Created
February 28, 2020 20:33
-
-
Save liangyy/69146113cac107a99d571a4b9c8726bb to your computer and use it in GitHub Desktop.
Download and clean up dependent data for lab 7 (HG471 @ UChicago)
This file contains 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 -c ftp://gsapubftp-anonymous@ftp.broadinstitute.org/bundle/b37/dbsnp_138.b37.vcf.gz.md5 | |
wget -c ftp://gsapubftp-anonymous@ftp.broadinstitute.org/bundle/b37/dbsnp_138.b37.vcf.gz | |
wget -c ftp://gsapubftp-anonymous@ftp.broadinstitute.org/bundle/b37/Mills_and_1000G_gold_standard.indels.b37.vcf.gz | |
wget -c ftp://gsapubftp-anonymous@ftp.broadinstitute.org/bundle/b37/Mills_and_1000G_gold_standard.indels.b37.vcf.gz.md5 | |
wget -c ftp://gsapubftp-anonymous@ftp.broadinstitute.org/bundle/b37/1000G_phase1.indels.b37.vcf.gz | |
wget -c ftp://gsapubftp-anonymous@ftp.broadinstitute.org/bundle/b37/1000G_phase1.indels.b37.vcf.gz.md5 | |
wget -c ftp://gsapubftp-anonymous@ftp.broadinstitute.org/bundle/b37/1000G_phase1.snps.high_confidence.b37.vcf.gz | |
wget -c ftp://gsapubftp-anonymous@ftp.broadinstitute.org/bundle/b37/1000G_phase1.snps.high_confidence.b37.vcf.gz.md5 | |
wget -c ftp://gsapubftp-anonymous@ftp.broadinstitute.org/bundle/b37/hapmap_3.3.b37.vcf.gz | |
wget -c ftp://gsapubftp-anonymous@ftp.broadinstitute.org/bundle/b37/hapmap_3.3.b37.vcf.gz.md5 | |
wget -c ftp://gsapubftp-anonymous@ftp.broadinstitute.org/bundle/b37/1000G_omni2.5.b37.vcf.gz | |
wget -c ftp://gsapubftp-anonymous@ftp.broadinstitute.org/bundle/b37/1000G_omni2.5.b37.vcf.gz.md5 | |
wget -c ftp://gsapubftp-anonymous@ftp.broadinstitute.org/bundle/b37/1000G_phase3_v4_20130502.sites.vcf.gz | |
wget -c ftp://gsapubftp-anonymous@ftp.broadinstitute.org/bundle/b37/1000G_phase3_v4_20130502.sites.vcf.gz.md5 | |
wget ftp://ftp.1000genomes.ebi.ac.uk//vol1/ftp/technical/reference/phase2_reference_assembly_sequence/hs37d5.fa.gz |
This file contains 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
module load samtools | |
module load picard | |
zcat hs37d5.fa.gz|head -n 48017254|tail -n 855078 > hs37d5_chr22.fa | |
samtools faidx hs37d5_chr22.fa | |
java -jar $PICARD CreateSequenceDictionary REFERENCE=hs37d5_chr22.fa OUTPUT=hs37d5_chr22.dict | |
module load htslib | |
unzipVCF () { | |
filename=$1 | |
echo Processing $filename | |
zcat /project2/hgen47100/data/lab7/$filename.gz > /project2/hgen47100/data/lab7/$filename | |
# tabix vcf /project2/hgen47100/data/lab7/$filename | |
# mv /project2/hgen47100/data/lab7/$filename.tmp /project2/hgen47100/data/lab7/$filename | |
# mv /project2/hgen47100/data/lab7/$filename.tmp.tbi /project2/hgen47100/data/lab7/$filename.tbi | |
} | |
unzipVCF "hapmap_3.3.b37.vcf" | |
unzipVCF "1000G_omni2.5.b37.vcf" | |
unzipVCF "1000G_phase1.snps.high_confidence.b37.vcf" | |
unzipVCF "dbsnp_138.b37.vcf" |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment