Last active
February 27, 2025 06:18
-
-
Save fo40225/f135b50b3e47d0997098264c3d28e590 to your computer and use it in GitHub Desktop.
annovar + intervar
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| wget http://www.openbioinformatics.org/annovar/download/0wgxR2rIVP/annovar.latest.tar.gz | |
| tar axvf annovar.latest.tar.gz | |
| cd annovar | |
| # downadad additional script | |
| wget http://www.openbioinformatics.org/annovar/download/prepare_annovar_user.pl | |
| chmod a+x prepare_annovar_user.pl | |
| wget -O index_annovar.pl https://github.com/WGLab/doc-ANNOVAR/files/6670482/index_annovar.txt | |
| chmod a+x index_annovar.pl | |
| # download hg19 all database | |
| perl annotate_variation.pl --downdb --webfrom annovar --buildver hg19 refGene humandb/ | |
| perl annotate_variation.pl --downdb --webfrom annovar --buildver hg19 refGeneWithVer humandb/ | |
| perl annotate_variation.pl --downdb --webfrom annovar --buildver hg19 ensGene humandb/ | |
| perl annotate_variation.pl --downdb --webfrom annovar --buildver hg19 knownGene humandb/ | |
| perl annotate_variation.pl --downdb --webfrom annovar --buildver hg19 ljb26_all humandb/ | |
| perl annotate_variation.pl --downdb --webfrom annovar --buildver hg19 dbnsfp30a humandb/ | |
| perl annotate_variation.pl --downdb --webfrom annovar --buildver hg19 dbnsfp33a humandb/ | |
| perl annotate_variation.pl --downdb --webfrom annovar --buildver hg19 dbnsfp35a humandb/ | |
| # dbnsfp41a is broken | |
| #perl annotate_variation.pl --downdb --webfrom annovar --buildver hg19 dbnsfp41a humandb/ | |
| perl annotate_variation.pl --downdb --webfrom annovar --buildver hg19 dbnsfp42a humandb/ | |
| perl annotate_variation.pl --downdb --webfrom annovar --buildver hg19 dbnsfp47a humandb/ | |
| perl annotate_variation.pl --downdb --webfrom annovar --buildver hg19 dbscsnv11 humandb/ | |
| perl annotate_variation.pl --downdb --webfrom annovar --buildver hg19 cosmic70 humandb/ | |
| perl annotate_variation.pl --downdb --webfrom annovar --buildver hg19 esp6500siv2_ea humandb/ | |
| perl annotate_variation.pl --downdb --webfrom annovar --buildver hg19 esp6500siv2_aa humandb/ | |
| perl annotate_variation.pl --downdb --webfrom annovar --buildver hg19 esp6500siv2_all humandb/ | |
| perl annotate_variation.pl --downdb --webfrom annovar --buildver hg19 exac03 humandb/ | |
| perl annotate_variation.pl --downdb --webfrom annovar --buildver hg19 exac03nontcga humandb/ | |
| perl annotate_variation.pl --downdb --webfrom annovar --buildver hg19 exac03nonpsych humandb/ | |
| perl annotate_variation.pl --downdb --webfrom annovar --buildver hg19 gene4denovo201907 humandb/ | |
| perl annotate_variation.pl --downdb --webfrom annovar --buildver hg19 gnomad_exome humandb/ | |
| perl annotate_variation.pl --downdb --webfrom annovar --buildver hg19 gnomad_genome humandb/ | |
| perl annotate_variation.pl --downdb --webfrom annovar --buildver hg19 gnomad211_exome humandb/ | |
| perl annotate_variation.pl --downdb --webfrom annovar --buildver hg19 gnomad211_genome humandb/ | |
| # The GnomAD4 database must be generated by manually using GnomAD4 hg38 vcf `picard LiftoverVcf` to hg19 vcf and `bcftools query` to txt. | |
| #perl annotate_variation.pl --downdb --webfrom annovar --buildver hg19 gnomad40_exome humandb/ | |
| #perl annotate_variation.pl --downdb --webfrom annovar --buildver hg19 gnomad40_genome humandb/ | |
| #perl annotate_variation.pl --downdb --webfrom annovar --buildver hg19 gnomad41_exome humandb/ | |
| #perl annotate_variation.pl --downdb --webfrom annovar --buildver hg19 gnomad41_genome humandb/ | |
| perl annotate_variation.pl --downdb --webfrom annovar --buildver hg19 kaviar_20150923 humandb/ | |
| perl annotate_variation.pl --downdb --webfrom annovar --buildver hg19 hrcr1 humandb/ | |
| perl annotate_variation.pl --downdb --webfrom annovar --buildver hg19 1000g2014oct humandb/ | |
| perl annotate_variation.pl --downdb --webfrom annovar --buildver hg19 1000g2015aug humandb/ | |
| perl annotate_variation.pl --downdb --webfrom annovar --buildver hg19 avsnp142 humandb/ | |
| # avsnp144 is broken, https://annovar.openbioinformatics.org/en/latest/articles/dbSNP/#additional-discussions | |
| #perl annotate_variation.pl --downdb --webfrom annovar --buildver hg19 avsnp144 humandb/ | |
| perl annotate_variation.pl --downdb --webfrom annovar --buildver hg19 avsnp147 humandb/ | |
| perl annotate_variation.pl --downdb --webfrom annovar --buildver hg19 avsnp150 humandb/ | |
| perl annotate_variation.pl --downdb --webfrom annovar --buildver hg19 avsnp151 humandb/ | |
| perl annotate_variation.pl --downdb --webfrom annovar --buildver hg19 nci60 humandb/ | |
| perl annotate_variation.pl --downdb --webfrom annovar --buildver hg19 icgc28 humandb/ | |
| perl annotate_variation.pl --downdb --webfrom annovar --buildver hg19 clinvar_20140702 humandb/ | |
| perl annotate_variation.pl --downdb --webfrom annovar --buildver hg19 clinvar_20140902 humandb/ | |
| perl annotate_variation.pl --downdb --webfrom annovar --buildver hg19 clinvar_20150330 humandb/ | |
| perl annotate_variation.pl --downdb --webfrom annovar --buildver hg19 clinvar_20150629 humandb/ | |
| perl annotate_variation.pl --downdb --webfrom annovar --buildver hg19 clinvar_20151201 humandb/ | |
| perl annotate_variation.pl --downdb --webfrom annovar --buildver hg19 clinvar_20160302 humandb/ | |
| perl annotate_variation.pl --downdb --webfrom annovar --buildver hg19 clinvar_20161128 humandb/ | |
| perl annotate_variation.pl --downdb --webfrom annovar --buildver hg19 clinvar_20170130 humandb/ | |
| perl annotate_variation.pl --downdb --webfrom annovar --buildver hg19 clinvar_20170501 humandb/ | |
| perl annotate_variation.pl --downdb --webfrom annovar --buildver hg19 clinvar_20170905 humandb/ | |
| perl annotate_variation.pl --downdb --webfrom annovar --buildver hg19 clinvar_20180603 humandb/ | |
| perl annotate_variation.pl --downdb --webfrom annovar --buildver hg19 clinvar_20190305 humandb/ | |
| perl annotate_variation.pl --downdb --webfrom annovar --buildver hg19 clinvar_20200316 humandb/ | |
| perl annotate_variation.pl --downdb --webfrom annovar --buildver hg19 clinvar_20210123 humandb/ | |
