Files
digital-patients/stage_data.nf

87 lines
3.9 KiB
Plaintext

nextflow.enable.dsl=2
process STAGE_DATA {
container 'ubuntu:22.04'
memory '4 GB'
cpus 2
script:
"""
BASE="/omic/eureka/digital-patients"
echo "=== Installing dependencies ==="
apt-get update -qq && apt-get install -y -qq openssh-client sshpass curl > /dev/null 2>&1
echo "=== Cleaning up old _parts directories ==="
find \$BASE -name "*_parts" -type d -exec rm -rf {} + 2>/dev/null || true
echo "Cleanup done"
echo "=== Creating directory structure ==="
mkdir -p \$BASE/imputed \$BASE/healthy \$BASE/supporting-data/vcf \$BASE/supporting-data/ucsc-liftover \$BASE/supporting-data/genome \$BASE/output
echo "=== Current state of PVC ==="
ls -la \$BASE/ 2>/dev/null
download() {
local remote="\$1"
local local_path="\$2"
if [ -f "\$local_path" ]; then
echo "SKIP (exists): \$local_path"
ls -lh "\$local_path"
return
fi
echo "Downloading: \$remote -> \$local_path"
sshpass -p 'bl3rg3r5' scp -o StrictHostKeyChecking=no -o UserKnownHostsFile=/dev/null -P 9100 "omic@nucleus.omic.ai:\$remote" "\$local_path"
ls -lh "\$local_path"
}
echo "=== Downloading imputed files ==="
download "/mnt/Avatar/imputed/ukbb/imputed/F5_SCHIZO.gwas.imputed_v3.both_sexes.tsv.bgz" "\$BASE/imputed/F5_SCHIZO.gwas.imputed_v3.both_sexes.tsv.bgz"
download "/mnt/Avatar/imputed/ukbb/imputed/F5_SCHIZO.gwas.imputed_v3.female.tsv.bgz" "\$BASE/imputed/F5_SCHIZO.gwas.imputed_v3.female.tsv.bgz"
download "/mnt/Avatar/imputed/ukbb/imputed/F5_SCHIZO.gwas.imputed_v3.male.tsv.bgz" "\$BASE/imputed/F5_SCHIZO.gwas.imputed_v3.male.tsv.bgz"
echo "=== Downloading gnomad files ==="
download "/mnt/Avatar/digital_patient/gnomad.genomes.v4.1.sites.female.txt" "\$BASE/healthy/gnomad.genomes.v4.1.sites.female.txt"
download "/mnt/Avatar/digital_patient/gnomad.genomes.v4.1.sites.male.txt" "\$BASE/healthy/gnomad.genomes.v4.1.sites.male.txt"
echo "=== Downloading supporting-data files ==="
download "/mnt/Avatar/dd/synthea/supporting-data/genome/hg38.fa" "\$BASE/supporting-data/genome/hg38.fa"
download "/mnt/Avatar/dd/synthea/supporting-data/genome/hg38.dict" "\$BASE/supporting-data/genome/hg38.dict"
download "/mnt/Avatar/dd/synthea/supporting-data/ucsc-liftover/hg19ToHg38.over.chain.gz" "\$BASE/supporting-data/ucsc-liftover/hg19ToHg38.over.chain.gz"
download "/mnt/Avatar/dd/synthea/supporting-data/vcf/vcf_template.vcf" "\$BASE/supporting-data/vcf/vcf_template.vcf"
echo "=== Downloading phenotype file ==="
download "/mnt/Avatar/imputed/ukbb/metadata/ukbb_phenotypes.csv" "\$BASE/ukbb_phenotypes_filtered.csv"
echo "=== Copying small files from DRS (already on PVC via DRS upload) ==="
# These were uploaded via DRS and should already be on PVC
# If not, they're in the git repo that WES cloned
for f in MANE.GRCh38.v1.3.update.tsv regulon.rda LM22_sourceGEP_ensg.txt; do
if [ ! -f "\$BASE/\$f" ]; then
echo "Small file missing on PVC, checking if available from WES workdir..."
# WES clones the repo, so the file might be in the current workdir's repo
else
echo "SKIP (exists): \$BASE/\$f"
fi
done
echo "=== Final verification ==="
echo "Imputed:"
ls -lh \$BASE/imputed/*.bgz 2>/dev/null || echo " NONE"
echo "Healthy:"
ls -lh \$BASE/healthy/*.txt 2>/dev/null || echo " NONE"
echo "Genome:"
ls -lh \$BASE/supporting-data/genome/* 2>/dev/null || echo " NONE"
echo "Supporting-data:"
ls -lh \$BASE/supporting-data/vcf/* \$BASE/supporting-data/ucsc-liftover/* 2>/dev/null || echo " NONE"
echo "Small files:"
ls -lh \$BASE/MANE* \$BASE/regulon* \$BASE/LM22* \$BASE/ukbb* 2>/dev/null || echo " NONE"
echo "=== STAGING COMPLETE ==="
"""
}
workflow {
STAGE_DATA()
}