Upload New File

Variant_calling/MergeByChromosome/05.merged_H_surjet_genouest_bychrom.5.sh

+#!/bin/bash
+#SBATCH --mem=40G
+#SBATCH -c 8
+#SBATCH --partition=dgimi-eha
+
+# Load necessary modules
+module load JDK/jdk.8_x64
+
+# Navigate to the working directory
+cd /lustre/durandk/HELICOVERPA/ref_HZEA
+#BUILD REF GENOME
+
+#/nfs/work/faw_adaptation/programs/gatk-4.1.2.0/gatk CreateSequenceDictionary  -R=NC_061456.1.chromosome.5.fna  -O=NC_061456.1.chromosome.5.dict
+#/nfs/work/faw_adaptation/programs/bowtie2-2.3.4.1-linux-x86_64/bowtie2-build /lustre/durandk/HELICOVERPA/ref_HZEA/NC_061456.1.chromosome.5.fna /lustre/durandk/HELICOVERPA/ref_HZEA/NC_061456.1.chromosome.5
+#/storage/simple/projects/faw_adaptation/programs/samtools-1.9/samtools faidx /lustre/durandk/HELICOVERPA/ref_HZEA/NC_061456.1.chromosome.5.fna
+
+cd /lustre/durandk/HELICOVERPA/ref_HZEA/VARIANT_CALLING/
+
+#while read line
+#do  /nfs/work/faw_adaptation/programs/gatk-4.1.2.0/gatk SelectVariants  -R /lustre/durandk/HELICOVERPA/ref_HZEA/NC_061456.1.chromosome.5.fna   -V $line.g.vcf.gz  -O $line.chromosome.5.g.vcf.gz --select "CHROM == 'NC_061456.1'"
+#done <95liste.txt
+# Step 1:  The following command combines multiple GVCF files into a single file using GATK CombineGVCFs tool.
+
+/nfs/work/faw_adaptation/programs/gatk-4.1.2.0/gatk CombineGVCFs -R /lustre/durandk/HELICOVERPA/ref_HZEA/NC_061456.1.chromosome.5.fna -O merged.Surjeet_95_HA.chromosome.5.g.vcf.gz --variant  SRR24497453.chromosome.5.g.vcf.gz --variant  SRR24497454.chromosome.5.g.vcf.gz --variant  SRR24497455.chromosome.5.g.vcf.gz --variant  SRR24497456.chromosome.5.g.vcf.gz --variant  SRR24497457.chromosome.5.g.vcf.gz --variant  SRR24497458.chromosome.5.g.vcf.gz --variant  SRR24497459.chromosome.5.g.vcf.gz --variant  SRR24497460.chromosome.5.g.vcf.gz --variant  SRR24497461.chromosome.5.g.vcf.gz --variant  SRR24497462.chromosome.5.g.vcf.gz --variant  SRR24497463.chromosome.5.g.vcf.gz --variant  SRR24497464.chromosome.5.g.vcf.gz --variant  SRR24497465.chromosome.5.g.vcf.gz --variant  SRR24497466.chromosome.5.g.vcf.gz --variant  SRR24497467.chromosome.5.g.vcf.gz --variant  SRR24497468.chromosome.5.g.vcf.gz --variant  SRR24497469.chromosome.5.g.vcf.gz --variant  SRR24497470.chromosome.5.g.vcf.gz --variant  SRR24497471.chromosome.5.g.vcf.gz --variant  SRR24497472.chromosome.5.g.vcf.gz --variant  SRR24497473.chromosome.5.g.vcf.gz --variant  SRR24497474.chromosome.5.g.vcf.gz --variant  SRR24497475.chromosome.5.g.vcf.gz --variant  SRR24497476.chromosome.5.g.vcf.gz --variant  SRR24497477.chromosome.5.g.vcf.gz --variant  SRR24497478.chromosome.5.g.vcf.gz --variant  SRR24497479.chromosome.5.g.vcf.gz --variant  SRR24497480.chromosome.5.g.vcf.gz --variant  SRR24497481.chromosome.5.g.vcf.gz --variant  SRR24497482.chromosome.5.g.vcf.gz --variant  SRR24497483.chromosome.5.g.vcf.gz --variant  SRR24497484.chromosome.5.g.vcf.gz --variant  SRR24497485.chromosome.5.g.vcf.gz --variant  SRR24497486.chromosome.5.g.vcf.gz --variant  SRR24497487.chromosome.5.g.vcf.gz --variant  SRR24497488.chromosome.5.g.vcf.gz --variant  SRR24497489.chromosome.5.g.vcf.gz --variant  SRR24497490.chromosome.5.g.vcf.gz --variant  SRR24497491.chromosome.5.g.vcf.gz --variant  SRR24497492.chromosome.5.g.vcf.gz --variant  SRR24497493.chromosome.5.g.vcf.gz --variant  SRR24497494.chromosome.5.g.vcf.gz --variant  SRR24497495.chromosome.5.g.vcf.gz --variant  SRR24497496.chromosome.5.g.vcf.gz --variant  SRR24497497.chromosome.5.g.vcf.gz --variant  SRR24497498.chromosome.5.g.vcf.gz --variant  SRR24497499.chromosome.5.g.vcf.gz --variant  SRR24497500.chromosome.5.g.vcf.gz --variant  SRR24497501.chromosome.5.g.vcf.gz --variant  SRR24497502.chromosome.5.g.vcf.gz --variant  SRR24497503.chromosome.5.g.vcf.gz --variant  SRR24497504.chromosome.5.g.vcf.gz --variant  SRR24497505.chromosome.5.g.vcf.gz --variant  SRR24497506.chromosome.5.g.vcf.gz --variant  SRR24497507.chromosome.5.g.vcf.gz --variant  SRR24497508.chromosome.5.g.vcf.gz --variant  SRR24497509.chromosome.5.g.vcf.gz --variant  SRR24497510.chromosome.5.g.vcf.gz --variant  SRR24497511.chromosome.5.g.vcf.gz --variant  SRR24497512.chromosome.5.g.vcf.gz --variant  SRR24497513.chromosome.5.g.vcf.gz --variant  SRR24497514.chromosome.5.g.vcf.gz --variant  SRR24497515.chromosome.5.g.vcf.gz --variant  SRR24497516.chromosome.5.g.vcf.gz --variant  SRR24497517.chromosome.5.g.vcf.gz --variant  SRR24497518.chromosome.5.g.vcf.gz --variant  SRR24497519.chromosome.5.g.vcf.gz --variant  SRR24497520.chromosome.5.g.vcf.gz --variant  SRR24497521.chromosome.5.g.vcf.gz --variant  SRR24497522.chromosome.5.g.vcf.gz --variant  SRR24497523.chromosome.5.g.vcf.gz --variant  SRR24497524.chromosome.5.g.vcf.gz --variant  SRR24497525.chromosome.5.g.vcf.gz --variant  SRR24497526.chromosome.5.g.vcf.gz --variant  SRR24497527.chromosome.5.g.vcf.gz --variant  SRR24497528.chromosome.5.g.vcf.gz --variant  SRR24497529.chromosome.5.g.vcf.gz --variant  SRR24497530.chromosome.5.g.vcf.gz --variant  SRR24497531.chromosome.5.g.vcf.gz --variant  SRR24497532.chromosome.5.g.vcf.gz --variant  SRR24497533.chromosome.5.g.vcf.gz --variant  SRR24497534.chromosome.5.g.vcf.gz --variant  SRR24497535.chromosome.5.g.vcf.gz --variant  SRR24497536.chromosome.5.g.vcf.gz --variant  SRR24497537.chromosome.5.g.vcf.gz --variant  SRR24497538.chromosome.5.g.vcf.gz --variant  SRR24497539.chromosome.5.g.vcf.gz --variant  SRR24497540.chromosome.5.g.vcf.gz --variant  SRR24497541.chromosome.5.g.vcf.gz --variant  SRR24497542.chromosome.5.g.vcf.gz --variant  SRR24497543.chromosome.5.g.vcf.gz --variant  SRR24497544.chromosome.5.g.vcf.gz --variant  SRR24497545.chromosome.5.g.vcf.gz --variant  SRR24497546.chromosome.5.g.vcf.gz --variant  SRR24497547.chromosome.5.g.vcf.gz 
+
+# Step 2: The following command performs variant calling using GATK GenotypeGVCFs tool on the merged GVCF file.
+
+/storage/simple/projects/faw_adaptation/programs/gatk-4.1.2.0/gatk GenotypeGVCFs -R /lustre/durandk/HELICOVERPA/ref_HZEA/NC_061456.1.chromosome.5.fna --variant merged.Surjeet_95_HA.chromosome.5.g.vcf.gz -O merged.Surjeet_95_HA.chromosome.5.vcf3.vcf.gz -all-sites
+
+# Step 3:  The following command selects only SNP variants from the genotyped VCF file.
+
+/storage/simple/projects/faw_adaptation/programs/gatk-4.1.2.0/gatk SelectVariants -select-type SNP -R /lustre/durandk/HELICOVERPA/ref_HZEA/NC_061456.1.chromosome.5.fna -V merged.Surjeet_95_HA.chromosome.5.vcf3.vcf.gz -O merged.Surjeet_95_HA.chromosome.5.SNP.vcf.gz
+
+# Step 4: The following command annotates SNPs based on certain filtering criteria using GATK VariantFiltration tool.
+
+/storage/simple/projects/faw_adaptation/programs/gatk-4.1.2.0/gatk VariantFiltration -R /lustre/durandk/HELICOVERPA/ref_HZEA/NC_061456.1.chromosome.5.fna -V merged.Surjeet_95_HA.chromosome.5.SNP.vcf.gz --filter-expression "QD < 2.0 || FS > 60.0 || MQ < 40.0 || MQRankSum < -12.5 || ReadPosRankSum < -8.0" --filter-name "my_snp_filter" -O merged.Surjeet_95_HA.chromosome.5.SNP.annotated.vcf.gz
+
+# Step 5: The following command filters out the SNPs that do not pass the specified criteria.
+
+
+zcat merged.Surjeet_95_HA.chromosome.5.SNP.annotated.vcf.gz | grep -P '#|PASS' | /storage/simple/projects/faw_adaptation/programs/vcftools_0.1.13/bin/vcftools --vcf - --out merged.Surjeet_95_HA.chromosome.5.SNP --recode
+
+
+# Step 6:  The following command compresses the filtered VCF file.
+
+/storage/simple/projects/faw_adaptation/programs/htslib-1.9/bgzip merged.Surjeet_95_HA.chromosome.5.SNP.recode.vcf
+
+# Step 7: The following command indexes the compressed VCF file.
+
+/storage/simple/projects/faw_adaptation/programs/htslib-1.9/tabix -p vcf merged.Surjeet_95_HA.chromosome.5.SNP.recode.vcf.gz
+
+  
+
+
+