RUN.txt

# You may want to add these to your .bashrc or .bash_profile
export STRELKA_PATH="~/shared/strelka"
export GATK3_PATH="~/shared/gatk3.8.jar"

conda activate hla

dna_pipeline.py \
  --genome ~/shared/GRCh38/Homo_sapiens_assembly38.fasta \
  --sample G001 \
  --outdir outtumor \
  --known1 ~/shared/GRCh38/Mills_and_1000G_gold_standard.indels.hg38.vcf.gz \
  --known2 ~/shared/GRCh38/1000G_phase1.snps.high_confidence.hg38.vcf.gz \
  --snpsites ~/shared/GRCh38/Homo_sapiens_assembly38.dbsnp138.vcf \
  --germline ~/shared/GRCh38/af-only-gnomad.hg38.vcf.gz \
  --pon ~/shared/GRCh38/1000g_pon.hg38.vcf.gz \
  --threads 20 \
  --vep-db GRCh38 \
  --vep-version 102 \
  --hla-fasta ~/shared/hla_reference/hla_reference_dna.fasta \
  NormalR1.fastq.gz NormalR2.fastq.gz \
  TumorR1.fastq.gz TumorR2.fastq.gz
  
rna_pipeline.py \
  --genome ~/shared/GRCh38/Homo_sapiens_assembly38.fasta \
  --genome-star ~/shared/GRCh38/STARIndex \
  --genome-ref ~/shared/GRCh38/gencode.v34.primary_assembly.annotation.gtf \
  --sample G001 \
  --outdir outrna \
  --known1 ~/shared/GRCh38/Mills_and_1000G_gold_standard.indels.hg38.vcf.gz \
  --known2 ~/shared/GRCh38/1000G_phase1.snps.high_confidence.hg38.vcf.gz \
  --snpsites ~/shared/GRCh38/Homo_sapiens_assembly38.dbsnp138.vcf \
  --threads 20 \
  --vep-db GRCh38 \
  --vep-version 102 \
  --hla-fasta ~/shared/hla_reference/hla_reference_rna.fasta \
  RNAR1.fastq.gz RNAR2.fastq.gz
  
merge_results.py \
  --dna outtumor/annotated.hg38_multianno.vcf \
  --dna-names Tumor
  --rna outrna/annotated.hg38_multianno.vcf \
  --rna-names RNA
  --rna-counts outrna/gene.counts' \
  --ensembl-version 102

mhc_predict.py \
  --hla outtumor/Tumor_hla_genotype.tsv outrna/hla_genotype.tsv \
  --variants overlap_final.txt \
  --alleles ~/shared/alleles.txt