| perl annotate_variation.pl --downdb --webfrom annovar --buildver hg19 clinvar_20210501 humandb/ | |
| perl annotate_variation.pl --downdb --webfrom annovar --buildver hg19 clinvar_20220320 humandb/ | |
| perl annotate_variation.pl --downdb --webfrom annovar --buildver hg19 clinvar_20221231 humandb/ | |
| perl annotate_variation.pl --downdb --webfrom annovar --buildver hg19 clinvar_20240611 humandb/ | |
| perl annotate_variation.pl --downdb --webfrom annovar --buildver hg19 regsnpintron humandb/ | |
| perl annotate_variation.pl --downdb --webfrom ucsc --buildver hg19 rmsk humandb/ | |
| # downadad all hg38 database | |
| perl annotate_variation.pl --downdb --webfrom annovar --buildver hg38 refGene humandb/ | |
| perl annotate_variation.pl --downdb --webfrom annovar --buildver hg38 refGeneWithVer humandb/ | |
| perl annotate_variation.pl --downdb --webfrom annovar --buildver hg38 ensGene humandb/ | |
| perl annotate_variation.pl --downdb --webfrom annovar --buildver hg38 knownGene humandb/ | |
| perl annotate_variation.pl --downdb --webfrom annovar --buildver hg38 ljb26_all humandb/ | |
| perl annotate_variation.pl --downdb --webfrom annovar --buildver hg38 dbnsfp30a humandb/ | |
| perl annotate_variation.pl --downdb --webfrom annovar --buildver hg38 dbnsfp33a humandb/ | |
| perl annotate_variation.pl --downdb --webfrom annovar --buildver hg38 dbnsfp35a humandb/ | |
| #perl annotate_variation.pl --downdb --webfrom annovar --buildver hg38 dbnsfp41a humandb/ | |
| perl annotate_variation.pl --downdb --webfrom annovar --buildver hg38 dbnsfp42a humandb/ | |
| perl annotate_variation.pl --downdb --webfrom annovar --buildver hg38 dbnsfp47a humandb/ | |
| perl annotate_variation.pl --downdb --webfrom annovar --buildver hg38 dbscsnv11 humandb/ | |
| perl annotate_variation.pl --downdb --webfrom annovar --buildver hg38 cosmic70 humandb/ | |
| perl annotate_variation.pl --downdb --webfrom annovar --buildver hg38 esp6500siv2_ea humandb/ | |
| perl annotate_variation.pl --downdb --webfrom annovar --buildver hg38 esp6500siv2_aa humandb/ | |
| perl annotate_variation.pl --downdb --webfrom annovar --buildver hg38 esp6500siv2_all humandb/ | |
| perl annotate_variation.pl --downdb --webfrom annovar --buildver hg38 exac03 humandb/ | |
| perl annotate_variation.pl --downdb --webfrom annovar --buildver hg38 exac03nontcga humandb/ | |
| perl annotate_variation.pl --downdb --webfrom annovar --buildver hg38 exac03nonpsych humandb/ | |
| perl annotate_variation.pl --downdb --webfrom annovar --buildver hg38 gene4denovo201907 humandb/ | |
| perl annotate_variation.pl --downdb --webfrom annovar --buildver hg38 gnomad_exome humandb/ | |
| perl annotate_variation.pl --downdb --webfrom annovar --buildver hg38 gnomad_genome humandb/ | |
| perl annotate_variation.pl --downdb --webfrom annovar --buildver hg38 gnomad211_exome humandb/ | |
| perl annotate_variation.pl --downdb --webfrom annovar --buildver hg38 gnomad211_genome humandb/ | |
| perl annotate_variation.pl --downdb --webfrom annovar --buildver hg38 gnomad40_exome humandb/ | |
| perl annotate_variation.pl --downdb --webfrom annovar --buildver hg38 gnomad40_genome humandb/ | |
