Skip to content
Variant Calling Test Run

Adding GitHub Action for Variant Calling Test Run #14

Sign in to view logs

Adding GitHub Action for Variant Calling Test Run

Adding GitHub Action for Variant Calling Test Run #14

Workflow file for this run

.github/workflows/variant-calling-test-run.yml at 7009dee
name: Variant Calling Test Run
on:
pull_request:
paths:
- 'variantCalling/variantCalling.wdl'
- '.github/workflows/variant-calling-test-run.yml'
jobs:
test:
runs-on: ubuntu-latest
steps:
- uses: actions/checkout@v4
- name: Install required tools
run: |
# Install system packages
sudo apt-get update
sudo apt-get install -y wget curl unzip default-jre samtools bwa tabix
# Download and install GATK
wget https://github.com/broadinstitute/gatk/releases/download/4.4.0.0/gatk-4.4.0.0.zip
unzip gatk-4.4.0.0.zip
# Make gatk executable available
sudo ln -s $PWD/gatk-4.4.0.0/gatk /usr/local/bin/gatk
- name: Install Cromwell
run: |
wget https://github.com/broadinstitute/cromwell/releases/download/86/cromwell-86.jar
mv cromwell-86.jar cromwell.jar
- name: Setup Test Data
run: |
mkdir -p test/data
cd test/data
# Download reference chromosome 20 from NCBI
wget ftp://ftp.ncbi.nlm.nih.gov/genomes/archive/old_genbank/Eukaryotes/vertebrates_mammals/Homo_sapiens/GRCh38/Primary_Assembly/assembled_chromosomes/FASTA/chr20.fa.gz
gunzip chr20.fa.gz
# Add "chr" prefix to sequence name
sed 's/^>20/>chr20/' chr20.fa > ref.fasta
rm chr20.fa
# Create sequence dictionary and index
samtools faidx ref.fasta
gatk CreateSequenceDictionary -R ref.fasta -O ref.fasta.dict
# Generate BWA indexes
bwa index ref.fasta
# Create a minimal synthetic dbSNP VCF for testing
# Write header lines
echo '##fileformat=VCFv4.2' > dbsnp.vcf
echo '##reference=GRCh38' >> dbsnp.vcf
echo '##INFO=<ID=RS,Number=1,Type=Integer,Description="dbSNP ID">' >> dbsnp.vcf
echo "##contig=<ID=chr20,length=$(grep "^chr20" ref.fasta.fai | cut -f2)>" >> dbsnp.vcf
# Write tab-separated header line using printf
printf "#CHROM\tPOS\tID\tREF\tALT\tQUAL\tFILTER\tINFO\n" >> dbsnp.vcf
# Write variants
printf "chr20\t1000100\trs1234567\tA\tG\t.\tPASS\tRS=1234567\n" >> dbsnp.vcf
printf "chr20\t1000200\trs2345678\tT\tC\t.\tPASS\tRS=2345678\n" >> dbsnp.vcf
printf "chr20\t1000300\trs3456789\tG\tA\t.\tPASS\tRS=3456789\n" >> dbsnp.vcf
printf "chr20\t1000400\trs4567890\tC\tT\t.\tPASS\tRS=4567890\n" >> dbsnp.vcf
printf "chr20\t1000500\trs5678901\tAG\tA\t.\tPASS\tRS=5678901\n" >> dbsnp.vcf
gatk IndexFeatureFile -I dbsnp.vcf
# Create synthetic Mills and 1000G indels VCF
# Write header lines
echo '##fileformat=VCFv4.2' > mills_1000G.vcf
echo '##reference=GRCh38' >> mills_1000G.vcf
echo '##INFO=<ID=TYPE,Number=1,Type=String,Description="Type of variant">' >> mills_1000G.vcf
echo '##INFO=<ID=SOURCE,Number=1,Type=String,Description="Source of variant">' >> mills_1000G.vcf
echo "##contig=<ID=chr20,length=$(grep "^chr20" ref.fasta.fai | cut -f2)>" >> mills_1000G.vcf
