output_prefix+"."+itype+".interpreted_regions.bed", header=False, index=False, sep="\t")
+
+ sub_scores = {
+
+
+(base) anusri@brahma:/mnt/lab_data2/anusri/chrombpnet/logs/checkpoint/JAN_02_2023$ nano combine_deepshap.py
+
+ GNU nano 6.2 combine_deepshap.py
+
+import pandas as pd
+import os
+import deepdish as dd
+import numpy as np
+from tqdm import tqdm
+
+#data = pd.read_csv("model_dir_atac.csv",header=None)
+#ddtpe="ATAC"
+#ddtpen=ddtpe+"_PE"
+#cell_types=["HEPG2", "K562", "GM12878", "H1ESC", "IMR90"]
+#cell_types=[ "H1ESC", "IMR90"]
+#cell_types=["K562", "GM12878", "H1ESC", "IMR90", "HEPG2"]
+#cell_types=["IMR90"]
+#itype="counts"
+
+#data = pd.read_csv("model_dir_dnase.csv",header=None)
+data = pd.read_csv("v1/model_dir_dnase_v2_interpret.csv",header=None)
+ddtpe="DNASE"
+ddtpen=ddtpe+"_SE"
+#ddtpen=ddtpe+"_SE"
+#cell_types=["HEPG2", "K562", "GM12878", "H1ESC", "IMR90"]
+#cell_types=["K562", "GM12878", "H1ESC", "IMR90", "HEPG2"]
+#cell_types=["HEPG2", "K562"]
+#cell_types=["K562"]
+#cell_types=["GM12878", "IMR90"]
+#cell_types=["GM12878_new", "IMR90_new", "H1ESC_new"]
+cell_types=["GM12878", "IMR90", "H1ESC"]
+#cell_types=[ "IMR90"]
+itype="profile"
+
+
+
+#data = pd.read_csv("model_dir_dnase.csv",header=None)
+
+
+NARROWPEAK_SCHEMA = ["chr", "start", "end", "1", "2", "3", "4", "5", "6", "summit"]
+
+def filter_regions_to_peaks(bed_of_interest, merged, scores):
+
+ output_prefix="/oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/chrombpnet/folds/"+ddtpe+"/"+cell_type+"/merge_folds_new_may_05_24_atac/in_peaks"
+
+ boi = bed_of_interest[["chr", "start", "end", "summit"]].to_numpy().tolist()
+ merged_val = merged[[0,1,2,9]].to_numpy().tolist()
+
+ indices=[]
+
+
+(base) anusri@brahma:/mnt/lab_data2/anusri/chrombpnet/logs/checkpoint/JAN_02_2023$ python combine_deepshap.py
+0 /oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/chrombpnet/folds/DNASE/GM12878_new/fold_0/
+ 0 1 2 3 4 5 6 7 8 9
+0 chr1 100027296 100027501 Peak_249793 205 . 2.96340 20.50725 18.78049 111
+1 chr1 100028565 100029246 Peak_167826 551 . 4.46107 55.12105 53.20545 364
+2 chr1 100034564 100034745 Peak_131731 932 . 2.44294 93.27672 91.24131 94
+3 chr1 100037049 100037386 Peak_143616 778 . 2.20879 77.80008 75.80809 249
+4 chr1 100037049 100037386 Peak_266435 174 . 1.51482 17.42906 15.73164 89
+dict_keys(['shap'])
+(277907, 4, 2114)
+1 /oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/chrombpnet/folds/DNASE/GM12878_new/fold_1/
+ 0 1 2 3 4 5 6 7 8 9
+0 chr1 100027296 100027501 Peak_249793 205 . 2.96340 20.50725 18.78049 111
+1 chr1 100028565 100029246 Peak_167826 551 . 4.46107 55.12105 53.20545 364
+2 chr1 100034564 100034745 Peak_131731 932 . 2.44294 93.27672 91.24131 94
+3 chr1 100037049 100037386 Peak_143616 778 . 2.20879 77.80008 75.80809 249
+4 chr1 100037049 100037386 Peak_266435 174 . 1.51482 17.42906 15.73164 89
+(277907, 4, 2114)
+(277907, 4, 2114)
+2 /oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/chrombpnet/folds/DNASE/GM12878_new/fold_2/
+ 0 1 2 3 4 5 6 7 8 9
+0 chr1 100027296 100027501 Peak_249793 205 . 2.96340 20.50725 18.78049 111
+1 chr1 100028565 100029246 Peak_167826 551 . 4.46107 55.12105 53.20545 364
+2 chr1 100034564 100034745 Peak_131731 932 . 2.44294 93.27672 91.24131 94
+3 chr1 100037049 100037386 Peak_143616 778 . 2.20879 77.80008 75.80809 249
+4 chr1 100037049 100037386 Peak_266435 174 . 1.51482 17.42906 15.73164 89
+(277907, 4, 2114)
+(277907, 4, 2114)
+3 /oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/chrombpnet/folds/DNASE/GM12878_new/fold_3/
+ 0 1 2 3 4 5 6 7 8 9
+0 chr1 100027296 100027501 Peak_249793 205 . 2.96340 20.50725 18.78049 111
+1 chr1 100028565 100029246 Peak_167826 551 . 4.46107 55.12105 53.20545 364
+2 chr1 100034564 100034745 Peak_131731 932 . 2.44294 93.27672 91.24131 94
+3 chr1 100037049 100037386 Peak_143616 778 . 2.20879 77.80008 75.80809 249
+4 chr1 100037049 100037386 Peak_266435 174 . 1.51482 17.42906 15.73164 89
+(277907, 4, 2114)
+(277907, 4, 2114)
+4 /oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/chrombpnet/folds/DNASE/GM12878_new/fold_4/
+ 0 1 2 3 4 5 6 7 8 9
+0 chr1 100027296 100027501 Peak_249793 205 . 2.96340 20.50725 18.78049 111
+1 chr1 100028565 100029246 Peak_167826 551 . 4.46107 55.12105 53.20545 364
+2 chr1 100034564 100034745 Peak_131731 932 . 2.44294 93.27672 91.24131 94
+3 chr1 100037049 100037386 Peak_143616 778 . 2.20879 77.80008 75.80809 249
+4 chr1 100037049 100037386 Peak_266435 174 . 1.51482 17.42906 15.73164 89
+(277907, 4, 2114)
+(277907, 4, 2114)
+Traceback (most recent call last):
+ File "combine_deepshap.py", line 131, in
+ assert(one_hots.shape==output.shape)
+AttributeError: 'NoneType' object has no attribute 'shape'
+(base) anusri@brahma:/mnt/lab_data2/anusri/chrombpnet/logs/checkpoint/JAN_02_2023$
diff --git a/logs/checkpoint/JAN_02_2023/screenlog/output_run_train_test_making.log b/logs/checkpoint/JAN_02_2023/screenlog/output_run_train_test_making.log
new file mode 100644
index 00000000..a989eb4e
--- /dev/null
+++ b/logs/checkpoint/JAN_02_2023/screenlog/output_run_train_test_making.log
@@ -0,0 +1,1074 @@
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+API Deep Neural Network Library (oneDNN) to use the following CPU instructions in performance-critical operations: AVX2 AVX512F FMA
+To enable them in other operations, rebuild TensorFlow with the appropriate compiler flags.
+2024-05-08 17:19:42.964276: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1525] Created device /job:localhost/replica:0/task:0/device:GPU:0 with 10544 MB memory:
+ -> device: 0, name: NVIDIA TITAN V, pci bus id: 0000:3b:00.0, compute capability: 7.0
+/users/anusri/anaconda3/envs/chrombpnet/lib/python3.8/site-packages/keras/layers/core/lambda_layer.py:303: UserWarning: is not loaded, but a Lambda layer uses it. It
+ may cause errors.
+ function = cls._parse_function_from_config(config, custom_objects,
+WARNING:tensorflow:Compiled the loaded model, but the compiled metrics have yet to be built. `model.compile_metrics` will be empty until you train or evaluate the mod
+el.
+2024-05-08 17:19:45.953741: W tensorflow/python/util/util.cc:368] Sets are not currently considered sequences, but this may change in the future, so consider avoiding
+ using them.
+CUDA_VISIBLE_DEVICES=0 python get_new_tf_model_format.py -i /oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/chrombpnet/folds/ATAC/GM12878_25M/GM12878_25M_
+07.18.2022_bias_transfer_1234_fold_1_data_type_ATAC_PE/chrombpnet_model/chrombpnet_wo_bias.h5 -o /oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/chrombpne
+t/folds/ATAC/GM12878_25M/GM12878_25M_07.18.2022_bias_transfer_1234_fold_1_data_type_ATAC_PE/chrombpnet_model/new_model_formats_may_7_24/ -f chrombpnet_wo_bias
+2024-05-08 17:19:56.143978: I tensorflow/core/platform/cpu_feature_guard.cc:151] This TensorFlow binary is optimized with oneAPI Deep Neural Network Library (oneDNN)
+to use the following CPU instructions in performance-critical operations: AVX2 AVX512F FMA
+To enable them in other operations, rebuild TensorFlow with the appropriate compiler flags.
+2024-05-08 17:19:56.986398: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1525] Created device /job:localhost/replica:0/task:0/device:GPU:0 with 10544 MB memory:
+ -> device: 0, name: NVIDIA TITAN V, pci bus id: 0000:3b:00.0, compute capability: 7.0
+WARNING:tensorflow:Compiled the loaded model, but the compiled metrics have yet to be built. `model.compile_metrics` will be empty until you train or evaluate the mod
+el.
+2024-05-08 17:19:58.881749: W tensorflow/python/util/util.cc:368] Sets are not currently considered sequences, but this may change in the future, so consider avoiding
+ using them.
+CUDA_VISIBLE_DEVICES=0 python get_new_tf_model_format.py -i /oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/chrombpnet/folds/ATAC/GM12878_25M/GM12878_25M_
+07.18.2022_bias_transfer_1234_fold_1_data_type_ATAC_PE/chrombpnet_model/bias_model_scaled.h5 -o /oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/chrombpnet
+/folds/ATAC/GM12878_25M/GM12878_25M_07.18.2022_bias_transfer_1234_fold_1_data_type_ATAC_PE/chrombpnet_model/new_model_formats_may_7_24/ -f bias_model_scaled
+2024-05-08 17:20:05.765619: I tensorflow/core/platform/cpu_feature_guard.cc:151] This TensorFlow binary is optimized with oneAPI Deep Neural Network Library (oneDNN)
+to use the following CPU instructions in performance-critical operations: AVX2 AVX512F FMA
+To enable them in other operations, rebuild TensorFlow with the appropriate compiler flags.
+2024-05-08 17:20:06.720573: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1525] Created device /job:localhost/replica:0/task:0/device:GPU:0 with 10544 MB memory:
+ -> device: 0, name: NVIDIA TITAN V, pci bus id: 0000:3b:00.0, compute capability: 7.0
+WARNING:tensorflow:Compiled the loaded model, but the compiled metrics have yet to be built. `model.compile_metrics` will be empty until you train or evaluate the mod
+el.
+2024-05-08 17:20:07.852851: W tensorflow/python/util/util.cc:368] Sets are not currently considered sequences, but this may change in the future, so consider avoiding
+ using them.
+/oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/chrombpnet/folds/ATAC/GM12878_25M/GM12878_25M_07.18.2022_bias_transfer_1234_fold_2_data_type_ATAC_PE/chrom
+bpnet_model/new_model_formats_may_7_24/chrombpnet
+CUDA_VISIBLE_DEVICES=0 python get_new_tf_model_format.py -i /oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/chrombpnet/folds/ATAC/GM12878_25M/GM12878_25M_
+07.18.2022_bias_transfer_1234_fold_2_data_type_ATAC_PE/chrombpnet_model/chrombpnet.h5 -o /oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/chrombpnet/folds/
+ATAC/GM12878_25M/GM12878_25M_07.18.2022_bias_transfer_1234_fold_2_data_type_ATAC_PE/chrombpnet_model/new_model_formats_may_7_24/ -f chrombpnet
+2024-05-08 17:21:06.639026: I tensorflow/core/platform/cpu_feature_guard.cc:151] This TensorFlow binary is optimized with oneAPI Deep Neural Network Library (oneDNN)
+to use the following CPU instructions in performance-critical operations: AVX2 AVX512F FMA
+To enable them in other operations, rebuild TensorFlow with the appropriate compiler flags.
+2024-05-08 17:21:07.500995: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1525] Created device /job:localhost/replica:0/task:0/device:GPU:0 with 10544 MB memory:
+ -> device: 0, name: NVIDIA TITAN V, pci bus id: 0000:3b:00.0, compute capability: 7.0
+/users/anusri/anaconda3/envs/chrombpnet/lib/python3.8/site-packages/keras/layers/core/lambda_layer.py:303: UserWarning: is not loaded, but a Lambda layer uses it. It
+ may cause errors.
+ function = cls._parse_function_from_config(config, custom_objects,
+WARNING:tensorflow:Compiled the loaded model, but the compiled metrics have yet to be built. `model.compile_metrics` will be empty until you train or evaluate the mod
+el.
+2024-05-08 17:21:10.411772: W tensorflow/python/util/util.cc:368] Sets are not currently considered sequences, but this may change in the future, so consider avoiding
+ using them.
+CUDA_VISIBLE_DEVICES=0 python get_new_tf_model_format.py -i /oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/chrombpnet/folds/ATAC/GM12878_25M/GM12878_25M_
+07.18.2022_bias_transfer_1234_fold_2_data_type_ATAC_PE/chrombpnet_model/chrombpnet_wo_bias.h5 -o /oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/chrombpne
+t/folds/ATAC/GM12878_25M/GM12878_25M_07.18.2022_bias_transfer_1234_fold_2_data_type_ATAC_PE/chrombpnet_model/new_model_formats_may_7_24/ -f chrombpnet_wo_bias
+2024-05-08 17:21:18.588274: I tensorflow/core/platform/cpu_feature_guard.cc:151] This TensorFlow binary is optimized with oneAPI Deep Neural Network Library (oneDNN)
+to use the following CPU instructions in performance-critical operations: AVX2 AVX512F FMA
+To enable them in other operations, rebuild TensorFlow with the appropriate compiler flags.
+2024-05-08 17:21:19.421367: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1525] Created device /job:localhost/replica:0/task:0/device:GPU:0 with 10544 MB memory:
+ -> device: 0, name: NVIDIA TITAN V, pci bus id: 0000:3b:00.0, compute capability: 7.0
+WARNING:tensorflow:Compiled the loaded model, but the compiled metrics have yet to be built. `model.compile_metrics` will be empty until you train or evaluate the mod
+el.
+2024-05-08 17:21:21.320962: W tensorflow/python/util/util.cc:368] Sets are not currently considered sequences, but this may change in the future, so consider avoiding
+ using them.
+CUDA_VISIBLE_DEVICES=0 python get_new_tf_model_format.py -i /oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/chrombpnet/folds/ATAC/GM12878_25M/GM12878_25M_
+07.18.2022_bias_transfer_1234_fold_2_data_type_ATAC_PE/chrombpnet_model/bias_model_scaled.h5 -o /oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/chrombpnet
+/folds/ATAC/GM12878_25M/GM12878_25M_07.18.2022_bias_transfer_1234_fold_2_data_type_ATAC_PE/chrombpnet_model/new_model_formats_may_7_24/ -f bias_model_scaled
+2024-05-08 17:21:27.980334: I tensorflow/core/platform/cpu_feature_guard.cc:151] This TensorFlow binary is optimized with oneAPI Deep Neural Network Library (oneDNN)
+to use the following CPU instructions in performance-critical operations: AVX2 AVX512F FMA
+To enable them in other operations, rebuild TensorFlow with the appropriate compiler flags.
+2024-05-08 17:21:28.847539: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1525] Created device /job:localhost/replica:0/task:0/device:GPU:0 with 10544 MB memory:
+ -> device: 0, name: NVIDIA TITAN V, pci bus id: 0000:3b:00.0, compute capability: 7.0
+WARNING:tensorflow:Compiled the loaded model, but the compiled metrics have yet to be built. `model.compile_metrics` will be empty until you train or evaluate the mod
+el.
+2024-05-08 17:21:29.972416: W tensorflow/python/util/util.cc:368] Sets are not currently considered sequences, but this may change in the future, so consider avoiding
+ using them.
+/oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/chrombpnet/folds/ATAC/GM12878_25M/GM12878_25M_07.18.2022_bias_transfer_1234_fold_3_data_type_ATAC_PE/chrom
+bpnet_model/new_model_formats_may_7_24/chrombpnet
+CUDA_VISIBLE_DEVICES=0 python get_new_tf_model_format.py -i /oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/chrombpnet/folds/ATAC/GM12878_25M/GM12878_25M_
+07.18.2022_bias_transfer_1234_fold_3_data_type_ATAC_PE/chrombpnet_model/chrombpnet.h5 -o /oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/chrombpnet/folds/
+ATAC/GM12878_25M/GM12878_25M_07.18.2022_bias_transfer_1234_fold_3_data_type_ATAC_PE/chrombpnet_model/new_model_formats_may_7_24/ -f chrombpnet
+2024-05-08 17:21:35.110948: I tensorflow/core/platform/cpu_feature_guard.cc:151] This TensorFlow binary is optimized with oneAPI Deep Neural Network Library (oneDNN)
+to use the following CPU instructions in performance-critical operations: AVX2 AVX512F FMA
+To enable them in other operations, rebuild TensorFlow with the appropriate compiler flags.
+2024-05-08 17:21:35.984856: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1525] Created device /job:localhost/replica:0/task:0/device:GPU:0 with 10544 MB memory:
+ -> device: 0, name: NVIDIA TITAN V, pci bus id: 0000:3b:00.0, compute capability: 7.0
+/users/anusri/anaconda3/envs/chrombpnet/lib/python3.8/site-packages/keras/layers/core/lambda_layer.py:303: UserWarning: is not loaded, but a Lambda layer uses it. It
+ may cause errors.
+ function = cls._parse_function_from_config(config, custom_objects,
+WARNING:tensorflow:Compiled the loaded model, but the compiled metrics have yet to be built. `model.compile_metrics` will be empty until you train or evaluate the mod
+el.
+2024-05-08 17:21:38.919540: W tensorflow/python/util/util.cc:368] Sets are not currently considered sequences, but this may change in the future, so consider avoiding
+ using them.
+CUDA_VISIBLE_DEVICES=0 python get_new_tf_model_format.py -i /oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/chrombpnet/folds/ATAC/GM12878_25M/GM12878_25M_
+07.18.2022_bias_transfer_1234_fold_3_data_type_ATAC_PE/chrombpnet_model/chrombpnet_wo_bias.h5 -o /oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/chrombpne
+t/folds/ATAC/GM12878_25M/GM12878_25M_07.18.2022_bias_transfer_1234_fold_3_data_type_ATAC_PE/chrombpnet_model/new_model_formats_may_7_24/ -f chrombpnet_wo_bias
+2024-05-08 17:21:47.507873: I tensorflow/core/platform/cpu_feature_guard.cc:151] This TensorFlow binary is optimized with oneAPI Deep Neural Network Library (oneDNN)
+to use the following CPU instructions in performance-critical operations: AVX2 AVX512F FMA
+To enable them in other operations, rebuild TensorFlow with the appropriate compiler flags.
+2024-05-08 17:21:48.430584: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1525] Created device /job:localhost/replica:0/task:0/device:GPU:0 with 10544 MB memory:
+ -> device: 0, name: NVIDIA TITAN V, pci bus id: 0000:3b:00.0, compute capability: 7.0
+WARNING:tensorflow:Compiled the loaded model, but the compiled metrics have yet to be built. `model.compile_metrics` will be empty until you train or evaluate the mod
+el.
+2024-05-08 17:21:50.432826: W tensorflow/python/util/util.cc:368] Sets are not currently considered sequences, but this may change in the future, so consider avoiding
+ using them.
+CUDA_VISIBLE_DEVICES=0 python get_new_tf_model_format.py -i /oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/chrombpnet/folds/ATAC/GM12878_25M/GM12878_25M_
+07.18.2022_bias_transfer_1234_fold_3_data_type_ATAC_PE/chrombpnet_model/bias_model_scaled.h5 -o /oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/chrombpnet
+/folds/ATAC/GM12878_25M/GM12878_25M_07.18.2022_bias_transfer_1234_fold_3_data_type_ATAC_PE/chrombpnet_model/new_model_formats_may_7_24/ -f bias_model_scaled
+2024-05-08 17:22:13.871855: I tensorflow/core/platform/cpu_feature_guard.cc:151] This TensorFlow binary is optimized with oneAPI Deep Neural Network Library (oneDNN)
+to use the following CPU instructions in performance-critical operations: AVX2 AVX512F FMA
+To enable them in other operations, rebuild TensorFlow with the appropriate compiler flags.
+2024-05-08 17:22:14.828533: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1525] Created device /job:localhost/replica:0/task:0/device:GPU:0 with 10544 MB memory:
+ -> device: 0, name: NVIDIA TITAN V, pci bus id: 0000:3b:00.0, compute capability: 7.0
+WARNING:tensorflow:Compiled the loaded model, but the compiled metrics have yet to be built. `model.compile_metrics` will be empty until you train or evaluate the mod
+el.
+2024-05-08 17:22:15.902654: W tensorflow/python/util/util.cc:368] Sets are not currently considered sequences, but this may change in the future, so consider avoiding
+ using them.
+/oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/chrombpnet/folds/ATAC/GM12878_25M/GM12878_25M_07.18.2022_bias_transfer_1234_fold_4_data_type_ATAC_PE/chrom
+bpnet_model/new_model_formats_may_7_24/chrombpnet
+CUDA_VISIBLE_DEVICES=0 python get_new_tf_model_format.py -i /oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/chrombpnet/folds/ATAC/GM12878_25M/GM12878_25M_
+07.18.2022_bias_transfer_1234_fold_4_data_type_ATAC_PE/chrombpnet_model/chrombpnet.h5 -o /oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/chrombpnet/folds/
+ATAC/GM12878_25M/GM12878_25M_07.18.2022_bias_transfer_1234_fold_4_data_type_ATAC_PE/chrombpnet_model/new_model_formats_may_7_24/ -f chrombpnet
+2024-05-08 17:22:21.608257: I tensorflow/core/platform/cpu_feature_guard.cc:151] This TensorFlow binary is optimized with oneAPI Deep Neural Network Library (oneDNN)
+to use the following CPU instructions in performance-critical operations: AVX2 AVX512F FMA
+To enable them in other operations, rebuild TensorFlow with the appropriate compiler flags.
+2024-05-08 17:22:22.443972: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1525] Created device /job:localhost/replica:0/task:0/device:GPU:0 with 10544 MB memory:
+ -> device: 0, name: NVIDIA TITAN V, pci bus id: 0000:3b:00.0, compute capability: 7.0
+/users/anusri/anaconda3/envs/chrombpnet/lib/python3.8/site-packages/keras/layers/core/lambda_layer.py:303: UserWarning: is not loaded, but a Lambda layer uses it. It
+ may cause errors.
+ function = cls._parse_function_from_config(config, custom_objects,
+WARNING:tensorflow:Compiled the loaded model, but the compiled metrics have yet to be built. `model.compile_metrics` will be empty until you train or evaluate the mod
+el.
+2024-05-08 17:22:25.417244: W tensorflow/python/util/util.cc:368] Sets are not currently considered sequences, but this may change in the future, so consider avoiding
+ using them.
+CUDA_VISIBLE_DEVICES=0 python get_new_tf_model_format.py -i /oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/chrombpnet/folds/ATAC/GM12878_25M/GM12878_25M_
+07.18.2022_bias_transfer_1234_fold_4_data_type_ATAC_PE/chrombpnet_model/chrombpnet_wo_bias.h5 -o /oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/chrombpne
+t/folds/ATAC/GM12878_25M/GM12878_25M_07.18.2022_bias_transfer_1234_fold_4_data_type_ATAC_PE/chrombpnet_model/new_model_formats_may_7_24/ -f chrombpnet_wo_bias
+2024-05-08 17:22:33.227533: I tensorflow/core/platform/cpu_feature_guard.cc:151] This TensorFlow binary is optimized with oneAPI Deep Neural Network Library (oneDNN)
+to use the following CPU instructions in performance-critical operations: AVX2 AVX512F FMA
+To enable them in other operations, rebuild TensorFlow with the appropriate compiler flags.
+2024-05-08 17:22:34.085172: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1525] Created device /job:localhost/replica:0/task:0/device:GPU:0 with 10544 MB memory:
+ -> device: 0, name: NVIDIA TITAN V, pci bus id: 0000:3b:00.0, compute capability: 7.0
+WARNING:tensorflow:Compiled the loaded model, but the compiled metrics have yet to be built. `model.compile_metrics` will be empty until you train or evaluate the mod
+el.
+2024-05-08 17:22:36.045850: W tensorflow/python/util/util.cc:368] Sets are not currently considered sequences, but this may change in the future, so consider avoiding
+ using them.
+CUDA_VISIBLE_DEVICES=0 python get_new_tf_model_format.py -i /oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/chrombpnet/folds/ATAC/GM12878_25M/GM12878_25M_
+07.18.2022_bias_transfer_1234_fold_4_data_type_ATAC_PE/chrombpnet_model/bias_model_scaled.h5 -o /oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/chrombpnet
+/folds/ATAC/GM12878_25M/GM12878_25M_07.18.2022_bias_transfer_1234_fold_4_data_type_ATAC_PE/chrombpnet_model/new_model_formats_may_7_24/ -f bias_model_scaled
+2024-05-08 17:22:42.261302: I tensorflow/core/platform/cpu_feature_guard.cc:151] This TensorFlow binary is optimized with oneAPI Deep Neural Network Library (oneDNN)
+to use the following CPU instructions in performance-critical operations: AVX2 AVX512F FMA
+To enable them in other operations, rebuild TensorFlow with the appropriate compiler flags.
+2024-05-08 17:22:43.177161: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1525] Created device /job:localhost/replica:0/task:0/device:GPU:0 with 10544 MB memory:
+ -> device: 0, name: NVIDIA TITAN V, pci bus id: 0000:3b:00.0, compute capability: 7.0
+WARNING:tensorflow:Compiled the loaded model, but the compiled metrics have yet to be built. `model.compile_metrics` will be empty until you train or evaluate the mod
+el.
+2024-05-08 17:22:44.292704: W tensorflow/python/util/util.cc:368] Sets are not currently considered sequences, but this may change in the future, so consider avoiding
+ using them.
+/oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/chrombpnet/folds/ATAC/GM12878_5M/GM12878_5M_07.18.2022_bias_transfer_1234_fold_0_data_type_ATAC_PE/chrombp
+net_model/new_model_formats_may_7_24/chrombpnet
+CUDA_VISIBLE_DEVICES=0 python get_new_tf_model_format.py -i /oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/chrombpnet/folds/ATAC/GM12878_5M/GM12878_5M_07
+.18.2022_bias_transfer_1234_fold_0_data_type_ATAC_PE/chrombpnet_model/chrombpnet.h5 -o /oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/chrombpnet/folds/AT
+AC/GM12878_5M/GM12878_5M_07.18.2022_bias_transfer_1234_fold_0_data_type_ATAC_PE/chrombpnet_model/new_model_formats_may_7_24/ -f chrombpnet
+2024-05-08 17:22:49.870656: I tensorflow/core/platform/cpu_feature_guard.cc:151] This TensorFlow binary is optimized with oneAPI Deep Neural Network Library (oneDNN)
+to use the following CPU instructions in performance-critical operations: AVX2 AVX512F FMA
+To enable them in other operations, rebuild TensorFlow with the appropriate compiler flags.
+2024-05-08 17:22:50.758515: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1525] Created device /job:localhost/replica:0/task:0/device:GPU:0 with 10544 MB memory:
+ -> device: 0, name: NVIDIA TITAN V, pci bus id: 0000:3b:00.0, compute capability: 7.0
+/users/anusri/anaconda3/envs/chrombpnet/lib/python3.8/site-packages/keras/layers/core/lambda_layer.py:303: UserWarning: is not loaded, but a Lambda layer uses it. It
+ may cause errors.
+ function = cls._parse_function_from_config(config, custom_objects,
+WARNING:tensorflow:Compiled the loaded model, but the compiled metrics have yet to be built. `model.compile_metrics` will be empty until you train or evaluate the mod
+el.
+2024-05-08 17:22:53.742819: W tensorflow/python/util/util.cc:368] Sets are not currently considered sequences, but this may change in the future, so consider avoiding
+ using them.
+CUDA_VISIBLE_DEVICES=0 python get_new_tf_model_format.py -i /oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/chrombpnet/folds/ATAC/GM12878_5M/GM12878_5M_07
+.18.2022_bias_transfer_1234_fold_0_data_type_ATAC_PE/chrombpnet_model/chrombpnet_wo_bias.h5 -o /oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/chrombpnet/
+folds/ATAC/GM12878_5M/GM12878_5M_07.18.2022_bias_transfer_1234_fold_0_data_type_ATAC_PE/chrombpnet_model/new_model_formats_may_7_24/ -f chrombpnet_wo_bias
+2024-05-08 17:23:02.190957: I tensorflow/core/platform/cpu_feature_guard.cc:151] This TensorFlow binary is optimized with oneAPI Deep Neural Network Library (oneDNN)
+to use the following CPU instructions in performance-critical operations: AVX2 AVX512F FMA
+To enable them in other operations, rebuild TensorFlow with the appropriate compiler flags.
+2024-05-08 17:23:03.032869: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1525] Created device /job:localhost/replica:0/task:0/device:GPU:0 with 10544 MB memory:
+ -> device: 0, name: NVIDIA TITAN V, pci bus id: 0000:3b:00.0, compute capability: 7.0
+WARNING:tensorflow:Compiled the loaded model, but the compiled metrics have yet to be built. `model.compile_metrics` will be empty until you train or evaluate the mod
+el.
+2024-05-08 17:23:05.011775: W tensorflow/python/util/util.cc:368] Sets are not currently considered sequences, but this may change in the future, so consider avoiding
+ using them.
+CUDA_VISIBLE_DEVICES=0 python get_new_tf_model_format.py -i /oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/chrombpnet/folds/ATAC/GM12878_5M/GM12878_5M_07
+.18.2022_bias_transfer_1234_fold_0_data_type_ATAC_PE/chrombpnet_model/bias_model_scaled.h5 -o /oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/chrombpnet/f
+olds/ATAC/GM12878_5M/GM12878_5M_07.18.2022_bias_transfer_1234_fold_0_data_type_ATAC_PE/chrombpnet_model/new_model_formats_may_7_24/ -f bias_model_scaled
+2024-05-08 17:23:14.086272: I tensorflow/core/platform/cpu_feature_guard.cc:151] This TensorFlow binary is optimized with oneAPI Deep Neural Network Library (oneDNN)
+to use the following CPU instructions in performance-critical operations: AVX2 AVX512F FMA
+To enable them in other operations, rebuild TensorFlow with the appropriate compiler flags.
+2024-05-08 17:23:14.893562: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1525] Created device /job:localhost/replica:0/task:0/device:GPU:0 with 10544 MB memory:
+ -> device: 0, name: NVIDIA TITAN V, pci bus id: 0000:3b:00.0, compute capability: 7.0
+WARNING:tensorflow:Compiled the loaded model, but the compiled metrics have yet to be built. `model.compile_metrics` will be empty until you train or evaluate the mod
+el.
+2024-05-08 17:23:15.930370: W tensorflow/python/util/util.cc:368] Sets are not currently considered sequences, but this may change in the future, so consider avoiding
+ using them.
+/oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/chrombpnet/folds/ATAC/GM12878_5M/GM12878_5M_07.18.2022_bias_transfer_1234_fold_1_data_type_ATAC_PE/chrombp
+net_model/new_model_formats_may_7_24/chrombpnet
+CUDA_VISIBLE_DEVICES=0 python get_new_tf_model_format.py -i /oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/chrombpnet/folds/ATAC/GM12878_5M/GM12878_5M_07
+.18.2022_bias_transfer_1234_fold_1_data_type_ATAC_PE/chrombpnet_model/chrombpnet.h5 -o /oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/chrombpnet/folds/AT
+AC/GM12878_5M/GM12878_5M_07.18.2022_bias_transfer_1234_fold_1_data_type_ATAC_PE/chrombpnet_model/new_model_formats_may_7_24/ -f chrombpnet
+2024-05-08 17:23:21.167530: I tensorflow/core/platform/cpu_feature_guard.cc:151] This TensorFlow binary is optimized with oneAPI Deep Neural Network Library (oneDNN)
+to use the following CPU instructions in performance-critical operations: AVX2 AVX512F FMA
+To enable them in other operations, rebuild TensorFlow with the appropriate compiler flags.
+2024-05-08 17:23:22.141746: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1525] Created device /job:localhost/replica:0/task:0/device:GPU:0 with 10544 MB memory:
+ -> device: 0, name: NVIDIA TITAN V, pci bus id: 0000:3b:00.0, compute capability: 7.0
+/users/anusri/anaconda3/envs/chrombpnet/lib/python3.8/site-packages/keras/layers/core/lambda_layer.py:303: UserWarning: is not loaded, but a Lambda layer uses it. It
+ may cause errors.
+ function = cls._parse_function_from_config(config, custom_objects,
+WARNING:tensorflow:Compiled the loaded model, but the compiled metrics have yet to be built. `model.compile_metrics` will be empty until you train or evaluate the mod
+el.
+2024-05-08 17:23:25.056023: W tensorflow/python/util/util.cc:368] Sets are not currently considered sequences, but this may change in the future, so consider avoiding
+ using them.
+CUDA_VISIBLE_DEVICES=0 python get_new_tf_model_format.py -i /oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/chrombpnet/folds/ATAC/GM12878_5M/GM12878_5M_07
+.18.2022_bias_transfer_1234_fold_1_data_type_ATAC_PE/chrombpnet_model/chrombpnet_wo_bias.h5 -o /oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/chrombpnet/
+folds/ATAC/GM12878_5M/GM12878_5M_07.18.2022_bias_transfer_1234_fold_1_data_type_ATAC_PE/chrombpnet_model/new_model_formats_may_7_24/ -f chrombpnet_wo_bias
+2024-05-08 17:23:33.568936: I tensorflow/core/platform/cpu_feature_guard.cc:151] This TensorFlow binary is optimized with oneAPI Deep Neural Network Library (oneDNN)
+to use the following CPU instructions in performance-critical operations: AVX2 AVX512F FMA
+To enable them in other operations, rebuild TensorFlow with the appropriate compiler flags.
