-
-
Save rhshah/45006892e2bfac6f9c8818d1ea7c2abf to your computer and use it in GitHub Desktop.
Convert TCGA MAFs to VCFs to use to annotate other VCF files with variant frequency in the various TCGA projects (including pancan12).
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
REF=/proj/b2010040/private/nobackup/autoseqer-genome/genome/human_g1k_v37_decoy.fasta | |
DICT=/proj/b2010040/private/nobackup/autoseqer-genome/genome/human_g1k_v37_decoy.dict | |
GATKJAR=/home/daniel.klevebring/projects/tcga-maf-to-vcf/GenomeAnalysisTK.jar | |
WORKDIR=$HOME/Crisp/dakl/tcga-maf-to-vcf | |
mkdir -p $WORKDIR | |
cd $WORKDIR | |
#unpack maf to workdir | |
tar xvfz ~/projects/tcga-maf-to-vcf/pancan_cleaned_mafs.tar.gz | |
if [ ! -f maf2vcf.pl ]; then | |
wget https://raw.githubusercontent.com/ckandoth/vcf2maf/master/maf2vcf.pl | |
fi | |
if [ ! -f vcfsorter.pl ]; then | |
wget https://gist.github.com/dakl/b14aa4648a1ef17cee8c/raw/f1de9791460a3a1f60217cd2e6c0cd72ae78ae91/vcfsorter.pl | |
fi | |
#MAF=/home/daniel.klevebring/Crisp/dakl/tcga-maf-to-vcf/somatic_mafs_cleaned/thca_cleaned.maf | |
MAFS=(`find $WORKDIR/somatic_mafs_cleaned|grep maf$`) | |
for MAF in ${MAFS[@]}; do | |
TMP=`basename $MAF` | |
GRP=tcga-${TMP/_cleaned.maf/} | |
echo -n "$GRP" | |
mkdir -p $GRP | |
perl maf2vcf.pl --input-maf $MAF --output-dir $GRP --ref-fasta $REF | |
VCFS=(`find $GRP|grep vcf$`) | |
#VCF=laml/TCGA-AB-2802-03B-01W-0728-08_vs_TCGA-AB-2802-11B-01W-0728-08.vcf | |
# sort the generated VCFs | |
for VCF in ${VCFS[@]}; do | |
SORTEDVCF=${VCF/.vcf/_sorted.vcf} | |
perl vcfsorter.pl $DICT $VCF |vt normalize -r $REF - |bgzip > $SORTEDVCF | |
tabix -p vcf $SORTEDVCF | |
#rm $VCF | |
done | |
SORTEDVCFS=(`find $GRP|grep _sorted.vcf$`) | |
FINALVCF=${GRP}-somatic.vcf.gz | |
bcftools merge --merge none --force-samples ${SORTEDVCFS[@]} |bgzip > $FINALVCF | |
tabix -p vcf $FINALVCF | |
echo " done." | |
rm -r $GRP | |
done |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment