crazyhottommy

cat ref.gene.txt
chr1 1736 4272 DDX11L1 +
chr1 4224 19233 WASH7P -
chr1 4224 7502 LOC100288778 -
chr1 7231 7299 MIR6859-1 -
chr1 7231 7299 MIR6859-2 -
chr1 7231 7299 MIR6859-3 -
chr1 7231 7299 MIR6859-4 -

crazyhottommy

#!/bin/bash
# function Extract for common file formats

function extract {
 if [ -z "$1" ]; then
    # display usage if no parameters given
    echo "Usage: extract <path/file_name>.<zip|rar|bz2|gz|tar|tbz2|tgz|Z|7z|xz|ex|tar.bz2|tar.gz|tar.xz>"
 else
    if [ -f "$1" ] ; then
        NAME=${1%.*}

crazyhottommy

crazyhottommy

Pandoc is a very useful tool to convert common formats.

First install pandoc on mac by:

brew install pandoc

pandoc requires pdflatex to convert to pdfs.

install mactex:
download it and just double click it should install it.

crazyhottommy

#! /bin/bash

### This script is used to filter the vcf file produced by lumpy/speedseq

set -e
set -u
set -o pipefail

function usage() {
    echo "

crazyhottommy

#! /bin/bash

### This script is used to filter the vcf file produced by lumpy/speedseq

set -e
set -u
set -o pipefail

function usage() {
    echo "

crazyhottommy

## imagine we have a file with one line header, and we want to keep the header after sorting
## use subshells http://bash.cyberciti.biz/guide/What_is_a_Subshell%3F  
(sed -n '1p' your_file; cat your_file | sed '1d' | sort) > sort_header.txt

## if you have two header lines and want to keep both of them:
(sed -n '1,2p' your_file; cat your_file | sed '1,2d' | sort) > sort_header.txt

## if you have many lines starting with "#" as header, like vcf files
(grep "^#" my_vcf; grep -v "^#" my_vcf | sort -k1,1V -k2,2n) > sorted.vcf

crazyhottommy

for i in {1..22} X Y
do
same=$(comm -12 <(cut -f1,2,4,5 keep_original_bam/TCGA-06-0125_$i.call.keep.txt | sort) <(cut -f1,2,4,5 keep_realigned_bam/TCGA-06-0125_$i.call.keep.txt| sort) | wc -l | tr -d " ")
original=`wc -l keep_original_bam/TCGA-06-0125_$i.call.keep.txt | awk '{print $1}'`
realigned=`wc -l keep_realigned_bam/TCGA-06-0125_$i.call.keep.txt |  awk '{print $1}'`
printf "chromosome $i, original_bam:$original, realigned_bam:$realigned, common:$same \n"
done

crazyhottommy

# output of mutect run for each chromosome
# the first line is the mutect version, the second line is the header
# keep the header and filter mutect results based on 10th and 35th columns.

for file in *.call.txt
do (sed -n '2p' $file; awk -F "\t" '$10=="COVERED" && $35=="KEEP"' $file) > ./keep/"${file%txt}"keep.txt
done

crazyhottommy

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