+2024-05-08 17:23:34.375546: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1525] Created device /job:localhost/replica:0/task:0/device:GPU:0 with 10544 MB memory:
+ -> device: 0, name: NVIDIA TITAN V, pci bus id: 0000:3b:00.0, compute capability: 7.0
+WARNING:tensorflow:Compiled the loaded model, but the compiled metrics have yet to be built. `model.compile_metrics` will be empty until you train or evaluate the mod
+el.
+2024-05-08 17:23:36.298993: W tensorflow/python/util/util.cc:368] Sets are not currently considered sequences, but this may change in the future, so consider avoiding
+ using them.
+CUDA_VISIBLE_DEVICES=0 python get_new_tf_model_format.py -i /oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/chrombpnet/folds/ATAC/GM12878_5M/GM12878_5M_07
+.18.2022_bias_transfer_1234_fold_1_data_type_ATAC_PE/chrombpnet_model/bias_model_scaled.h5 -o /oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/chrombpnet/f
+olds/ATAC/GM12878_5M/GM12878_5M_07.18.2022_bias_transfer_1234_fold_1_data_type_ATAC_PE/chrombpnet_model/new_model_formats_may_7_24/ -f bias_model_scaled
+2024-05-08 17:23:42.637151: I tensorflow/core/platform/cpu_feature_guard.cc:151] This TensorFlow binary is optimized with oneAPI Deep Neural Network Library (oneDNN)
+to use the following CPU instructions in performance-critical operations: AVX2 AVX512F FMA
+To enable them in other operations, rebuild TensorFlow with the appropriate compiler flags.
+2024-05-08 17:23:43.497484: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1525] Created device /job:localhost/replica:0/task:0/device:GPU:0 with 10544 MB memory:
+ -> device: 0, name: NVIDIA TITAN V, pci bus id: 0000:3b:00.0, compute capability: 7.0
+WARNING:tensorflow:Compiled the loaded model, but the compiled metrics have yet to be built. `model.compile_metrics` will be empty until you train or evaluate the mod
+el.
+2024-05-08 17:23:44.652868: W tensorflow/python/util/util.cc:368] Sets are not currently considered sequences, but this may change in the future, so consider avoiding
+ using them.
+/oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/chrombpnet/folds/ATAC/GM12878_5M/GM12878_5M_07.18.2022_bias_transfer_1234_fold_2_data_type_ATAC_PE/chrombp
+net_model/new_model_formats_may_7_24/chrombpnet
+CUDA_VISIBLE_DEVICES=0 python get_new_tf_model_format.py -i /oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/chrombpnet/folds/ATAC/GM12878_5M/GM12878_5M_07
+.18.2022_bias_transfer_1234_fold_2_data_type_ATAC_PE/chrombpnet_model/chrombpnet.h5 -o /oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/chrombpnet/folds/AT
+AC/GM12878_5M/GM12878_5M_07.18.2022_bias_transfer_1234_fold_2_data_type_ATAC_PE/chrombpnet_model/new_model_formats_may_7_24/ -f chrombpnet
+2024-05-08 17:23:49.789146: I tensorflow/core/platform/cpu_feature_guard.cc:151] This TensorFlow binary is optimized with oneAPI Deep Neural Network Library (oneDNN)
+to use the following CPU instructions in performance-critical operations: AVX2 AVX512F FMA
+To enable them in other operations, rebuild TensorFlow with the appropriate compiler flags.
+2024-05-08 17:23:50.660105: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1525] Created device /job:localhost/replica:0/task:0/device:GPU:0 with 10544 MB memory:
+ -> device: 0, name: NVIDIA TITAN V, pci bus id: 0000:3b:00.0, compute capability: 7.0
+/users/anusri/anaconda3/envs/chrombpnet/lib/python3.8/site-packages/keras/layers/core/lambda_layer.py:303: UserWarning: is not loaded, but a Lambda layer uses it. It
+ may cause errors.
+ function = cls._parse_function_from_config(config, custom_objects,
+WARNING:tensorflow:Compiled the loaded model, but the compiled metrics have yet to be built. `model.compile_metrics` will be empty until you train or evaluate the mod
+el.
+2024-05-08 17:23:53.621238: W tensorflow/python/util/util.cc:368] Sets are not currently considered sequences, but this may change in the future, so consider avoiding
+ using them.
+CUDA_VISIBLE_DEVICES=0 python get_new_tf_model_format.py -i /oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/chrombpnet/folds/ATAC/GM12878_5M/GM12878_5M_07
+.18.2022_bias_transfer_1234_fold_2_data_type_ATAC_PE/chrombpnet_model/chrombpnet_wo_bias.h5 -o /oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/chrombpnet/
+folds/ATAC/GM12878_5M/GM12878_5M_07.18.2022_bias_transfer_1234_fold_2_data_type_ATAC_PE/chrombpnet_model/new_model_formats_may_7_24/ -f chrombpnet_wo_bias
+2024-05-08 17:24:08.639312: I tensorflow/core/platform/cpu_feature_guard.cc:151] This TensorFlow binary is optimized with oneAPI Deep Neural Network Library (oneDNN)
+to use the following CPU instructions in performance-critical operations: AVX2 AVX512F FMA
+To enable them in other operations, rebuild TensorFlow with the appropriate compiler flags.
+2024-05-08 17:24:09.491289: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1525] Created device /job:localhost/replica:0/task:0/device:GPU:0 with 10544 MB memory:
+ -> device: 0, name: NVIDIA TITAN V, pci bus id: 0000:3b:00.0, compute capability: 7.0
+WARNING:tensorflow:Compiled the loaded model, but the compiled metrics have yet to be built. `model.compile_metrics` will be empty until you train or evaluate the mod
+el.
+2024-05-08 17:24:11.554826: W tensorflow/python/util/util.cc:368] Sets are not currently considered sequences, but this may change in the future, so consider avoiding
+ using them.
+CUDA_VISIBLE_DEVICES=0 python get_new_tf_model_format.py -i /oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/chrombpnet/folds/ATAC/GM12878_5M/GM12878_5M_07
+.18.2022_bias_transfer_1234_fold_2_data_type_ATAC_PE/chrombpnet_model/bias_model_scaled.h5 -o /oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/chrombpnet/f
+olds/ATAC/GM12878_5M/GM12878_5M_07.18.2022_bias_transfer_1234_fold_2_data_type_ATAC_PE/chrombpnet_model/new_model_formats_may_7_24/ -f bias_model_scaled
+2024-05-08 17:24:20.924526: I tensorflow/core/platform/cpu_feature_guard.cc:151] This TensorFlow binary is optimized with oneAPI Deep Neural Network Library (oneDNN)
+to use the following CPU instructions in performance-critical operations: AVX2 AVX512F FMA
+To enable them in other operations, rebuild TensorFlow with the appropriate compiler flags.
+2024-05-08 17:24:21.998121: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1525] Created device /job:localhost/replica:0/task:0/device:GPU:0 with 10544 MB memory:
+ -> device: 0, name: NVIDIA TITAN V, pci bus id: 0000:3b:00.0, compute capability: 7.0
+WARNING:tensorflow:Compiled the loaded model, but the compiled metrics have yet to be built. `model.compile_metrics` will be empty until you train or evaluate the mod
+el.
+2024-05-08 17:24:23.062140: W tensorflow/python/util/util.cc:368] Sets are not currently considered sequences, but this may change in the future, so consider avoiding
+ using them.
+/oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/chrombpnet/folds/ATAC/GM12878_5M/GM12878_5M_07.18.2022_bias_transfer_1234_fold_3_data_type_ATAC_PE/chrombp
+net_model/new_model_formats_may_7_24/chrombpnet
+CUDA_VISIBLE_DEVICES=0 python get_new_tf_model_format.py -i /oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/chrombpnet/folds/ATAC/GM12878_5M/GM12878_5M_07
+.18.2022_bias_transfer_1234_fold_3_data_type_ATAC_PE/chrombpnet_model/chrombpnet.h5 -o /oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/chrombpnet/folds/AT
+AC/GM12878_5M/GM12878_5M_07.18.2022_bias_transfer_1234_fold_3_data_type_ATAC_PE/chrombpnet_model/new_model_formats_may_7_24/ -f chrombpnet
+2024-05-08 17:24:28.363988: I tensorflow/core/platform/cpu_feature_guard.cc:151] This TensorFlow binary is optimized with oneAPI Deep Neural Network Library (oneDNN)
+to use the following CPU instructions in performance-critical operations: AVX2 AVX512F FMA
+To enable them in other operations, rebuild TensorFlow with the appropriate compiler flags.
+2024-05-08 17:24:29.209466: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1525] Created device /job:localhost/replica:0/task:0/device:GPU:0 with 10544 MB memory:
+ -> device: 0, name: NVIDIA TITAN V, pci bus id: 0000:3b:00.0, compute capability: 7.0
+/users/anusri/anaconda3/envs/chrombpnet/lib/python3.8/site-packages/keras/layers/core/lambda_layer.py:303: UserWarning: is not loaded, but a Lambda layer uses it. It
+ may cause errors.
+ function = cls._parse_function_from_config(config, custom_objects,
+WARNING:tensorflow:Compiled the loaded model, but the compiled metrics have yet to be built. `model.compile_metrics` will be empty until you train or evaluate the mod
+el.
+2024-05-08 17:24:32.222758: W tensorflow/python/util/util.cc:368] Sets are not currently considered sequences, but this may change in the future, so consider avoiding
+ using them.
+CUDA_VISIBLE_DEVICES=0 python get_new_tf_model_format.py -i /oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/chrombpnet/folds/ATAC/GM12878_5M/GM12878_5M_07
+.18.2022_bias_transfer_1234_fold_3_data_type_ATAC_PE/chrombpnet_model/chrombpnet_wo_bias.h5 -o /oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/chrombpnet/
+folds/ATAC/GM12878_5M/GM12878_5M_07.18.2022_bias_transfer_1234_fold_3_data_type_ATAC_PE/chrombpnet_model/new_model_formats_may_7_24/ -f chrombpnet_wo_bias
+2024-05-08 17:24:40.218888: I tensorflow/core/platform/cpu_feature_guard.cc:151] This TensorFlow binary is optimized with oneAPI Deep Neural Network Library (oneDNN)
+to use the following CPU instructions in performance-critical operations: AVX2 AVX512F FMA
+To enable them in other operations, rebuild TensorFlow with the appropriate compiler flags.
+2024-05-08 17:24:41.039893: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1525] Created device /job:localhost/replica:0/task:0/device:GPU:0 with 10544 MB memory:
+ -> device: 0, name: NVIDIA TITAN V, pci bus id: 0000:3b:00.0, compute capability: 7.0
+WARNING:tensorflow:Compiled the loaded model, but the compiled metrics have yet to be built. `model.compile_metrics` will be empty until you train or evaluate the mod
+el.
+2024-05-08 17:24:43.089973: W tensorflow/python/util/util.cc:368] Sets are not currently considered sequences, but this may change in the future, so consider avoiding
+ using them.
+CUDA_VISIBLE_DEVICES=0 python get_new_tf_model_format.py -i /oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/chrombpnet/folds/ATAC/GM12878_5M/GM12878_5M_07
+.18.2022_bias_transfer_1234_fold_3_data_type_ATAC_PE/chrombpnet_model/bias_model_scaled.h5 -o /oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/chrombpnet/f
+olds/ATAC/GM12878_5M/GM12878_5M_07.18.2022_bias_transfer_1234_fold_3_data_type_ATAC_PE/chrombpnet_model/new_model_formats_may_7_24/ -f bias_model_scaled
+2024-05-08 17:24:49.261156: I tensorflow/core/platform/cpu_feature_guard.cc:151] This TensorFlow binary is optimized with oneAPI Deep Neural Network Library (oneDNN)
+to use the following CPU instructions in performance-critical operations: AVX2 AVX512F FMA
+To enable them in other operations, rebuild TensorFlow with the appropriate compiler flags.
+2024-05-08 17:24:50.099090: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1525] Created device /job:localhost/replica:0/task:0/device:GPU:0 with 10544 MB memory:
+ -> device: 0, name: NVIDIA TITAN V, pci bus id: 0000:3b:00.0, compute capability: 7.0
+WARNING:tensorflow:Compiled the loaded model, but the compiled metrics have yet to be built. `model.compile_metrics` will be empty until you train or evaluate the mod
+el.
+2024-05-08 17:24:51.179503: W tensorflow/python/util/util.cc:368] Sets are not currently considered sequences, but this may change in the future, so consider avoiding
+ using them.
+/oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/chrombpnet/folds/ATAC/GM12878_5M/GM12878_5M_07.18.2022_bias_transfer_1234_fold_4_data_type_ATAC_PE/chrombp
+net_model/new_model_formats_may_7_24/chrombpnet
+CUDA_VISIBLE_DEVICES=0 python get_new_tf_model_format.py -i /oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/chrombpnet/folds/ATAC/GM12878_5M/GM12878_5M_07
+.18.2022_bias_transfer_1234_fold_4_data_type_ATAC_PE/chrombpnet_model/chrombpnet.h5 -o /oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/chrombpnet/folds/AT
+AC/GM12878_5M/GM12878_5M_07.18.2022_bias_transfer_1234_fold_4_data_type_ATAC_PE/chrombpnet_model/new_model_formats_may_7_24/ -f chrombpnet
+2024-05-08 17:24:56.506686: I tensorflow/core/platform/cpu_feature_guard.cc:151] This TensorFlow binary is optimized with oneAPI Deep Neural Network Library (oneDNN)
+to use the following CPU instructions in performance-critical operations: AVX2 AVX512F FMA
+To enable them in other operations, rebuild TensorFlow with the appropriate compiler flags.
+2024-05-08 17:24:57.337745: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1525] Created device /job:localhost/replica:0/task:0/device:GPU:0 with 10544 MB memory:
+ -> device: 0, name: NVIDIA TITAN V, pci bus id: 0000:3b:00.0, compute capability: 7.0
+/users/anusri/anaconda3/envs/chrombpnet/lib/python3.8/site-packages/keras/layers/core/lambda_layer.py:303: UserWarning: is not loaded, but a Lambda layer uses it. It
+ may cause errors.
+ function = cls._parse_function_from_config(config, custom_objects,
+WARNING:tensorflow:Compiled the loaded model, but the compiled metrics have yet to be built. `model.compile_metrics` will be empty until you train or evaluate the mod
+el.
+2024-05-08 17:25:00.304870: W tensorflow/python/util/util.cc:368] Sets are not currently considered sequences, but this may change in the future, so consider avoiding
+ using them.
+CUDA_VISIBLE_DEVICES=0 python get_new_tf_model_format.py -i /oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/chrombpnet/folds/ATAC/GM12878_5M/GM12878_5M_07
+.18.2022_bias_transfer_1234_fold_4_data_type_ATAC_PE/chrombpnet_model/chrombpnet_wo_bias.h5 -o /oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/chrombpnet/
+folds/ATAC/GM12878_5M/GM12878_5M_07.18.2022_bias_transfer_1234_fold_4_data_type_ATAC_PE/chrombpnet_model/new_model_formats_may_7_24/ -f chrombpnet_wo_bias
+2024-05-08 17:25:08.477283: I tensorflow/core/platform/cpu_feature_guard.cc:151] This TensorFlow binary is optimized with oneAPI Deep Neural Network Library (oneDNN)
+to use the following CPU instructions in performance-critical operations: AVX2 AVX512F FMA
+To enable them in other operations, rebuild TensorFlow with the appropriate compiler flags.
+2024-05-08 17:25:09.441939: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1525] Created device /job:localhost/replica:0/task:0/device:GPU:0 with 10544 MB memory:
+ -> device: 0, name: NVIDIA TITAN V, pci bus id: 0000:3b:00.0, compute capability: 7.0
+WARNING:tensorflow:Compiled the loaded model, but the compiled metrics have yet to be built. `model.compile_metrics` will be empty until you train or evaluate the mod
+el.
+2024-05-08 17:25:11.421551: W tensorflow/python/util/util.cc:368] Sets are not currently considered sequences, but this may change in the future, so consider avoiding
+ using them.
+CUDA_VISIBLE_DEVICES=0 python get_new_tf_model_format.py -i /oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/chrombpnet/folds/ATAC/GM12878_5M/GM12878_5M_07
+.18.2022_bias_transfer_1234_fold_4_data_type_ATAC_PE/chrombpnet_model/bias_model_scaled.h5 -o /oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/chrombpnet/f
+olds/ATAC/GM12878_5M/GM12878_5M_07.18.2022_bias_transfer_1234_fold_4_data_type_ATAC_PE/chrombpnet_model/new_model_formats_may_7_24/ -f bias_model_scaled
+2024-05-08 17:25:22.085647: I tensorflow/core/platform/cpu_feature_guard.cc:151] This TensorFlow binary is optimized with oneAPI Deep Neural Network Library (oneDNN)
+to use the following CPU instructions in performance-critical operations: AVX2 AVX512F FMA
+To enable them in other operations, rebuild TensorFlow with the appropriate compiler flags.
+2024-05-08 17:25:22.941967: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1525] Created device /job:localhost/replica:0/task:0/device:GPU:0 with 10544 MB memory:
+ -> device: 0, name: NVIDIA TITAN V, pci bus id: 0000:3b:00.0, compute capability: 7.0
+WARNING:tensorflow:Compiled the loaded model, but the compiled metrics have yet to be built. `model.compile_metrics` will be empty until you train or evaluate the mod
+el.
+2024-05-08 17:25:24.031961: W tensorflow/python/util/util.cc:368] Sets are not currently considered sequences, but this may change in the future, so consider avoiding
+ using them.
+(chrombpnet) anusri@brahma:/mnt/lab_data2/anusri/chrombpnet/upload_jsons/upload_scripts$ python run_conversion.py
+/mnt/lab_data2/anusri/chrombpnet/results/chrombpnet/ATAC_PE/GM12878/nautilus_runs/GM12878_03.01.2022_bias_128_4_1234_0.4_fold_0/chrombpnet_model/new_model_formats_may
+_7_24/chrombpnet
+/oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/chrombpnet/folds/ATAC/GM12878/GM12878_07.08.2022_bias_128_4_1234_0.4_fold_1_data_type_ATAC_PE/chrombpnet_m
+odel/new_model_formats_may_7_24/chrombpnet
+/oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/chrombpnet/folds/ATAC/GM12878/GM12878_07.08.2022_bias_128_4_1234_0.4_fold_2_data_type_ATAC_PE/chrombpnet_m
+odel/new_model_formats_may_7_24/chrombpnet
+/oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/chrombpnet/folds/ATAC/GM12878/GM12878_07.14.2022_bias_128_4_1234_0.4_fold_3_data_type_ATAC_PE/chrombpnet_m
+odel/new_model_formats_may_7_24/chrombpnet
+/oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/chrombpnet/folds/ATAC/GM12878/GM12878_07.07.2022_bias_128_4_1234_0.4_fold_4_data_type_ATAC_PE/chrombpnet_m
+odel/new_model_formats_may_7_24/chrombpnet
+/oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/chrombpnet/folds/ATAC/GM12878_250M/GM12878_250M_07.19.2022_bias_transfer_1234_fold_0_data_type_ATAC_PE/chr
+ombpnet_model/new_model_formats_may_7_24/chrombpnet
+/oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/chrombpnet/folds/ATAC/GM12878_250M/GM12878_250M_07.18.2022_bias_transfer_1234_fold_1_data_type_ATAC_PE/chr
+ombpnet_model/new_model_formats_may_7_24/chrombpnet
+/oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/chrombpnet/folds/ATAC/GM12878_250M/GM12878_250M_07.19.2022_bias_transfer_1234_fold_2_data_type_ATAC_PE/chr
+ombpnet_model/new_model_formats_may_7_24/chrombpnet
+/oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/chrombpnet/folds/ATAC/GM12878_250M/GM12878_250M_07.18.2022_bias_transfer_1234_fold_3_data_type_ATAC_PE/chr
+ombpnet_model/new_model_formats_may_7_24/chrombpnet
+/oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/chrombpnet/folds/ATAC/GM12878_250M/GM12878_250M_07.18.2022_bias_transfer_1234_fold_4_data_type_ATAC_PE/chr
+ombpnet_model/new_model_formats_may_7_24/chrombpnet
+/oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/chrombpnet/folds/ATAC/GM12878_100M/GM12878_100M_07.19.2022_bias_transfer_1234_fold_0_data_type_ATAC_PE/chr
+ombpnet_model/new_model_formats_may_7_24/chrombpnet
+/oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/chrombpnet/folds/ATAC/GM12878_100M/GM12878_100M_07.18.2022_bias_transfer_1234_fold_1_data_type_ATAC_PE/chr
+ombpnet_model/new_model_formats_may_7_24/chrombpnet
+/oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/chrombpnet/folds/ATAC/GM12878_100M/GM12878_100M_07.18.2022_bias_transfer_1234_fold_2_data_type_ATAC_PE/chr
+ombpnet_model/new_model_formats_may_7_24/chrombpnet
+/oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/chrombpnet/folds/ATAC/GM12878_100M/GM12878_100M_07.18.2022_bias_transfer_1234_fold_3_data_type_ATAC_PE/chr
+ombpnet_model/new_model_formats_may_7_24/chrombpnet
+/oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/chrombpnet/folds/ATAC/GM12878_100M/GM12878_100M_07.18.2022_bias_transfer_1234_fold_4_data_type_ATAC_PE/chr
+ombpnet_model/new_model_formats_may_7_24/chrombpnet
+/oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/chrombpnet/folds/ATAC/GM12878_50M/GM12878_50M_07.18.2022_bias_transfer_1234_fold_0_data_type_ATAC_PE/chrom
+bpnet_model/new_model_formats_may_7_24/chrombpnet
+/oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/chrombpnet/folds/ATAC/GM12878_50M/GM12878_50M_07.18.2022_bias_transfer_1234_fold_1_data_type_ATAC_PE/chrom
+bpnet_model/new_model_formats_may_7_24/chrombpnet
+/oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/chrombpnet/folds/ATAC/GM12878_50M/GM12878_50M_07.18.2022_bias_transfer_1234_fold_2_data_type_ATAC_PE/chrom
+bpnet_model/new_model_formats_may_7_24/chrombpnet
+/oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/chrombpnet/folds/ATAC/GM12878_50M/GM12878_50M_07.18.2022_bias_transfer_1234_fold_3_data_type_ATAC_PE/chrom
+bpnet_model/new_model_formats_may_7_24/chrombpnet
+/oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/chrombpnet/folds/ATAC/GM12878_50M/GM12878_50M_07.19.2022_bias_transfer_1234_fold_4_data_type_ATAC_PE/chrom
+bpnet_model/new_model_formats_may_7_24/chrombpnet
+/oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/chrombpnet/folds/ATAC/GM12878_25M/GM12878_25M_07.18.2022_bias_transfer_1234_fold_0_data_type_ATAC_PE/chrom
+bpnet_model/new_model_formats_may_7_24/chrombpnet
+/oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/chrombpnet/folds/ATAC/GM12878_25M/GM12878_25M_07.18.2022_bias_transfer_1234_fold_1_data_type_ATAC_PE/chrom
+bpnet_model/new_model_formats_may_7_24/chrombpnet
+/oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/chrombpnet/folds/ATAC/GM12878_25M/GM12878_25M_07.18.2022_bias_transfer_1234_fold_2_data_type_ATAC_PE/chrom
+bpnet_model/new_model_formats_may_7_24/chrombpnet
+/oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/chrombpnet/folds/ATAC/GM12878_25M/GM12878_25M_07.18.2022_bias_transfer_1234_fold_3_data_type_ATAC_PE/chrom
+bpnet_model/new_model_formats_may_7_24/chrombpnet
+/oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/chrombpnet/folds/ATAC/GM12878_25M/GM12878_25M_07.18.2022_bias_transfer_1234_fold_4_data_type_ATAC_PE/chrom
+bpnet_model/new_model_formats_may_7_24/chrombpnet
+/oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/chrombpnet/folds/ATAC/GM12878_5M/GM12878_5M_07.18.2022_bias_transfer_1234_fold_0_data_type_ATAC_PE/chrombp
+net_model/new_model_formats_may_7_24/chrombpnet
+/oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/chrombpnet/folds/ATAC/GM12878_5M/GM12878_5M_07.18.2022_bias_transfer_1234_fold_1_data_type_ATAC_PE/chrombp
+net_model/new_model_formats_may_7_24/chrombpnet
+/oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/chrombpnet/folds/ATAC/GM12878_5M/GM12878_5M_07.18.2022_bias_transfer_1234_fold_2_data_type_ATAC_PE/chrombp
+net_model/new_model_formats_may_7_24/chrombpnet
+/oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/chrombpnet/folds/ATAC/GM12878_5M/GM12878_5M_07.18.2022_bias_transfer_1234_fold_3_data_type_ATAC_PE/chrombp
+net_model/new_model_formats_may_7_24/chrombpnet
+/oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/chrombpnet/folds/ATAC/GM12878_5M/GM12878_5M_07.18.2022_bias_transfer_1234_fold_4_data_type_ATAC_PE/chrombp
+net_model/new_model_formats_may_7_24/chrombpnet
+(chrombpnet) anusri@brahma:/mnt/lab_data2/anusri/chrombpnet/upload_jsons/upload_scripts$ ls
+bias_models_atlas.csv get_train_test_regions.py new_run_train_test_making.py run_conversion_bias.py run_train_test_making.py
+convert_to_compressed.py GM12878 prepare_file_for_upload_models.py run_conversion_new.py temp
+get_new_tf_model_format.py k562.samstats.qc __pycache__ run_conversion.py upload_utils.py
+get_train_test_regions_bias.py new_metrics README.md run_train_test_making_bias.py
+(chrombpnet) anusri@brahma:/mnt/lab_data2/anusri/chrombpnet/upload_jsons/upload_scripts$ nano run_train_test_making.py
+
+ GNU nano 6.2 run_train_test_making.py
+import pandas as pd
+import os
+
+#model_atac = pd.read_csv("/mnt/lab_data2/anusri/chrombpnet/logs/checkpoint/JAN_02_2023/model_dir_atac.csv",sep=",", header=None)
+#model_atac = pd.read_csv("/mnt/lab_data2/anusri/chrombpnet/logs/checkpoint/JAN_02_2023/model_dir_dnase.csv",sep=",", header=None)
+model_atac = pd.read_csv("/mnt/lab_data2/anusri/chrombpnet/logs/checkpoint/JAN_02_2023/v1/model_dir_dnase_v2.1.csv",sep=",",header=None)
+
+#encode_id = {"K562": "ENCSR868FGK",
+# "GM12878": "ENCSR637XSC",
+# "HEPG2": "ENCSR291GJU",
+# "IMR90": "ENCSR200OML",
+# "H1ESC": "ENCDUMMY"}
+
+encode_id = {"K562": "ENCSR000EOT",
+ "GM12878": "ENCSR000EMT",
+ "HEPG2": "ENCSR149XIL",
+ "IMR90": "ENCSR477RTP",
+ "H1ESC": "ENCSR000EMU"}
+
+
+for i,r in model_atac.iterrows():
+ fold = r[0]
+ name = r[1]
+ model_path = r[2]
+
+ input_peaks=os.path.join(model_path,"chrombpnet_model/filtered.peaks.bed")
+ input_nonpeaks=os.path.join(model_path,"chrombpnet_model/filtered.nonpeaks.bed")
+ test_nonpeaks="/oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/ATAC/"+encode_id[name]+"/negatives_data/test/test."+fold+".filtere>
+ fold="/mnt/lab_data2/anusri/chrombpnet/splits/"+fold+".json"
+ output_path=os.path.join(model_path,"train_test_regions_may_7_2024/")
+
+ if not os.path.isfile(output_path+"nonpeaks.validationset.bed.gz"):
+ os.makedirs(output_path, exist_ok=True)
+ command=["python get_train_test_regions.py -ip"]+[input_peaks]+["-inp"]+[input_nonpeaks]+["-inpt"]+[test_nonpeaks]+["-f"]+[fold]+["->
+ command = " ".join(command)
+ print(command)
+ os.system(command)
+
+
+
+
+
+
+(chrombpnet) anusri@brahma:/mnt/lab_data2/anusri/chrombpnet/upload_jsons/upload_scripts$ nano run_conversion.py
+
+ GNU nano 6.2 run_conversion.py
+import pandas as pd
+import os
+
+#model_atac = pd.read_csv("/mnt/lab_data2/anusri/chrombpnet/logs/checkpoint/JAN_02_2023/model_dir_atac.csv",sep=",",header=None)
+#model_atac = pd.read_csv("/mnt/lab_data2/anusri/chrombpnet/logs/checkpoint/JAN_02_2023/model_dir_dnase.csv",sep=",",header=None)
+#model_atac = pd.read_csv("/mnt/lab_data2/anusri/chrombpnet/logs/checkpoint/JAN_02_2023/v1/model_dir_dnase_v2.1.csv",sep=",",header=None)
+model_atac = pd.read_csv("/mnt/lab_data2/anusri/chrombpnet/logs/checkpoint/JAN_02_2023/v1/model_dir_subsample_atac.csv",sep=",",header=None)
+
+
+for i,r in model_atac.iterrows():
+ fold = r[0]
+ name = r[1]
+ model_path = r[3]
+ input_path=os.path.join(model_path,"chrombpnet_model/chrombpnet.h5")
+ output_path=os.path.join(model_path,"chrombpnet_model/new_model_formats_may_7_24/chrombpnet")
+ output_dir=os.path.join(model_path,"chrombpnet_model/new_model_formats_may_7_24/")
+ print(output_path)
+ if not os.path.isfile(output_path+".tar"):
+
+ os.makedirs(os.path.join(model_path,"chrombpnet_model/new_model_formats_may_7_24/"), exist_ok=True)
+ command = "CUDA_VISIBLE_DEVICES=0 python get_new_tf_model_format.py -i "+input_path+" -o "+output_dir+" -f chrombpnet"
+ print(command)
+ os.system(command)
+
+ input_path=os.path.join(model_path,"chrombpnet_model/chrombpnet_wo_bias.h5")
+ output_path=os.path.join(model_path,"chrombpnet_model/new_model_formats_may_7_24/chrombpnet_wo_bias")
+
+ if not os.path.isfile(output_path+".tar"):
+ os.makedirs(os.path.join(model_path,"chrombpnet_model/new_model_formats_may_7_24/"), exist_ok=True)
+ command = "CUDA_VISIBLE_DEVICES=0 python get_new_tf_model_format.py -i "+input_path+" -o "+output_dir+" -f chrombpnet_wo_bias"
+ print(command)
+ os.system(command)
+
+ input_path=os.path.join(model_path,"chrombpnet_model/bias_model_scaled.h5")
+ output_path=os.path.join(model_path,"chrombpnet_model/new_model_formats_may_7_24/bias_model_scaled")
+
+ if not os.path.isfile(output_path+".tar"):
+ os.makedirs(os.path.join(model_path,"chrombpnet_model/new_model_formats_may_7_24/"), exist_ok=True)
+ command = "CUDA_VISIBLE_DEVICES=0 python get_new_tf_model_format.py -i "+input_path+" -o "+output_dir+" -f bias_model_scaled"
+ print(command)
+ os.system(command)
+
+
+(chrombpnet) anusri@brahma:/mnt/lab_data2/anusri/chrombpnet/upload_jsons/upload_scripts$ nano run_train_test_making.py
+
+ GNU nano 6.2 run_train_test_making.py
+import pandas as pd
+import os
+
+#model_atac = pd.read_csv("/mnt/lab_data2/anusri/chrombpnet/logs/checkpoint/JAN_02_2023/model_dir_atac.csv",sep=",", header=None)
+#model_atac = pd.read_csv("/mnt/lab_data2/anusri/chrombpnet/logs/checkpoint/JAN_02_2023/model_dir_dnase.csv",sep=",", header=None)
+#model_atac = pd.read_csv("/mnt/lab_data2/anusri/chrombpnet/logs/checkpoint/JAN_02_2023/v1/model_dir_dnase_v2.1.csv",sep=",",header=None)
+model_atac = pd.read_csv("/mnt/lab_data2/anusri/chrombpnet/logs/checkpoint/JAN_02_2023/v1/model_dir_subsample_atac.csv",sep=",",header=None)
+
+#encode_id = {"K562": "ENCSR868FGK",
+# "GM12878": "ENCSR637XSC",
+# "HEPG2": "ENCSR291GJU",
+# "IMR90": "ENCSR200OML",
+# "H1ESC": "ENCDUMMY"}
+
+encode_id = {"K562": "ENCSR000EOT",
+ "GM12878": "ENCSR000EMT",
+ "HEPG2": "ENCSR149XIL",
+ "IMR90": "ENCSR477RTP",
+ "H1ESC": "ENCSR000EMU"}
+
+
+for i,r in model_atac.iterrows():
+ fold = r[0]
+ name = r[1]
+ model_path = r[2]
+
+ input_peaks=os.path.join(model_path,"chrombpnet_model/filtered.peaks.bed")
+ input_nonpeaks=os.path.join(model_path,"chrombpnet_model/filtered.nonpeaks.bed")
