edawson

chmod a+x vcfsort.sh
vcfsort.sh trio.trim.vep.vcf.gz

edawson

grep -v "^@" $1 | awk '{print $1"\t"$2"\t"$3"\t"$5}' > $(dirname $1)/$(basename $1 .interval_list).bed && \
    bgzip $(dirname $1)/$(basename $1 .interval_list).bed && \
    tabix $(dirname $1)/$(basename $1 .interval_list).bed.gz

edawson

first_reads=$1
second_reads=$2

ddir=$(dirname $first_reads)
obase_first=$(basename $first_reads .fastq.gz)
obase_second=$(basename $second_reads .fastq.gz)

splitsz=4000000

if [ ! -z ${first_reads} ] && [ -e ${first_reads} ]

edawson

import sys
import gzip
from collections import defaultdict

if __name__ == "__main__":

    d_telo= defaultdict(list)
    d_centro = {}
    with gzip.open(sys.argv[1], "rt") as ifi:
        for line in ifi:

edawson

git clean -xfd
git submodule foreach --recursive git clean -xfd
git reset --hard
git submodule foreach --recursive git reset --hard
git submodule update --init --recursive

edawson

library(vcfR)

# Import VCF
my.vcf <- read.vcfR('my.vcf.gz')
# Combine CHROM thru FILTER cols + INFO cols
my.vcf.df <- cbind(as.data.frame(getFIX(my.vcf)), INFO2df(my.vcf))