Retrieve data for doing cancer calling evaluation using synthetic dataset 3

cancer-dream-syn3-getdata.sh

#!/bin/bash

set -eu -o pipefail

# Retrieve data for doing cancer calling evaluation using synthetic dataset 3
# from the ICGC-TCGA DREAM challenge:
# https://www.synapse.org/#!Synapse:syn312572/wiki/62018

# ==============================
# Exome only data
# ------------------------------

curl -sSO https://s3.amazonaws.com/bcbio_nextgen/dream/synthetic_challenge_set3_normal_NGv3_1.fq.gz
curl -sSO https://s3.amazonaws.com/bcbio_nextgen/dream/synthetic_challenge_set3_normal_NGv3_2.fq.gz

curl -sSO https://s3.amazonaws.com/bcbio_nextgen/dream/synthetic_challenge_set3_tumor_NGv3_1.fq.gz
curl -sSO https://s3.amazonaws.com/bcbio_nextgen/dream/synthetic_challenge_set3_tumor_NGv3_2.fq.gz

# ==============================
# Evaluation data and BED files
# ------------------------------

TUMOR_20PCTMASKED_TRUTH="synthetic_challenge_set3_tumor_20pctmasked_truth.tar.gz"

curl -sSO https://s3.amazonaws.com/bcbio_nextgen/dream/"$TUMOR_20PCTMASKED_TRUTH"
tar -xzvpf "$TUMOR_20PCTMASKED_TRUTH"

curl -sSO https://s3.amazonaws.com/bcbio_nextgen/dream/refseq-merged.bed.gz
curl -sSO https://s3.amazonaws.com/bcbio_nextgen/NGv3.bed.gz

gunzip *.bed.gz