+ test_nonpeaks="/oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/ATAC/"+encode_id[name]+"/negatives_data/test/test."+fold+".filtere>
+ fold="/mnt/lab_data2/anusri/chrombpnet/splits/"+fold+".json"
+ output_path=os.path.join(model_path,"train_test_regions_may_7_2024/")
+
+ if not os.path.isfile(output_path+"nonpeaks.validationset.bed.gz"):
+ os.makedirs(output_path, exist_ok=True)
+ command=["python get_train_test_regions.py -ip"]+[input_peaks]+["-inp"]+[input_nonpeaks]+["-inpt"]+[test_nonpeaks]+["-f"]+[fold]+["->
+ command = " ".join(command)
+ print(command)
+ os.system(command)
+
+
+
+
+
+(chrombpnet) anusri@brahma:/mnt/lab_data2/anusri/chrombpnet/upload_jsons/upload_scripts$ python run_train_test_making.py
+Traceback (most recent call last):
+ File "run_train_test_making.py", line 29, in
+ test_nonpeaks="/oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/ATAC/"+encode_id[name]+"/negatives_data/test/test."+fold+".filtered.negatives_with_summ
+it.bed"
+KeyError: '572M'
+(chrombpnet) anusri@brahma:/mnt/lab_data2/anusri/chrombpnet/upload_jsons/upload_scripts$ nano run_train_test_making.py
+
+ GNU nano 6.2 run_train_test_making.py
+import pandas as pd
+import os
+
+#model_atac = pd.read_csv("/mnt/lab_data2/anusri/chrombpnet/logs/checkpoint/JAN_02_2023/model_dir_atac.csv",sep=",", header=None)
+#model_atac = pd.read_csv("/mnt/lab_data2/anusri/chrombpnet/logs/checkpoint/JAN_02_2023/model_dir_dnase.csv",sep=",", header=None)
+#model_atac = pd.read_csv("/mnt/lab_data2/anusri/chrombpnet/logs/checkpoint/JAN_02_2023/v1/model_dir_dnase_v2.1.csv",sep=",",header=None)
+model_atac = pd.read_csv("/mnt/lab_data2/anusri/chrombpnet/logs/checkpoint/JAN_02_2023/v1/model_dir_subsample_atac.csv",sep=",",header=None)
+
+#encode_id = {"K562": "ENCSR868FGK",
+# "GM12878": "ENCSR637XSC",
+# "HEPG2": "ENCSR291GJU",
+# "IMR90": "ENCSR200OML",
+# "H1ESC": "ENCDUMMY"}
+
+encode_id = {"K562": "ENCSR000EOT",
+ "GM12878": "ENCSR000EMT",
+ "HEPG2": "ENCSR149XIL",
+ "IMR90": "ENCSR477RTP",
+ "H1ESC": "ENCSR000EMU"}
+
+
+for i,r in model_atac.iterrows():
+ fold = r[0]
+ name = r[1]
+ model_path = r[3]
+
+ input_peaks=os.path.join(model_path,"chrombpnet_model/filtered.peaks.bed")
+ input_nonpeaks=os.path.join(model_path,"chrombpnet_model/filtered.nonpeaks.bed")
+ test_nonpeaks="/oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/ATAC/"+encode_id[name]+"/negatives_data/test/test."+fold+".filtere>
+ fold="/mnt/lab_data2/anusri/chrombpnet/splits/"+fold+".json"
+ output_path=os.path.join(model_path,"train_test_regions_may_7_2024/")
+
+ if not os.path.isfile(output_path+"nonpeaks.validationset.bed.gz"):
+ os.makedirs(output_path, exist_ok=True)
+ command=["python get_train_test_regions.py -ip"]+[input_peaks]+["-inp"]+[input_nonpeaks]+["-inpt"]+[test_nonpeaks]+["-f"]+[fold]+["->
+ command = " ".join(command)
+ print(command)
+ os.system(command)
+
+
+
+
+
+(chrombpnet) anusri@brahma:/mnt/lab_data2/anusri/chrombpnet/upload_jsons/upload_scripts$ ls /oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/chrombpnet/fol
+ds/ATAC/GM12878_5M/GM12878_5M_07.18.2022_bias_transfer_1234_fold_4_data_type
+
+ls: cannot access '/oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/chrombpnet/folds/ATAC/GM12878_5M/GM12878_5M_07.18.2022_bias_transfer_1234_fold_4_data_t
+ype': No such file or directory
+(chrombpnet) anusri@brahma:/mnt/lab_data2/anusri/chrombpnet/upload_jsons/upload_scripts$ _ATAC_PE/chrombpnet_model/new_model_formats_may_7_24/chrombpnet
+bash: _ATAC_PE/chrombpnet_model/new_model_formats_may_7_24/chrombpnet: No such file or directory
+(chrombpnet) anusri@brahma:/mnt/lab_data2/anusri/chrombpnet/upload_jsons/upload_scripts$ ls /oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/chrombpnet/fol
+ds/ATAC/GM12878_5M/GM12878_5M_07.18.2022_bias_transfer_1234_fold_4_data_type_ATAC_PE/chrombpnet_model/
+bias_metrics.json chrombpnet.log.batch chrombpnet_wo_bias_only_nonpeaks.jsd.png
+bias_model_scaled.h5 chrombpnet_metrics.json chrombpnet_wo_bias_only_nonpeaks.png
+bias_only_nonpeaks.jsd.png chrombpnet_model_params.tsv chrombpnet_wo_bias_only_peaks.jsd.png
+bias_only_nonpeaks.png chrombpnet_only_nonpeaks.jsd.png chrombpnet_wo_bias_only_peaks.png
+bias_only_peaks.jsd.png chrombpnet_only_nonpeaks.png chrombpnet_wo_bias_peaks_and_nonpeaks.jsd.png
+bias_only_peaks.png chrombpnet_only_peaks.jsd.png chrombpnet_wo_bias_peaks_and_nonpeaks.png
+bias_peaks_and_nonpeaks.jsd.png chrombpnet_only_peaks.png chrombpnet_wo_bias_predictions.h5
+bias_peaks_and_nonpeaks.png chrombpnet.params.json filtered.nonpeaks.bed
+bias_predictions.h5 chrombpnet_peaks_and_nonpeaks.jsd.png filtered.peaks.bed
+chrombpnet.args.json chrombpnet_peaks_and_nonpeaks.png footprints/
+chrombpnet_data_params.tsv chrombpnet_predictions.h5 interpret/
+chrombpnet.h5 chrombpnet_wo_bias.h5 new_model_formats_may_7_24/
+chrombpnet.log chrombpnet_wo_bias_metrics.json train_chrombpnet_model.log
+(chrombpnet) anusri@brahma:/mnt/lab_data2/anusri/chrombpnet/upload_jsons/upload_scripts$ ls /oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/chrombpnet/fol
+ds/ATAC/GM12878_5M/GM12878_5M_07.18.2022_bias_transfer_1234_fold_4_data_type_ATAC_PE/chrombpnet_model/new_model_formats_may_7_24/
+bias_model_scaled bias_model_scaled.tar chrombpnet chrombpnet.tar chrombpnet_wo_bias chrombpnet_wo_bias.tar
+(chrombpnet) anusri@brahma:/mnt/lab_data2/anusri/chrombpnet/upload_jsons/upload_scripts$ nano run_train_test_making.py
+ GNU nano 6.2 run_train_test_making.py
+import pandas as pd
+import os
+
+#model_atac = pd.read_csv("/mnt/lab_data2/anusri/chrombpnet/logs/checkpoint/JAN_02_2023/model_dir_atac.csv",sep=",", header=None)
+#model_atac = pd.read_csv("/mnt/lab_data2/anusri/chrombpnet/logs/checkpoint/JAN_02_2023/model_dir_dnase.csv",sep=",", header=None)
+#model_atac = pd.read_csv("/mnt/lab_data2/anusri/chrombpnet/logs/checkpoint/JAN_02_2023/v1/model_dir_dnase_v2.1.csv",sep=",",header=None)
+model_atac = pd.read_csv("/mnt/lab_data2/anusri/chrombpnet/logs/checkpoint/JAN_02_2023/v1/model_dir_subsample_atac.csv",sep=",",header=None)
+
+#encode_id = {"K562": "ENCSR868FGK",
+# "GM12878": "ENCSR637XSC",
+# "HEPG2": "ENCSR291GJU",
+# "IMR90": "ENCSR200OML",
+# "H1ESC": "ENCDUMMY"}
+
+encode_id = {"K562": "ENCSR000EOT",
+ "GM12878": "ENCSR000EMT",
+ "HEPG2": "ENCSR149XIL",
+ "IMR90": "ENCSR477RTP",
+ "H1ESC": "ENCSR000EMU"}
+
+
+for i,r in model_atac.iterrows():
+ fold = r[0]
+ name = r[1]
+ model_path = r[3]
+
+ input_peaks=os.path.join(model_path,"chrombpnet_model/filtered.peaks.bed")
+ input_nonpeaks=os.path.join(model_path,"chrombpnet_model/filtered.nonpeaks.bed")
+ test_nonpeaks="/oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/ATAC/"+encode_id[name]+"/negatives_data/test/test."+fold+".filtere>
+ fold="/mnt/lab_data2/anusri/chrombpnet/splits/"+fold+".json"
+ output_path=os.path.join(model_path,"train_test_regions_may_7_2024/")
+
+ if not os.path.isfile(output_path+"nonpeaks.validationset.bed.gz"):
+ os.makedirs(output_path, exist_ok=True)
+ command=["python get_train_test_regions.py -ip"]+[input_peaks]+["-inp"]+[input_nonpeaks]+["-inpt"]+[test_nonpeaks]+["-f"]+[fold]+["->
+ command = " ".join(command)
+ print(command)
+ os.system(command)
+
+
+
+
+
+(chrombpnet) anusri@brahma:/mnt/lab_data2/anusri/chrombpnet/upload_jsons/upload_scripts$ python run_train_test_making.py
+Traceback (most recent call last):
+ File "run_train_test_making.py", line 29, in
+ test_nonpeaks="/oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/ATAC/"+encode_id[name]+"/negatives_data/test/test."+fold+".filtered.negatives_with_summ
+it.bed"
+KeyError: '572M'
+(chrombpnet) anusri@brahma:/mnt/lab_data2/anusri/chrombpnet/upload_jsons/upload_scripts$ nano run_train_test_making.py
+
+ GNU nano 6.2 run_train_test_making.py
+import pandas as pd
+import os
+
+#model_atac = pd.read_csv("/mnt/lab_data2/anusri/chrombpnet/logs/checkpoint/JAN_02_2023/model_dir_atac.csv",sep=",", header=None)
+#model_atac = pd.read_csv("/mnt/lab_data2/anusri/chrombpnet/logs/checkpoint/JAN_02_2023/model_dir_dnase.csv",sep=",", header=None)
+#model_atac = pd.read_csv("/mnt/lab_data2/anusri/chrombpnet/logs/checkpoint/JAN_02_2023/v1/model_dir_dnase_v2.1.csv",sep=",",header=None)
+model_atac = pd.read_csv("/mnt/lab_data2/anusri/chrombpnet/logs/checkpoint/JAN_02_2023/v1/model_dir_subsample_atac.csv",sep=",",header=None)
+
+#encode_id = {"K562": "ENCSR868FGK",
+# "GM12878": "ENCSR637XSC",
+# "HEPG2": "ENCSR291GJU",
+# "IMR90": "ENCSR200OML",
+# "H1ESC": "ENCDUMMY"}
+
+encode_id = {"K562": "ENCSR000EOT",
+ "GM12878": "ENCSR000EMT",
+ "HEPG2": "ENCSR149XIL",
+ "IMR90": "ENCSR477RTP",
+ "H1ESC": "ENCSR000EMU"}
+
+
+for i,r in model_atac.iterrows():
+ fold = r[0]
+ name = r[2]
+ model_path = r[3]
+
+ input_peaks=os.path.join(model_path,"chrombpnet_model/filtered.peaks.bed")
+ input_nonpeaks=os.path.join(model_path,"chrombpnet_model/filtered.nonpeaks.bed")
+ test_nonpeaks="/oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/ATAC/"+encode_id[name]+"/negatives_data/test/test."+fold+".filtere>
+ fold="/mnt/lab_data2/anusri/chrombpnet/splits/"+fold+".json"
+ output_path=os.path.join(model_path,"train_test_regions_may_7_2024/")
+
+ if not os.path.isfile(output_path+"nonpeaks.validationset.bed.gz"):
+ os.makedirs(output_path, exist_ok=True)
+ command=["python get_train_test_regions.py -ip"]+[input_peaks]+["-inp"]+[input_nonpeaks]+["-inpt"]+[test_nonpeaks]+["-f"]+[fold]+["->
+ command = " ".join(command)
+ print(command)
+ os.system(command)
+
+
+
+
+
+(chrombpnet) anusri@brahma:/mnt/lab_data2/anusri/chrombpnet/upload_jsons/upload_scripts$ python run_train_test_making.py
+python get_train_test_regions.py -ip /oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/chrombpnet/folds/ATAC/GM12878_250M/GM12878_250M_07.19.2022_bias_tran
+sfer_1234_fold_0_data_type_ATAC_PE/chrombpnet_model/filtered.peaks.bed -inp /oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/chrombpnet/folds/ATAC/GM12878_
+250M/GM12878_250M_07.19.2022_bias_transfer_1234_fold_0_data_type_ATAC_PE/chrombpnet_model/filtered.nonpeaks.bed -inpt /oak/stanford/groups/akundaje/projects/chromatin
+-atlas-2022/ATAC/ENCSR000EMT/negatives_data/test/test.fold_0.filtered.negatives_with_summit.bed -f /mnt/lab_data2/anusri/chrombpnet/splits/fold_0.json -o /oak/stanfor
+d/groups/akundaje/projects/chromatin-atlas-2022/chrombpnet/folds/ATAC/GM12878_250M/GM12878_250M_07.19.2022_bias_transfer_1234_fold_0_data_type_ATAC_PE/train_test_regi
+ons_may_7_2024/
+python get_train_test_regions.py -ip /oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/chrombpnet/folds/ATAC/GM12878_250M/GM12878_250M_07.18.2022_bias_tran
+sfer_1234_fold_1_data_type_ATAC_PE/chrombpnet_model/filtered.peaks.bed -inp /oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/chrombpnet/folds/ATAC/GM12878_
+250M/GM12878_250M_07.18.2022_bias_transfer_1234_fold_1_data_type_ATAC_PE/chrombpnet_model/filtered.nonpeaks.bed -inpt /oak/stanford/groups/akundaje/projects/chromatin
+-atlas-2022/ATAC/ENCSR000EMT/negatives_data/test/test.fold_1.filtered.negatives_with_summit.bed -f /mnt/lab_data2/anusri/chrombpnet/splits/fold_1.json -o /oak/stanfor
+d/groups/akundaje/projects/chromatin-atlas-2022/chrombpnet/folds/ATAC/GM12878_250M/GM12878_250M_07.18.2022_bias_transfer_1234_fold_1_data_type_ATAC_PE/train_test_regi
+ons_may_7_2024/
+python get_train_test_regions.py -ip /oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/chrombpnet/folds/ATAC/GM12878_250M/GM12878_250M_07.19.2022_bias_tran
+sfer_1234_fold_2_data_type_ATAC_PE/chrombpnet_model/filtered.peaks.bed -inp /oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/chrombpnet/folds/ATAC/GM12878_
+250M/GM12878_250M_07.19.2022_bias_transfer_1234_fold_2_data_type_ATAC_PE/chrombpnet_model/filtered.nonpeaks.bed -inpt /oak/stanford/groups/akundaje/projects/chromatin
+-atlas-2022/ATAC/ENCSR000EMT/negatives_data/test/test.fold_2.filtered.negatives_with_summit.bed -f /mnt/lab_data2/anusri/chrombpnet/splits/fold_2.json -o /oak/stanfor
+d/groups/akundaje/projects/chromatin-atlas-2022/chrombpnet/folds/ATAC/GM12878_250M/GM12878_250M_07.19.2022_bias_transfer_1234_fold_2_data_type_ATAC_PE/train_test_regi
+ons_may_7_2024/
+python get_train_test_regions.py -ip /oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/chrombpnet/folds/ATAC/GM12878_250M/GM12878_250M_07.18.2022_bias_tran
+sfer_1234_fold_3_data_type_ATAC_PE/chrombpnet_model/filtered.peaks.bed -inp /oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/chrombpnet/folds/ATAC/GM12878_
+250M/GM12878_250M_07.18.2022_bias_transfer_1234_fold_3_data_type_ATAC_PE/chrombpnet_model/filtered.nonpeaks.bed -inpt /oak/stanford/groups/akundaje/projects/chromatin
+-atlas-2022/ATAC/ENCSR000EMT/negatives_data/test/test.fold_3.filtered.negatives_with_summit.bed -f /mnt/lab_data2/anusri/chrombpnet/splits/fold_3.json -o /oak/stanfor
+d/groups/akundaje/projects/chromatin-atlas-2022/chrombpnet/folds/ATAC/GM12878_250M/GM12878_250M_07.18.2022_bias_transfer_1234_fold_3_data_type_ATAC_PE/train_test_regi
+ons_may_7_2024/
+python get_train_test_regions.py -ip /oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/chrombpnet/folds/ATAC/GM12878_250M/GM12878_250M_07.18.2022_bias_tran
+sfer_1234_fold_4_data_type_ATAC_PE/chrombpnet_model/filtered.peaks.bed -inp /oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/chrombpnet/folds/ATAC/GM12878_
+250M/GM12878_250M_07.18.2022_bias_transfer_1234_fold_4_data_type_ATAC_PE/chrombpnet_model/filtered.nonpeaks.bed -inpt /oak/stanford/groups/akundaje/projects/chromatin
+-atlas-2022/ATAC/ENCSR000EMT/negatives_data/test/test.fold_4.filtered.negatives_with_summit.bed -f /mnt/lab_data2/anusri/chrombpnet/splits/fold_4.json -o /oak/stanfor
+d/groups/akundaje/projects/chromatin-atlas-2022/chrombpnet/folds/ATAC/GM12878_250M/GM12878_250M_07.18.2022_bias_transfer_1234_fold_4_data_type_ATAC_PE/train_test_regi
+ons_may_7_2024/
+python get_train_test_regions.py -ip /oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/chrombpnet/folds/ATAC/GM12878_100M/GM12878_100M_07.19.2022_bias_tran
+sfer_1234_fold_0_data_type_ATAC_PE/chrombpnet_model/filtered.peaks.bed -inp /oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/chrombpnet/folds/ATAC/GM12878_
+100M/GM12878_100M_07.19.2022_bias_transfer_1234_fold_0_data_type_ATAC_PE/chrombpnet_model/filtered.nonpeaks.bed -inpt /oak/stanford/groups/akundaje/projects/chromatin
+-atlas-2022/ATAC/ENCSR000EMT/negatives_data/test/test.fold_0.filtered.negatives_with_summit.bed -f /mnt/lab_data2/anusri/chrombpnet/splits/fold_0.json -o /oak/stanfor
+d/groups/akundaje/projects/chromatin-atlas-2022/chrombpnet/folds/ATAC/GM12878_100M/GM12878_100M_07.19.2022_bias_transfer_1234_fold_0_data_type_ATAC_PE/train_test_regi
+ons_may_7_2024/
+python get_train_test_regions.py -ip /oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/chrombpnet/folds/ATAC/GM12878_100M/GM12878_100M_07.18.2022_bias_tran
+sfer_1234_fold_1_data_type_ATAC_PE/chrombpnet_model/filtered.peaks.bed -inp /oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/chrombpnet/folds/ATAC/GM12878_
+100M/GM12878_100M_07.18.2022_bias_transfer_1234_fold_1_data_type_ATAC_PE/chrombpnet_model/filtered.nonpeaks.bed -inpt /oak/stanford/groups/akundaje/projects/chromatin
+-atlas-2022/ATAC/ENCSR000EMT/negatives_data/test/test.fold_1.filtered.negatives_with_summit.bed -f /mnt/lab_data2/anusri/chrombpnet/splits/fold_1.json -o /oak/stanfor
+d/groups/akundaje/projects/chromatin-atlas-2022/chrombpnet/folds/ATAC/GM12878_100M/GM12878_100M_07.18.2022_bias_transfer_1234_fold_1_data_type_ATAC_PE/train_test_regi
+ons_may_7_2024/
+python get_train_test_regions.py -ip /oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/chrombpnet/folds/ATAC/GM12878_100M/GM12878_100M_07.18.2022_bias_tran
+sfer_1234_fold_2_data_type_ATAC_PE/chrombpnet_model/filtered.peaks.bed -inp /oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/chrombpnet/folds/ATAC/GM12878_
+100M/GM12878_100M_07.18.2022_bias_transfer_1234_fold_2_data_type_ATAC_PE/chrombpnet_model/filtered.nonpeaks.bed -inpt /oak/stanford/groups/akundaje/projects/chromatin
+-atlas-2022/ATAC/ENCSR000EMT/negatives_data/test/test.fold_2.filtered.negatives_with_summit.bed -f /mnt/lab_data2/anusri/chrombpnet/splits/fold_2.json -o /oak/stanfor
+d/groups/akundaje/projects/chromatin-atlas-2022/chrombpnet/folds/ATAC/GM12878_100M/GM12878_100M_07.18.2022_bias_transfer_1234_fold_2_data_type_ATAC_PE/train_test_regi
+ons_may_7_2024/
+python get_train_test_regions.py -ip /oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/chrombpnet/folds/ATAC/GM12878_100M/GM12878_100M_07.18.2022_bias_tran
+sfer_1234_fold_3_data_type_ATAC_PE/chrombpnet_model/filtered.peaks.bed -inp /oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/chrombpnet/folds/ATAC/GM12878_
+100M/GM12878_100M_07.18.2022_bias_transfer_1234_fold_3_data_type_ATAC_PE/chrombpnet_model/filtered.nonpeaks.bed -inpt /oak/stanford/groups/akundaje/projects/chromatin
+-atlas-2022/ATAC/ENCSR000EMT/negatives_data/test/test.fold_3.filtered.negatives_with_summit.bed -f /mnt/lab_data2/anusri/chrombpnet/splits/fold_3.json -o /oak/stanfor
+d/groups/akundaje/projects/chromatin-atlas-2022/chrombpnet/folds/ATAC/GM12878_100M/GM12878_100M_07.18.2022_bias_transfer_1234_fold_3_data_type_ATAC_PE/train_test_regi
+ons_may_7_2024/
+python get_train_test_regions.py -ip /oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/chrombpnet/folds/ATAC/GM12878_100M/GM12878_100M_07.18.2022_bias_tran
+sfer_1234_fold_4_data_type_ATAC_PE/chrombpnet_model/filtered.peaks.bed -inp /oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/chrombpnet/folds/ATAC/GM12878_
+100M/GM12878_100M_07.18.2022_bias_transfer_1234_fold_4_data_type_ATAC_PE/chrombpnet_model/filtered.nonpeaks.bed -inpt /oak/stanford/groups/akundaje/projects/chromatin
+-atlas-2022/ATAC/ENCSR000EMT/negatives_data/test/test.fold_4.filtered.negatives_with_summit.bed -f /mnt/lab_data2/anusri/chrombpnet/splits/fold_4.json -o /oak/stanfor
+d/groups/akundaje/projects/chromatin-atlas-2022/chrombpnet/folds/ATAC/GM12878_100M/GM12878_100M_07.18.2022_bias_transfer_1234_fold_4_data_type_ATAC_PE/train_test_regi
+ons_may_7_2024/
+python get_train_test_regions.py -ip /oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/chrombpnet/folds/ATAC/GM12878_50M/GM12878_50M_07.18.2022_bias_transf
+er_1234_fold_0_data_type_ATAC_PE/chrombpnet_model/filtered.peaks.bed -inp /oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/chrombpnet/folds/ATAC/GM12878_50
+M/GM12878_50M_07.18.2022_bias_transfer_1234_fold_0_data_type_ATAC_PE/chrombpnet_model/filtered.nonpeaks.bed -inpt /oak/stanford/groups/akundaje/projects/chromatin-atl
+as-2022/ATAC/ENCSR000EMT/negatives_data/test/test.fold_0.filtered.negatives_with_summit.bed -f /mnt/lab_data2/anusri/chrombpnet/splits/fold_0.json -o /oak/stanford/gr
+oups/akundaje/projects/chromatin-atlas-2022/chrombpnet/folds/ATAC/GM12878_50M/GM12878_50M_07.18.2022_bias_transfer_1234_fold_0_data_type_ATAC_PE/train_test_regions_ma
+y_7_2024/
+python get_train_test_regions.py -ip /oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/chrombpnet/folds/ATAC/GM12878_50M/GM12878_50M_07.18.2022_bias_transf
+er_1234_fold_1_data_type_ATAC_PE/chrombpnet_model/filtered.peaks.bed -inp /oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/chrombpnet/folds/ATAC/GM12878_50
+M/GM12878_50M_07.18.2022_bias_transfer_1234_fold_1_data_type_ATAC_PE/chrombpnet_model/filtered.nonpeaks.bed -inpt /oak/stanford/groups/akundaje/projects/chromatin-atl
+as-2022/ATAC/ENCSR000EMT/negatives_data/test/test.fold_1.filtered.negatives_with_summit.bed -f /mnt/lab_data2/anusri/chrombpnet/splits/fold_1.json -o /oak/stanford/gr
+oups/akundaje/projects/chromatin-atlas-2022/chrombpnet/folds/ATAC/GM12878_50M/GM12878_50M_07.18.2022_bias_transfer_1234_fold_1_data_type_ATAC_PE/train_test_regions_ma
+y_7_2024/
+python get_train_test_regions.py -ip /oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/chrombpnet/folds/ATAC/GM12878_50M/GM12878_50M_07.18.2022_bias_transf
+er_1234_fold_2_data_type_ATAC_PE/chrombpnet_model/filtered.peaks.bed -inp /oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/chrombpnet/folds/ATAC/GM12878_50
+M/GM12878_50M_07.18.2022_bias_transfer_1234_fold_2_data_type_ATAC_PE/chrombpnet_model/filtered.nonpeaks.bed -inpt /oak/stanford/groups/akundaje/projects/chromatin-atl
+as-2022/ATAC/ENCSR000EMT/negatives_data/test/test.fold_2.filtered.negatives_with_summit.bed -f /mnt/lab_data2/anusri/chrombpnet/splits/fold_2.json -o /oak/stanford/gr
+oups/akundaje/projects/chromatin-atlas-2022/chrombpnet/folds/ATAC/GM12878_50M/GM12878_50M_07.18.2022_bias_transfer_1234_fold_2_data_type_ATAC_PE/train_test_regions_ma
+y_7_2024/
+python get_train_test_regions.py -ip /oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/chrombpnet/folds/ATAC/GM12878_50M/GM12878_50M_07.18.2022_bias_transf
+er_1234_fold_3_data_type_ATAC_PE/chrombpnet_model/filtered.peaks.bed -inp /oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/chrombpnet/folds/ATAC/GM12878_50
+M/GM12878_50M_07.18.2022_bias_transfer_1234_fold_3_data_type_ATAC_PE/chrombpnet_model/filtered.nonpeaks.bed -inpt /oak/stanford/groups/akundaje/projects/chromatin-atl
+as-2022/ATAC/ENCSR000EMT/negatives_data/test/test.fold_3.filtered.negatives_with_summit.bed -f /mnt/lab_data2/anusri/chrombpnet/splits/fold_3.json -o /oak/stanford/gr
+oups/akundaje/projects/chromatin-atlas-2022/chrombpnet/folds/ATAC/GM12878_50M/GM12878_50M_07.18.2022_bias_transfer_1234_fold_3_data_type_ATAC_PE/train_test_regions_ma
+y_7_2024/
+python get_train_test_regions.py -ip /oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/chrombpnet/folds/ATAC/GM12878_50M/GM12878_50M_07.19.2022_bias_transf
+er_1234_fold_4_data_type_ATAC_PE/chrombpnet_model/filtered.peaks.bed -inp /oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/chrombpnet/folds/ATAC/GM12878_50
+M/GM12878_50M_07.19.2022_bias_transfer_1234_fold_4_data_type_ATAC_PE/chrombpnet_model/filtered.nonpeaks.bed -inpt /oak/stanford/groups/akundaje/projects/chromatin-atl
+as-2022/ATAC/ENCSR000EMT/negatives_data/test/test.fold_4.filtered.negatives_with_summit.bed -f /mnt/lab_data2/anusri/chrombpnet/splits/fold_4.json -o /oak/stanford/gr
+oups/akundaje/projects/chromatin-atlas-2022/chrombpnet/folds/ATAC/GM12878_50M/GM12878_50M_07.19.2022_bias_transfer_1234_fold_4_data_type_ATAC_PE/train_test_regions_ma
+y_7_2024/
+python get_train_test_regions.py -ip /oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/chrombpnet/folds/ATAC/GM12878_25M/GM12878_25M_07.18.2022_bias_transf
+er_1234_fold_0_data_type_ATAC_PE/chrombpnet_model/filtered.peaks.bed -inp /oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/chrombpnet/folds/ATAC/GM12878_25
+M/GM12878_25M_07.18.2022_bias_transfer_1234_fold_0_data_type_ATAC_PE/chrombpnet_model/filtered.nonpeaks.bed -inpt /oak/stanford/groups/akundaje/projects/chromatin-atl
+as-2022/ATAC/ENCSR000EMT/negatives_data/test/test.fold_0.filtered.negatives_with_summit.bed -f /mnt/lab_data2/anusri/chrombpnet/splits/fold_0.json -o /oak/stanford/gr
+oups/akundaje/projects/chromatin-atlas-2022/chrombpnet/folds/ATAC/GM12878_25M/GM12878_25M_07.18.2022_bias_transfer_1234_fold_0_data_type_ATAC_PE/train_test_regions_ma
+y_7_2024/
+python get_train_test_regions.py -ip /oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/chrombpnet/folds/ATAC/GM12878_25M/GM12878_25M_07.18.2022_bias_transf
+er_1234_fold_1_data_type_ATAC_PE/chrombpnet_model/filtered.peaks.bed -inp /oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/chrombpnet/folds/ATAC/GM12878_25
+M/GM12878_25M_07.18.2022_bias_transfer_1234_fold_1_data_type_ATAC_PE/chrombpnet_model/filtered.nonpeaks.bed -inpt /oak/stanford/groups/akundaje/projects/chromatin-atl
+as-2022/ATAC/ENCSR000EMT/negatives_data/test/test.fold_1.filtered.negatives_with_summit.bed -f /mnt/lab_data2/anusri/chrombpnet/splits/fold_1.json -o /oak/stanford/gr
+oups/akundaje/projects/chromatin-atlas-2022/chrombpnet/folds/ATAC/GM12878_25M/GM12878_25M_07.18.2022_bias_transfer_1234_fold_1_data_type_ATAC_PE/train_test_regions_ma
+y_7_2024/
+python get_train_test_regions.py -ip /oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/chrombpnet/folds/ATAC/GM12878_25M/GM12878_25M_07.18.2022_bias_transf
+er_1234_fold_2_data_type_ATAC_PE/chrombpnet_model/filtered.peaks.bed -inp /oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/chrombpnet/folds/ATAC/GM12878_25
+M/GM12878_25M_07.18.2022_bias_transfer_1234_fold_2_data_type_ATAC_PE/chrombpnet_model/filtered.nonpeaks.bed -inpt /oak/stanford/groups/akundaje/projects/chromatin-atl
+as-2022/ATAC/ENCSR000EMT/negatives_data/test/test.fold_2.filtered.negatives_with_summit.bed -f /mnt/lab_data2/anusri/chrombpnet/splits/fold_2.json -o /oak/stanford/gr
+oups/akundaje/projects/chromatin-atlas-2022/chrombpnet/folds/ATAC/GM12878_25M/GM12878_25M_07.18.2022_bias_transfer_1234_fold_2_data_type_ATAC_PE/train_test_regions_ma
+y_7_2024/
+python get_train_test_regions.py -ip /oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/chrombpnet/folds/ATAC/GM12878_25M/GM12878_25M_07.18.2022_bias_transf
+er_1234_fold_3_data_type_ATAC_PE/chrombpnet_model/filtered.peaks.bed -inp /oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/chrombpnet/folds/ATAC/GM12878_25
+M/GM12878_25M_07.18.2022_bias_transfer_1234_fold_3_data_type_ATAC_PE/chrombpnet_model/filtered.nonpeaks.bed -inpt /oak/stanford/groups/akundaje/projects/chromatin-atl
+as-2022/ATAC/ENCSR000EMT/negatives_data/test/test.fold_3.filtered.negatives_with_summit.bed -f /mnt/lab_data2/anusri/chrombpnet/splits/fold_3.json -o /oak/stanford/gr
+oups/akundaje/projects/chromatin-atlas-2022/chrombpnet/folds/ATAC/GM12878_25M/GM12878_25M_07.18.2022_bias_transfer_1234_fold_3_data_type_ATAC_PE/train_test_regions_ma
+y_7_2024/
+python get_train_test_regions.py -ip /oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/chrombpnet/folds/ATAC/GM12878_25M/GM12878_25M_07.18.2022_bias_transf
+er_1234_fold_4_data_type_ATAC_PE/chrombpnet_model/filtered.peaks.bed -inp /oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/chrombpnet/folds/ATAC/GM12878_25
+M/GM12878_25M_07.18.2022_bias_transfer_1234_fold_4_data_type_ATAC_PE/chrombpnet_model/filtered.nonpeaks.bed -inpt /oak/stanford/groups/akundaje/projects/chromatin-atl
+as-2022/ATAC/ENCSR000EMT/negatives_data/test/test.fold_4.filtered.negatives_with_summit.bed -f /mnt/lab_data2/anusri/chrombpnet/splits/fold_4.json -o /oak/stanford/gr
+oups/akundaje/projects/chromatin-atlas-2022/chrombpnet/folds/ATAC/GM12878_25M/GM12878_25M_07.18.2022_bias_transfer_1234_fold_4_data_type_ATAC_PE/train_test_regions_ma
+y_7_2024/
+python get_train_test_regions.py -ip /oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/chrombpnet/folds/ATAC/GM12878_5M/GM12878_5M_07.18.2022_bias_transfer
+_1234_fold_0_data_type_ATAC_PE/chrombpnet_model/filtered.peaks.bed -inp /oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/chrombpnet/folds/ATAC/GM12878_5M/G
+M12878_5M_07.18.2022_bias_transfer_1234_fold_0_data_type_ATAC_PE/chrombpnet_model/filtered.nonpeaks.bed -inpt /oak/stanford/groups/akundaje/projects/chromatin-atlas-2
+022/ATAC/ENCSR000EMT/negatives_data/test/test.fold_0.filtered.negatives_with_summit.bed -f /mnt/lab_data2/anusri/chrombpnet/splits/fold_0.json -o /oak/stanford/groups
+/akundaje/projects/chromatin-atlas-2022/chrombpnet/folds/ATAC/GM12878_5M/GM12878_5M_07.18.2022_bias_transfer_1234_fold_0_data_type_ATAC_PE/train_test_regions_may_7_20
+24/
+python get_train_test_regions.py -ip /oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/chrombpnet/folds/ATAC/GM12878_5M/GM12878_5M_07.18.2022_bias_transfer
+_1234_fold_1_data_type_ATAC_PE/chrombpnet_model/filtered.peaks.bed -inp /oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/chrombpnet/folds/ATAC/GM12878_5M/G
+M12878_5M_07.18.2022_bias_transfer_1234_fold_1_data_type_ATAC_PE/chrombpnet_model/filtered.nonpeaks.bed -inpt /oak/stanford/groups/akundaje/projects/chromatin-atlas-2
+022/ATAC/ENCSR000EMT/negatives_data/test/test.fold_1.filtered.negatives_with_summit.bed -f /mnt/lab_data2/anusri/chrombpnet/splits/fold_1.json -o /oak/stanford/groups
+/akundaje/projects/chromatin-atlas-2022/chrombpnet/folds/ATAC/GM12878_5M/GM12878_5M_07.18.2022_bias_transfer_1234_fold_1_data_type_ATAC_PE/train_test_regions_may_7_20
+24/
+python get_train_test_regions.py -ip /oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/chrombpnet/folds/ATAC/GM12878_5M/GM12878_5M_07.18.2022_bias_transfer
+_1234_fold_2_data_type_ATAC_PE/chrombpnet_model/filtered.peaks.bed -inp /oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/chrombpnet/folds/ATAC/GM12878_5M/G
+M12878_5M_07.18.2022_bias_transfer_1234_fold_2_data_type_ATAC_PE/chrombpnet_model/filtered.nonpeaks.bed -inpt /oak/stanford/groups/akundaje/projects/chromatin-atlas-2
+022/ATAC/ENCSR000EMT/negatives_data/test/test.fold_2.filtered.negatives_with_summit.bed -f /mnt/lab_data2/anusri/chrombpnet/splits/fold_2.json -o /oak/stanford/groups
