make-star-reference-genome.sh

# Requires the STAR executable to be at:
#     /pipeline/packages/star
#

# Overhang is set to the read length (template cycles) of 142 - 1:
#
OVERHANG=141

git clone \
    https://github.com/dpryan79/ChromosomeMappings.git \
    ~/git/ChromosomeMappings

cvbio FetchEnsemblGtf \
    --release 96 \
    --build 38 \
    --species "Homo sapiens" \
    --out Homo_sapiens.GRCh38.96.gtf

cvbio UpdateDataContigNames \
    -i Homo_sapiens.GRCh38.96.gtf \
    -o Homo_sapiens.GRCh38.96.ucsc-named.gtf \
    -m ~/git/ChromosomeMappings/GRCh38_ensembl2UCSC.txt \
    --comment-chars '#' \
    --columns 0 \
    --skip-missing false

cvbio-pipelines PrepareStarReferenceData \
    -i /pipeline/reference-data/references/hs38DH/hs38DH.fa \
    -g Homo_sapiens.GRCh38.96.ucsc-named.gtf \
    -o hs38DH-"${OVERHANG}"n-"$(/pipeline/packages/star --version)" \
    --overhang "${OVERHANG}" \
    --threads "$(nproc)" \
    > execution-report.txt \
    2> pipeline.log