| perl annotate_variation.pl --downdb --webfrom annovar --buildver hg38 gnomad41_exome humandb/ | |
| perl annotate_variation.pl --downdb --webfrom annovar --buildver hg38 gnomad41_genome humandb/ | |
| perl annotate_variation.pl --downdb --webfrom annovar --buildver hg38 kaviar_20150923 humandb/ | |
| perl annotate_variation.pl --downdb --webfrom annovar --buildver hg38 hrcr1 humandb/ | |
| perl annotate_variation.pl --downdb --webfrom annovar --buildver hg38 1000g2014oct humandb/ | |
| perl annotate_variation.pl --downdb --webfrom annovar --buildver hg38 1000g2015aug humandb/ | |
| perl annotate_variation.pl --downdb --webfrom annovar --buildver hg38 avsnp142 humandb/ | |
| #perl annotate_variation.pl --downdb --webfrom annovar --buildver hg38 avsnp144 humandb/ | |
| perl annotate_variation.pl --downdb --webfrom annovar --buildver hg38 avsnp147 humandb/ | |
| perl annotate_variation.pl --downdb --webfrom annovar --buildver hg38 avsnp150 humandb/ | |
| perl annotate_variation.pl --downdb --webfrom annovar --buildver hg38 avsnp151 humandb/ | |
| perl annotate_variation.pl --downdb --webfrom annovar --buildver hg38 nci60 humandb/ | |
| perl annotate_variation.pl --downdb --webfrom annovar --buildver hg38 icgc28 humandb/ | |
| perl annotate_variation.pl --downdb --webfrom annovar --buildver hg38 clinvar_20140702 humandb/ | |
| perl annotate_variation.pl --downdb --webfrom annovar --buildver hg38 clinvar_20140902 humandb/ | |
| perl annotate_variation.pl --downdb --webfrom annovar --buildver hg38 clinvar_20150330 humandb/ | |
| perl annotate_variation.pl --downdb --webfrom annovar --buildver hg38 clinvar_20150629 humandb/ | |
| perl annotate_variation.pl --downdb --webfrom annovar --buildver hg38 clinvar_20151201 humandb/ | |
| perl annotate_variation.pl --downdb --webfrom annovar --buildver hg38 clinvar_20160302 humandb/ | |
| perl annotate_variation.pl --downdb --webfrom annovar --buildver hg38 clinvar_20161128 humandb/ | |
| perl annotate_variation.pl --downdb --webfrom annovar --buildver hg38 clinvar_20170130 humandb/ | |
| perl annotate_variation.pl --downdb --webfrom annovar --buildver hg38 clinvar_20170501 humandb/ | |
| perl annotate_variation.pl --downdb --webfrom annovar --buildver hg38 clinvar_20170905 humandb/ | |
| perl annotate_variation.pl --downdb --webfrom annovar --buildver hg38 clinvar_20180603 humandb/ | |
| perl annotate_variation.pl --downdb --webfrom annovar --buildver hg38 clinvar_20190305 humandb/ | |
| perl annotate_variation.pl --downdb --webfrom annovar --buildver hg38 clinvar_20200316 humandb/ | |
| perl annotate_variation.pl --downdb --webfrom annovar --buildver hg38 clinvar_20210123 humandb/ | |
| perl annotate_variation.pl --downdb --webfrom annovar --buildver hg38 clinvar_20210501 humandb/ | |
| perl annotate_variation.pl --downdb --webfrom annovar --buildver hg38 clinvar_20220320 humandb/ | |
| perl annotate_variation.pl --downdb --webfrom annovar --buildver hg38 clinvar_20221231 humandb/ | |
| perl annotate_variation.pl --downdb --webfrom annovar --buildver hg38 clinvar_20240611 humandb/ | |