+/akundaje/projects/chromatin-atlas-2022/chrombpnet/folds/ATAC/GM12878_5M/GM12878_5M_07.18.2022_bias_transfer_1234_fold_2_data_type_ATAC_PE/train_test_regions_may_7_20
+24/
+python get_train_test_regions.py -ip /oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/chrombpnet/folds/ATAC/GM12878_5M/GM12878_5M_07.18.2022_bias_transfer
+_1234_fold_3_data_type_ATAC_PE/chrombpnet_model/filtered.peaks.bed -inp /oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/chrombpnet/folds/ATAC/GM12878_5M/G
+M12878_5M_07.18.2022_bias_transfer_1234_fold_3_data_type_ATAC_PE/chrombpnet_model/filtered.nonpeaks.bed -inpt /oak/stanford/groups/akundaje/projects/chromatin-atlas-2
+022/ATAC/ENCSR000EMT/negatives_data/test/test.fold_3.filtered.negatives_with_summit.bed -f /mnt/lab_data2/anusri/chrombpnet/splits/fold_3.json -o /oak/stanford/groups
+/akundaje/projects/chromatin-atlas-2022/chrombpnet/folds/ATAC/GM12878_5M/GM12878_5M_07.18.2022_bias_transfer_1234_fold_3_data_type_ATAC_PE/train_test_regions_may_7_20
+24/
+python get_train_test_regions.py -ip /oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/chrombpnet/folds/ATAC/GM12878_5M/GM12878_5M_07.18.2022_bias_transfer
+_1234_fold_4_data_type_ATAC_PE/chrombpnet_model/filtered.peaks.bed -inp /oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/chrombpnet/folds/ATAC/GM12878_5M/G
+M12878_5M_07.18.2022_bias_transfer_1234_fold_4_data_type_ATAC_PE/chrombpnet_model/filtered.nonpeaks.bed -inpt /oak/stanford/groups/akundaje/projects/chromatin-atlas-2
+022/ATAC/ENCSR000EMT/negatives_data/test/test.fold_4.filtered.negatives_with_summit.bed -f /mnt/lab_data2/anusri/chrombpnet/splits/fold_4.json -o /oak/stanford/groups
+/akundaje/projects/chromatin-atlas-2022/chrombpnet/folds/ATAC/GM12878_5M/GM12878_5M_07.18.2022_bias_transfer_1234_fold_4_data_type_ATAC_PE/train_test_regions_may_7_20
+24/
+(chrombpnet) anusri@brahma:/mnt/lab_data2/anusri/chrombpnet/upload_jsons/upload_scripts$ ls
+bias_models_atlas.csv GM12878 __pycache__ run_train_test_making_bias.py
+convert_to_compressed.py k562.samstats.qc README.md run_train_test_making.py
+get_new_tf_model_format.py new_metrics run_conversion_bias.py temp
+get_train_test_regions_bias.py new_run_train_test_making.py run_conversion_new.py upload_utils.py
+get_train_test_regions.py prepare_file_for_upload_models.py run_conversion.py
+(chrombpnet) anusri@brahma:/mnt/lab_data2/anusri/chrombpnet/upload_jsons/upload_scripts$ python run_train_test_making.py
diff --git a/logs/checkpoint/JAN_02_2023/screenlog/output_train_test_making_bias.log b/logs/checkpoint/JAN_02_2023/screenlog/output_train_test_making_bias.log
new file mode 100644
index 00000000..f6ff9ba8
--- /dev/null
+++ b/logs/checkpoint/JAN_02_2023/screenlog/output_train_test_making_bias.log
@@ -0,0 +1,1074 @@
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ print(output_path)
+ os.makedirs(output_path, exist_ok=True)
+ command=["python get_train_test_regions_bias.py "]+["-inp"]+[input_nonpeaks]+["-f"]+[fold]+["-o"]+[output_path]
+ command = " ".join(command)
+ print(command)
+ os.system(command)
+
+ else:
+ print(output_path)
+ break
+
+
+(chrombpnet) anusri@brahma:/mnt/lab_data2/anusri/chrombpnet/upload_jsons/upload_scripts$ python run_train_test_making_bias.py
+/mnt/lab_data2/anusri/chrombpnet/results/chrombpnet/ATAC_PE/GM12878/nautilus_runs/GM12878_03.01.2022_bias_128_4_1234_0.4_fold_0/train_test_regions_bias_may_7_2024/
+(chrombpnet) anusri@brahma:/mnt/lab_data2/anusri/chrombpnet/upload_jsons/upload_scripts$ nano run_train_test_making_bias.py
+
+import pandas as pd
+import os
+
+model_atac = pd.read_csv("/mnt/lab_data2/anusri/chrombpnet/logs/checkpoint/JAN_02_2023/model_dir_atac.csv",sep=",", header=None)
+#model_atac = pd.read_csv("/mnt/lab_data2/anusri/chrombpnet/logs/checkpoint/JAN_02_2023/model_dir_dnase.csv",sep=",", header=None)
+#model_atac=pd.read_csv("bias_models_atlas.csv", sep=',', header=None)
+#model_atac=pd.read_csv("model_dir_dnase_v2.1_bias.csv", sep=',', header=None)
+
+
+
+
+encode_id = {"K562": "ENCSR868FGK",
+ "GM12878": "ENCSR637XSC",
+ "HEPG2": "ENCSR291GJU",
+ "IMR90": "ENCSR200OML",
+ "H1ESC": "ENCDUMMY"}
+
+encode_id = {"K562": "ENCSR000EOT",
+ "GM12878": "ENCSR000EMT",
+ "HEPG2": "ENCSR149XIL",
+ "IMR90": "ENCSR477RTP",
+ "H1ESC": "ENCSR000EMU"}
+
+
+for i,r in model_atac.iterrows():
+ fold = r[0]
+ GNU nano 6.2 run_train_test_making_bias.py
+ name = r[1]
+ model_path = r[2]
+
+ #input_peaks=os.path.join(model_path,"chrombpnet_model/filtered.peaks.bed")
+ input_nonpeaks=os.path.join(model_path,"bias_model/filtered.bias_nonpeaks.bed")
+ #test_nonpeaks="/oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/DNASE/"+encode_id[name]+"/negatives_data/test/test.>
+ fold="/mnt/lab_data2/anusri/chrombpnet/splits/"+fold+".json"
+ output_path=os.path.join(model_path,"train_test_regions_bias_may_7_2024/")
+
+ if not os.path.isfile(input_nonpeaks):
+ cellline=input_nonpeaks.split("/")[10]
+ biasth=input_nonpeaks.split("/")[11].split("_")[6]
+ foldn=input_nonpeaks.split("/")[11].split("_")[8]
+ #print(cellline,biasth,foldn)
+ ddatype="ATAC_PE"
+ outputdir=os.path.join(model_path,"bias_model/newgen/")
+ if not os.path.isfile(os.path.join(model_path,"bias_model/newgen/filtered.bias_nonpeaks.bed")):
+ os.makedirs(outputdir, exist_ok=True)
+ print(outputdir)
+ command = "bash make_missing_bed_regions.sh "+cellline+" "+biasth+" "+foldn+" "+outputdir+" "+ddatype
+ os.system(command)
+ print(command)
+ else:
+ input_nonpeaks=os.path.join(model_path,"bias_model/newgen/filtered.bias_nonpeaks.bed")
+
+ if not os.path.isfile(output_path+"nonpeaks.validationset.bed.gz"):
+ print(output_path)
+ os.makedirs(output_path, exist_ok=True)
+ command=["python get_train_test_regions_bias.py "]+["-inp"]+[input_nonpeaks]+["-f"]+[fold]+["-o"]+[output_path]
+ command = " ".join(command)
+ print(command)
+ os.system(command)
+ break
+ else:
+ print(output_path)
+
+
+
+
+(chrombpnet) anusri@brahma:/mnt/lab_data2/anusri/chrombpnet/upload_jsons/upload_scripts$ python run_train_test_making_bias.py
+/mnt/lab_data2/anusri/chrombpnet/results/chrombpnet/ATAC_PE/GM12878/nautilus_runs/GM12878_03.01.2022_bias_128_4_1234_0.4_fold_0/train_test_regions_bias_may_7_2024/
+/oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/chrombpnet/folds/ATAC/GM12878/GM12878_07.08.2022_bias_128_4_1234_0.4_fold_1_data_type_ATAC_PE/train_test_r
+egions_bias_may_7_2024/
+/oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/chrombpnet/folds/ATAC/GM12878/GM12878_07.08.2022_bias_128_4_1234_0.4_fold_2_data_type_ATAC_PE/train_test_r
+egions_bias_may_7_2024/
+python get_train_test_regions_bias.py -inp /oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/chrombpnet/folds/ATAC/GM12878/GM12878_07.08.2022_bias_128_4_12
+34_0.4_fold_2_data_type_ATAC_PE/bias_model/newgen/filtered.bias_nonpeaks.bed -f /mnt/lab_data2/anusri/chrombpnet/splits/fold_2.json -o /oak/stanford/groups/akundaje/p
+rojects/chromatin-atlas-2022/chrombpnet/folds/ATAC/GM12878/GM12878_07.08.2022_bias_128_4_1234_0.4_fold_2_data_type_ATAC_PE/train_test_regions_bias_may_7_2024/
+(chrombpnet) anusri@brahma:/mnt/lab_data2/anusri/chrombpnet/upload_jsons/upload_scripts$ ls /oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/chrombpnet/fol
+ds/ATAC/GM12878/GM12878_07.08.2022_bias_128_4_1234_0.4_fold_2_data_type_ATAC_PE/train_test_regions_bias_may_7_2024/
+nonpeaks.testset.bed.gz nonpeaks.trainingset.bed.gz nonpeaks.validationset.bed.gz
+(chrombpnet) anusri@brahma:/mnt/lab_data2/anusri/chrombpnet/upload_jsons/upload_scripts$ ls bias_models_atlas.csv
+ k562.samstats.qc __pycache__ run_train_test_making.py convert_to_compressed.py make_missing_bed_regions.sh
+ README.md temp
+get_new_tf_model_format.py model_dir_dnase_v2.1_bias.csv run_conversion_bias.py upload_utils.py
+get_train_test_regions_bias.py new_metrics run_conversion_new.py
+get_train_test_regions.py new_run_train_test_making.py run_conversion.py
+GM12878 prepare_file_for_upload_models.py run_train_test_making_bias.py
+(chrombpnet) anusri@brahma:/mnt/lab_data2/anusri/chrombpnet/upload_jsons/upload_scripts$ nano run_train_test_making_bias.py
+
+import pandas as pd
+import os
+
+model_atac = pd.read_csv("/mnt/lab_data2/anusri/chrombpnet/logs/checkpoint/JAN_02_2023/model_dir_atac.csv",sep=",", header=None)
+#model_atac = pd.read_csv("/mnt/lab_data2/anusri/chrombpnet/logs/checkpoint/JAN_02_2023/model_dir_dnase.csv",sep=",", header=None)
+#model_atac=pd.read_csv("bias_models_atlas.csv", sep=',', header=None)
+#model_atac=pd.read_csv("model_dir_dnase_v2.1_bias.csv", sep=',', header=None)
+
+
+
+
+encode_id = {"K562": "ENCSR868FGK",
+ "GM12878": "ENCSR637XSC",
+ "HEPG2": "ENCSR291GJU",
+ "IMR90": "ENCSR200OML",
+ "H1ESC": "ENCDUMMY"}
+
+encode_id = {"K562": "ENCSR000EOT",
+ "GM12878": "ENCSR000EMT",
+ "HEPG2": "ENCSR149XIL",
+ "IMR90": "ENCSR477RTP",
+ "H1ESC": "ENCSR000EMU"}
+
+
+for i,r in model_atac.iterrows():
+ GNU nano 6.2 run_train_test_making_bias.py
+ fold = r[0]
+ name = r[1]
+ model_path = r[2]
+
+ #input_peaks=os.path.join(model_path,"chrombpnet_model/filtered.peaks.bed")
+ input_nonpeaks=os.path.join(model_path,"bias_model/filtered.bias_nonpeaks.bed")
+ #test_nonpeaks="/oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/DNASE/"+encode_id[name]+"/negatives_data/test/test.>
+ fold="/mnt/lab_data2/anusri/chrombpnet/splits/"+fold+".json"
+ output_path=os.path.join(model_path,"train_test_regions_bias_may_7_2024/")
+
+ if not os.path.isfile(input_nonpeaks):
+ cellline=input_nonpeaks.split("/")[10]
+ biasth=input_nonpeaks.split("/")[11].split("_")[6]
+ foldn=input_nonpeaks.split("/")[11].split("_")[8]
+ #print(cellline,biasth,foldn)
+ ddatype="ATAC_PE"
+ outputdir=os.path.join(model_path,"bias_model/newgen/")
+ if not os.path.isfile(os.path.join(model_path,"bias_model/newgen/filtered.bias_nonpeaks.bed")):
+ os.makedirs(outputdir, exist_ok=True)
+ print(outputdir)
+ command = "bash make_missing_bed_regions.sh "+cellline+" "+biasth+" "+foldn+" "+outputdir+" "+ddatype
+ os.system(command)
+ print(command)
+ else:
+ input_nonpeaks=os.path.join(model_path,"bias_model/newgen/filtered.bias_nonpeaks.bed")
+
+ if not os.path.isfile(output_path+"nonpeaks.validationset.bed.gz"):
+ print(output_path)
+ os.makedirs(output_path, exist_ok=True)
+ command=["python get_train_test_regions_bias.py "]+["-inp"]+[input_nonpeaks]+["-f"]+[fold]+["-o"]+[output_path]
+ command = " ".join(command)
+ print(command)
+ os.system(command)
+ break
+ else:
+ print(output_path)
+
+
+
+(chrombpnet) anusri@brahma:/mnt/lab_data2/anusri/chrombpnet/upload_jsons/upload_scripts$ nano make_missing_bed_regions.sh
+
+python /mnt/lab_data2/anusri/chrombpnet/src/helpers/hyperparameters/find_bias_hyperparams.py \
+ GNU nano 6.2 make_missing_bed_regions.sh
+cellline=$1
+biasth=$2
+foldn=$3
+outputdir=$4
+ddatype=$5
+echo "python /mnt/lab_data2/anusri/chrombpnet/src/helpers/hyperparameters/find_bias_hyperparams.py \\
+ --genome=/mnt/lab_data2/anusri/chrombpnet/reference/hg38.genome.fa \\
+ --bigwig=/mnt/lab_data2/anusri/chrombpnet/results/chrombpnet/$ddatype/$cellline/data/$cellline"_unstranded.bw" \\
+ --peaks=/mnt/lab_data2/anusri/chrombpnet/results/chrombpnet/$ddatype/$cellline/data/peaks_no_blacklist.bed \\
+ --nonpeaks=/mnt/lab_data2/anusri/chrombpnet/results/chrombpnet/$ddatype/$cellline/negatives_data_$foldn/negatives_with_summit.be>
+ --outlier_threshold=0.99 \\
+ --chr_fold_path=/mnt/lab_data2/anusri/chrombpnet/splits/fold_$foldn.json \\
+ --inputlen=2114 \\
+ --outputlen=1000 \\
+ --max_jitter=0 \\
+ --filters=128 \\
+ --n_dilation_layers=4 \\
+ --bias_threshold_factor=$biasth \\
+ --output_dir $outputdir"
+
+python /mnt/lab_data2/anusri/chrombpnet/src/helpers/hyperparameters/find_bias_hyperparams.py \
+ --genome=/mnt/lab_data2/anusri/chrombpnet/reference/hg38.genome.fa \
+ --bigwig=/mnt/lab_data2/anusri/chrombpnet/results/chrombpnet/$ddatype/$cellline/data/$cellline"_unstranded.bw" \
+ --peaks=/mnt/lab_data2/anusri/chrombpnet/results/chrombpnet/$ddatype/$cellline/data/peaks_no_blacklist.bed \
+ --nonpeaks=/mnt/lab_data2/anusri/chrombpnet/results/chrombpnet/$ddatype/$cellline/negatives_data_$foldn/negatives_with_summit.be>
+ --outlier_threshold=0.99 \
+ --chr_fold_path=/mnt/lab_data2/anusri/chrombpnet/splits/fold_$foldn.json \
+ --inputlen=2114 \
+ --outputlen=1000 \
+ --max_jitter=0 \
+ --filters=128 \
+ --n_dilation_layers=4 \
+ --bias_threshold_factor=$biasth \
+ --output_dir $outputdir
+
+
+
+
+
+(chrombpnet) anusri@brahma:/mnt/lab_data2/anusri/chrombpnet/upload_jsons/upload_scripts$ python run_train_test_making_bias.py
+/mnt/lab_data2/anusri/chrombpnet/results/chrombpnet/ATAC_PE/GM12878/nautilus_runs/GM12878_03.01.2022_bias_128_4_1234_0.4_fold_0/train_test_regions_bias_may_7_2024/
+/oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/chrombpnet/folds/ATAC/GM12878/GM12878_07.08.2022_bias_128_4_1234_0.4_fold_1_data_type_ATAC_PE/train_test_r
+egions_bias_may_7_2024/
+/oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/chrombpnet/folds/ATAC/GM12878/GM12878_07.08.2022_bias_128_4_1234_0.4_fold_2_data_type_ATAC_PE/train_test_r
+egions_bias_may_7_2024/
+/oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/chrombpnet/folds/ATAC/GM12878/GM12878_07.14.2022_bias_128_4_1234_0.4_fold_3_data_type_ATAC_PE/bias_model/n
+ewgen/
+python /mnt/lab_data2/anusri/chrombpnet/src/helpers/hyperparameters/find_bias_hyperparams.py \
+ --genome=/mnt/lab_data2/anusri/chrombpnet/reference/hg38.genome.fa \
+ --bigwig=/mnt/lab_data2/anusri/chrombpnet/results/chrombpnet/ATAC_PE/GM12878/data/GM12878_unstranded.bw \
+ --peaks=/mnt/lab_data2/anusri/chrombpnet/results/chrombpnet/ATAC_PE/GM12878/data/peaks_no_blacklist.bed \
+ --nonpeaks=/mnt/lab_data2/anusri/chrombpnet/results/chrombpnet/ATAC_PE/GM12878/negatives_data_3/negatives_with_summit.be>
+ --outlier_threshold=0.99 \
+ --chr_fold_path=/mnt/lab_data2/anusri/chrombpnet/splits/fold_3.json \
+ --inputlen=2114 \
+ --outputlen=1000 \
+ --max_jitter=0 \
+ --filters=128 \
+ --n_dilation_layers=4 \
+ --bias_threshold_factor=0.4 \
+ --output_dir /oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/chrombpnet/folds/ATAC/GM12878/GM12878_07.14.2022_bias_128_4_1234_0.4_fold_3_data_type_
+ATAC_PE/bias_model/newgen/
+evaluating hyperparameters on the following chromosomes ['chr1', 'chr2', 'chr3', 'chr4', 'chr7', 'chr8', 'chr9', 'chr11', 'chr12', 'chr13', 'chr15', 'chr16', 'chr17',
+ 'chr19', 'chrX', 'chrY', 'chr6', 'chr21']
+Number of non peaks input: 443544
+Number of non peaks filtered because the input/output is on the edge: 0
+Number of non peaks being used: 443544
+Number of non peaks input: 56135
+Number of non peaks filtered because the input/output is on the edge: 0
+Number of non peaks being used: 56135
+Number of peaks input: 221772
+Number of peaks filtered because the input/output is on the edge: 0
+Number of peaks being used: 221772
+Upper bound counts cut-off for bias model training: 82.4
+Number of nonpeaks after the upper-bount cut-off: 221322
+Number of nonpeaks after applying upper-bound cut-off and removing outliers : 206958
+counts_loss_weight: 5.2
+bash make_missing_bed_regions.sh GM12878 0.4 3 /oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/chrombpnet/folds/ATAC/GM12878/GM12878_07.14.2022_bias_128_4
+_1234_0.4_fold_3_data_type_ATAC_PE/bias_model/newgen/ ATAC_PE
+/oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/chrombpnet/folds/ATAC/GM12878/GM12878_07.14.2022_bias_128_4_1234_0.4_fold_3_data_type_ATAC_PE/train_test_r
+egions_bias_may_7_2024/
+python get_train_test_regions_bias.py -inp /oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/chrombpnet/folds/ATAC/GM12878/GM12878_07.14.2022_bias_128_4_12
+34_0.4_fold_3_data_type_ATAC_PE/bias_model/filtered.bias_nonpeaks.bed -f /mnt/lab_data2/anusri/chrombpnet/splits/fold_3.json -o /oak/stanford/groups/akundaje/projects
+/chromatin-atlas-2022/chrombpnet/folds/ATAC/GM12878/GM12878_07.14.2022_bias_128_4_1234_0.4_fold_3_data_type_ATAC_PE/train_test_regions_bias_may_7_2024/
+Traceback (most recent call last):
+ File "get_train_test_regions_bias.py", line 17, in
+ nonpeaks = pd.read_csv(args.input_nonpeaks, sep="\t", header=None, names=NARROWPEAK_SCHEMA)
+ File "/users/anusri/anaconda3/envs/chrombpnet/lib/python3.8/site-packages/pandas/util/_decorators.py", line 211, in wrapper
+ return func(*args, **kwargs)
+ File "/users/anusri/anaconda3/envs/chrombpnet/lib/python3.8/site-packages/pandas/util/_decorators.py", line 331, in wrapper
+ return func(*args, **kwargs)
+ File "/users/anusri/anaconda3/envs/chrombpnet/lib/python3.8/site-packages/pandas/io/parsers/readers.py", line 950, in read_csv
+ return _read(filepath_or_buffer, kwds)
+ File "/users/anusri/anaconda3/envs/chrombpnet/lib/python3.8/site-packages/pandas/io/parsers/readers.py", line 605, in _read
+ parser = TextFileReader(filepath_or_buffer, **kwds)
+ File "/users/anusri/anaconda3/envs/chrombpnet/lib/python3.8/site-packages/pandas/io/parsers/readers.py", line 1442, in __init__
+ self._engine = self._make_engine(f, self.engine)
+ File "/users/anusri/anaconda3/envs/chrombpnet/lib/python3.8/site-packages/pandas/io/parsers/readers.py", line 1735, in _make_engine
+ self.handles = get_handle(
+ File "/users/anusri/anaconda3/envs/chrombpnet/lib/python3.8/site-packages/pandas/io/common.py", line 856, in get_handle
+ handle = open(
+FileNotFoundError: [Errno 2] No such file or directory: '/oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/chrombpnet/folds/ATAC/GM12878/GM12878_07.14.2022_
+bias_128_4_1234_0.4_fold_3_data_type_ATAC_PE/bias_model/filtered.bias_nonpeaks.bed'
+(chrombpnet) anusri@brahma:/mnt/lab_data2/anusri/chrombpnet/upload_jsons/upload_scripts$ ls /oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/chrombpnet/fol
+ds/ATAC/GM12878/GM12878_07.14.2022_bias_12
+ls: cannot access '/oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/chrombpnet/folds/ATAC/GM12878/GM12878_07.14.2022_bias_12': No such file or directory
+(chrombpnet) anusri@brahma:/mnt/lab_data2/anusri/chrombpnet/upload_jsons/upload_scripts$ ls /oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/chrombpnet/fol
+ds/ATAC/GM12878/GM12878_07.14.2022_bias_128_4_1234_0.4_fold_3_data_type_ATAC_PE/bias_model/
+bias.h5 newgen new_model_formats new_model_formats_v1 new_model_formats_v2 new_model_formats_vf
+(chrombpnet) anusri@brahma:/mnt/lab_data2/anusri/chrombpnet/upload_jsons/upload_scripts$ ls /oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/chrombpnet/fol
+ds/ATAC/GM12878/GM12878_07.14.2022_bias_128_4_1234_0.4_fold_3_data_type_ATAC_PE/bias_model/new
+ls: cannot access '/oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/chrombpnet/folds/ATAC/GM12878/GM12878_07.14.2022_bias_128_4_1234_0.4_fold_3_data_type_A
+TAC_PE/bias_model/new': No such file or directory
+(chrombpnet) anusri@brahma:/mnt/lab_data2/anusri/chrombpnet/upload_jsons/upload_scripts$ ls /oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/chrombpnet/fol
+ds/ATAC/GM12878/GM12878_07.14.2022_bias_128_4_1234_0.4_fold_3_data_type_ATAC_PE/bias_model/newgen/
+bias_data_params.tsv bias_model_params.tsv filtered.bias_nonpeaks.bed
+(chrombpnet) anusri@brahma:/mnt/lab_data2/anusri/chrombpnet/upload_jsons/upload_scripts$ nano
+bias_models_atlas.csv make_missing_bed_regions.sh run_conversion_bias.py
+convert_to_compressed.py model_dir_dnase_v2.1_bias.csv run_conversion_new.py
+get_new_tf_model_format.py new_metrics/ run_conversion.py
+get_train_test_regions_bias.py new_run_train_test_making.py run_train_test_making_bias.py
+get_train_test_regions.py prepare_file_for_upload_models.py run_train_test_making.py
+GM12878/ __pycache__/ temp/
+k562.samstats.qc README.md upload_utils.py
+(chrombpnet) anusri@brahma:/mnt/lab_data2/anusri/chrombpnet/upload_jsons/upload_scripts$ nano run_train_test_making_bias.py
+
+import pandas as pd
+import os
+
+model_atac = pd.read_csv("/mnt/lab_data2/anusri/chrombpnet/logs/checkpoint/JAN_02_2023/model_dir_atac.csv",sep=",", header=None)
+#model_atac = pd.read_csv("/mnt/lab_data2/anusri/chrombpnet/logs/checkpoint/JAN_02_2023/model_dir_dnase.csv",sep=",", header=None)
+#model_atac=pd.read_csv("bias_models_atlas.csv", sep=',', header=None)
+#model_atac=pd.read_csv("model_dir_dnase_v2.1_bias.csv", sep=',', header=None)
+
+
+
+
+encode_id = {"K562": "ENCSR868FGK",
+ "GM12878": "ENCSR637XSC",
+ "HEPG2": "ENCSR291GJU",
+ "IMR90": "ENCSR200OML",
+ "H1ESC": "ENCDUMMY"}
+
+encode_id = {"K562": "ENCSR000EOT",
+ "GM12878": "ENCSR000EMT",
+ "HEPG2": "ENCSR149XIL",
+ "IMR90": "ENCSR477RTP",
+ "H1ESC": "ENCSR000EMU"}
+
+
+for i,r in model_atac.iterrows():
+ GNU nano 6.2 run_train_test_making_bias.py
+ fold = r[0]
+ name = r[1]
+ model_path = r[2]
+
+ #input_peaks=os.path.join(model_path,"chrombpnet_model/filtered.peaks.bed")
+ input_nonpeaks=os.path.join(model_path,"bias_model/filtered.bias_nonpeaks.bed")
+ #test_nonpeaks="/oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/DNASE/"+encode_id[name]+"/negatives_data/test/test.>
+ fold="/mnt/lab_data2/anusri/chrombpnet/splits/"+fold+".json"
+ output_path=os.path.join(model_path,"train_test_regions_bias_may_7_2024/")
+
+ if not os.path.isfile(input_nonpeaks):
+ cellline=input_nonpeaks.split("/")[10]
+ biasth=input_nonpeaks.split("/")[11].split("_")[6]
+ foldn=input_nonpeaks.split("/")[11].split("_")[8]
+ #print(cellline,biasth,foldn)
+ ddatype="ATAC_PE"
+ outputdir=os.path.join(model_path,"bias_model/newgen/")
+ if not os.path.isfile(os.path.join(model_path,"bias_model/newgen/filtered.bias_nonpeaks.bed")):
+ os.makedirs(outputdir, exist_ok=True)
+ print(outputdir)
+ command = "bash make_missing_bed_regions.sh "+cellline+" "+biasth+" "+foldn+" "+outputdir+" "+ddatype
+ os.system(command)
+ print(command)
+ input_nonpeaks=os.path.join(model_path,"bias_model/newgen/filtered.bias_nonpeaks.bed")
+ else:
+ input_nonpeaks=os.path.join(model_path,"bias_model/newgen/filtered.bias_nonpeaks.bed")
+
+ if not os.path.isfile(output_path+"nonpeaks.validationset.bed.gz"):
+ print(output_path)
+ os.makedirs(output_path, exist_ok=True)
+ command=["python get_train_test_regions_bias.py "]+["-inp"]+[input_nonpeaks]+["-f"]+[fold]+["-o"]+[output_path]
+ command = " ".join(command)
+ print(command)
+ os.system(command)
+ break
+ else:
+ print(output_path)
+
+
+(chrombpnet) anusri@brahma:/mnt/lab_data2/anusri/chrombpnet/upload_jsons/upload_scripts$ python run_train_test_making_bias.py /mnt/lab_data2/anusri/chrombpn
+et/results/chrombpnet/ATAC_PE/GM12878/nautilus_runs/GM12878_03.01.2022_bias_128_4_1234_0.4_fold_0/train_test_regions_bias_may_7_2024/
+/oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/chrombpnet/folds/ATAC/GM12878/GM12878_07.08.2022_bias_128_4_1234_0.4_fold_1_data_type_ATAC_PE/train_test_r
+egions_bias_may_7_2024/
+/oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/chrombpnet/folds/ATAC/GM12878/GM12878_07.08.2022_bias_128_4_1234_0.4_fold_2_data_type_ATAC_PE/train_test_r
+egions_bias_may_7_2024/
+/oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/chrombpnet/folds/ATAC/GM12878/GM12878_07.14.2022_bias_128_4_1234_0.4_fold_3_data_type_ATAC_PE/train_test_r
+egions_bias_may_7_2024/
+python get_train_test_regions_bias.py -inp /oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/chrombpnet/folds/ATAC/GM12878/GM12878_07.14.2022_bias_128_4_12
+34_0.4_fold_3_data_type_ATAC_PE/bias_model/newgen/filtered.bias_nonpeaks.bed -f /mnt/lab_data2/anusri/chrombpnet/splits/fold_3.json -o /oak/stanford/groups/akundaje/p
+rojects/chromatin-atlas-2022/chrombpnet/folds/ATAC/GM12878/GM12878_07.14.2022_bias_128_4_1234_0.4_fold_3_data_type_ATAC_PE/train_test_regions_bias_may_7_2024/
+(chrombpnet) anusri@brahma:/mnt/lab_data2/anusri/chrombpnet/upload_jsons/upload_scripts$ nano run_train_test_making_bias.py
+
+import pandas as pd
+import os
+
+model_atac = pd.read_csv("/mnt/lab_data2/anusri/chrombpnet/logs/checkpoint/JAN_02_2023/model_dir_atac.csv",sep=",", header=None)
+#model_atac = pd.read_csv("/mnt/lab_data2/anusri/chrombpnet/logs/checkpoint/JAN_02_2023/model_dir_dnase.csv",sep=",", header=None)
+#model_atac=pd.read_csv("bias_models_atlas.csv", sep=',', header=None)
+#model_atac=pd.read_csv("model_dir_dnase_v2.1_bias.csv", sep=',', header=None)
+
+
+
+
+encode_id = {"K562": "ENCSR868FGK",
+ "GM12878": "ENCSR637XSC",
+ "HEPG2": "ENCSR291GJU",
+ "IMR90": "ENCSR200OML",
+ "H1ESC": "ENCDUMMY"}
+
+encode_id = {"K562": "ENCSR000EOT",
+ "GM12878": "ENCSR000EMT",
+ "HEPG2": "ENCSR149XIL",
+ "IMR90": "ENCSR477RTP",
+ "H1ESC": "ENCSR000EMU"}
+
+
+for i,r in model_atac.iterrows():
+ fold = r[0]
+ break
+ GNU nano 6.2 run_train_test_making_bias.py
+ name = r[1]
+ model_path = r[2]
+
+ #input_peaks=os.path.join(model_path,"chrombpnet_model/filtered.peaks.bed")
+ input_nonpeaks=os.path.join(model_path,"bias_model/filtered.bias_nonpeaks.bed")
+ #test_nonpeaks="/oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/DNASE/"+encode_id[name]+"/negatives_data/test/test.>
+ fold="/mnt/lab_data2/anusri/chrombpnet/splits/"+fold+".json"
+ output_path=os.path.join(model_path,"train_test_regions_bias_may_7_2024/")
+
+ if not os.path.isfile(input_nonpeaks):
+ cellline=input_nonpeaks.split("/")[10]
+ biasth=input_nonpeaks.split("/")[11].split("_")[6]
+ foldn=input_nonpeaks.split("/")[11].split("_")[8]
+ #print(cellline,biasth,foldn)
+ ddatype="ATAC_PE"
+ outputdir=os.path.join(model_path,"bias_model/newgen/")
+ if not os.path.isfile(os.path.join(model_path,"bias_model/newgen/filtered.bias_nonpeaks.bed")):
+ os.makedirs(outputdir, exist_ok=True)
+ print(outputdir)
+ command = "bash make_missing_bed_regions.sh "+cellline+" "+biasth+" "+foldn+" "+outputdir+" "+ddatype
+ os.system(command)
+ print(command)
+ input_nonpeaks=os.path.join(model_path,"bias_model/newgen/filtered.bias_nonpeaks.bed")
+ else:
+ input_nonpeaks=os.path.join(model_path,"bias_model/newgen/filtered.bias_nonpeaks.bed")
+
+ if not os.path.isfile(output_path+"nonpeaks.validationset.bed.gz"):
+ print(output_path)
+ os.makedirs(output_path, exist_ok=True)
+ command=["python get_train_test_regions_bias.py "]+["-inp"]+[input_nonpeaks]+["-f"]+[fold]+["-o"]+[output_path]
+ command = " ".join(command)
+ print(command)
+ os.system(command)
+ else:
+ print(output_path)
+
+
+
+
+(chrombpnet) anusri@brahma:/mnt/lab_data2/anusri/chrombpnet/upload_jsons/upload_scripts$ ls -l
+total 112
+-rwxr-xr-x 1 anusri kundaje 3349 Aug 28 2023 bias_models_atlas.csv
+-rwxr-xr-x 1 anusri kundaje 1885 Jul 26 2023 convert_to_compressed.py
+-rwxr-xr-x 1 anusri kundaje 1043 May 24 13:08 get_new_tf_model_format.py
+-rwxr-xr-x 1 anusri kundaje 1779 Aug 17 2023 get_train_test_regions_bias.py
+-rwxr-xr-x 1 anusri kundaje 2171 May 7 17:48 get_train_test_regions.py
+drwxr-xr-x 3 anusri kundaje 4096 May 8 17:06 GM12878
+-rwxr-xr-x 1 anusri kundaje 323 Jul 26 2023 k562.samstats.qc
+-rw-r--r-- 1 anusri kundaje 1800 May 24 16:00 make_missing_bed_regions.sh
+-rwxr-xr-x 1 anusri kundaje 2401 May 24 12:44 model_dir_dnase_v2.1_bias.csv
+drwxr-xr-x 2 anusri kundaje 4096 Jul 26 2023 new_metrics
+-rwxr-xr-x 1 anusri kundaje 1610 May 8 00:28 new_run_train_test_making.py
+-rwxr-xr-x 1 anusri kundaje 11094 Aug 17 2023 prepare_file_for_upload_models.py
+drwxr-xr-x 2 anusri kundaje 4096 Jul 26 2023 __pycache__
+-rw-r--r-- 1 anusri kundaje 68 May 6 23:11 README.md
+-rwxr-xr-x 1 anusri kundaje 1471 May 24 12:47 run_conversion_bias.py
+-rwxr-xr-x 1 anusri kundaje 1954 May 24 13:49 run_conversion_new.py
+-rwxr-xr-x 1 anusri kundaje 2219 May 8 17:10 run_conversion.py
+-rwxr-xr-x 1 anusri kundaje 2459 May 24 16:12 run_train_test_making_bias.py
+-rwxr-xr-x 1 anusri kundaje 1786 May 8 18:14 run_train_test_making.py
+drwxr-xr-x 2 anusri kundaje 4096 May 7 18:59 temp
+-rwxr-xr-x 1 anusri kundaje 23747 Jul 26 2023 upload_utils.py
+(chrombpnet) anusri@brahma:/mnt/lab_data2/anusri/chrombpnet/upload_jsons/upload_scripts$ python run_train_test_making_bias.py
+/mnt/lab_data2/anusri/chrombpnet/results/chrombpnet/ATAC_PE/GM12878/nautilus_runs/GM12878_03.01.2022_bias_128_4_1234_0.4_fold_0/train_test_regions_bias_may_7_2024/
+/oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/chrombpnet/folds/ATAC/GM12878/GM12878_07.08.2022_bias_128_4_1234_0.4_fold_1_data_type_ATAC_PE/train_test_r
+egions_bias_may_7_2024/
+/oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/chrombpnet/folds/ATAC/GM12878/GM12878_07.08.2022_bias_128_4_1234_0.4_fold_2_data_type_ATAC_PE/train_test_r
+egions_bias_may_7_2024/
+/oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/chrombpnet/folds/ATAC/GM12878/GM12878_07.14.2022_bias_128_4_1234_0.4_fold_3_data_type_ATAC_PE/train_test_r
+egions_bias_may_7_2024/
+/oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/chrombpnet/folds/ATAC/GM12878/GM12878_07.07.2022_bias_128_4_1234_0.4_fold_4_data_type_ATAC_PE/bias_model/n
+ewgen/
+python /mnt/lab_data2/anusri/chrombpnet/src/helpers/hyperparameters/find_bias_hyperparams.py \
+ --genome=/mnt/lab_data2/anusri/chrombpnet/reference/hg38.genome.fa \
+ --bigwig=/mnt/lab_data2/anusri/chrombpnet/results/chrombpnet/ATAC_PE/GM12878/data/GM12878_unstranded.bw \
