From f47530c158578807bf8b229d8c193bf199e2152b Mon Sep 17 00:00:00 2001
From: Tim O'Donnell <timodonnell@gmail.com>
Date: Tue, 1 Oct 2019 17:40:07 -0400
Subject: [PATCH] fix
---
.../GENERATE.WITH_HPC_CLUSTER.sh | 34 ++++++++++++++++---
1 file changed, 30 insertions(+), 4 deletions(-)
diff --git a/downloads-generation/data_mass_spec_benchmark/GENERATE.WITH_HPC_CLUSTER.sh b/downloads-generation/data_mass_spec_benchmark/GENERATE.WITH_HPC_CLUSTER.sh
index d1fe18a9..1c5c098e 100755
--- a/downloads-generation/data_mass_spec_benchmark/GENERATE.WITH_HPC_CLUSTER.sh
+++ b/downloads-generation/data_mass_spec_benchmark/GENERATE.WITH_HPC_CLUSTER.sh
@@ -32,16 +32,16 @@ cp $SCRIPT_DIR/write_allele_list.py .
PEPTIDES=$(mhcflurry-downloads path data_mass_spec_annotated)/annotated_ms.csv.bz2
REFERENCES_DIR=$(mhcflurry-downloads path data_references)
+python write_allele_list.py "$PEPTIDES" --out alleles.txt
+mkdir predictions
+
+# First just chr1 peptides
python write_proteome_peptides.py \
"$PEPTIDES" \
"${REFERENCES_DIR}/uniprot_proteins.csv.bz2" \
--chromosome 1 \
--out proteome_peptides.chr1.csv
-python write_allele_list.py "$PEPTIDES" --out alleles.txt
-
-mkdir predictions
-
for kind in with_mass_spec no_mass_spec
do
python run_mhcflurry.py \
@@ -60,7 +60,33 @@ do
--cluster-script-prefix-path $SCRIPT_DIR/cluster_submit_script_header.mssm_hpc.lsf
done
+# Now all peptides
+python write_proteome_peptides.py \
+ "$PEPTIDES" \
+ "${REFERENCES_DIR}/uniprot_proteins.csv.bz2" \
+ --out proteome_peptides.all.csv
+
+for kind in with_mass_spec no_mass_spec
+do
+ python run_mhcflurry.py \
+ proteome_peptides.all.csv \
+ --chunk-size 500000 \
+ --batch-size 65536 \
+ --models-dir "$(mhcflurry-downloads path models_class1_pan)/models.$kind" \
+ --allele $(cat alleles.txt) \
+ --out "predictions/all.mhcflurry.$kind" \
+ --verbosity 1 \
+ --worker-log-dir "$SCRATCH_DIR/$DOWNLOAD_NAME" \
+ --cluster-parallelism \
+ --cluster-max-retries 15 \
+ --cluster-submit-command bsub \
+ --cluster-results-workdir ~/mhcflurry-scratch \
+ --cluster-script-prefix-path $SCRIPT_DIR/cluster_submit_script_header.mssm_hpc.lsf
+done
+
+
bzip2 proteome_peptides.chr1.csv
+bzip2 proteome_peptides.all.csv
cp $SCRIPT_ABSOLUTE_PATH .
bzip2 LOG.txt
--
GitLab