| perl annotate_variation.pl --downdb --webfrom annovar --buildver hg38 regsnpintron humandb/ | |
| perl annotate_variation.pl --downdb --webfrom ucsc --buildver hg38 rmsk humandb/ | |
| # reindex to speed up | |
| perl index_annovar.pl --skipsort --bin 1000 humandb/hg19_avsnp147.txt | |
| perl index_annovar.pl --skipsort --bin 50 humandb/hg19_dbnsfp47a.txt | |
| #perl index_annovar.pl --skipsort --bin 100 humandb/hg19_gnomad41_exome.txt | |
| #perl index_annovar.pl --skipsort --bin 1000 humandb/hg19_gnomad41_genome.txt | |
| #perl index_annovar.pl --skipsort --bin 100 humandb/hg19_gnomad_exome.txt | |
| perl index_annovar.pl --skipsort --bin 1000 humandb/hg19_gnomad_genome.txt | |
| perl index_annovar.pl --skipsort --bin 1000 humandb/hg19_hrcr1.txt | |
| perl index_annovar.pl --skipsort --bin 10000 humandb/hg19_icgc28.txt | |
| perl index_annovar.pl --skipsort --bin 1000 humandb/hg19_kaviar_20150923.txt | |
| perl index_annovar.pl --skipsort --bin 1000 humandb/hg38_avsnp147.txt | |
| perl index_annovar.pl --skipsort --bin 50 humandb/hg38_dbnsfp47a.txt | |
| perl index_annovar.pl --skipsort --bin 100 humandb/hg38_gnomad41_exome.txt | |
| #perl index_annovar.pl --skipsort --bin 1000 humandb/hg38_gnomad41_genome.txt | |
| #perl index_annovar.pl --skipsort --bin 100 humandb/hg38_gnomad_exome.txt | |
| perl index_annovar.pl --skipsort --bin 1000 humandb/hg38_gnomad_genome.txt | |
| perl index_annovar.pl --skipsort --bin 1000 humandb/hg38_hrcr1.txt | |
| perl index_annovar.pl --skipsort --bin 10000 humandb/hg38_icgc28.txt | |
| perl index_annovar.pl --skipsort --bin 1000 humandb/hg38_kaviar_20150923.txt | |
| cd .. | |
| # mimic wANNOVAR before 2024-07-12 | |
| perl annovar/table_annovar.pl annovar/example/ex2.vcf annovar/humandb/ --outfile ex2 --buildver hg38 \ | |
| --protocol refGene,1000g2015aug_all,1000g2015aug_afr,1000g2015aug_amr,1000g2015aug_eas,1000g2015aug_eur,1000g2015aug_sas,exac03,esp6500siv2_all,esp6500siv2_aa,esp6500siv2_ea,nci60,avsnp151,cosmic70,clinvar_20170905,dbnsfp33a,gnomad_exome,gnomad_genome \ | |
| --operation g,f,f,f,f,f,f,f,f,f,f,f,f,f,f,f,f,f \ | |
| --vcfinput --otherinfo --thread $(nproc) --maxgenethread $(nproc) | |
| # mimic wANNOVAR after 2024-07-12 | |
| perl annovar/table_annovar.pl annovar/example/ex2.vcf annovar/humandb/ --outfile ex2 --buildver hg38 \ | |
| --protocol refGeneWithVer,clinvar_20240611,dbnsfp47a,gnomad41_exome,gnomad41_genome \ | |
| --operation g,f,f,f,f \ | |
| --vcfinput --otherinfo --thread $(nproc) --maxgenethread $(nproc) | |
| # for intervar | |
| perl annovar/table_annovar.pl annovar/example/ex2.vcf annovar/humandb/ --outfile ex2 --buildver hg38 \ | |
| --protocol refGene,esp6500siv2_all,1000g2015aug,avsnp147,dbnsfp42a,clinvar_20210501,gnomad_genome,dbscsnv11,rmsk,ensGene,knownGene \ | |
| --operation g,f,f,f,f,f,f,f,r,g,g \ | |
| --vcfinput --otherinfo --thread $(nproc) --maxgenethread $(nproc) | |
| git clone https://github.com/WGLab/InterVar.git -b v2.2.1 | |
| wget https://omim.org/static/omim/data/mim2gene.txt | |
| mv mim2gene.txt InterVar/intervardb | |