+ --peaks=/mnt/lab_data2/anusri/chrombpnet/results/chrombpnet/ATAC_PE/GM12878/data/peaks_no_blacklist.bed \
+ --nonpeaks=/mnt/lab_data2/anusri/chrombpnet/results/chrombpnet/ATAC_PE/GM12878/negatives_data_4/negatives_with_summit.be>
+ --outlier_threshold=0.99 \
+ --chr_fold_path=/mnt/lab_data2/anusri/chrombpnet/splits/fold_4.json \
+ --inputlen=2114 \
+ --outputlen=1000 \
+ --max_jitter=0 \
+ --filters=128 \
+ --n_dilation_layers=4 \
+ --bias_threshold_factor=0.4 \
+ --output_dir /oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/chrombpnet/folds/ATAC/GM12878/GM12878_07.07.2022_bias_128_4_1234_0.4_fold_4_data_type_
+ATAC_PE/bias_model/newgen/
+evaluating hyperparameters on the following chromosomes ['chr1', 'chr2', 'chr3', 'chr4', 'chr5', 'chr6', 'chr8', 'chr9', 'chr11', 'chr12', 'chr14', 'chr15', 'chr16',
+'chr20', 'chr22', 'chrY', 'chr10', 'chr18']
+Number of non peaks input: 449946
+Number of non peaks filtered because the input/output is on the edge: 0
+Number of non peaks being used: 449946
+Number of non peaks input: 52934
+Number of non peaks filtered because the input/output is on the edge: 0
+Number of non peaks being used: 52934
+Number of peaks input: 224973
+Number of peaks filtered because the input/output is on the edge: 0
+Number of peaks being used: 224973
+Upper bound counts cut-off for bias model training: 82.0
+Number of nonpeaks after the upper-bount cut-off: 217013
+Number of nonpeaks after applying upper-bound cut-off and removing outliers : 202523
+counts_loss_weight: 5.3
+bash make_missing_bed_regions.sh GM12878 0.4 4 /oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/chrombpnet/folds/ATAC/GM12878/GM12878_07.07.2022_bias_128_4
+_1234_0.4_fold_4_data_type_ATAC_PE/bias_model/newgen/ ATAC_PE
+/oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/chrombpnet/folds/ATAC/GM12878/GM12878_07.07.2022_bias_128_4_1234_0.4_fold_4_data_type_ATAC_PE/train_test_r
+egions_bias_may_7_2024/
+python get_train_test_regions_bias.py -inp /oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/chrombpnet/folds/ATAC/GM12878/GM12878_07.07.2022_bias_128_4_12
+34_0.4_fold_4_data_type_ATAC_PE/bias_model/newgen/filtered.bias_nonpeaks.bed -f /mnt/lab_data2/anusri/chrombpnet/splits/fold_4.json -o /oak/stanford/groups/akundaje/p
+rojects/chromatin-atlas-2022/chrombpnet/folds/ATAC/GM12878/GM12878_07.07.2022_bias_128_4_1234_0.4_fold_4_data_type_ATAC_PE/train_test_regions_bias_may_7_2024/
+/mnt/lab_data2/anusri/chrombpnet/results/chrombpnet/ATAC_PE/K562/nautilus_runs/K562_02.17.2022_bias_128_4_1234_0.5_fold_0/train_test_regions_bias_may_7_2024/
+/oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/chrombpnet/folds/ATAC/K562/K562_07.07.2022_bias_128_4_2356_0.5_fold_1_data_type_ATAC_PE/train_test_regions
+_bias_may_7_2024/
+/oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/chrombpnet/folds/ATAC/K562/K562_07.07.2022_bias_128_4_2356_0.5_fold_2_data_type_ATAC_PE/train_test_regions
+_bias_may_7_2024/
+/oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/chrombpnet/folds/ATAC/K562/K562_07.07.2022_bias_128_4_2356_0.5_fold_3_data_type_ATAC_PE/train_test_regions
+_bias_may_7_2024/
+/oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/chrombpnet/folds/ATAC/K562/K562_07.07.2022_bias_128_4_2356_0.5_fold_4_data_type_ATAC_PE/train_test_regions
+_bias_may_7_2024/
+/mnt/lab_data2/anusri/chrombpnet/results/chrombpnet/ATAC_PE/HEPG2/nautilus_runs_jun16/HEPG2_05.09.2022_bias_128_4_1234_0.8_fold_0/train_test_regions_bias_may_7_2024/
+/oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/chrombpnet/folds/ATAC/HEPG2/HEPG2_06.07.2022_bias_128_4_1234_0.8_fold_1/bias_model/newgen/
+python /mnt/lab_data2/anusri/chrombpnet/src/helpers/hyperparameters/find_bias_hyperparams.py \
+ --genome=/mnt/lab_data2/anusri/chrombpnet/reference/hg38.genome.fa \
+ --bigwig=/mnt/lab_data2/anusri/chrombpnet/results/chrombpnet/ATAC_PE/HEPG2/data/HEPG2_unstranded.bw \
+ --peaks=/mnt/lab_data2/anusri/chrombpnet/results/chrombpnet/ATAC_PE/HEPG2/data/peaks_no_blacklist.bed \
+ --nonpeaks=/mnt/lab_data2/anusri/chrombpnet/results/chrombpnet/ATAC_PE/HEPG2/negatives_data_1/negatives_with_summit.be>
+ --outlier_threshold=0.99 \
+ --chr_fold_path=/mnt/lab_data2/anusri/chrombpnet/splits/fold_1.json \
+ --inputlen=2114 \
+ --outputlen=1000 \
+ --max_jitter=0 \
+ --filters=128 \
+ --n_dilation_layers=4 \
+ --bias_threshold_factor=0.8 \
+ --output_dir /oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/chrombpnet/folds/ATAC/HEPG2/HEPG2_06.07.2022_bias_128_4_1234_0.8_fold_1/bias_model/new
+gen/
+evaluating hyperparameters on the following chromosomes ['chr1', 'chr3', 'chr4', 'chr5', 'chr6', 'chr7', 'chr10', 'chr11', 'chr13', 'chr14', 'chr15', 'chr18', 'chr19'
+, 'chr20', 'chr21', 'chr22', 'chrX', 'chrY', 'chr12', 'chr17']
+Number of non peaks input: 432360
+Number of non peaks filtered because the input/output is on the edge: 0
+Number of non peaks being used: 432360
+Number of non peaks input: 63456
+Number of non peaks filtered because the input/output is on the edge: 0
+Number of non peaks being used: 63456
+Number of peaks input: 216180
+Number of peaks filtered because the input/output is on the edge: 0
+Number of peaks being used: 216180
+Upper bound counts cut-off for bias model training: 179.20000000000002
+Number of nonpeaks after the upper-bount cut-off: 301394
+Number of nonpeaks after applying upper-bound cut-off and removing outliers : 290833
+counts_loss_weight: 8.9
+bash make_missing_bed_regions.sh HEPG2 0.8 1 /oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/chrombpnet/folds/ATAC/HEPG2/HEPG2_06.07.2022_bias_128_4_1234_
+0.8_fold_1/bias_model/newgen/ ATAC_PE
+/oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/chrombpnet/folds/ATAC/HEPG2/HEPG2_06.07.2022_bias_128_4_1234_0.8_fold_1/train_test_regions_bias_may_7_2024
+/
+python get_train_test_regions_bias.py -inp /oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/chrombpnet/folds/ATAC/HEPG2/HEPG2_06.07.2022_bias_128_4_1234_0
+.8_fold_1/bias_model/newgen/filtered.bias_nonpeaks.bed -f /mnt/lab_data2/anusri/chrombpnet/splits/fold_1.json -o /oak/stanford/groups/akundaje/projects/chromatin-atla
+s-2022/chrombpnet/folds/ATAC/HEPG2/HEPG2_06.07.2022_bias_128_4_1234_0.8_fold_1/train_test_regions_bias_may_7_2024/
+/oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/chrombpnet/folds/ATAC/HEPG2/HEPG2_05.24.2022_bias_128_4_1234_0.8_fold_2/bias_model/newgen/
+python /mnt/lab_data2/anusri/chrombpnet/src/helpers/hyperparameters/find_bias_hyperparams.py \
+ --genome=/mnt/lab_data2/anusri/chrombpnet/reference/hg38.genome.fa \
+ --bigwig=/mnt/lab_data2/anusri/chrombpnet/results/chrombpnet/ATAC_PE/HEPG2/data/HEPG2_unstranded.bw \
+ --peaks=/mnt/lab_data2/anusri/chrombpnet/results/chrombpnet/ATAC_PE/HEPG2/data/peaks_no_blacklist.bed \
+ --nonpeaks=/mnt/lab_data2/anusri/chrombpnet/results/chrombpnet/ATAC_PE/HEPG2/negatives_data_2/negatives_with_summit.be>
+ --outlier_threshold=0.99 \
+ --chr_fold_path=/mnt/lab_data2/anusri/chrombpnet/splits/fold_2.json \
+ --inputlen=2114 \
+ --outputlen=1000 \
+ --max_jitter=0 \
+ --filters=128 \
+ --n_dilation_layers=4 \
+ --bias_threshold_factor=0.8 \
+ --output_dir /oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/chrombpnet/folds/ATAC/HEPG2/HEPG2_05.24.2022_bias_128_4_1234_0.8_fold_2/bias_model/new
+gen/
+evaluating hyperparameters on the following chromosomes ['chr1', 'chr2', 'chr3', 'chr5', 'chr6', 'chr8', 'chr9', 'chr10', 'chr13', 'chr14', 'chr16', 'chr17', 'chr18',
+ 'chr19', 'chr20', 'chr21', 'chrX', 'chr22', 'chr7']
+Number of non peaks input: 469546
+Number of non peaks filtered because the input/output is on the edge: 0
+Number of non peaks being used: 469546
+Number of non peaks input: 44863
+Number of non peaks filtered because the input/output is on the edge: 0
+Number of non peaks being used: 44863
+Number of peaks input: 234773
+Number of peaks filtered because the input/output is on the edge: 0
+Number of peaks being used: 234773
+Upper bound counts cut-off for bias model training: 183.20000000000002
+Number of nonpeaks after the upper-bount cut-off: 323981
+Number of nonpeaks after applying upper-bound cut-off and removing outliers : 312059
+counts_loss_weight: 9.3
+bash make_missing_bed_regions.sh HEPG2 0.8 2 /oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/chrombpnet/folds/ATAC/HEPG2/HEPG2_05.24.2022_bias_128_4_1234_
+0.8_fold_2/bias_model/newgen/ ATAC_PE
+/oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/chrombpnet/folds/ATAC/HEPG2/HEPG2_05.24.2022_bias_128_4_1234_0.8_fold_2/train_test_regions_bias_may_7_2024
+/
+python get_train_test_regions_bias.py -inp /oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/chrombpnet/folds/ATAC/HEPG2/HEPG2_05.24.2022_bias_128_4_1234_0
+.8_fold_2/bias_model/newgen/filtered.bias_nonpeaks.bed -f /mnt/lab_data2/anusri/chrombpnet/splits/fold_2.json -o /oak/stanford/groups/akundaje/projects/chromatin-atla
+s-2022/chrombpnet/folds/ATAC/HEPG2/HEPG2_05.24.2022_bias_128_4_1234_0.8_fold_2/train_test_regions_bias_may_7_2024/
+/oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/chrombpnet/folds/ATAC/HEPG2/HEPG2_05.22.2022_bias_128_4_1234_0.8_fold_3/bias_model/newgen/
+python /mnt/lab_data2/anusri/chrombpnet/src/helpers/hyperparameters/find_bias_hyperparams.py \
+ --genome=/mnt/lab_data2/anusri/chrombpnet/reference/hg38.genome.fa \
+ --bigwig=/mnt/lab_data2/anusri/chrombpnet/results/chrombpnet/ATAC_PE/HEPG2/data/HEPG2_unstranded.bw \
+ --peaks=/mnt/lab_data2/anusri/chrombpnet/results/chrombpnet/ATAC_PE/HEPG2/data/peaks_no_blacklist.bed \
+ --nonpeaks=/mnt/lab_data2/anusri/chrombpnet/results/chrombpnet/ATAC_PE/HEPG2/negatives_data_3/negatives_with_summit.be>
+ --outlier_threshold=0.99 \
+ --chr_fold_path=/mnt/lab_data2/anusri/chrombpnet/splits/fold_3.json \
+ --inputlen=2114 \
+ --outputlen=1000 \
+ --max_jitter=0 \
+ --filters=128 \
+ --n_dilation_layers=4 \
+ --bias_threshold_factor=0.8 \
+ --output_dir /oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/chrombpnet/folds/ATAC/HEPG2/HEPG2_05.22.2022_bias_128_4_1234_0.8_fold_3/bias_model/new
+gen/
+evaluating hyperparameters on the following chromosomes ['chr1', 'chr2', 'chr3', 'chr4', 'chr7', 'chr8', 'chr9', 'chr11', 'chr12', 'chr13', 'chr15', 'chr16', 'chr17',
+ 'chr19', 'chrX', 'chrY', 'chr6', 'chr21']
+Number of non peaks input: 442374
+Number of non peaks filtered because the input/output is on the edge: 0
+Number of non peaks being used: 442374
+Number of non peaks input: 58449
+Number of non peaks filtered because the input/output is on the edge: 0
+Number of non peaks being used: 58449
+Number of peaks input: 221187
+Number of peaks filtered because the input/output is on the edge: 0
+Number of peaks being used: 221187
+Upper bound counts cut-off for bias model training: 180.8
+Number of nonpeaks after the upper-bount cut-off: 307832
+Number of nonpeaks after applying upper-bound cut-off and removing outliers : 295914
+counts_loss_weight: 9.0
+bash make_missing_bed_regions.sh HEPG2 0.8 3 /oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/chrombpnet/folds/ATAC/HEPG2/HEPG2_05.22.2022_bias_128_4_1234_
+0.8_fold_3/bias_model/newgen/ ATAC_PE
+/oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/chrombpnet/folds/ATAC/HEPG2/HEPG2_05.22.2022_bias_128_4_1234_0.8_fold_3/train_test_regions_bias_may_7_2024
+/
+python get_train_test_regions_bias.py -inp /oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/chrombpnet/folds/ATAC/HEPG2/HEPG2_05.22.2022_bias_128_4_1234_0
+.8_fold_3/bias_model/newgen/filtered.bias_nonpeaks.bed -f /mnt/lab_data2/anusri/chrombpnet/splits/fold_3.json -o /oak/stanford/groups/akundaje/projects/chromatin-atla
+s-2022/chrombpnet/folds/ATAC/HEPG2/HEPG2_05.22.2022_bias_128_4_1234_0.8_fold_3/train_test_regions_bias_may_7_2024/
+/oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/chrombpnet/folds/ATAC/HEPG2/HEPG2_05.22.2022_bias_128_4_1234_0.8_fold_4/bias_model/newgen/
+python /mnt/lab_data2/anusri/chrombpnet/src/helpers/hyperparameters/find_bias_hyperparams.py \
+ --genome=/mnt/lab_data2/anusri/chrombpnet/reference/hg38.genome.fa \
+ --bigwig=/mnt/lab_data2/anusri/chrombpnet/results/chrombpnet/ATAC_PE/HEPG2/data/HEPG2_unstranded.bw \
+ --peaks=/mnt/lab_data2/anusri/chrombpnet/results/chrombpnet/ATAC_PE/HEPG2/data/peaks_no_blacklist.bed \
+ --nonpeaks=/mnt/lab_data2/anusri/chrombpnet/results/chrombpnet/ATAC_PE/HEPG2/negatives_data_4/negatives_with_summit.be>
+ --outlier_threshold=0.99 \
+ --chr_fold_path=/mnt/lab_data2/anusri/chrombpnet/splits/fold_4.json \
+ --inputlen=2114 \
+ --outputlen=1000 \
+ --max_jitter=0 \
+ --filters=128 \
+ --n_dilation_layers=4 \
+ --bias_threshold_factor=0.8 \
+ --output_dir /oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/chrombpnet/folds/ATAC/HEPG2/HEPG2_05.22.2022_bias_128_4_1234_0.8_fold_4/bias_model/new
+gen/
+evaluating hyperparameters on the following chromosomes ['chr1', 'chr2', 'chr3', 'chr4', 'chr5', 'chr6', 'chr8', 'chr9', 'chr11', 'chr12', 'chr14', 'chr15', 'chr16',
+'chr20', 'chr22', 'chrY', 'chr10', 'chr18']
+Number of non peaks input: 452368
+Number of non peaks filtered because the input/output is on the edge: 0
+Number of non peaks being used: 452368
+Number of non peaks input: 53452
+Number of non peaks filtered because the input/output is on the edge: 0
+Number of non peaks being used: 53452
+Number of peaks input: 226184
+Number of peaks filtered because the input/output is on the edge: 0
+Number of peaks being used: 226184
+Upper bound counts cut-off for bias model training: 181.60000000000002
+Number of nonpeaks after the upper-bount cut-off: 312731
+Number of nonpeaks after applying upper-bound cut-off and removing outliers : 301166
+counts_loss_weight: 9.3
+bash make_missing_bed_regions.sh HEPG2 0.8 4 /oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/chrombpnet/folds/ATAC/HEPG2/HEPG2_05.22.2022_bias_128_4_1234_
+0.8_fold_4/bias_model/newgen/ ATAC_PE
+/oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/chrombpnet/folds/ATAC/HEPG2/HEPG2_05.22.2022_bias_128_4_1234_0.8_fold_4/train_test_regions_bias_may_7_2024
+/
+python get_train_test_regions_bias.py -inp /oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/chrombpnet/folds/ATAC/HEPG2/HEPG2_05.22.2022_bias_128_4_1234_0
+.8_fold_4/bias_model/newgen/filtered.bias_nonpeaks.bed -f /mnt/lab_data2/anusri/chrombpnet/splits/fold_4.json -o /oak/stanford/groups/akundaje/projects/chromatin-atla
+s-2022/chrombpnet/folds/ATAC/HEPG2/HEPG2_05.22.2022_bias_128_4_1234_0.8_fold_4/train_test_regions_bias_may_7_2024/
+/mnt/lab_data2/anusri/chrombpnet/results/chrombpnet/ATAC_PE/IMR90/nautilus_runs_apr12/IMR90_04.09.2022_bias_128_4_1234_0.4_fold_0/train_test_regions_bias_may_7_2024/
+/oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/chrombpnet/folds/ATAC/IMR90/IMR90_07.17.2022_bias_128_4_1234_0.3_fold_1_data_type_ATAC_PE/bias_model/newge
+n/
+python /mnt/lab_data2/anusri/chrombpnet/src/helpers/hyperparameters/find_bias_hyperparams.py \
+ --genome=/mnt/lab_data2/anusri/chrombpnet/reference/hg38.genome.fa \
+ --bigwig=/mnt/lab_data2/anusri/chrombpnet/results/chrombpnet/ATAC_PE/IMR90/data/IMR90_unstranded.bw \
+ --peaks=/mnt/lab_data2/anusri/chrombpnet/results/chrombpnet/ATAC_PE/IMR90/data/peaks_no_blacklist.bed \
+ --nonpeaks=/mnt/lab_data2/anusri/chrombpnet/results/chrombpnet/ATAC_PE/IMR90/negatives_data_1/negatives_with_summit.be>
+ --outlier_threshold=0.99 \
+ --chr_fold_path=/mnt/lab_data2/anusri/chrombpnet/splits/fold_1.json \
+ --inputlen=2114 \
+ --outputlen=1000 \
+ --max_jitter=0 \
+ --filters=128 \
+ --n_dilation_layers=4 \
+ --bias_threshold_factor=0.3 \
+ --output_dir /oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/chrombpnet/folds/ATAC/IMR90/IMR90_07.17.2022_bias_128_4_1234_0.3_fold_1_data_type_ATAC
+_PE/bias_model/newgen/
+evaluating hyperparameters on the following chromosomes ['chr1', 'chr3', 'chr4', 'chr5', 'chr6', 'chr7', 'chr10', 'chr11', 'chr13', 'chr14', 'chr15', 'chr18', 'chr19'
+, 'chr20', 'chr21', 'chr22', 'chrX', 'chrY', 'chr12', 'chr17']
+Number of non peaks input: 421900
+Number of non peaks filtered because the input/output is on the edge: 0
+Number of non peaks being used: 421900
+Number of non peaks input: 54195
+Number of non peaks filtered because the input/output is on the edge: 0
+Number of non peaks being used: 54195
+Number of peaks input: 210950
+Number of peaks filtered because the input/output is on the edge: 0
+Number of peaks being used: 210950
+Upper bound counts cut-off for bias model training: 15.299999999999999
+Number of nonpeaks after the upper-bount cut-off: 245967
+Number of nonpeaks after applying upper-bound cut-off and removing outliers : 210817
+counts_loss_weight: 0.8
+bash make_missing_bed_regions.sh IMR90 0.3 1 /oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/chrombpnet/folds/ATAC/IMR90/IMR90_07.17.2022_bias_128_4_1234_
+0.3_fold_1_data_type_ATAC_PE/bias_model/newgen/ ATAC_PE
+/oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/chrombpnet/folds/ATAC/IMR90/IMR90_07.17.2022_bias_128_4_1234_0.3_fold_1_data_type_ATAC_PE/train_test_regio
+ns_bias_may_7_2024/
+python get_train_test_regions_bias.py -inp /oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/chrombpnet/folds/ATAC/IMR90/IMR90_07.17.2022_bias_128_4_1234_0
+.3_fold_1_data_type_ATAC_PE/bias_model/newgen/filtered.bias_nonpeaks.bed -f /mnt/lab_data2/anusri/chrombpnet/splits/fold_1.json -o /oak/stanford/groups/akundaje/proje
+cts/chromatin-atlas-2022/chrombpnet/folds/ATAC/IMR90/IMR90_07.17.2022_bias_128_4_1234_0.3_fold_1_data_type_ATAC_PE/train_test_regions_bias_may_7_2024/
+/oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/chrombpnet/folds/ATAC/IMR90/IMR90_07.17.2022_bias_128_4_1234_0.3_fold_2_data_type_ATAC_PE/bias_model/newge
+n/
+python /mnt/lab_data2/anusri/chrombpnet/src/helpers/hyperparameters/find_bias_hyperparams.py \
+ --genome=/mnt/lab_data2/anusri/chrombpnet/reference/hg38.genome.fa \
+ --bigwig=/mnt/lab_data2/anusri/chrombpnet/results/chrombpnet/ATAC_PE/IMR90/data/IMR90_unstranded.bw \
+ --peaks=/mnt/lab_data2/anusri/chrombpnet/results/chrombpnet/ATAC_PE/IMR90/data/peaks_no_blacklist.bed \
+ --nonpeaks=/mnt/lab_data2/anusri/chrombpnet/results/chrombpnet/ATAC_PE/IMR90/negatives_data_2/negatives_with_summit.be>
+ --outlier_threshold=0.99 \
+ --chr_fold_path=/mnt/lab_data2/anusri/chrombpnet/splits/fold_2.json \
+ --inputlen=2114 \
+ --outputlen=1000 \
+ --max_jitter=0 \
+ --filters=128 \
+ --n_dilation_layers=4 \
+ --bias_threshold_factor=0.3 \
+ --output_dir /oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/chrombpnet/folds/ATAC/IMR90/IMR90_07.17.2022_bias_128_4_1234_0.3_fold_2_data_type_ATAC
+_PE/bias_model/newgen/
+evaluating hyperparameters on the following chromosomes ['chr1', 'chr2', 'chr3', 'chr5', 'chr6', 'chr8', 'chr9', 'chr10', 'chr13', 'chr14', 'chr16', 'chr17', 'chr18',
+ 'chr19', 'chr20', 'chr21', 'chrX', 'chr22', 'chr7']
+Number of non peaks input: 431806
+Number of non peaks filtered because the input/output is on the edge: 0
+Number of non peaks being used: 431806
+Number of non peaks input: 49242
+Number of non peaks filtered because the input/output is on the edge: 0
+Number of non peaks being used: 49242
+Number of peaks input: 215903
+Number of peaks filtered because the input/output is on the edge: 0
+Number of peaks being used: 215903
+Upper bound counts cut-off for bias model training: 15.299999999999999
+Number of nonpeaks after the upper-bount cut-off: 249002
+Number of nonpeaks after applying upper-bound cut-off and removing outliers : 215886
+counts_loss_weight: 0.8
+bash make_missing_bed_regions.sh IMR90 0.3 2 /oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/chrombpnet/folds/ATAC/IMR90/IMR90_07.17.2022_bias_128_4_1234_
+0.3_fold_2_data_type_ATAC_PE/bias_model/newgen/ ATAC_PE
+/oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/chrombpnet/folds/ATAC/IMR90/IMR90_07.17.2022_bias_128_4_1234_0.3_fold_2_data_type_ATAC_PE/train_test_regio
+ns_bias_may_7_2024/
+python get_train_test_regions_bias.py -inp /oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/chrombpnet/folds/ATAC/IMR90/IMR90_07.17.2022_bias_128_4_1234_0
+.3_fold_2_data_type_ATAC_PE/bias_model/newgen/filtered.bias_nonpeaks.bed -f /mnt/lab_data2/anusri/chrombpnet/splits/fold_2.json -o /oak/stanford/groups/akundaje/proje
+cts/chromatin-atlas-2022/chrombpnet/folds/ATAC/IMR90/IMR90_07.17.2022_bias_128_4_1234_0.3_fold_2_data_type_ATAC_PE/train_test_regions_bias_may_7_2024/
+/oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/chrombpnet/folds/ATAC/IMR90/IMR90_07.08.2022_bias_128_4_1234_0.4_fold_3_data_type_ATAC_PE/bias_model/newge
+n/
+python /mnt/lab_data2/anusri/chrombpnet/src/helpers/hyperparameters/find_bias_hyperparams.py \
+ --genome=/mnt/lab_data2/anusri/chrombpnet/reference/hg38.genome.fa \
+ --bigwig=/mnt/lab_data2/anusri/chrombpnet/results/chrombpnet/ATAC_PE/IMR90/data/IMR90_unstranded.bw \
+ --peaks=/mnt/lab_data2/anusri/chrombpnet/results/chrombpnet/ATAC_PE/IMR90/data/peaks_no_blacklist.bed \
+ --nonpeaks=/mnt/lab_data2/anusri/chrombpnet/results/chrombpnet/ATAC_PE/IMR90/negatives_data_3/negatives_with_summit.be>
+ --outlier_threshold=0.99 \
+ --chr_fold_path=/mnt/lab_data2/anusri/chrombpnet/splits/fold_3.json \
+ --inputlen=2114 \
+ --outputlen=1000 \
+ --max_jitter=0 \
+ --filters=128 \
+ --n_dilation_layers=4 \
+ --bias_threshold_factor=0.4 \
+ --output_dir /oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/chrombpnet/folds/ATAC/IMR90/IMR90_07.08.2022_bias_128_4_1234_0.4_fold_3_data_type_ATAC
+_PE/bias_model/newgen/
+evaluating hyperparameters on the following chromosomes ['chr1', 'chr2', 'chr3', 'chr4', 'chr7', 'chr8', 'chr9', 'chr11', 'chr12', 'chr13', 'chr15', 'chr16', 'chr17',
+ 'chr19', 'chrX', 'chrY', 'chr6', 'chr21']
+Number of non peaks input: 423416
+Number of non peaks filtered because the input/output is on the edge: 0
+Number of non peaks being used: 423416
+Number of non peaks input: 53437
+Number of non peaks filtered because the input/output is on the edge: 0
+Number of non peaks being used: 53437
+Number of peaks input: 211708
+Number of peaks filtered because the input/output is on the edge: 0
+Number of peaks being used: 211708
+Upper bound counts cut-off for bias model training: 20.400000000000002
+Number of nonpeaks after the upper-bount cut-off: 302560
+Number of nonpeaks after applying upper-bound cut-off and removing outliers : 270679
+counts_loss_weight: 1.0
+bash make_missing_bed_regions.sh IMR90 0.4 3 /oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/chrombpnet/folds/ATAC/IMR90/IMR90_07.08.2022_bias_128_4_1234_
+0.4_fold_3_data_type_ATAC_PE/bias_model/newgen/ ATAC_PE
+/oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/chrombpnet/folds/ATAC/IMR90/IMR90_07.08.2022_bias_128_4_1234_0.4_fold_3_data_type_ATAC_PE/train_test_regio
+ns_bias_may_7_2024/
+python get_train_test_regions_bias.py -inp /oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/chrombpnet/folds/ATAC/IMR90/IMR90_07.08.2022_bias_128_4_1234_0
+.4_fold_3_data_type_ATAC_PE/bias_model/newgen/filtered.bias_nonpeaks.bed -f /mnt/lab_data2/anusri/chrombpnet/splits/fold_3.json -o /oak/stanford/groups/akundaje/proje
+cts/chromatin-atlas-2022/chrombpnet/folds/ATAC/IMR90/IMR90_07.08.2022_bias_128_4_1234_0.4_fold_3_data_type_ATAC_PE/train_test_regions_bias_may_7_2024/
+/oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/chrombpnet/folds/ATAC/IMR90/IMR90_07.07.2022_bias_128_4_1234_0.4_fold_4_data_type_ATAC_PE/bias_model/newge
+n/
+python /mnt/lab_data2/anusri/chrombpnet/src/helpers/hyperparameters/find_bias_hyperparams.py \
+ --genome=/mnt/lab_data2/anusri/chrombpnet/reference/hg38.genome.fa \
+ --bigwig=/mnt/lab_data2/anusri/chrombpnet/results/chrombpnet/ATAC_PE/IMR90/data/IMR90_unstranded.bw \
+ --peaks=/mnt/lab_data2/anusri/chrombpnet/results/chrombpnet/ATAC_PE/IMR90/data/peaks_no_blacklist.bed \
+ --nonpeaks=/mnt/lab_data2/anusri/chrombpnet/results/chrombpnet/ATAC_PE/IMR90/negatives_data_4/negatives_with_summit.be>
+ --outlier_threshold=0.99 \
+ --chr_fold_path=/mnt/lab_data2/anusri/chrombpnet/splits/fold_4.json \
+ --inputlen=2114 \
+ --outputlen=1000 \
+ --max_jitter=0 \
+ --filters=128 \
+ --n_dilation_layers=4 \
+ --bias_threshold_factor=0.4 \
+ --output_dir /oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/chrombpnet/folds/ATAC/IMR90/IMR90_07.07.2022_bias_128_4_1234_0.4_fold_4_data_type_ATAC
+_PE/bias_model/newgen/
+evaluating hyperparameters on the following chromosomes ['chr1', 'chr2', 'chr3', 'chr4', 'chr5', 'chr6', 'chr8', 'chr9', 'chr11', 'chr12', 'chr14', 'chr15', 'chr16',
+'chr20', 'chr22', 'chrY', 'chr10', 'chr18']
+Number of non peaks input: 431762
+Number of non peaks filtered because the input/output is on the edge: 0
+Number of non peaks being used: 431762
+Number of non peaks input: 49264
+Number of non peaks filtered because the input/output is on the edge: 0
+Number of non peaks being used: 49264
+Number of peaks input: 215881
+Number of peaks filtered because the input/output is on the edge: 0
+Number of peaks being used: 215881
+Upper bound counts cut-off for bias model training: 20.400000000000002
+Number of nonpeaks after the upper-bount cut-off: 310100
+Number of nonpeaks after applying upper-bound cut-off and removing outliers : 277437
+counts_loss_weight: 1.0
+bash make_missing_bed_regions.sh IMR90 0.4 4 /oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/chrombpnet/folds/ATAC/IMR90/IMR90_07.07.2022_bias_128_4_1234_
+0.4_fold_4_data_type_ATAC_PE/bias_model/newgen/ ATAC_PE
+/oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/chrombpnet/folds/ATAC/IMR90/IMR90_07.07.2022_bias_128_4_1234_0.4_fold_4_data_type_ATAC_PE/train_test_regio
+ns_bias_may_7_2024/
+python get_train_test_regions_bias.py -inp /oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/chrombpnet/folds/ATAC/IMR90/IMR90_07.07.2022_bias_128_4_1234_0
+.4_fold_4_data_type_ATAC_PE/bias_model/newgen/filtered.bias_nonpeaks.bed -f /mnt/lab_data2/anusri/chrombpnet/splits/fold_4.json -o /oak/stanford/groups/akundaje/proje
+cts/chromatin-atlas-2022/chrombpnet/folds/ATAC/IMR90/IMR90_07.07.2022_bias_128_4_1234_0.4_fold_4_data_type_ATAC_PE/train_test_regions_bias_may_7_2024/
+/mnt/lab_data2/anusri/chrombpnet/results/chrombpnet/ATAC_PE/H1ESC/nautilus_runs_jun16/H1ESC_05.09.2022_bias_128_4_1234_0.8_fold_0/train_test_regions_bias_may_7_2024/
+/oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/chrombpnet/folds/ATAC/H1ESC/H1ESC_07.23.2022_bias_128_4_1234_0.7_fold_1_data_type_ATAC_PE/bias_model/newge
+n/
+python /mnt/lab_data2/anusri/chrombpnet/src/helpers/hyperparameters/find_bias_hyperparams.py \
+ --genome=/mnt/lab_data2/anusri/chrombpnet/reference/hg38.genome.fa \
+ --bigwig=/mnt/lab_data2/anusri/chrombpnet/results/chrombpnet/ATAC_PE/H1ESC/data/H1ESC_unstranded.bw \
+ --peaks=/mnt/lab_data2/anusri/chrombpnet/results/chrombpnet/ATAC_PE/H1ESC/data/peaks_no_blacklist.bed \
+ --nonpeaks=/mnt/lab_data2/anusri/chrombpnet/results/chrombpnet/ATAC_PE/H1ESC/negatives_data_1/negatives_with_summit.be>
+ --outlier_threshold=0.99 \
+ --chr_fold_path=/mnt/lab_data2/anusri/chrombpnet/splits/fold_1.json \
+ --inputlen=2114 \
+ --outputlen=1000 \
+ --max_jitter=0 \
+ --filters=128 \
+ --n_dilation_layers=4 \
+ --bias_threshold_factor=0.7 \
+ --output_dir /oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/chrombpnet/folds/ATAC/H1ESC/H1ESC_07.23.2022_bias_128_4_1234_0.7_fold_1_data_type_ATAC
+_PE/bias_model/newgen/
+evaluating hyperparameters on the following chromosomes ['chr1', 'chr3', 'chr4', 'chr5', 'chr6', 'chr7', 'chr10', 'chr11', 'chr13', 'chr14', 'chr15', 'chr18', 'chr19'
+, 'chr20', 'chr21', 'chr22', 'chrX', 'chrY', 'chr12', 'chr17']
+Number of non peaks input: 374898
+Number of non peaks filtered because the input/output is on the edge: 0
+Number of non peaks being used: 374898
+Number of non peaks input: 49122
+Number of non peaks filtered because the input/output is on the edge: 0
+Number of non peaks being used: 49122
+Number of peaks input: 187449
+Number of peaks filtered because the input/output is on the edge: 0
+Number of peaks being used: 187449
+Upper bound counts cut-off for bias model training: 51.8
+Number of nonpeaks after the upper-bount cut-off: 263750
+Number of nonpeaks after applying upper-bound cut-off and removing outliers : 249443
+counts_loss_weight: 3.2
+bash make_missing_bed_regions.sh H1ESC 0.7 1 /oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/chrombpnet/folds/ATAC/H1ESC/H1ESC_07.23.2022_bias_128_4_1234_
+0.7_fold_1_data_type_ATAC_PE/bias_model/newgen/ ATAC_PE
+/oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/chrombpnet/folds/ATAC/H1ESC/H1ESC_07.23.2022_bias_128_4_1234_0.7_fold_1_data_type_ATAC_PE/train_test_regio
+ns_bias_may_7_2024/
+python get_train_test_regions_bias.py -inp /oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/chrombpnet/folds/ATAC/H1ESC/H1ESC_07.23.2022_bias_128_4_1234_0
+.7_fold_1_data_type_ATAC_PE/bias_model/newgen/filtered.bias_nonpeaks.bed -f /mnt/lab_data2/anusri/chrombpnet/splits/fold_1.json -o /oak/stanford/groups/akundaje/proje
+cts/chromatin-atlas-2022/chrombpnet/folds/ATAC/H1ESC/H1ESC_07.23.2022_bias_128_4_1234_0.7_fold_1_data_type_ATAC_PE/train_test_regions_bias_may_7_2024/
+/oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/chrombpnet/folds/ATAC/H1ESC/H1ESC_07.17.2022_bias_128_4_1234_0.8_fold_2_data_type_ATAC_PE/bias_model/newge
+n/
+python /mnt/lab_data2/anusri/chrombpnet/src/helpers/hyperparameters/find_bias_hyperparams.py \
+ --genome=/mnt/lab_data2/anusri/chrombpnet/reference/hg38.genome.fa \
+ --bigwig=/mnt/lab_data2/anusri/chrombpnet/results/chrombpnet/ATAC_PE/H1ESC/data/H1ESC_unstranded.bw \
+ --peaks=/mnt/lab_data2/anusri/chrombpnet/results/chrombpnet/ATAC_PE/H1ESC/data/peaks_no_blacklist.bed \
+ --nonpeaks=/mnt/lab_data2/anusri/chrombpnet/results/chrombpnet/ATAC_PE/H1ESC/negatives_data_2/negatives_with_summit.be>
+ --outlier_threshold=0.99 \
+ --chr_fold_path=/mnt/lab_data2/anusri/chrombpnet/splits/fold_2.json \
+ --inputlen=2114 \
+ --outputlen=1000 \
+ --max_jitter=0 \
+ --filters=128 \
+ --n_dilation_layers=4 \
+ --bias_threshold_factor=0.8 \
+ --output_dir /oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/chrombpnet/folds/ATAC/H1ESC/H1ESC_07.17.2022_bias_128_4_1234_0.8_fold_2_data_type_ATAC
+_PE/bias_model/newgen/
+evaluating hyperparameters on the following chromosomes ['chr1', 'chr2', 'chr3', 'chr5', 'chr6', 'chr8', 'chr9', 'chr10', 'chr13', 'chr14', 'chr16', 'chr17', 'chr18',
+ 'chr19', 'chr20', 'chr21', 'chrX', 'chr22', 'chr7']
+Number of non peaks input: 383216
+Number of non peaks filtered because the input/output is on the edge: 0
+Number of non peaks being used: 383216
+Number of non peaks input: 44963
+Number of non peaks filtered because the input/output is on the edge: 0
+Number of non peaks being used: 44963
+Number of peaks input: 191608
+Number of peaks filtered because the input/output is on the edge: 0
+Number of peaks being used: 191608
+Upper bound counts cut-off for bias model training: 59.2
+Number of nonpeaks after the upper-bount cut-off: 305890
+Number of nonpeaks after applying upper-bound cut-off and removing outliers : 292161
+counts_loss_weight: 3.5
+bash make_missing_bed_regions.sh H1ESC 0.8 2 /oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/chrombpnet/folds/ATAC/H1ESC/H1ESC_07.17.2022_bias_128_4_1234_
+0.8_fold_2_data_type_ATAC_PE/bias_model/newgen/ ATAC_PE
+/oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/chrombpnet/folds/ATAC/H1ESC/H1ESC_07.17.2022_bias_128_4_1234_0.8_fold_2_data_type_ATAC_PE/train_test_regio
+ns_bias_may_7_2024/
+python get_train_test_regions_bias.py -inp /oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/chrombpnet/folds/ATAC/H1ESC/H1ESC_07.17.2022_bias_128_4_1234_0
+.8_fold_2_data_type_ATAC_PE/bias_model/newgen/filtered.bias_nonpeaks.bed -f /mnt/lab_data2/anusri/chrombpnet/splits/fold_2.json -o /oak/stanford/groups/akundaje/proje
+cts/chromatin-atlas-2022/chrombpnet/folds/ATAC/H1ESC/H1ESC_07.17.2022_bias_128_4_1234_0.8_fold_2_data_type_ATAC_PE/train_test_regions_bias_may_7_2024/
+/oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/chrombpnet/folds/ATAC/H1ESC/H1ESC_07.17.2022_bias_128_4_1234_0.8_fold_3_data_type_ATAC_PE/bias_model/newge
+n/
+python /mnt/lab_data2/anusri/chrombpnet/src/helpers/hyperparameters/find_bias_hyperparams.py \
+ --genome=/mnt/lab_data2/anusri/chrombpnet/reference/hg38.genome.fa \
+ --bigwig=/mnt/lab_data2/anusri/chrombpnet/results/chrombpnet/ATAC_PE/H1ESC/data/H1ESC_unstranded.bw \
+ --peaks=/mnt/lab_data2/anusri/chrombpnet/results/chrombpnet/ATAC_PE/H1ESC/data/peaks_no_blacklist.bed \
+ --nonpeaks=/mnt/lab_data2/anusri/chrombpnet/results/chrombpnet/ATAC_PE/H1ESC/negatives_data_3/negatives_with_summit.be>
+ --outlier_threshold=0.99 \
+ --chr_fold_path=/mnt/lab_data2/anusri/chrombpnet/splits/fold_3.json \
+ --inputlen=2114 \
+ --outputlen=1000 \
+ --max_jitter=0 \
+ --filters=128 \
+ --n_dilation_layers=4 \
+ --bias_threshold_factor=0.8 \
+ --output_dir /oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/chrombpnet/folds/ATAC/H1ESC/H1ESC_07.17.2022_bias_128_4_1234_0.8_fold_3_data_type_ATAC
+_PE/bias_model/newgen/
+evaluating hyperparameters on the following chromosomes ['chr1', 'chr2', 'chr3', 'chr4', 'chr7', 'chr8', 'chr9', 'chr11', 'chr12', 'chr13', 'chr15', 'chr16', 'chr17',
+ 'chr19', 'chrX', 'chrY', 'chr6', 'chr21']
+Number of non peaks input: 380640
+Number of non peaks filtered because the input/output is on the edge: 0
+Number of non peaks being used: 380640
+Number of non peaks input: 46251
+Number of non peaks filtered because the input/output is on the edge: 0
+Number of non peaks being used: 46251
+Number of peaks input: 190320
+Number of peaks filtered because the input/output is on the edge: 0
+Number of peaks being used: 190320
+Upper bound counts cut-off for bias model training: 59.2
+Number of nonpeaks after the upper-bount cut-off: 304110
+Number of nonpeaks after applying upper-bound cut-off and removing outliers : 290114
+counts_loss_weight: 3.5
+bash make_missing_bed_regions.sh H1ESC 0.8 3 /oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/chrombpnet/folds/ATAC/H1ESC/H1ESC_07.17.2022_bias_128_4_1234_
+0.8_fold_3_data_type_ATAC_PE/bias_model/newgen/ ATAC_PE
+/oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/chrombpnet/folds/ATAC/H1ESC/H1ESC_07.17.2022_bias_128_4_1234_0.8_fold_3_data_type_ATAC_PE/train_test_regio
+ns_bias_may_7_2024/
+python get_train_test_regions_bias.py -inp /oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/chrombpnet/folds/ATAC/H1ESC/H1ESC_07.17.2022_bias_128_4_1234_0
+.8_fold_3_data_type_ATAC_PE/bias_model/newgen/filtered.bias_nonpeaks.bed -f /mnt/lab_data2/anusri/chrombpnet/splits/fold_3.json -o /oak/stanford/groups/akundaje/proje
+cts/chromatin-atlas-2022/chrombpnet/folds/ATAC/H1ESC/H1ESC_07.17.2022_bias_128_4_1234_0.8_fold_3_data_type_ATAC_PE/train_test_regions_bias_may_7_2024/
+/oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/chrombpnet/folds/ATAC/H1ESC/H1ESC_07.17.2022_bias_128_4_1234_0.8_fold_4_data_type_ATAC_PE/train_test_regio
+ns_bias_may_7_2024/
+(chrombpnet) anusri@brahma:/mnt/lab_data2/anusri/chrombpnet/upload_jsons/upload_scripts$
diff --git a/logs/checkpoint/JAN_02_2023/screenlog/output_zenodo_upload.log b/logs/checkpoint/JAN_02_2023/screenlog/output_zenodo_upload.log
new file mode 100644
index 00000000..a4f1f6d0
--- /dev/null
+++ b/logs/checkpoint/JAN_02_2023/screenlog/output_zenodo_upload.log
@@ -0,0 +1,364 @@
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+(base) anusri@brahma:/oak/stanford/groups/akundaje/anusri/chrombpnet_zenodo_uploads_reformatted$ ls
+AFGR_ChromBPNet GM12878_ATAC_Subsampled_ChromBPNet scripts zips_upload
+Bias_correction_baselines GM12878_bias_transfer_models script_zip.sh
+compress_deepshap.py H1ESC_ATAC_ChromBPNet SMC_scATAC_ChromBPNet
+fix_h5_for_chrombpnet.py Microglia_scATAC_ChromBPNet Variant_effect_prediction_benchmarking
+(base) anusri@brahma:/oak/stanford/groups/akundaje/anusri/chrombpnet_zenodo_uploads_reformatted$ bash script_zip.sh
+updating: Microglia_scATAC_ChromBPNet/ (stored 0%)
+updating: Microglia_scATAC_ChromBPNet/models/ (stored 0%)
+updating: Microglia_scATAC_ChromBPNet/models/fold_0/ (stored 0%)
+updating: Microglia_scATAC_ChromBPNet/models/fold_0/chrombpnet.tar (deflated 11%)
+updating: Microglia_scATAC_ChromBPNet/models/fold_0/bias_model_scaled.tar (deflated 30%)
+updating: Microglia_scATAC_ChromBPNet/models/fold_0/chrombpnet.h5 (deflated 12%)
+updating: Microglia_scATAC_ChromBPNet/models/fold_0/bias_model_scaled.h5 (deflated 26%)
+updating: Microglia_scATAC_ChromBPNet/models/fold_0/chrombpnet_nobias.h5 (deflated 7%)
+updating: Microglia_scATAC_ChromBPNet/models/fold_0/chrombpnet_nobias.tar (deflated 9%)
+updating: Microglia_scATAC_ChromBPNet/models/fold_1/ (stored 0%)
+updating: Microglia_scATAC_ChromBPNet/models/fold_1/chrombpnet.tar (deflated 11%)
+updating: Microglia_scATAC_ChromBPNet/models/fold_1/bias_model_scaled.tar (deflated 30%)
+updating: Microglia_scATAC_ChromBPNet/models/fold_1/chrombpnet.h5 (deflated 13%)
+updating: Microglia_scATAC_ChromBPNet/models/fold_1/bias_model_scaled.h5 (deflated 25%)
+updating: Microglia_scATAC_ChromBPNet/models/fold_1/chrombpnet_nobias.h5 (deflated 7%)
+updating: Microglia_scATAC_ChromBPNet/models/fold_1/chrombpnet_nobias.tar (deflated 9%)
+updating: Microglia_scATAC_ChromBPNet/models/fold_3/ (stored 0%)
+updating: Microglia_scATAC_ChromBPNet/models/fold_3/chrombpnet.tar (deflated 11%)
+updating: Microglia_scATAC_ChromBPNet/models/fold_3/bias_model_scaled.tar (deflated 30%)
+updating: Microglia_scATAC_ChromBPNet/models/fold_3/chrombpnet.h5 (deflated 12%)
+updating: Microglia_scATAC_ChromBPNet/models/fold_3/bias_model_scaled.h5 (deflated 25%)
+updating: Microglia_scATAC_ChromBPNet/models/fold_3/chrombpnet_nobias.h5 (deflated 7%)
+updating: Microglia_scATAC_ChromBPNet/models/fold_3/chrombpnet_nobias.tar (deflated 9%)
+updating: Microglia_scATAC_ChromBPNet/models/fold_4/ (stored 0%)
+updating: Microglia_scATAC_ChromBPNet/models/fold_4/chrombpnet.tar (deflated 11%)
+updating: Microglia_scATAC_ChromBPNet/models/fold_4/bias_model_scaled.tar (deflated 30%)
+updating: Microglia_scATAC_ChromBPNet/models/fold_4/chrombpnet.h5 (deflated 12%)
+updating: Microglia_scATAC_ChromBPNet/models/fold_4/bias_model_scaled.h5 (deflated 25%)
+updating: Microglia_scATAC_ChromBPNet/models/fold_4/chrombpnet_nobias.h5 (deflated 7%)
+updating: Microglia_scATAC_ChromBPNet/models/fold_4/chrombpnet_nobias.tar (deflated 9%)
+updating: Microglia_scATAC_ChromBPNet/models/fold_2/ (stored 0%)
+updating: Microglia_scATAC_ChromBPNet/models/fold_2/chrombpnet.tar (deflated 11%)
+updating: Microglia_scATAC_ChromBPNet/models/fold_2/bias_model_scaled.tar (deflated 30%)
+updating: Microglia_scATAC_ChromBPNet/models/fold_2/chrombpnet.h5 (deflated 11%)
+updating: Microglia_scATAC_ChromBPNet/models/fold_2/bias_model_scaled.h5 (deflated 27%)
+updating: Microglia_scATAC_ChromBPNet/models/fold_2/chrombpnet_nobias.h5 (deflated 7%)
+updating: Microglia_scATAC_ChromBPNet/models/fold_2/chrombpnet_nobias.tar (deflated 9%)
+updating: Microglia_scATAC_ChromBPNet/evaluation/ (stored 0%)
+updating: Microglia_scATAC_ChromBPNet/evaluation/fold_0/ (stored 0%)
+updating: Microglia_scATAC_ChromBPNet/evaluation/fold_0/footprints/ (stored 0%)
+updating: Microglia_scATAC_ChromBPNet/evaluation/fold_0/footprints/corrected_footprints_score.txt (deflated 53%)
+updating: Microglia_scATAC_ChromBPNet/evaluation/fold_0/footprints/corrected_footprints.h5 (deflated 63%)
+updating: Microglia_scATAC_ChromBPNet/evaluation/fold_1/ (stored 0%)
+updating: Microglia_scATAC_ChromBPNet/evaluation/fold_1/footprints/ (stored 0%)
+updating: Microglia_scATAC_ChromBPNet/evaluation/fold_1/footprints/corrected_footprints_score.txt (deflated 53%)
+updating: Microglia_scATAC_ChromBPNet/evaluation/fold_1/footprints/corrected_footprints.h5 (deflated 63%)
+updating: Microglia_scATAC_ChromBPNet/evaluation/fold_3/ (stored 0%)
+updating: Microglia_scATAC_ChromBPNet/evaluation/fold_3/footprints/ (stored 0%)
+updating: Microglia_scATAC_ChromBPNet/evaluation/fold_3/footprints/corrected_footprints_score.txt (deflated 53%)
+updating: Microglia_scATAC_ChromBPNet/evaluation/fold_3/footprints/corrected_footprints.h5 (deflated 63%)
+updating: Microglia_scATAC_ChromBPNet/evaluation/fold_4/ (stored 0%)
+updating: Microglia_scATAC_ChromBPNet/evaluation/fold_4/footprints/ (stored 0%)
+updating: Microglia_scATAC_ChromBPNet/evaluation/fold_4/footprints/corrected_footprints_score.txt (deflated 53%)
+updating: Microglia_scATAC_ChromBPNet/evaluation/fold_4/footprints/corrected_footprints.h5 (deflated 63%)
+updating: Microglia_scATAC_ChromBPNet/evaluation/fold_2/ (stored 0%)
+updating: Microglia_scATAC_ChromBPNet/evaluation/fold_2/footprints/ (stored 0%)
+updating: Microglia_scATAC_ChromBPNet/evaluation/fold_2/footprints/corrected_footprints_score.txt (deflated 53%)
+updating: Microglia_scATAC_ChromBPNet/evaluation/fold_2/footprints/corrected_footprints.h5 (deflated 63%)
+updating: Microglia_scATAC_ChromBPNet/data/ (stored 0%)
+updating: Microglia_scATAC_ChromBPNet/data/fold_0/ (stored 0%)
+updating: Microglia_scATAC_ChromBPNet/data/fold_0/nonpeaks.validationset.bed.gz (deflated 0%)
+updating: Microglia_scATAC_ChromBPNet/data/fold_0/peaks.validationset.bed.gz (deflated 0%)
+updating: Microglia_scATAC_ChromBPNet/data/fold_0/peaks.trainingset.bed.gz (deflated 0%)
+updating: Microglia_scATAC_ChromBPNet/data/fold_0/nonpeaks.trainingset.bed.gz (deflated 0%)
+updating: Microglia_scATAC_ChromBPNet/data/fold_0/peaks.testset.bed.gz (deflated 0%)
+updating: Microglia_scATAC_ChromBPNet/data/fold_1/ (stored 0%)
+updating: Microglia_scATAC_ChromBPNet/data/fold_1/nonpeaks.validationset.bed.gz (deflated 0%)
+updating: Microglia_scATAC_ChromBPNet/data/fold_1/peaks.validationset.bed.gz (deflated 0%)
+updating: Microglia_scATAC_ChromBPNet/data/fold_1/peaks.trainingset.bed.gz (deflated 0%)
+updating: Microglia_scATAC_ChromBPNet/data/fold_1/nonpeaks.trainingset.bed.gz (deflated 0%)
+updating: Microglia_scATAC_ChromBPNet/data/fold_1/peaks.testset.bed.gz (deflated 0%)
+updating: Microglia_scATAC_ChromBPNet/data/fold_3/ (stored 0%)
+updating: Microglia_scATAC_ChromBPNet/data/fold_3/nonpeaks.validationset.bed.gz (deflated 0%)
+updating: Microglia_scATAC_ChromBPNet/data/fold_3/peaks.validationset.bed.gz (deflated 0%)
+updating: Microglia_scATAC_ChromBPNet/data/fold_3/peaks.trainingset.bed.gz (deflated 0%)
+updating: Microglia_scATAC_ChromBPNet/data/fold_3/nonpeaks.trainingset.bed.gz (deflated 0%)
+updating: Microglia_scATAC_ChromBPNet/data/fold_3/peaks.testset.bed.gz (deflated 0%)
+updating: Microglia_scATAC_ChromBPNet/data/fold_4/ (stored 0%)
+updating: Microglia_scATAC_ChromBPNet/data/fold_4/nonpeaks.validationset.bed.gz (deflated 0%)
+updating: Microglia_scATAC_ChromBPNet/data/fold_4/peaks.validationset.bed.gz (deflated 0%)
+updating: Microglia_scATAC_ChromBPNet/data/fold_4/peaks.trainingset.bed.gz (deflated 0%)
+updating: Microglia_scATAC_ChromBPNet/data/fold_4/nonpeaks.trainingset.bed.gz (deflated 0%)
+updating: Microglia_scATAC_ChromBPNet/data/fold_4/peaks.testset.bed.gz (deflated 0%)
+updating: Microglia_scATAC_ChromBPNet/data/fold_2/ (stored 0%)
+updating: Microglia_scATAC_ChromBPNet/data/fold_2/nonpeaks.validationset.bed.gz (deflated 0%)
+updating: Microglia_scATAC_ChromBPNet/data/fold_2/peaks.validationset.bed.gz (deflated 0%)
+updating: Microglia_scATAC_ChromBPNet/data/fold_2/peaks.trainingset.bed.gz (deflated 0%)
+updating: Microglia_scATAC_ChromBPNet/data/fold_2/nonpeaks.trainingset.bed.gz (deflated 0%)
+updating: Microglia_scATAC_ChromBPNet/data/fold_2/peaks.testset.bed.gz (deflated 0%)
+updating: Microglia_scATAC_ChromBPNet/logs/ (stored 0%)
+updating: Microglia_scATAC_ChromBPNet/logs/fold_0/ (stored 0%)
+updating: Microglia_scATAC_ChromBPNet/logs/fold_0/chrombpnet_data_params.tsv (deflated 25%)
+updating: Microglia_scATAC_ChromBPNet/logs/fold_0/chrombpnet.args.json (deflated 69%)
+updating: Microglia_scATAC_ChromBPNet/logs/fold_0/chrombpnet.log (deflated 50%)
+updating: Microglia_scATAC_ChromBPNet/logs/fold_0/chrombpnet_predictions.h5 (deflated 1%)
+updating: Microglia_scATAC_ChromBPNet/logs/fold_0/chrombpnet_only_peaks.jsd.png (deflated 32%)
+updating: Microglia_scATAC_ChromBPNet/logs/fold_0/chrombpnet.log.batch (deflated 71%)
+updating: Microglia_scATAC_ChromBPNet/logs/fold_0/train_chrombpnet_model.log (deflated 95%)
+updating: Microglia_scATAC_ChromBPNet/logs/fold_0/chrombpnet_metrics.json (deflated 67%)
+updating: Microglia_scATAC_ChromBPNet/logs/fold_0/chrombpnet_only_peaks.png (deflated 4%)
+updating: Microglia_scATAC_ChromBPNet/logs/fold_0/chrombpnet.params.json (deflated 50%)
+updating: Microglia_scATAC_ChromBPNet/logs/fold_0/chrombpnet_model_params.tsv (deflated 45%)
+updating: Microglia_scATAC_ChromBPNet/logs/fold_1/ (stored 0%)
+updating: Microglia_scATAC_ChromBPNet/logs/fold_1/chrombpnet_data_params.tsv (deflated 22%)
+updating: Microglia_scATAC_ChromBPNet/logs/fold_1/chrombpnet.args.json (deflated 69%)
+updating: Microglia_scATAC_ChromBPNet/logs/fold_1/chrombpnet.log (deflated 49%)
+updating: Microglia_scATAC_ChromBPNet/logs/fold_1/chrombpnet_predictions.h5 (deflated 1%)
+updating: Microglia_scATAC_ChromBPNet/logs/fold_1/chrombpnet_only_peaks.jsd.png (deflated 32%)
+updating: Microglia_scATAC_ChromBPNet/logs/fold_1/chrombpnet.log.batch (deflated 71%)
+updating: Microglia_scATAC_ChromBPNet/logs/fold_1/train_chrombpnet_model.log (deflated 95%)
+updating: Microglia_scATAC_ChromBPNet/logs/fold_1/chrombpnet_metrics.json (deflated 67%)
+updating: Microglia_scATAC_ChromBPNet/logs/fold_1/chrombpnet_only_peaks.png (deflated 4%)
+updating: Microglia_scATAC_ChromBPNet/logs/fold_1/chrombpnet.params.json (deflated 50%)
+updating: Microglia_scATAC_ChromBPNet/logs/fold_1/chrombpnet_model_params.tsv (deflated 45%)
+updating: Microglia_scATAC_ChromBPNet/logs/fold_3/ (stored 0%)
+updating: Microglia_scATAC_ChromBPNet/logs/fold_3/chrombpnet_data_params.tsv (deflated 26%)
+updating: Microglia_scATAC_ChromBPNet/logs/fold_3/chrombpnet.args.json (deflated 69%)
+updating: Microglia_scATAC_ChromBPNet/logs/fold_3/chrombpnet.log (deflated 49%)
+updating: Microglia_scATAC_ChromBPNet/logs/fold_3/chrombpnet_predictions.h5 (deflated 1%)
+updating: Microglia_scATAC_ChromBPNet/logs/fold_3/chrombpnet_only_peaks.jsd.png (deflated 32%)
+updating: Microglia_scATAC_ChromBPNet/logs/fold_3/chrombpnet.log.batch (deflated 71%)
+updating: Microglia_scATAC_ChromBPNet/logs/fold_3/train_chrombpnet_model.log (deflated 95%)
+updating: Microglia_scATAC_ChromBPNet/logs/fold_3/chrombpnet_metrics.json (deflated 68%)
+updating: Microglia_scATAC_ChromBPNet/logs/fold_3/chrombpnet_only_peaks.png (deflated 4%)
+updating: Microglia_scATAC_ChromBPNet/logs/fold_3/chrombpnet.params.json (deflated 50%)
+updating: Microglia_scATAC_ChromBPNet/logs/fold_3/chrombpnet_model_params.tsv (deflated 45%)
+updating: Microglia_scATAC_ChromBPNet/logs/fold_4/ (stored 0%)
+updating: Microglia_scATAC_ChromBPNet/logs/fold_4/chrombpnet_data_params.tsv (deflated 25%)
+updating: Microglia_scATAC_ChromBPNet/logs/fold_4/chrombpnet.args.json (deflated 69%)
+updating: Microglia_scATAC_ChromBPNet/logs/fold_4/chrombpnet.log (deflated 50%)
+updating: Microglia_scATAC_ChromBPNet/logs/fold_4/chrombpnet_predictions.h5 (deflated 1%)
+updating: Microglia_scATAC_ChromBPNet/logs/fold_4/chrombpnet_only_peaks.jsd.png (deflated 32%)
+updating: Microglia_scATAC_ChromBPNet/logs/fold_4/chrombpnet.log.batch (deflated 71%)
+updating: Microglia_scATAC_ChromBPNet/logs/fold_4/train_chrombpnet_model.log (deflated 95%)
+updating: Microglia_scATAC_ChromBPNet/logs/fold_4/chrombpnet_metrics.json (deflated 67%)
+updating: Microglia_scATAC_ChromBPNet/logs/fold_4/chrombpnet_only_peaks.png (deflated 3%)
+updating: Microglia_scATAC_ChromBPNet/logs/fold_4/chrombpnet.params.json (deflated 49%)
+updating: Microglia_scATAC_ChromBPNet/logs/fold_4/chrombpnet_model_params.tsv (deflated 46%)
+updating: Microglia_scATAC_ChromBPNet/logs/fold_2/ (stored 0%)
+updating: Microglia_scATAC_ChromBPNet/logs/fold_2/chrombpnet_data_params.tsv (deflated 25%)
+updating: Microglia_scATAC_ChromBPNet/logs/fold_2/chrombpnet.args.json (deflated 69%)
+updating: Microglia_scATAC_ChromBPNet/logs/fold_2/chrombpnet.log (deflated 49%)
+updating: Microglia_scATAC_ChromBPNet/logs/fold_2/chrombpnet_predictions.h5 (deflated 1%)
+updating: Microglia_scATAC_ChromBPNet/logs/fold_2/chrombpnet_only_peaks.jsd.png (deflated 33%)
+updating: Microglia_scATAC_ChromBPNet/logs/fold_2/chrombpnet.log.batch (deflated 71%)
+updating: Microglia_scATAC_ChromBPNet/logs/fold_2/train_chrombpnet_model.log (deflated 95%)
+updating: Microglia_scATAC_ChromBPNet/logs/fold_2/chrombpnet_metrics.json (deflated 67%)
+updating: Microglia_scATAC_ChromBPNet/logs/fold_2/chrombpnet_only_peaks.png (deflated 4%)
+updating: Microglia_scATAC_ChromBPNet/logs/fold_2/chrombpnet.params.json (deflated 50%)
+updating: Microglia_scATAC_ChromBPNet/logs/fold_2/chrombpnet_model_params.tsv (deflated 46%)
+ adding: Microglia_scATAC_ChromBPNet/README.md (deflated 71%)
+ adding: Microglia_scATAC_ChromBPNet/data/cluster24_microglia_pooled_unstranded.bw (deflated 10%)
+ adding: Microglia_scATAC_ChromBPNet/logs/script_sub.sh (deflated 75%)
+ adding: Microglia_scATAC_ChromBPNet/logs/make_bigwigs.sh (deflated 45%)
+ adding: Microglia_scATAC_ChromBPNet/logs/script.sh (deflated 63%)
+updating: GM12878_bias_transfer_models/ (stored 0%)
+updating: GM12878_bias_transfer_models/ATAC/ (stored 0%)
+updating: GM12878_bias_transfer_models/ATAC/NAKED_DNA_bias/ (stored 0%)
+updating: GM12878_bias_transfer_models/ATAC/NAKED_DNA_bias/models/ (stored 0%)
+updating: GM12878_bias_transfer_models/ATAC/NAKED_DNA_bias/models/chrombpnet.tar (deflated 11%)
+updating: GM12878_bias_transfer_models/ATAC/NAKED_DNA_bias/models/bias_model_scaled.tar (deflated 30%)
+updating: GM12878_bias_transfer_models/ATAC/NAKED_DNA_bias/models/chrombpnet.h5 (deflated 12%)
+updating: GM12878_bias_transfer_models/ATAC/NAKED_DNA_bias/models/bias_model_scaled.h5 (deflated 16%)
+updating: GM12878_bias_transfer_models/ATAC/NAKED_DNA_bias/models/chrombpnet_nobias.h5 (deflated 7%)
+updating: GM12878_bias_transfer_models/ATAC/NAKED_DNA_bias/models/chrombpnet_nobias.tar (deflated 9%)
+updating: GM12878_bias_transfer_models/ATAC/NAKED_DNA_bias/evaluation/ (stored 0%)
+updating: GM12878_bias_transfer_models/ATAC/NAKED_DNA_bias/evaluation/interpret/ (stored 0%)
+updating: GM12878_bias_transfer_models/ATAC/NAKED_DNA_bias/evaluation/interpret/GM12878.interpret.args.json (deflated 54%)
+updating: GM12878_bias_transfer_models/ATAC/NAKED_DNA_bias/evaluation/interpret/GM12878.profile_compressed.h5 (deflated 20%)
+updating: GM12878_bias_transfer_models/ATAC/NAKED_DNA_bias/evaluation/interpret/GM12878.counts_compressed.h5 (deflated 16%)
+updating: GM12878_bias_transfer_models/ATAC/NAKED_DNA_bias/evaluation/interpret/interpret.log (deflated 93%)
+updating: GM12878_bias_transfer_models/ATAC/NAKED_DNA_bias/evaluation/interpret/GM12878.interpreted_regions.bed.gz (deflated 0%)
+updating: GM12878_bias_transfer_models/ATAC/NAKED_DNA_bias/evaluation/modisco/ (stored 0%)
+updating: GM12878_bias_transfer_models/ATAC/NAKED_DNA_bias/evaluation/modisco/modiscolite_counts.h5 (deflated 66%)
+updating: GM12878_bias_transfer_models/ATAC/NAKED_DNA_bias/evaluation/modisco/modiscolite_profile.h5 (deflated 67%)
+updating: GM12878_bias_transfer_models/ATAC/NAKED_DNA_bias/evaluation/footprints/ (stored 0%)
+updating: GM12878_bias_transfer_models/ATAC/NAKED_DNA_bias/evaluation/footprints/footprints_score.txt (deflated 44%)
+updating: GM12878_bias_transfer_models/ATAC/NAKED_DNA_bias/evaluation/footprints/motif_footprints.h5 (deflated 59%)
+updating: GM12878_bias_transfer_models/ATAC/NAKED_DNA_bias/evaluation/footprints/footprints.h5 (deflated 61%)
+updating: GM12878_bias_transfer_models/ATAC/NAKED_DNA_bias/data/ (stored 0%)
+updating: GM12878_bias_transfer_models/ATAC/NAKED_DNA_bias/data/nonpeaks.validationset.bed.gz (deflated 0%)
+updating: GM12878_bias_transfer_models/ATAC/NAKED_DNA_bias/data/peaks.validationset.bed.gz (deflated 0%)
+updating: GM12878_bias_transfer_models/ATAC/NAKED_DNA_bias/data/peaks.trainingset.bed.gz (deflated 0%)
+updating: GM12878_bias_transfer_models/ATAC/NAKED_DNA_bias/data/nonpeaks.trainingset.bed.gz (deflated 0%)
+updating: GM12878_bias_transfer_models/ATAC/NAKED_DNA_bias/data/peaks.testset.bed.gz (deflated 0%)
+updating: GM12878_bias_transfer_models/ATAC/NAKED_DNA_bias/logs/ (stored 0%)
+updating: GM12878_bias_transfer_models/ATAC/NAKED_DNA_bias/logs/chrombpnet_data_params.tsv (deflated 23%)
+updating: GM12878_bias_transfer_models/ATAC/NAKED_DNA_bias/logs/chrombpnet.args.json (deflated 66%)
+updating: GM12878_bias_transfer_models/ATAC/NAKED_DNA_bias/logs/chrombpnet.log (deflated 51%)
+updating: GM12878_bias_transfer_models/ATAC/NAKED_DNA_bias/logs/chrombpnet.log.batch (deflated 72%)
+updating: GM12878_bias_transfer_models/ATAC/NAKED_DNA_bias/logs/train_chrombpnet_model.log (deflated 95%)
+updating: GM12878_bias_transfer_models/ATAC/NAKED_DNA_bias/logs/chrombpnet.params.json (deflated 39%)
+updating: GM12878_bias_transfer_models/ATAC/NAKED_DNA_bias/logs/chrombpnet_model_params.tsv (deflated 31%)
+updating: GM12878_bias_transfer_models/ATAC/NAKED_DNA_bias/bias_models/ (stored 0%)
+updating: GM12878_bias_transfer_models/ATAC/NAKED_DNA_bias/bias_models/models/ (stored 0%)
+updating: GM12878_bias_transfer_models/ATAC/NAKED_DNA_bias/bias_models/models/naked_dna_bias.tar (deflated 30%)
+updating: GM12878_bias_transfer_models/ATAC/NAKED_DNA_bias/bias_models/models/naked_dna_bias.h5 (deflated 16%)
+updating: GM12878_bias_transfer_models/ATAC/NAKED_DNA_bias/bias_models/evaluation/ (stored 0%)
+updating: GM12878_bias_transfer_models/ATAC/NAKED_DNA_bias/bias_models/evaluation/interpret/ (stored 0%)
+updating: GM12878_bias_transfer_models/ATAC/NAKED_DNA_bias/bias_models/evaluation/interpret/NAKED.counts_compressed.h5 (deflated 16%)
+updating: GM12878_bias_transfer_models/ATAC/NAKED_DNA_bias/bias_models/evaluation/interpret/interpret.log (deflated 92%)
+updating: GM12878_bias_transfer_models/ATAC/NAKED_DNA_bias/bias_models/evaluation/interpret/NAKED.interpreted_regions.bed.gz (deflated 0%)
+updating: GM12878_bias_transfer_models/ATAC/NAKED_DNA_bias/bias_models/evaluation/interpret/NAKED.profile_compressed.h5 (deflated 23%)
+updating: GM12878_bias_transfer_models/ATAC/NAKED_DNA_bias/bias_models/evaluation/interpret/NAKED.interpret.args.json (deflated 48%)
+updating: GM12878_bias_transfer_models/ATAC/NAKED_DNA_bias/bias_models/evaluation/modisco/ (stored 0%)
+updating: GM12878_bias_transfer_models/ATAC/NAKED_DNA_bias/bias_models/evaluation/modisco/modiscolite_counts.h5 (deflated 65%)
+updating: GM12878_bias_transfer_models/ATAC/NAKED_DNA_bias/bias_models/evaluation/modisco/modiscolite_profile.h5 (deflated 64%)
+updating: GM12878_bias_transfer_models/ATAC/NAKED_DNA_bias/bias_models/data/ (stored 0%)
+updating: GM12878_bias_transfer_models/ATAC/NAKED_DNA_bias/bias_models/data/peaks.validationset.bed.gz (deflated 0%)
+updating: GM12878_bias_transfer_models/ATAC/NAKED_DNA_bias/bias_models/data/naked_dna_atac_unstranded.bw (deflated 10%)
+updating: GM12878_bias_transfer_models/ATAC/NAKED_DNA_bias/bias_models/data/peaks.trainingset.bed.gz (deflated 0%)
+updating: GM12878_bias_transfer_models/ATAC/NAKED_DNA_bias/bias_models/data/nonpeaks.input.bed.gz (deflated 0%)
+updating: GM12878_bias_transfer_models/ATAC/NAKED_DNA_bias/bias_models/data/peaks.testset.bed.gz (deflated 0%)
+updating: GM12878_bias_transfer_models/ATAC/NAKED_DNA_bias/bias_models/data/peaks.input.bed.gz (deflated 0%)
+updating: GM12878_bias_transfer_models/ATAC/NAKED_DNA_bias/bias_models/logs/ (stored 0%)
+updating: GM12878_bias_transfer_models/ATAC/NAKED_DNA_bias/bias_models/logs/bias.params.json (deflated 38%)
+updating: GM12878_bias_transfer_models/ATAC/NAKED_DNA_bias/bias_models/logs/bias.log (deflated 52%)
+updating: GM12878_bias_transfer_models/ATAC/NAKED_DNA_bias/bias_models/logs/bias_model_params.tsv (deflated 21%)
+updating: GM12878_bias_transfer_models/ATAC/NAKED_DNA_bias/bias_models/logs/bias_predictions.h (deflated 1%)
+updating: GM12878_bias_transfer_models/ATAC/NAKED_DNA_bias/bias_models/logs/bias_model_train.log (deflated 97%)
+updating: GM12878_bias_transfer_models/ATAC/NAKED_DNA_bias/bias_models/logs/bias.args.json (deflated 61%)
+updating: GM12878_bias_transfer_models/ATAC/NAKED_DNA_bias/bias_models/logs/bias_data_params.tsv (deflated 26%)
+updating: GM12878_bias_transfer_models/ATAC/NAKED_DNA_bias/bias_models/logs/bias_metrics.json (deflated 52%)
+updating: GM12878_bias_transfer_models/ATAC/NAKED_DNA_bias/bias_models/logs/bias.log.batch (deflated 70%)
+updating: GM12878_bias_transfer_models/ATAC/HEPG2_invivo_bias/ (stored 0%)
+updating: GM12878_bias_transfer_models/ATAC/HEPG2_invivo_bias/models/ (stored 0%)
+updating: GM12878_bias_transfer_models/ATAC/HEPG2_invivo_bias/models/chrombpnet.tar (deflated 10%)
+updating: GM12878_bias_transfer_models/ATAC/HEPG2_invivo_bias/models/bias_model_scaled.tar (deflated 30%)
+updating: GM12878_bias_transfer_models/ATAC/HEPG2_invivo_bias/models/chrombpnet.h5 (deflated 7%)
+updating: GM12878_bias_transfer_models/ATAC/HEPG2_invivo_bias/models/bias_model_scaled.h5 (deflated 12%)
+updating: GM12878_bias_transfer_models/ATAC/HEPG2_invivo_bias/models/chrombpnet_nobias.h5 (deflated 7%)
+updating: GM12878_bias_transfer_models/ATAC/HEPG2_invivo_bias/models/chrombpnet_nobias.tar (deflated 8%)
+updating: GM12878_bias_transfer_models/ATAC/HEPG2_invivo_bias/evaluation/ (stored 0%)
+updating: GM12878_bias_transfer_models/ATAC/HEPG2_invivo_bias/evaluation/interpret/ (stored 0%)
