REFERENCES.txt

# Instructions on how to install references for GRCh38

# Install GSUTIL to download references
# You need to create .boto config with gsutil config and then disable integrity check by setting this line check_hashes = if_fast_else_skip
pip install gsutil

cd ~/shared
# Download references for GRCh38 and build STAR index
mkdir -p GRCh38
cd GRCh38
gsutil -m cp -r gs://gcp-public-data--broad-references/hg38/v0/Homo_sapiens_assembly38.fasta* .
gsutil -m cp -r gs://gcp-public-data--broad-references/hg38/v0/Homo_sapiens_assembly38.dict .
gsutil -m cp -r gs://gcp-public-data--broad-references/hg38/v0/Mills_and_1000G_gold_standard.indels.hg38.vcf.gz* .
gsutil -m cp -r gs://gcp-public-data--broad-references/hg38/v0/1000G_phase1.snps.high_confidence.hg38.vcf.gz* .
gsutil -m cp -r gs://gcp-public-data--broad-references/hg38/v0/Homo_sapiens_assembly38.dbsnp138.vcf* .
gsutil -m cp -r gs://gatk-best-practices/somatic-hg38/1000g_pon.hg38.vcf.gz* .
gsutil -m cp -r gs://gatk-best-practices/somatic-hg38/af-only-gnomad.hg38.vcf.gz* .
wget ftp://ftp.ebi.ac.uk/pub/databases/gencode/Gencode_human/release_34/gencode.v34.primary_assembly.annotation.gtf.gz
gunzip gencode.v34.primary_assembly.annotation.gtf.gz
mkdir -p STARIndex
STAR --runMode genomeGenerate --runThreadN 20 --genomeDir STARIndex \
  --genomeFastaFiles Homo_sapiens_assembly38.fasta \
  --sjdbGTFfile gencode.v34.primary_assembly.annotation.gtf