| python InterVar/Intervar.py \ | |
| --input=ex2.avinput \ | |
| --output=ex2 \ | |
| --buildver=hg38 \ | |
| --database_intervar=InterVar/intervardb \ | |
| --table_annovar=annovar/table_annovar.pl \ | |
| --convert2annovar=annovar/convert2annovar.pl \ | |
| --annotate_variation=annovar/annotate_variation.pl \ | |
| --database_locat=annovar/humandb \ | |
| --skip_annovar | |
| # everything | |
| perl annovar/table_annovar.pl annovar/example/ex2.vcf annovar/humandb/ --outfile ex2 --buildver hg38 \ | |
| --protocol refGene,1000g2015aug_all,1000g2015aug_afr,1000g2015aug_amr,1000g2015aug_eas,1000g2015aug_eur,1000g2015aug_sas,exac03,esp6500siv2_all,esp6500siv2_aa,esp6500siv2_ea,nci60,avsnp147,cosmic70,clinvar_20240611,dbnsfp47a,gnomad_exome,gnomad_genome,dbscsnv11,rmsk,ensGene,knownGene,kaviar_20150923,hrcr1,regsnpintron,gene4denovo201907,icgc28,refGeneWithVer,gnomad41_exome,gnomad41_genome \ | |
| --operation g,f,f,f,f,f,f,f,f,f,f,f,f,f,f,f,f,f,f,r,g,g,f,f,f,f,f,g,f,f \ | |
| --vcfinput --otherinfo --thread $(nproc) --maxgenethread $(nproc) | |
| # more speed up (--mingenelinecount 1) | |
| annotate_variation.pl | |
| 206c206 | |
| < 'thread=i'=>\$thread, 'maxgenethread=i'=>\$maxgenethread) or pod2usage (); | |
| --- | |
| > 'thread=i'=>\$thread, 'maxgenethread=i'=>\$maxgenethread, 'mingenelinecount=i'=>\$mingenelinecount) or pod2usage (); | |
| table_annovar.pl | |
| 15c15 | |
| < our ($outfile, $buildver, $remove, $checkfile, $protocol, $operation, $otherinfo, $onetranscript, $nastring, $genericdbfile, $gff3dbfile, $bedfile, $vcfdbfile, $csvout, $argument, $tempdir, $vcfinput, $dot2underline, $thread, $maxgenethread, $polishgene, $xreffile, $convertarg, $codingarg, $intronhgvs); | |
| --- | |
| > our ($outfile, $buildver, $remove, $checkfile, $protocol, $operation, $otherinfo, $onetranscript, $nastring, $genericdbfile, $gff3dbfile, $bedfile, $vcfdbfile, $csvout, $argument, $tempdir, $vcfinput, $dot2underline, $thread, $maxgenethread, $mingenelinecount, $polishgene, $xreffile, $convertarg, $codingarg, $intronhgvs); | |
| 33c33 | |
| < 'thread=i'=>\$thread, 'maxgenethread=i'=>\$maxgenethread, 'polishgene!'=>\$polishgene, 'xreffile=s'=>\$xreffile, 'convertarg=s'=>\$convertarg, 'codingarg=s'=>\$codingarg, | |
| --- | |
| > 'thread=i'=>\$thread, 'maxgenethread=i'=>\$maxgenethread, 'mingenelinecount=i'=>\$mingenelinecount, 'polishgene!'=>\$polishgene, 'xreffile=s'=>\$xreffile, 'convertarg=s'=>\$convertarg, 'codingarg=s'=>\$codingarg, | |
| 441a442,444 | |
| > if ($mingenelinecount) { | |
| > $sc .= " -mingenelinecount $mingenelinecount"; | |
| > } | |
| 832a836 | |
| > --mingenelinecount <int> min line counts to enable threaded gene-based annotation (default: 1000000) | |
| 968a973,978 | |
| > | |
| > =item B<--mingenelinecount> | |
| > | |
| > specify the minimum line counts to enable threaded gene-based annotation | |
| > (default: 1000000). For input files with less lines, the threaded annotation | |
| > will not be used, since it actually cost more time than non-threaded annotation. |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment