#下载依赖包
sudo apt-get install -y curl rsync tar make perl perl-base tabix
#设置perl环境变量
export PERL_PATH=~/perl5
#在perl安装依赖包
curl -L http://cpanmin.us | perl - --notest -l $PERL_PATH LWP::Simple LWP::Protocol::https Archive::Extract Archive::Tar Archive::Zip CGI DBI Time::HiRes
export PERL5LIB=$PERL_PATH/lib/perl5:$PERL_PATH/lib/perl5/x86_64-linux
#新建vep安装目录
export VEP_PATH=~/vep
export VEP_DATA=~/.vep
#下载vep
mkdir $VEP_PATH $VEP_DATA; cd $VEP_PATH
curl -LO https://github.com/Ensembl/ensembl-tools/archive/release/84.tar.gz
tar -zxf 84.tar.gz --starting-file variant_effect_predictor --transform=‘s|.*/|./|g‘
#设置环境变量
export PERL5LIB=$VEP_PATH:$PERL5LIB
export PATH=$VEP_PATH/htslib:$PATH
#下载注释包
rsync -zvh rsync://ftp.ensembl.org/ensembl/pub/release-84/variation/VEP/homo_sapiens_vep_84_GRCh{37,38}.tar.gz $VEP_DATA
rsync -zvh rsync://ftp.ensembl.org/ensembl/pub/release-84/variation/VEP/mus_musculus_vep_84_GRCm38.tar.gz $VEP_DATA
cat $VEP_DATA/*_vep_84_GRC{h37,h38,m38}.tar.gz | tar -izxf - -C $VEP_DATA
#安装 Ensembl API, the reference FASTAs
perl convert_cache.pl --species homo_sapiens --version 84_GRCh37,84_GRCh38 --dir $VEP_DATA --force_overwrite to overwrite
perl convert_cache.pl --species mus_musculus --version 84_GRCm38 --dir $VEP_DATA
#下载 ExAC r0.3 VCF，因为是google链接，可能不能下载，需要在其他网页下载
curl -L https://googledrive.com/host/0B6o74flPT8FAYnBJTk9aTF9WVnM > $VEP_DATA/ExAC.r0.3.sites.minus_somatic.vcf.gz
tabix -p vcf $VEP_DATA/ExAC.r0.3.sites.minus_somatic.vcf.gz
#安装完成，测试
perl variant_effect_predictor.pl --species homo_sapiens --assembly GRCh37 --offline --no_progress --everything --shift_hgvs 1 --check_existing --check_alleles --total_length --allele_number --no_escape --xref_refseq --dir $VEP_DATA --fasta $VEP_DATA/homo_sapiens/84_GRCh37/Homo_sapiens.GRCh37.75.dna.primary_assembly.fa.gz --plugin ExAC,$VEP_DATA/ExAC.r0.3.sites.minus_somatic.vcf.gz --input_file example_GRCh37.vcf --output_file example_GRCh37.vep.txt
#可以看到下列文件，即注释成功。
- Read existing cache info
- Loaded plugin: ExAC
- Starting...
- Detected format of input file as vcf
- Read 173 variants into buffer
- Checking for existing variations
- Reading transcript data from cache and/or database
- Retrieved 3097 transcripts (0 mem, 3162 cached, 0 DB, 65 duplicates)
- Reading regulatory data from cache and/or database
- Retrieved 14876 regulatory features (0 mem, 14877 cached, 0 DB, 1 duplicates)
- Analyzing chromosome 21
- Analyzing variants
- Analyzing RegulatoryFeatures
- Analyzing MotifFeatures
- Calculating consequences
- Analyzing chromosome 22
- Analyzing variants
- Analyzing RegulatoryFeatures
- Analyzing MotifFeatures
- Calculating consequences
- Processed 173 total variants (29 vars/sec, 29 vars/sec total)
- Wrote stats summary to example_GRCh37.vep.txt_summary.html
- Finished!