+updating: GM12878_bias_transfer_models/ATAC/HEPG2_invivo_bias/evaluation/interpret/GM12878.profile_compressed.h5 (deflated 20%)
+updating: GM12878_bias_transfer_models/ATAC/HEPG2_invivo_bias/evaluation/interpret/GM12878.counts_compressed.h5 (deflated 16%)
+updating: GM12878_bias_transfer_models/ATAC/HEPG2_invivo_bias/evaluation/modisco/ (stored 0%)
+updating: GM12878_bias_transfer_models/ATAC/HEPG2_invivo_bias/evaluation/modisco/modiscolite_counts.h5 (deflated 66%)
+updating: GM12878_bias_transfer_models/ATAC/HEPG2_invivo_bias/evaluation/modisco/modiscolite_profile.h5 (deflated 67%)
+updating: GM12878_bias_transfer_models/ATAC/HEPG2_invivo_bias/evaluation/footprints/ (stored 0%)
+updating: GM12878_bias_transfer_models/ATAC/HEPG2_invivo_bias/evaluation/footprints/footprinting.log (deflated 98%)
+updating: GM12878_bias_transfer_models/ATAC/HEPG2_invivo_bias/evaluation/footprints/motif_footprints.h5 (deflated 59%)
+updating: GM12878_bias_transfer_models/ATAC/HEPG2_invivo_bias/logs/ (stored 0%)
+updating: GM12878_bias_transfer_models/ATAC/HEPG2_invivo_bias/logs/run_GM12878_bias_dil_8_fold_0.yml (deflated 68%)
+updating: GM12878_bias_transfer_models/ATAC/HEPG2_invivo_bias/logs/transfer_bias_atac.yml (deflated 68%)
+updating: GM12878_bias_transfer_models/DNASE/ (stored 0%)
+updating: GM12878_bias_transfer_models/DNASE/NAKED_DNA_bias/ (stored 0%)
+updating: GM12878_bias_transfer_models/DNASE/NAKED_DNA_bias/models/ (stored 0%)
+updating: GM12878_bias_transfer_models/DNASE/NAKED_DNA_bias/models/chrombpnet.tar (deflated 11%)
+updating: GM12878_bias_transfer_models/DNASE/NAKED_DNA_bias/models/bias_model_scaled.tar (deflated 30%)
+updating: GM12878_bias_transfer_models/DNASE/NAKED_DNA_bias/models/chrombpnet.h5 (deflated 13%)
+updating: GM12878_bias_transfer_models/DNASE/NAKED_DNA_bias/models/bias_model_scaled.h5 (deflated 12%)
+updating: GM12878_bias_transfer_models/DNASE/NAKED_DNA_bias/models/chrombpnet_nobias.h5 (deflated 7%)
+updating: GM12878_bias_transfer_models/DNASE/NAKED_DNA_bias/models/chrombpnet_nobias.tar (deflated 9%)
+updating: GM12878_bias_transfer_models/DNASE/NAKED_DNA_bias/evaluation/ (stored 0%)
+updating: GM12878_bias_transfer_models/DNASE/NAKED_DNA_bias/evaluation/interpret/ (stored 0%)
+updating: GM12878_bias_transfer_models/DNASE/NAKED_DNA_bias/evaluation/interpret/GM12878.interpret.args.json (deflated 54%)
+updating: GM12878_bias_transfer_models/DNASE/NAKED_DNA_bias/evaluation/interpret/GM12878.profile_compressed.h5 (deflated 20%)
+updating: GM12878_bias_transfer_models/DNASE/NAKED_DNA_bias/evaluation/interpret/GM12878.counts_compressed.h5 (deflated 16%)
+updating: GM12878_bias_transfer_models/DNASE/NAKED_DNA_bias/evaluation/interpret/interpret.log (deflated 93%)
+updating: GM12878_bias_transfer_models/DNASE/NAKED_DNA_bias/evaluation/interpret/GM12878.interpreted_regions.bed.gz (deflated 0%)
+updating: GM12878_bias_transfer_models/DNASE/NAKED_DNA_bias/evaluation/modisco/ (stored 0%)
+updating: GM12878_bias_transfer_models/DNASE/NAKED_DNA_bias/evaluation/modisco/modiscolite_counts.h5 (deflated 66%)
+updating: GM12878_bias_transfer_models/DNASE/NAKED_DNA_bias/evaluation/modisco/modiscolite_profile.h5 (deflated 68%)
+updating: GM12878_bias_transfer_models/DNASE/NAKED_DNA_bias/evaluation/footprints/ (stored 0%)
+updating: GM12878_bias_transfer_models/DNASE/NAKED_DNA_bias/data/ (stored 0%)
+updating: GM12878_bias_transfer_models/DNASE/NAKED_DNA_bias/data/nonpeaks.validationset.bed.gz (deflated 0%)
+updating: GM12878_bias_transfer_models/DNASE/NAKED_DNA_bias/data/peaks.validationset.bed.gz (deflated 0%)
+updating: GM12878_bias_transfer_models/DNASE/NAKED_DNA_bias/data/peaks.trainingset.bed.gz (deflated 0%)
+updating: GM12878_bias_transfer_models/DNASE/NAKED_DNA_bias/data/nonpeaks.trainingset.bed.gz (deflated 0%)
+updating: GM12878_bias_transfer_models/DNASE/NAKED_DNA_bias/data/peaks.testset.bed.gz (deflated 0%)
+updating: GM12878_bias_transfer_models/DNASE/NAKED_DNA_bias/logs/ (stored 0%)
+updating: GM12878_bias_transfer_models/DNASE/NAKED_DNA_bias/logs/chrombpnet_data_params.tsv (deflated 27%)
+updating: GM12878_bias_transfer_models/DNASE/NAKED_DNA_bias/logs/chrombpnet.args.json (deflated 67%)
+updating: GM12878_bias_transfer_models/DNASE/NAKED_DNA_bias/logs/chrombpnet.log (deflated 50%)
+updating: GM12878_bias_transfer_models/DNASE/NAKED_DNA_bias/logs/chrombpnet.log.batch (deflated 70%)
+updating: GM12878_bias_transfer_models/DNASE/NAKED_DNA_bias/logs/train_chrombpnet_model.log (deflated 95%)
+updating: GM12878_bias_transfer_models/DNASE/NAKED_DNA_bias/logs/chrombpnet.params.json (deflated 40%)
+updating: GM12878_bias_transfer_models/DNASE/NAKED_DNA_bias/logs/chrombpnet_model_params.tsv (deflated 31%)
+updating: GM12878_bias_transfer_models/DNASE/NAKED_DNA_bias/bias_models/ (stored 0%)
+updating: GM12878_bias_transfer_models/DNASE/NAKED_DNA_bias/bias_models/models/ (stored 0%)
+updating: GM12878_bias_transfer_models/DNASE/NAKED_DNA_bias/bias_models/models/naked_dna_bias.tar (deflated 30%)
+updating: GM12878_bias_transfer_models/DNASE/NAKED_DNA_bias/bias_models/models/naked_dna_bias.h5 (deflated 12%)
+updating: GM12878_bias_transfer_models/DNASE/NAKED_DNA_bias/bias_models/evaluation/ (stored 0%)
+updating: GM12878_bias_transfer_models/DNASE/NAKED_DNA_bias/bias_models/evaluation/interpret/ (stored 0%)
+updating: GM12878_bias_transfer_models/DNASE/NAKED_DNA_bias/bias_models/evaluation/interpret/NAKED.counts_compressed.h5 (deflated 17%)
+updating: GM12878_bias_transfer_models/DNASE/NAKED_DNA_bias/bias_models/evaluation/interpret/interpret.log (deflated 92%)
+updating: GM12878_bias_transfer_models/DNASE/NAKED_DNA_bias/bias_models/evaluation/interpret/NAKED.interpreted_regions.bed.gz (deflated 0%)
+updating: GM12878_bias_transfer_models/DNASE/NAKED_DNA_bias/bias_models/evaluation/interpret/NAKED.profile_compressed.h5 (deflated 21%)
+updating: GM12878_bias_transfer_models/DNASE/NAKED_DNA_bias/bias_models/evaluation/interpret/NAKED.interpret.args.json (deflated 48%)
+updating: GM12878_bias_transfer_models/DNASE/NAKED_DNA_bias/bias_models/evaluation/modisco/ (stored 0%)
+updating: GM12878_bias_transfer_models/DNASE/NAKED_DNA_bias/bias_models/evaluation/modisco/modiscolite_counts.h5 (deflated 65%)
+updating: GM12878_bias_transfer_models/DNASE/NAKED_DNA_bias/bias_models/evaluation/modisco/modiscolite_profile.h5 (deflated 66%)
+updating: GM12878_bias_transfer_models/DNASE/NAKED_DNA_bias/bias_models/data/ (stored 0%)
+updating: GM12878_bias_transfer_models/DNASE/NAKED_DNA_bias/bias_models/data/peaks.validationset.bed.gz (deflated 0%)
+updating: GM12878_bias_transfer_models/DNASE/NAKED_DNA_bias/bias_models/data/naked_dna_atac_unstranded.bw (deflated 11%)
+updating: GM12878_bias_transfer_models/DNASE/NAKED_DNA_bias/bias_models/data/peaks.trainingset.bed.gz (deflated 0%)
+updating: GM12878_bias_transfer_models/DNASE/NAKED_DNA_bias/bias_models/data/nonpeaks.input.bed.gz (deflated 0%)
+updating: GM12878_bias_transfer_models/DNASE/NAKED_DNA_bias/bias_models/data/peaks.testset.bed.gz (deflated 0%)
+updating: GM12878_bias_transfer_models/DNASE/NAKED_DNA_bias/bias_models/data/peaks.input.bed.gz (deflated 0%)
+updating: GM12878_bias_transfer_models/DNASE/NAKED_DNA_bias/bias_models/logs/ (stored 0%)
+updating: GM12878_bias_transfer_models/DNASE/NAKED_DNA_bias/bias_models/logs/bias.params.json (deflated 39%)
+updating: GM12878_bias_transfer_models/DNASE/NAKED_DNA_bias/bias_models/logs/bias.log (deflated 51%)
+updating: GM12878_bias_transfer_models/DNASE/NAKED_DNA_bias/bias_models/logs/bias_model_params.tsv (deflated 22%)
+updating: GM12878_bias_transfer_models/DNASE/NAKED_DNA_bias/bias_models/logs/bias_predictions.h (deflated 1%)
+updating: GM12878_bias_transfer_models/DNASE/NAKED_DNA_bias/bias_models/logs/bias_model_train.log (deflated 96%)
+updating: GM12878_bias_transfer_models/DNASE/NAKED_DNA_bias/bias_models/logs/bias.args.json (deflated 61%)
+updating: GM12878_bias_transfer_models/DNASE/NAKED_DNA_bias/bias_models/logs/bias_data_params.tsv (deflated 26%)
+updating: GM12878_bias_transfer_models/DNASE/NAKED_DNA_bias/bias_models/logs/bias_metrics.json (deflated 52%)
+updating: GM12878_bias_transfer_models/DNASE/NAKED_DNA_bias/bias_models/logs/bias.log.batch (deflated 71%)
+ adding: GM12878_bias_transfer_models/README.md (deflated 66%)
+ adding: GM12878_bias_transfer_models/ATAC/NAKED_DNA_bias/data/README.md (deflated 15%)
+ adding: GM12878_bias_transfer_models/ATAC/NAKED_DNA_bias/logs/interpret_script.sh (deflated 66%)
+ adding: GM12878_bias_transfer_models/ATAC/NAKED_DNA_bias/logs/script.sh (deflated 73%)
+ adding: GM12878_bias_transfer_models/ATAC/NAKED_DNA_bias/bias_models/logs/interpret_script.sh (deflated 66%)
+ adding: GM12878_bias_transfer_models/ATAC/NAKED_DNA_bias/bias_models/logs/script.sh (deflated 66%)
+ adding: GM12878_bias_transfer_models/ATAC/HEPG2_invivo_bias/README.md (deflated 17%)
+ adding: GM12878_bias_transfer_models/ATAC/HEPG2_invivo_bias/.script.sh.swp (deflated 94%)
+ adding: GM12878_bias_transfer_models/ATAC/HEPG2_invivo_bias/logs/interpret_script.sh (deflated 62%)
+ adding: GM12878_bias_transfer_models/ATAC/HEPG2_invivo_bias/logs/script.sh (deflated 67%)
+ adding: GM12878_bias_transfer_models/DNASE/NAKED_DNA_bias/data/README.md (deflated 36%)
+ adding: GM12878_bias_transfer_models/DNASE/NAKED_DNA_bias/logs/interpret_script.sh (deflated 66%)
+ adding: GM12878_bias_transfer_models/DNASE/NAKED_DNA_bias/logs/script.sh (deflated 73%)
+ adding: GM12878_bias_transfer_models/DNASE/NAKED_DNA_bias/bias_models/logs/nonpeaks.validationset.bed.gz (deflated 0%)
+ adding: GM12878_bias_transfer_models/DNASE/NAKED_DNA_bias/bias_models/logs/interpret_script.sh (deflated 66%)
+ adding: GM12878_bias_transfer_models/DNASE/NAKED_DNA_bias/bias_models/logs/nonpeaks.trainingset.bed.gz (deflated 0%)
+ adding: GM12878_bias_transfer_models/DNASE/NAKED_DNA_bias/bias_models/logs/script.sh (deflated 68%)
+(base) anusri@brahma:/oak/stanford/groups/akundaje/anusri/chrombpnet_zenodo_uploads_reformatted$
diff --git a/logs/checkpoint/JAN_02_2023/script_make_bigwig.sh b/logs/checkpoint/JAN_02_2023/script_make_bigwig.sh
new file mode 100644
index 00000000..9e6cab57
--- /dev/null
+++ b/logs/checkpoint/JAN_02_2023/script_make_bigwig.sh
@@ -0,0 +1,164 @@
+
+#merge_folds_all_regions_may_05_24/$cellty"_folds_merged".counts_scores_new_compressed.bw
+
+# cellty=IMR90
+# dtty=ATAC
+# python /mnt/lab_data2/anusri/chrombpnet/src/evaluation/make_bigwigs/importance_hdf5_to_bigwig.py \
+# -h5 /oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/chrombpnet/folds/$dtty/$cellty/merge_folds_all_regions_may_05_24/$cellty"_folds_merged".profile_scores_new_compressed.h5 \
+# -r /oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/chrombpnet/folds/$dtty/$cellty/merge_folds_all_regions_may_05_24/$cellty"_folds_merged".profile_scores_new_compressed.bed.gz \
+# -c /mnt/lab_data2/anusri/chrombpnet/reference/chrom.sizes \
+# -o /oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/chrombpnet/folds/$dtty/$cellty/interpret_upload/average_preds/$cellty"_folds_merged".profile_scores_new_compressed.bw \
+# -s /oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/chrombpnet/folds/$dtty/$cellty/interpret_upload/average_preds/$cellty"_folds_merged".profile_scores_new_compressed.stats \
+#
+# cellty=GM12878
+# dtty=ATAC
+# python /mnt/lab_data2/anusri/chrombpnet/src/evaluation/make_bigwigs/importance_hdf5_to_bigwig.py \
+# -h5 /oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/chrombpnet/folds/$dtty/$cellty/merge_folds_all_regions_may_05_24/$cellty"_folds_merged".profile_scores_new_compressed.h5 \
+# -r /oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/chrombpnet/folds/$dtty/$cellty/merge_folds_all_regions_may_05_24/$cellty"_folds_merged".profile_scores_new_compressed.bed.gz \
+# -c /mnt/lab_data2/anusri/chrombpnet/reference/chrom.sizes \
+# -o /oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/chrombpnet/folds/$dtty/$cellty/interpret_upload/average_preds/$cellty"_folds_merged".profile_scores_new_compressed.bw \
+# -s /oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/chrombpnet/folds/$dtty/$cellty/interpret_upload/average_preds/$cellty"_folds_merged".profile_scores_new_compressed.stats \
+#
+# cellty=H1ESC
+# dtty=ATAC
+# python /mnt/lab_data2/anusri/chrombpnet/src/evaluation/make_bigwigs/importance_hdf5_to_bigwig.py \
+# -h5 /oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/chrombpnet/folds/$dtty/$cellty/merge_folds_all_regions_may_05_24/$cellty"_folds_merged".profile_scores_new_compressed.h5 \
+# -r /oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/chrombpnet/folds/$dtty/$cellty/merge_folds_all_regions_may_05_24/$cellty"_folds_merged".profile_scores_new_compressed.bed.gz \
+# -c /mnt/lab_data2/anusri/chrombpnet/reference/chrom.sizes \
+# -o /oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/chrombpnet/folds/$dtty/$cellty/interpret_upload/average_preds/$cellty"_folds_merged".profile_scores_new_compressed.bw \
+# -s /oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/chrombpnet/folds/$dtty/$cellty/interpret_upload/average_preds/$cellty"_folds_merged".profile_scores_new_compressed.stats \
+
+# cellty=IMR90_new
+# dtty=DNASE
+# python /mnt/lab_data2/anusri/chrombpnet/src/evaluation/make_bigwigs/importance_hdf5_to_bigwig.py \
+# -h5 /oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/chrombpnet/folds/$dtty/$cellty/merge_folds_all_regions_jun_11_24/$cellty"_folds_merged".profile_scores_new_compressed.h5 \
+# -r /oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/chrombpnet/folds/$dtty/$cellty/merge_folds_all_regions_jun_11_24/$cellty"_folds_merged".profile_scores_new_compressed.bed.gz \
+# -c /mnt/lab_data2/anusri/chrombpnet/reference/chrom.sizes \
+# -o /oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/chrombpnet/folds/$dtty/$cellty/interpret_upload/average_preds/$cellty"_folds_merged".profile_scores_new_compressed.bw \
+# -s /oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/chrombpnet/folds/$dtty/$cellty/interpret_upload/average_preds/$cellty"_folds_merged".profile_scores_new_compressed.stats \
+#
+# cellty=H1ESC_new
+# dtty=DNASE
+# python /mnt/lab_data2/anusri/chrombpnet/src/evaluation/make_bigwigs/importance_hdf5_to_bigwig.py \
+# -h5 /oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/chrombpnet/folds/$dtty/$cellty/merge_folds_all_regions_jun_11_24/$cellty"_folds_merged".profile_scores_new_compressed.h5 \
+# -r /oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/chrombpnet/folds/$dtty/$cellty/merge_folds_all_regions_jun_11_24/$cellty"_folds_merged".profile_scores_new_compressed.bed.gz \
+# -c /mnt/lab_data2/anusri/chrombpnet/reference/chrom.sizes \
+# -o /oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/chrombpnet/folds/$dtty/$cellty/interpret_upload/average_preds/$cellty"_folds_merged".profile_scores_new_compressed.bw \
+# -s /oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/chrombpnet/folds/$dtty/$cellty/interpret_upload/average_preds/$cellty"_folds_merged".profile_scores_new_compressed.stats \
+#
+# cellty=GM12878_new
+# dtty=DNASE
+# python /mnt/lab_data2/anusri/chrombpnet/src/evaluation/make_bigwigs/importance_hdf5_to_bigwig.py \
+# -h5 /oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/chrombpnet/folds/$dtty/$cellty/merge_folds_all_regions_jun_11_24/$cellty"_folds_merged".profile_scores_new_compressed.h5 \
+# -r /oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/chrombpnet/folds/$dtty/$cellty/merge_folds_all_regions_jun_11_24/$cellty"_folds_merged".profile_scores_new_compressed.bed.gz \
+# -c /mnt/lab_data2/anusri/chrombpnet/reference/chrom.sizes \
+# -o /oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/chrombpnet/folds/$dtty/$cellty/interpret_upload/average_preds/$cellty"_folds_merged".profile_scores_new_compressed.bw \
+# -s /oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/chrombpnet/folds/$dtty/$cellty/interpret_upload/average_preds/$cellty"_folds_merged".profile_scores_new_compressed.stats \
+#
+
+
+# cellty=IMR90
+# dtty=ATAC
+# python /mnt/lab_data2/anusri/chrombpnet/src/evaluation/make_bigwigs/importance_hdf5_to_bigwig.py \
+# -h5 /oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/chrombpnet/folds/$dtty/$cellty/merge_folds_all_regions_may_05_24/$cellty"_folds_merged".counts_scores_new_compressed.h5 \
+# -r /oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/chrombpnet/folds/$dtty/$cellty/merge_folds_all_regions_may_05_24/$cellty"_folds_merged".counts_scores_new_compressed.bed.gz \
+# -c /mnt/lab_data2/anusri/chrombpnet/reference/chrom.sizes \
+# -o /oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/chrombpnet/folds/$dtty/$cellty/interpret_upload/average_preds/$cellty"_folds_merged".counts_scores_new_compressed.bw \
+# -s /oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/chrombpnet/folds/$dtty/$cellty/interpret_upload/average_preds/$cellty"_folds_merged".counts_scores_new_compressed.stats \
+#
+# cellty=GM12878
+# dtty=ATAC
+# python /mnt/lab_data2/anusri/chrombpnet/src/evaluation/make_bigwigs/importance_hdf5_to_bigwig.py \
+# -h5 /oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/chrombpnet/folds/$dtty/$cellty/merge_folds_all_regions_may_05_24/$cellty"_folds_merged".counts_scores_new_compressed.h5 \
+# -r /oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/chrombpnet/folds/$dtty/$cellty/merge_folds_all_regions_may_05_24/$cellty"_folds_merged".counts_scores_new_compressed.bed.gz \
+# -c /mnt/lab_data2/anusri/chrombpnet/reference/chrom.sizes \
+# -o /oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/chrombpnet/folds/$dtty/$cellty/interpret_upload/average_preds/$cellty"_folds_merged".counts_scores_new_compressed.bw \
+# -s /oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/chrombpnet/folds/$dtty/$cellty/interpret_upload/average_preds/$cellty"_folds_merged".counts_scores_new_compressed.stats \
+#
+# cellty=H1ESC
+# dtty=ATAC
+# python /mnt/lab_data2/anusri/chrombpnet/src/evaluation/make_bigwigs/importance_hdf5_to_bigwig.py \
+# -h5 /oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/chrombpnet/folds/$dtty/$cellty/merge_folds_all_regions_may_05_24/$cellty"_folds_merged".counts_scores_new_compressed.h5 \
+# -r /oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/chrombpnet/folds/$dtty/$cellty/merge_folds_all_regions_may_05_24/$cellty"_folds_merged".counts_scores_new_compressed.bed.gz \
+# -c /mnt/lab_data2/anusri/chrombpnet/reference/chrom.sizes \
+# -o /oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/chrombpnet/folds/$dtty/$cellty/interpret_upload/average_preds/$cellty"_folds_merged".counts_scores_new_compressed.bw \
+# -s /oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/chrombpnet/folds/$dtty/$cellty/interpret_upload/average_preds/$cellty"_folds_merged".counts_scores_new_compressed.stats \
+
+# cellty=IMR90_new
+# dtty=DNASE
+# python /mnt/lab_data2/anusri/chrombpnet/src/evaluation/make_bigwigs/importance_hdf5_to_bigwig.py \
+# -h5 /oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/chrombpnet/folds/$dtty/$cellty/merge_folds_all_regions_jun_11_24/$cellty"_folds_merged".counts_scores_new_compressed.h5 \
+# -r /oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/chrombpnet/folds/$dtty/$cellty/merge_folds_all_regions_jun_11_24/$cellty"_folds_merged".counts_scores_new_compressed.bed.gz \
+# -c /mnt/lab_data2/anusri/chrombpnet/reference/chrom.sizes \
+# -o /oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/chrombpnet/folds/$dtty/$cellty/interpret_upload/average_preds/$cellty"_folds_merged".counts_scores_new_compressed.bw \
+# -s /oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/chrombpnet/folds/$dtty/$cellty/interpret_upload/average_preds/$cellty"_folds_merged".counts_scores_new_compressed.stats \
+#
+# cellty=H1ESC_new
+# dtty=DNASE
+# python /mnt/lab_data2/anusri/chrombpnet/src/evaluation/make_bigwigs/importance_hdf5_to_bigwig.py \
+# -h5 /oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/chrombpnet/folds/$dtty/$cellty/merge_folds_all_regions_jun_11_24/$cellty"_folds_merged".counts_scores_new_compressed.h5 \
+# -r /oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/chrombpnet/folds/$dtty/$cellty/merge_folds_all_regions_jun_11_24/$cellty"_folds_merged".counts_scores_new_compressed.bed.gz \
+# -c /mnt/lab_data2/anusri/chrombpnet/reference/chrom.sizes \
+# -o /oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/chrombpnet/folds/$dtty/$cellty/interpret_upload/average_preds/$cellty"_folds_merged".counts_scores_new_compressed.bw \
+# -s /oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/chrombpnet/folds/$dtty/$cellty/interpret_upload/average_preds/$cellty"_folds_merged".counts_scores_new_compressed.stats \
+#
+# cellty=GM12878_new
+# dtty=DNASE
+# python /mnt/lab_data2/anusri/chrombpnet/src/evaluation/make_bigwigs/importance_hdf5_to_bigwig.py \
+# -h5 /oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/chrombpnet/folds/$dtty/$cellty/merge_folds_all_regions_jun_11_24/$cellty"_folds_merged".counts_scores_new_compressed.h5 \
+# -r /oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/chrombpnet/folds/$dtty/$cellty/merge_folds_all_regions_jun_11_24/$cellty"_folds_merged".counts_scores_new_compressed.bed.gz \
+# -c /mnt/lab_data2/anusri/chrombpnet/reference/chrom.sizes \
+# -o /oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/chrombpnet/folds/$dtty/$cellty/interpret_upload/average_preds/$cellty"_folds_merged".counts_scores_new_compressed.bw \
+# -s /oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/chrombpnet/folds/$dtty/$cellty/interpret_upload/average_preds/$cellty"_folds_merged".counts_scores_new_compressed.stats \
+#
+#
+# python /mnt/lab_data2/anusri/chrombpnet/src/evaluation/make_bigwigs/importance_hdf5_to_bigwig.py \
+# -h5 /oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/chrombpnet/folds/DNASE/HEPG2/merge_folds_all_regions_jun_11_24/HEPG2_folds_merged.counts_scores_new_compressed.h5 \
+# -r /oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/chrombpnet/folds/DNASE/HEPG2/merge_folds_all_regions_jun_11_24/HEPG2_folds_merged.counts_scores_new_compressed.bed.gz \
+# -c /mnt/lab_data2/anusri/chrombpnet/reference/chrom.sizes \
+# -o /oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/chrombpnet/folds/DNASE/HEPG2/interpret_upload/average_preds/HEPG2_folds_merged.counts_scores.bw \
+# -s /oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/chrombpnet/folds/DNASE/HEPG2/interpret_upload/average_preds/HEPG2_folds_merged.counts_scores.stats \
+#
+# python /mnt/lab_data2/anusri/chrombpnet/src/evaluation/make_bigwigs/importance_hdf5_to_bigwig.py \
+# -h5 /oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/chrombpnet/folds/DNASE/HEPG2/merge_folds_all_regions_jun_11_24/HEPG2_folds_merged.profile_scores_new_compressed.h5 \
+# -r /oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/chrombpnet/folds/DNASE/HEPG2/merge_folds_all_regions_jun_11_24/HEPG2_folds_merged.profile_scores_new_compressed.bed.gz \
+# -c /mnt/lab_data2/anusri/chrombpnet/reference/chrom.sizes \
+# -o /oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/chrombpnet/folds/DNASE/HEPG2/interpret_upload/average_preds/HEPG2_folds_merged.profile_scores.bw \
+# -s /oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/chrombpnet/folds/DNASE/HEPG2/interpret_upload/average_preds/HEPG2_folds_merged.profile_scores.stats \
+
+
+python /mnt/lab_data2/anusri/chrombpnet/src/evaluation/make_bigwigs/importance_hdf5_to_bigwig.py \
+ -h5 /oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/chrombpnet/folds/DNASE/K562/merge_folds_all_regions_jun_11_24/K562_folds_merged.counts_scores_new_compressed.h5 \
+ -r /oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/chrombpnet/folds/DNASE/K562/merge_folds_all_regions_jun_11_24/K562_folds_merged.profile_scores_new_compressed.bed.gz \
+ -c /mnt/lab_data2/anusri/chrombpnet/reference/chrom.sizes \
+ -o /oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/chrombpnet/folds/DNASE/K562/interpret_upload/average_preds/K562_folds_merged.counts_scores.bw \
+ -s /oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/chrombpnet/folds/DNASE/K562/interpret_upload/average_preds/K562_folds_merged.counts_scores.stats \
+
+python /mnt/lab_data2/anusri/chrombpnet/src/evaluation/make_bigwigs/importance_hdf5_to_bigwig.py \
+ -h5 /oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/chrombpnet/folds/DNASE/K562/merge_folds_all_regions_jun_11_24/K562_folds_merged.profile_scores_new_compressed.h5 \
+ -r /oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/chrombpnet/folds/DNASE/K562/merge_folds_all_regions_jun_11_24/K562_folds_merged.profile_scores_new_compressed.bed.gz \
+ -c /mnt/lab_data2/anusri/chrombpnet/reference/chrom.sizes \
+ -o /oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/chrombpnet/folds/DNASE/K562/interpret_upload/average_preds/K562_folds_merged.profile_scores.bw \
+ -s /oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/chrombpnet/folds/DNASE/K562/interpret_upload/average_preds/K562_folds_merged.profile_scores.stats \
+
+
+#python /mnt/lab_data2/anusri/chrombpnet/src/evaluation/make_bigwigs/importance_hdf5_to_bigwig.py \
+# -h5 /oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/chrombpnet/folds/ATAC/HEPG2/merge_folds_all_regions_jun_11_24/HEPG2_folds_merged.profile_scores_new_compressed.h5 \
+# -r /mnt/lab_data2/anusri/chrombpnet/results/chrombpnet/hepg2.merged.atac.dnase.peaks.bed \
+# -c /mnt/lab_data2/anusri/chrombpnet/reference/chrom.sizes \
+# -o /oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/chrombpnet/folds/ATAC/HEPG2/interpret_upload/average_preds/HEPG2_folds_merged.profile_scores.bw \
+# -s /oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/chrombpnet/folds/ATAC/HEPG2/interpret_upload/average_preds/HEPG2_folds_merged.profile_scores.stats \
+
+#python /mnt/lab_data2/anusri/chrombpnet/src/evaluation/make_bigwigs/importance_hdf5_to_bigwig.py \
+# -h5 /oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/chrombpnet/folds/ATAC/K562/merge_folds_new_may_05_24/K562_folds_merged.profile_scores_new_compressed.h5 \
+# -r /mnt/lab_data2/anusri/chrombpnet/results/chrombpnet/k562.merged.atac.dnase.peaks.bed \
+# -c /mnt/lab_data2/anusri/chrombpnet/reference/chrom.sizes \
+# -o /oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/chrombpnet/folds/ATAC/K562/interpret_upload/average_preds/K562_folds_merged.profile_scores.bw \
+# -s /oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/chrombpnet/folds/ATAC/K562/interpret_upload/average_preds/K562_folds_merged.profile_scores.stats \
+
+
+
+
+
+
+
diff --git a/logs/checkpoint/JAN_02_2023/script_temp.sh b/logs/checkpoint/JAN_02_2023/script_temp.sh
new file mode 100644
index 00000000..72952270
--- /dev/null
+++ b/logs/checkpoint/JAN_02_2023/script_temp.sh
@@ -0,0 +1,9 @@
+oakdir="/oak/stanford/groups/akundaje/projects/chromatin-atlas-2022/chrombpnet/folds/DNASE/"
+celltype="GM12878"
+python /mnt/lab_data2/anusri/chrombpnet/src/evaluation/make_bigwigs/importance_hdf5_to_bigwig.py \
+ -h5 $oakdir/$celltype/merge_folds_new/$celltype"_folds_merged.counts_scores_new_compressed.h5" \
+ -r $oakdir/$celltype/merge_folds_new/$celltype"_folds_merged.counts_scores_new_compressed.unzip.bed" \
+ -c /mnt/lab_data2/anusri/chrombpnet/reference/chrom.sizes \
+ -o $oakdir/$celltype/merge_folds_new/$celltype"_folds_merged.counts_scores.bw" \
+ -s $oakdir/$celltype/merge_folds_new/$celltype"_folds_merged.counts_scores.stat" \
+ -t 1
diff --git a/logs/checkpoint/JAN_20_2024/marginal_footprints/a.out b/logs/checkpoint/JAN_20_2024/marginal_footprints/a.out
new file mode 100644
index 00000000..e69de29b
diff --git a/logs/checkpoint/JAN_20_2024/marginal_footprints/list.txt b/logs/checkpoint/JAN_20_2024/marginal_footprints/list.txt
new file mode 100644
index 00000000..e615cf31
--- /dev/null
+++ b/logs/checkpoint/JAN_20_2024/marginal_footprints/list.txt
@@ -0,0 +1,8 @@
+HEPG2_COUNTS_metacluster_0_pattern_1
+GM12878_COUNTS_metacluster_0_pattern_9
+K562_COUNTS_metacluster_0_pattern_0
+H1ESC_COUNTS_metacluster_0_pattern_1
+IMR90_COUNTS_metacluster_0_pattern_3
+K562_COUNTS_metacluster_0_pattern_2
+GM12878_COUNTS_metacluster_0_pattern_1
+
diff --git a/logs/checkpoint/JAN_20_2024/marginal_footprints/output/ATAC/GM12878/footprints.h5 b/logs/checkpoint/JAN_20_2024/marginal_footprints/output/ATAC/GM12878/footprints.h5
new file mode 100644
index 0000000000000000000000000000000000000000..8848582d6d5c4cb4446907cb64cd014d1a84bea8
GIT binary patch
literal 62374
zcmeFa2|Sg}`#*l{yX=Gvk`xIcTav6LgbEcRLXsp&+e!B9dn$xv-}m)6_I+QorDO?7
zk|h1-K8Mfq`Sktt|31Ih?|Gir>-Rjyx$l{|X6Bl?ueoN-d#-!V@lsP#p`m1_L?Mox
z97T+x!v!~QKQ>Cp={{zL{>a5g^#`JvaPBLVSP#MTSDs*f!{N8~nM6@C1R4f_gg2
z$|#s~lmDi_Q4B>+h7XZ%61Mz*lmyh2k7y$goVoGTxCjg@+{F_%^=e@w?zEAQ8YO@W
z5uiv>zI#NFg^f&8Q)zLbIJkxLak=Bx?2#g{5
zrEoq09AQX)Z3Dd{iW0Hn07@dHCo2fAqXbfTG0f%!Z(m`4e#j1bD*K#`*-MfFq-bU^~5nwj{76fh`GaN#JiJfxm7)p6_qHAO9;nZnqz=EWa0z3v9eMwz+Qp8>!mXqx=pD
z{0fh=ZRpV^i$4pG|NOq*Z#ZQOkN-|QUcdRew!)u)$L%(l{|b+@iEL`ffA=@%l@*!)
zp8ijz{-)=D4IV#7^WP=S82=Mp0UzJO<3Gt|E4n3tEeUK%U`qm968IZQ;IG5u0{=)n
zjyjB2mfwrV3l;GBH`mR7BURgal;0tNU*Yk@jq`DvEdDG!{_}af-*Czn9{-(qTwigc
zlNA00JdWC6{wqA5xG~>s>dDXk=Dgy0?B|q!cKkOz|7-9#>o4&5)vTZTK>;7%!s9>5
zWh=TRfh`GaNnlF?TN3yiN#L);<3j&PJRY#|eILIUkE?0pm1}d|{5Mjytw;GC68IG!
zm)g*yO%{I^9{>4!YJS5hTX_6;;_<1I8=a)^C*bjb4d%bX<5F6i8uH)$&3T2*@V}@3
zQ>nk{`Co&_wSIxe-OGRK0R?<~3y=RKm#yfQ1hyowC4nsoY)Rm6B!RyUkBj^x@i?~;
zURi!G9`85C=igj6|BX~_>rsA(1b&6b>o>kv8qfS!`vI2sHY)#x
zw>ht=dHo{8Ka~8N-u^ZF0oY&c2fUs5sRI=7@vZ%UpX9O?-IBnT1hyowC4nso{EZ~=
z*X;+${jK){2nh(_k_kaU1SsUU?U`Um15yr$(6V)=JsxX~2<#5(AJM_)d3r^yWgGH6
z4EjoTVT!W9{dSS#vnpY@A%~JH57biFB+x1R~b8-%0wlN;3Hb=!nmB
zCa_~v(eY9uFK$OZdu8h7kO?^GBA#Y0>o<=ar2JkbbA8A=C)};VoKonCjh)GifnztQ
z>A75Xm{)2246#k$VI{|StkhU_?y~;6&B0trHG`lgK$2?eoxk_gL4})gdBCu_4?{6E
zx;k`+%}0f$)Q@(^8GJwbCh=VNJwCD3xLdc|Up=e2kx~84akS4Y+?GS4yZSRQavV%l
zI`7Z(a&b0|ul5jb=f0H9p<$BSL?TjS
zeOO^Jzk~hl#mgYoc7UZM1zq;w`_kIE_9oVhX&29J=ne0>pCiP91KAiq2L
zOoE)`OQn-GWXhDq2UwoBtpYx|%N$2&e0gUYdrl=ga8CF$C#hA661vjt`)X)b@5K&g
z#me)(^4qWLVeWI=wJwNb8eTQ_o+tCO*jY7F$ny3Eg3Sf);%6-m7CnQ)t8_`&Cm
z{Q7RkXv2@as|2eLbi!Pp3Ln`=zi!$taKGQJWBRG9&a~@%#I2;rJ*`+!8HrCtA^qq?Ad~PlEI$b>)UWa**%)3WzJ$=UeLC7aCtamFLg(zfVgkL91LxW+G=LJ3K4hbM^9t#>whkPY~d3Ja#xqzOvl@WH~
z6B&zT%@y*Q#XE{?JVGgoVZq~zDxt=H{9ia#6tb;|n@^@JpY8H0y2sSG
zBR}LL5)5SNTe#H8HUxP0>Mw|2jjDf_P@1-l}J2~xUpOBQKJuo@3-1IoiE%9hS
zy?J4UI5_)=)ogrbSEaSgRMu8q&Lip)MffEFoiXTz6Yz9pi(Xuk0^J
zxkkM{932h$PO-a8DxhW&5Xoxp42oXZu6Ss&XJ=vIBd4R6<1bjg2)f|h-pKko-vLa?
zeNa4bMrUQaUL@6R`}UZy+JSJD8QX@=%d!FyJAK{&tHxigFY%b>D#_wE~fs7TlQk;l_2s(g(h}l-nUo6+Yjxzu}{9Fw`D4+63CHw
zkKB~=*N>#TW_!{6@*%nxWP8ev9ZY8T7QSQD{UsHonn*l6Uo!DnY~MS}fc??W@@^bx
zrk6=slW(A+ogs;d1ku(tNd)7^_NIrR=1T?`LzKRgHQ9CoXH
z(Ks+s7VQ$0+vKs7%RCZmK-gX*O1RhM?i8CWIO>^mLh^%O_#BH1`_;T$JuMv;i9w-9
z%=+A#NvNf;hv3226`t_1rQm@xqB~9{**JIv6G!hKtFx=8OTUmJ-%A0)q!j$GUQsyR
zDtiB5X^`pcU_h#c+Md#P`rP%L$pQU$fzZJsg0ISZ8cs}Gy%gdbm>+rPBAM{4+F2ZU
zr!q_H9tU0zYt`TTRThsvdOdn*G)}45Y@dKv?TVx4=jGLFQCjij4&X2m=Mm4AKVm-d
zBtoI28xU7tUtb5W`Ud!icnwXB4fSXgfFXRmu@Rv)H8r=udvkMBBMdh+G*H0;4GoRZ
z!F*^+06m0)#F3Kl+GLK;hN_RDBE^#$(EN<`bvRdBi}R2+)YYT?VJ4a#NVpa{XI
zYhfx9$7QXBO+y0pFd6;ZR#sQ(avH!!QKH
z$c3;52pQ553PQ%EL0T1_Qd@(nL6Z?7Y3SV)2o0YjW(Nt5Z*2?>365BUKFbK%;g}*>
zkRW7RjkW=hSyfea6;e%gbrlu{U37hNx@W9z&Lb}K1RBO6Be#S2uR5)Tmp_EOs;@AM7O~k!lMGZa_A~BC~71D
zI>-oy#!%-`m18IrJ-=jcks>C8C$51=TUufo4QY
z5yGNl1mqY3Qe0DD$%}*t3wjIzEm9b{uo!q%RmIQ{A(1f@2LZNf3`I)_BNzp;N~A6D
zR(Tk0NrG<%+7{r-A*GRL!y+O>S^ynBQpFA>h)aMeH8qI5kVO0gph;Pf$G{Ob3M1l%
ze=#Uxc(18-;U`D*0nwzo*j9iW0ULS_l?tjpRDMMNo1udv0rf|W#gp*=`%YQtkafZ^
z5rOO%Gm0PyeJyT9}6+mZ;|8xaK9W>YQHm3QT?
z%pNi>T4JcwTTI|KFPUP#=5Wk)rz`aaVONVQsZorv_hj~&-ANyxs%d8fm!cids|uBb
zcP>g6@{{ehcT-L~bm`b9pq6T5trhDp4LBNdV$U8k3y?}Lo}u~SQ>1ZBQfC$`-C6K{
zuxoeyGgm+n6QkoU;t^wn)n(9Ppw_ojvAz*~$Bhg7g~gLVNoWR;W*Rb{xQ=Bum!1gz
zkP?4^IJYRE_xkl_Hjy;q_(3@@p!Lmur+shg
zF)&G@W%^J4cuo9Cqp%5LFE@b)`&s$@giK?2Rg2|{+YT5$QlYU+u^{KUBd?=G58gR&
z8k3*8bC`_roFVPQ0=cOccJn5avrh^+OU|hAmF~Z=E$@#
z_ojgidot;%e^9?WDx;=&mzuJA%CXxPWEMbY+fANYQK=tU?#{&>)K#)vE2@5W7papilPe)g0
zRp-vJ&Z`u?%fVWU@7dni&q=9pupY2;a^|0}J7xE2@LZ|pdJWpRkb2o-^^H)j&xM8e
z-%tzyW#MHj**N)*Ik55IcsQ5k{UcJeF~<*|@&3*lA)R@#8|1Veh)*JGwR+==@@(KQ
z`Lwc5tzkA`BA;EU=+X1cnGj?OWslUW4l2Gm&rHbAos?Wxv5#df{ABBbPVccS^ZWM!
ze|E|Jk?Kf>6L*h%PQcn^V+z=^qhklA#@RB6)4kTILD1WtwQ&?ik|~z!N*YmC+3x$r
zrv@F(m=Ow>69xhi}RAr-+UpCr4BJ$?`vsYsOu
zWaf6<^KkB`ELwPRZz${=tuJqpWXQF*i&@Mzz@+0I*PAeh8;5r&?D2~_gOYY@x&1me
zpofn?iz(_hzc8@ZS`c+?R%{bueBTPXv1l&&cS5T?43S2LWUEiOmuvubuYvMDTT8><
zsFvPjRFr{`R)5;J`n&6Cyd$5kbI-|xxfg+lX@<;YEbF9;@9|65(`Wh&IUbbDbmuSW
zR3YVMA-6fq9ink^kMbWe$KXJT(aO~T)GH;H5
zsi601Jldu&QO?z$1!_$Ax4GF~e`I~${_P@pO4&iV>#Zy|h#zt@-7jB7N)rN)$j>(~oMGRN(%V}M0$Q4$v{9fXe7_tU{L(x@^2s~)
z@%D)JsSHkUhvTgCR3InrrX5rMId40j?6(pV(&hGLGZGJvBz{*|J?8HA`a&n*mv|MY
zYbbI=hWEH&;#hH%sy
z*Ow@AI=gSxXJ$_pyNn)D5Pg4JWjk?qI_T(#PPrVLw~zYs4-!=sQl|q?tXaCf%vGCX
zx^{B8wvYo3-2}$H!*_kjj#NLa_|BXb>VEd_-diaKsq*)m_bjHsxch+Ck%b=8IuV
z=FBsoqBcfACcisXyiwCf@JD`QMykdqeR(_fp*&92XC-ZefQVQ(TYp@Tp1*^g--e{%
zSn8>5->wAp$S6cdhLDSmN|LYmWnFYj`+DS$m``3qP;wZzgoo>N+;Sg@;MVaFRNz8&
z^)WbT0^K!;$9`Z{z1*u)|TEWw2l1OuCkzy_q%+wd81SfjQEavDSN6T-4+
zYJ%Fj7!-s`2xP&-20R==O5tz}QU)@MImwFf!^Pko`P4xmgiywaQ3Q3hF`fWlJ6!2j
z*C1t)g>H2%L}0aWF#%S&UtJGn)KF7dQBhUj)Y4pEg(TO*CkD0E*otxt
z7FJzfTLstXuy}o44O}$iT3%BF;Bpv2F9;&3sjIE7!jvH^?W&r}^5T+8Y#9brVruFz
zWks0s(wfq;l9bY1Olo#sT6#uXX=8bPbzvK5XlyR8sjI5Rw$xNtR+N|3)M3lZDq*!1
zkSDx@s>+J0YS{crh(a)x$a)!Eka077xf)@~nCM82W1S!POK+J(8Lu7-{5KM&NB!qy2I~WWF0-6vsRe?d1
z5kfD910dK1mPfL~dj+6+Xld}KizH-aC
zuN{H+gGehDwS{)cKDQz?)4bMQzuLA|2EM(0ZfIjO;izMN?ewLumfc=V{N)dYb_QB0
zc@3(2eSQSAgxgd>p~ZE!HR~GEJ=b}vyoM$PYO75no$jb9R0T}|^3{W{*Ai4ajF}F4
z&yQB@Y!6Xd%eGz=-pTmxj$Te?5ja}jd=V-;=GsCk8y>t$@9h%-Uwhy
z8>cP~xxDL!!C7KAo@1b52@t;))TF+!Lp37?m3yWO`=R|}u82aigZoL1%lEH&tnvd&
zm4NLe@7^T_c?Gat_Oqi{KKdZ_yI|vob(C(R&@vY(AZJ~=&FvF$GIGo#{lZ5%F1Nbw
zNSd}Pv0Lu}PLX`4WM;vrr>?}&2r553DRvaJ_S5eiAC
zI)nzi1f4%l@*2Fkq~dD$$WXIa#M5e3f4@=nBht^ej0!NcRIPwEPI#_aCQEGxOO3%}
zY+koOBa=QK%N(Cni2HGv55x8+&Aq>vlZ2
zm_6c1uQ8r~rgYzqZ3E<=37;11T_@U0(pkK6y!*)aGeEk#KgH>kkduavykOloUp1?W
zk6te8udL~`X6nq^QBr{C*43*!n4Rfv8_(^wJ;*NUI?KwOknNYG_}cKUbo^=tV7-}1
zKa@E1ne%~VmgRRr?q28Ex|{VxwLc1pn}?_+!~v6}KFgf%C)VtD6Hl7&*;-#Qwz1+|
zyCh;DJi@JG-4g|*d3?BHHO~kw_L%3>XRE14i+MWEnRo#d)5Yjx^<#42H79B>3CF{}
z)T^Uo6mh3l540`NJz;rt@Zh0wtxHYfCSYBb{fc??ViLMpLQtgmkQDkrmgI@jJ)*ax
zQahzDXjX&6)@OH{&pEXFjLe
z#;;=~5O66V`h;uNyCXd8QpU|XlVA~jPBXn2WxsIW@36DX867pL`3tP4PO_{;C2;ON
zTYmy*Dga+av6*R!gS0OSiQD)p!aJt>te!lJH>BIIx|3iBkgxBRTc^hiKJ2v{;M6qw
zPR(AJx<~Jsu>!w=Yu|}|(jZ76J;S-TtCzaPY7XOOJ~NpRr4di~?WJ9whqYGO4tY@H
z!4lTU{3L(-<#x@Mb>l%Uf>l>v0uo#8Ru={Kqinmu-J(>+vsai11HCS(GgL0u5bvsY
z3zE4oYUHZ1PyZ%k5@=R;f8;JNMZl>weZWuc3adaMf5dh)ea;WHzL0%%H$Q=+he8JB
zR2-R~I0$^{3Ol*JQ*c?V@tt>Ohy=r&)U%mR@NVg=-AiM-LvfY_socEohPMkR4GNUF
zNAAn0lQesTdV~HmXN|te1WC5_dFfto{rEMhZ#+9TMfv{vF6CziM?D^c>mq$7clQNK
zQdeFdQ5llC8I-~M{PR?*Q02+@{5Ey&7r;XUC9IrHNp9nX(-?+zdq8R9{S%YCI1)T!d2)?l8~aaDbcUOc`^3AMa~
zi*$|Qyv#)Z1L4cs)7QuOfU}>+Ys&H@-V$o8ImIzAhKb9gHg?k-(?>}e&9*nLr+~nL
z;rnZe4UzJDDZ{NXwzorB9oHJX36h?XtEjdMNn9t7uFU>$Lgi%iA2FZEA+LzILg$8a
z?rt6)9-bbao}OObj}YhM8pr)avp`~MBWZBNSgPVINKiDn6zgu9RsDz~K
zK^a*oDQS5HHD%SK$5oE0oieeozF-E<>f4ywyNATYga-JAhOXu@bw!1P
z5+cGv2PCBB4vOyE#lyqPyA$y3mL9jfRSXl!Tawh!C~5va~qAF#CRH;`M7V
zGW2R_u)nvny{)OS9$GCLYAd0LA-F0l%FE8o&IJWU1%=sZ$w|p+X;8p0kd&GRg_f3_
zl9ZH|nvn_8(o-Q3l2emlN5ap`MEnJ*$;rvkGMfeqAVNmEC_4u_DCE4n{Jetv0@%ex
z0Q$(Mu&}ToKQ|{A_9yJr?Cea~mzn8lDaio#B*OK@i}<+s*tpo|F;UUapb9;C4D~e(
zDi#QViXIw*=o+G&c=d!j3DwZo&)3)22l)6tdV~xZAD>6?4>xF#yU!z->IX*;z>S~4
zfWW|@09YLIfI18H7C)MBRY2_xf#U(*p@S57hiV-hgm^F~CA@-zkODzLV<>VE3^^e~
z1mTGvCa^&PxFG^Zi60!ZzWBxk>DUh^fT*g=_Xx4BUg074qFwp
zc-X03igOVlkb&^*;&n3ZQT=z?8O674v6L5ibMLKL_a1rAWBK4>95{t}F6y;V&LKnR
z-=1Bd8fmv4A}C+MlU_J_TwLhZ`NyC&*~UPn&cc@J(S?Vr-3~j}Cxn?}M!YXH9cPKq
znc7VW@|SeeLy0^Dd+LrOe7T*xwuK4SV#Ni&X+B_ZN-m<^@}
zpy|=$7iAjWJR;wRttRq~81jph%o-}#zMs}>7FGW4D4<98wc%M8!2?%IDom5-m7ShdXA4yH
zs;p~!xZe_645$aqOr`Ny_rRSmWaVcnlpn0RJg03dWzr6P%V0uq`MDD#uuVL>qS0IZ
zCNuV}(q3{#ZV-tgoC*D2gc#~VF^4wemIJ>Hk%9VL#+vaeZ
zdfyp4#YxPibD6`+qOqu#=APN;BJUx$S(U`$Xf7)%T7&
zSd%41_%&%L>HA%i0Q)o3B-|Pay(6LyobmCIzLPx8W#KzT?8AL!S4h0rB?b^@7-E?t
z*u&1G)#UVC%}4pfWfZpr$0yx=H2YPKb)6yrW0bU4gm*kA?K|O-V?-|>9}(eOz$VD2B9j@->
zj@X6$AV|lsFjgR(nvwWpziV!x3ZWtMHPTl7Vf&oib99(D&8l*{WWQ^+2}{-A2FBVu+{mYomgqN;{;_pD+^bmyKkM}
z-Eiy&i~anC=W@()55&{K)1zd=1ekB=@#E3E+V_3w$b4+cFp+fsR<6MU&lyaW05Cuk
z7`*EL3}M8hM`>!xv0@c;vuH{I+2vCgceBt0KLz_wb5IC3=8r`MS#UVd*vuscpG~nN
zE3h0WXA)$2>^=*wpR5bcyj4^o8Q+$FeCHU!^=B-EkJz}<+6uG6&&v7F0$r-Gg=T{f
znp0XD#K%k7JN7R=De`JQ7`+}vO6Bx6>oMr?-M6Q?d%UZ$lc;K0e)svnLx-`-?R-HQ~6sa<2=IoX^xQ(`lW
zT4Hf;OSq;)Bx$_^j4GYGx2k8cI$5Kq?eqZzo)^8Y7W;femj6oPiLQ6d$u+r>#ePEr
zg1!}xtNk0lfzJ{rs+^oJ-%|bL7i86a=^3}?*qo=?`j2ViX-RsDyIR0^Zzw}{Opbzx
zmd0ey?UPQxc{YGT{m#ytX>wL5O*s+p{8r-3gDNW&V&)iWRDIj$p-X_$9rRmgI@2L~%X);|MdKW^{lt(k?3WLj6Mpap}|1
z4JWbsEzuYD3O!3f!z$1eK#@F9?`a{m*zS|
z1OWFH#Zx70RP*9)Cn)GZUS-~=)9paNZ_tMAMUQisH19`FfMmcWd
z8{Y5{XvsiK8t@%5d=f#Fn}W>78D#A-s@ua!?(};*Cs=#3DT07cX
z>mb~yz}7XlwSvYPqMt0sI8)b<}ujEh=B{S-aMd&)~m8&2r`R`
zD=I51N(%D}N-C=1YlW4iMMb5R_07$op}L}^7(Qzo@+{Dzgl%l^XsyE(6_!*Y57-E*
z%1g^Iwau+94b_-(XkTlF_BGhp%BnhOIjO6v1h6ZxNDo12!!E#g1@gund<^Ky%K?PH
zxB$-DRfcn=r5heZsbvIZWic!yctQ*(J;cbRB`_UfQC?OGee`L7V+U(OOj0-t6ErKq
z3UNWi`U6`5YlhE=v;ldc4wn(hfg@up0nX5b*rM=Cg|{r>qKKkYVo~r-6h_2Yg=h`(
z!9p1#^`UD}M?szoGDcbg9g-J@0itP$y29olbs$;`l^8d|aB9tt3=915
zL2RAKs6vd8h;{Ujm<|5)7wnKNXE;ut-#-CU=i>y{U7A1dTMy8$g(X*Ka{qx}~z
zI^9Xx;R>R34W626zx>#P4K81+b(aqt>J)J2-tIlG7QM1qTz>$xmgn6$oNsuU&pMXh
z>eRx@LvDIa_tv(;;n)!|e;>k20R41vSwL8DxKR5^BExn0rLY}DuggT%DES9m%|yc;
z13=ooSr9XPlFA*WJ5?){X=<5$gCP6WOyqXQ>RF8XQ=gVydqKXi
z!1@gKik^V`kuMDnHnydl<0v{Cb<+8wCD&CaqfUTLka3FqsNmV8_`yM&>l)9gm$vhP
zoTB=oioKUR7*wJGt8whJoDg~Icjf`EjVvb!$Ahp9BEw`)?O)x}(o0MI1ZF4gOl;q@
z(q&kWalcYD6Q&M~<-VIf%%!C(-JU4>KpVshgcLC}%?@5ZeXU%ZZxt;R`5iMa`IgO3
zB(bQRKR_Ss{Pz7pA~-W_p`==B&fdOe-$g%Cm8Bka^Q=w52hyc}AQkv@#x;uNOSNQE
z^?s$uL9f%p3eJ1h>e2%;=AsK8X#?ZKPaS-l3^@uFmiRRp!$0pPT|aq^Mm<1twcuR@nUAj?N@127K0D6P9#!urrn3y`427Twf#3
zzj_&SbpIYZb3i8@6EJckjthGRfpQ5EGokonI
z!kxtkL#&o~lHc1%bAHI-I6*5a;o1x^TkQ1qYRFepC33J^Qf4S)2wVLg8JQ5lDxt$;
zc8K9JFt)bp>F4I7&y0QYRe{m;rQ;86-{-{je%=b(xQ^}K&I4W+$FK8ShNm986n>wN
zGxxB*;gNeLJN!9AjJ{mepX)6G*qt>cu0+RL?(Z8V0K`n9YK{%AwWX97&rF9MPP4y4
z4KBJ->V-4a+UoN<_o_Pf$?>Xnd)VDG={)S9BI;Bqvj9GM%*b=4&yeq?G4AJnM^|k9
zJf}0(JZr*X=EBN#kM_OfOJ^k{G+QX!{)mYS2aDW=)K4>XR*i&BkMv)nbCrKT=(scf
z%?~9pQJe9PWaS@0V_!ri!?oI2NgCbO_1!0w);@Q={vtJW_Fy8x8;bqL_rWD0Y0avy
zH@)7vGcR8qru=%IuD04b+3f}QHBE{=syUnd@k*jm9lHG6gN0%=cz9RgWpp69z@m%K%HWFZy@OTTFHf
zw#O0;a0%~F8SpuK`Hp}r{nf}g`@u#a%}m7lqAgb7+}n;6RW+hSx$>;zr|I8TOck9y
z*O>nNDlpQkrR!FDIsE9Xg+cqez|&LrY_9eAE*}4osP^ovQzAL=?Yl$2jdu9GVBJ!M
zUii-UZafAg+V59KI@O7fOI*9O06IB8my6FxI=3uRNG-cnq=#r4Iav>Ot_QXz68d9=
zn}D?PwEj1%VvW~I%d_j$lG*VSbJfFp7Y{vs{xbj0#5ZYRQ+`>$nY7NWd!mqv)+{^a
zWz_}IaGMzcmXGBYi-#N%0dYL#?$(vh-<$Td6rjnDIp>)ADP=~etnZ_qwHKWdF#s8#
zEwaPcPh^`KGWHgl@XmD{+qtmJBX}^GvYM1aRsB6MB=)E^Qz$@?6oh-($>1$8@
zBX7~^{wg|ElW61Zr{2zMM)zhn#{vBdM#ppKeOh{|miw{?wLuDTO
z8N0e&0e-w0SALvw+Piip&+3f&c4DpL>rU$5S@I_qo-A2Y7_tJfa|IVln@xlwjQIBW
zoVxfXE1a2F7dum@E}52L@Zs<|@N_WtbSnQNCXX52qC)?%YecN&QRsW8AI(Izah;(7
zreMmH&H3rP;tS1_PfE~&9p4u+*VnH5r(oc2{-~XBGlFdZepw0mpUwh>TQrm)+aa
zSBP%VI(sJE3Y1^;5eOOqha^gp&J$XpFhZ&j!jZ#Sia~6gfLq4Lp
zt@;eKjeVh%VHxHi>(Q4Sln>>{=@*@Z@o1}ro_jv`k_@wrx#UG(y|R6F4ZPBq$<(QL
zKl6RS2-Iq~*dI7m{mks<8x{S2+IA-1x1;3TsTM
z38Vld0Fw}N4&K}VjRzTs*&!1$hjk#$K`cD54Y|