# Write tab-separated header line
printf "#CHROM\tPOS\tID\tREF\tALT\tQUAL\tFILTER\tINFO\n" >> mills_1000G.vcf
# Write variants
printf "chr20\t1000150\tMILL1\tAT\tA\t.\tPASS\tTYPE=deletion;SOURCE=MILLS\n" >> mills_1000G.vcf
printf "chr20\t1000250\tMILL2\tG\tGTT\t.\tPASS\tTYPE=insertion;SOURCE=MILLS\n" >> mills_1000G.vcf
printf "chr20\t1000350\tG1000_1\tCTA\tC\t.\tPASS\tTYPE=deletion;SOURCE=1000G\n" >> mills_1000G.vcf
printf "chr20\t1000450\tG1000_2\tT\tTAGC\t.\tPASS\tTYPE=insertion;SOURCE=1000G\n" >> mills_1000G.vcf
bgzip mills_1000G.vcf
tabix -p vcf mills_1000G.vcf.gz
# Create synthetic known indels VCF
# Write header lines
echo '##fileformat=VCFv4.2' > known_indels.vcf
echo '##reference=GRCh38' >> known_indels.vcf
echo '##INFO=<ID=TYPE,Number=1,Type=String,Description="Type of variant">' >> known_indels.vcf
echo "##contig=<ID=chr20,length=$(grep "^chr20" ref.fasta.fai | cut -f2)>" >> known_indels.vcf
# Write tab-separated header line
printf "#CHROM\tPOS\tID\tREF\tALT\tQUAL\tFILTER\tINFO\n" >> known_indels.vcf
# Write variants
printf "chr20\t1000550\tindel1\tAT\tA\t.\tPASS\tTYPE=deletion\n" >> known_indels.vcf
printf "chr20\t1000650\tindel2\tG\tGTT\t.\tPASS\tTYPE=insertion\n" >> known_indels.vcf
printf "chr20\t1000750\tindel3\tCTA\tC\t.\tPASS\tTYPE=deletion\n" >> known_indels.vcf
bgzip known_indels.vcf
tabix -p vcf known_indels.vcf.gz
# Create minimal test region
echo -e "chr20\t1000000\t1100000" > test.bed
# Create test JSON with all reference files
cat << EOF > ../test-inputs.json
{
"PanelBwaGatk4Annovar.sample_batch": [
{
"sample_name": "test_sample",
"bam_file": "test/data/test.unmapped.bam",
"bed_file": "test/data/test.bed"
}
],
"PanelBwaGatk4Annovar.reference_genome": {
"ref_name": "hg38",
"ref_fasta": "test/data/ref.fasta",
"ref_fasta_index": "test/data/ref.fasta.fai",
"ref_dict": "test/data/ref.fasta.dict",
"ref_pac": "test/data/ref.fasta.pac",
"ref_sa": "test/data/ref.fasta.sa",
"ref_amb": "test/data/ref.fasta.amb",
"ref_ann": "test/data/ref.fasta.ann",
"ref_bwt": "test/data/ref.fasta.bwt",
"dbSNP_vcf": "test/data/dbsnp.vcf",
"dbSNP_vcf_index": "test/data/dbsnp.vcf.idx",
"known_indels_sites_VCFs": [
"test/data/mills_1000G.vcf.gz",
"test/data/known_indels.vcf.gz"
],
"known_indels_sites_indices": [
"test/data/mills_1000G.vcf.gz.tbi",
"test/data/known_indels.vcf.gz.tbi"
],
"annovar_protocols": "refGene",
"annovar_operation": "g"
}
}
EOF
- name: Generate test BAM
run: |
samtools view -b -o test/data/test.unmapped.bam \
<(echo -e "@RG\tID:test\tSM:test_sample\tPL:ILLUMINA\n@SQ\tSN:chr20\tLN:63025520\nread1\t4\t*\t0\t0\t*\t*\t0\t0\tACTG\tFFFF\tRG:Z:test")
- name: Run test workflow
run: |
java -jar cromwell.jar run variantCalling/variantCalling.wdl -i test/test-inputs.json
- name: Check outputs
run: |
# Basic output existence checks
test -f $(find cromwell-executions -name "*.recal.bam")
test -f $(find cromwell-executions -name "*.GATK.vcf")
test -f $(find cromwell-executions -name "*_multianno.txt")