#!/usr/bin/bash

#purpose: identify SNV and InDels from paired tumor and normal samples
#set env
work_dir=/home/zhanghl/data_3/workshop/practice1_ovary
reference=/home/zhanghl/supporting_files/Homo_sapiens_glk_v37/human_b37_bundle/human_g1k_v37.fasta  
bwa_dir=/home/zhanghl/supporting_softwares/bwa-0.7.10
picard_dir=/home/zhanghl/supporting_softwares/picard
gatk=/home/zhanghl/supporting_softwares/GenomeAnalysisTK/gatk-4.0.8.1/gatk
cosmic=/home/zhanghl/supporting_files/Homo_sapiens_glk_v37/human_b37_bundle/b37_cosmic_v54_120711.vcf
snp=/home/zhanghl/supporting_files/Homo_sapiens_glk_v37/human_b37_bundle/dbsnp_138.b37.vcf
indel=/home/zhanghl/supporting_files/Homo_sapiens_glk_v37/human_b37_bundle/1000G_phase1.indels.b37.vcf

mutect2_function(){
    local normal_sample_name=$1
    local tumor_sample_name=$2
    local input=$3
    local output=$4
    
     $gatk Mutect2 \
     -R $reference \
     -I  ${input}/${tumor_sample_name}.sorted.dedup.recal.bam \
     -I  ${input}/${normal_sample_name}.sorted.dedup.recal.bam \
     -tumor ${tumor_sample_name} \
     -normal ${normal_sample_name} \
     -O ${output}/${tumor_sample_name}.mutect2.vcf
     
     $gatk FilterMutectCalls -V  ${output}/${tumor_sample_name}.mutect2.vcf -O  ${output}/${tumor_sample_name}.mutect2.filter.vcf
     }

start=$(date +%s)
time mutect2_function \
SRR5141045 \
SRR5141046 \
/input_dir \
/output_dir
end=$(date +%s)
dur=$((end-start))
echo $dur/60