#!/bin/bash
echo 'This is to run VEP version 93 cache 94 GRCh37'
# Program path
VEP_path=/mnt/bigHDD/resource/ref_and_tools/tools/ensembl-vep/vep
dir_cache=/mnt/bigHDD/resource/ref_and_tools/tools/ensembl-vep/caches/homo_sapiens_merged
fasta_file=/mnt/bigHDD/resource/ref_and_tools/reference/human/ensembl/GRCh37.75/Homo_sapiens.GRCh37.75.dna.primary_assembly.fa
# Get current directory's VCF files
ls | grep .vcf > input_VCF.file.list.txt
echo 'Input VCF file list created (input_VCF.file.list.txt)'
# Create output directory
mkdir VEP_ver93_cache94_GRCh37_result
outdir='/VEP_ver93_cache94_GRCh37_result/'
echo 'Output direcory created (VEP_ver93_cache94_GRCh37_result)'
# Get current directory path and output directory
input_path=$(pwd)
output_path=$input_path$outdir
output_file='_VEP.ver93.cache94.grch37.txt'
# Conducting VEP programm
for x in $(cat input_VCF.file.list.txt)
do
echo $x
output_file_name=$output_path$x$output_file
$VEP_path --no_stats --offline --tab --verbose --protein --symbol --uniprot \
--canonical --sift b --polyphen b \
--cache --cache_version 94 --dir_cache $dir_cache \
-i $x \
-o $output_file_name \
--fasta $fasta_file
#echo $output_file_name
done
'Bioinformatics(생정보학)' 카테고리의 다른 글
TCGA somatic maf files (0) | 2018.12.03 |
---|---|
VEP variant location (0) | 2018.11.22 |
Cancer subclone calculation (0) | 2018.10.02 |
protein localization관련 db (0) | 2018.06.22 |
RNAseq cufflinks로 나온 genes.fpkm_tracking파일 합치기 (0) | 2018.05.21 |