From 92720e6b988fa3f3b0e2b9a6a8916a7b78a4a714 Mon Sep 17 00:00:00 2001
From: Tim O'Donnell <timodonnell@gmail.com>
Date: Wed, 9 Oct 2019 12:36:55 -0400
Subject: [PATCH] Add data_expression download
---
.../data_expression/GENERATE.sh | 57 +++++++++++++++++++
mhcflurry/downloads.yml | 4 ++
2 files changed, 61 insertions(+)
create mode 100755 downloads-generation/data_expression/GENERATE.sh
diff --git a/downloads-generation/data_expression/GENERATE.sh b/downloads-generation/data_expression/GENERATE.sh
new file mode 100755
index 00000000..c780b42f
--- /dev/null
+++ b/downloads-generation/data_expression/GENERATE.sh
@@ -0,0 +1,57 @@
+#!/bin/bash
+#
+# Download published gene expression data corresponding to some of our mass
+# spec datasets.
+#
+#
+set -e
+set -x
+
+DOWNLOAD_NAME=data_expression
+SCRATCH_DIR=${TMPDIR-/tmp}/mhcflurry-downloads-generation
+SCRIPT_ABSOLUTE_PATH="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)/$(basename "${BASH_SOURCE[0]}")"
+SCRIPT_DIR=$(dirname "$SCRIPT_ABSOLUTE_PATH")
+
+mkdir -p "$SCRATCH_DIR"
+rm -rf "$SCRATCH_DIR/$DOWNLOAD_NAME"
+mkdir "$SCRATCH_DIR/$DOWNLOAD_NAME"
+
+# Send stdout and stderr to a logfile included with the archive.
+exec > >(tee -ia "$SCRATCH_DIR/$DOWNLOAD_NAME/LOG.txt")
+exec 2> >(tee -ia "$SCRATCH_DIR/$DOWNLOAD_NAME/LOG.txt" >&2)
+
+date
+
+cd $SCRATCH_DIR/$DOWNLOAD_NAME
+
+# Many cell line sequencing data is available from:
+# Available from SRA [access required] at:
+# https://www.ebi.ac.uk/ega/studies/EGAS00001000610
+
+# CCLE cell lines
+DATASET=ccle
+mkdir $DATASET
+cd $DATASET
+wget -q https://data.broadinstitute.org/ccle/CCLE_RNAseq_rsem_genes_tpm_20180929.txt.gz
+wget -q https://data.broadinstitute.org/ccle/CCLE_miRNA_20181103.gct
+cd ..
+
+# B721.221
+DATASET=b721221
+mkdir $DATASET
+cd $DATASET
+wget -q https://www.ncbi.nlm.nih.gov/geo/download/?acc=GSE93315&format=file
+cd ..
+
+DATASET=pancan-xena
+mkdir $DATASET
+cd $DATASET
+wget -q https://pancanatlas.xenahubs.net/download/probeMap/hugo_gencode_good_hg19_V24lift37_probemap
+wget -q https://pancanatlas.xenahubs.net/download/EB++AdjustPANCAN_IlluminaHiSeq_RNASeqV2.geneExp.xena.gz
+cd ..
+
+cp $SCRIPT_ABSOLUTE_PATH .
+bzip2 LOG.txt
+RESULT="$SCRATCH_DIR/${DOWNLOAD_NAME}.$(date +%Y%m%d).tar.bz2"
+tar -cjf "$RESULT" *
+echo "Created archive: $RESULT"
diff --git a/mhcflurry/downloads.yml b/mhcflurry/downloads.yml
index 76a9360d..4089fb78 100644
--- a/mhcflurry/downloads.yml
+++ b/mhcflurry/downloads.yml
@@ -37,6 +37,10 @@ releases:
url: https://github.com/openvax/mhcflurry/releases/download/pre-1.4.0/data_mass_spec_annotated.20190930.tar.bz2
default: false
+ - name: data_expression
+ url: https://github.com/openvax/mhcflurry/releases/download/1.4.0/data_expression.20191009.tar.bz2
+ default: false
+
- name: data_references
url: https://github.com/openvax/mhcflurry/releases/download/pre-1.4.0/data_references.20190927.tar.bz2
default: false
--
GitLab