ShujiaHuang

def merge_region(position_region, delta=1):
    """Merge a batch of sorted region

    Parameters
    ----------
    ``position_region``: a list like, required
        A regions (2D) array, format like: [[start1,end1], [start2,end2], ...]

    ``delta``: Integer, optinal

ShujiaHuang

#Known datasets: GATK bundle for human b37 reference
# 
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

ShujiaHuang

root@iZ88i9o3weiZ:~# apt-get update
Err http://mirrors.aliyuncs.com trusty InRelease

Err http://mirrors.aliyuncs.com trusty-security InRelease

Err http://mirrors.aliyuncs.com trusty-updates InRelease

Err http://mirrors.aliyuncs.com trusty-proposed InRelease

Err http://mirrors.aliyuncs.com trusty-backports InRelease

ShujiaHuang

$ cat /proc/cpuinfo
processor	: 0
vendor_id	: GenuineIntel
cpu family	: 6
model		: 44
model name	: Intel(R) Xeon(R) CPU           X5650  @ 2.67GHz
stepping	: 2
microcode	: 20
cpu MHz		: 1600.000
cache size	: 12288 KB

ShujiaHuang

### Read Fa sequence ###
sub ReadFaSeq {

    my ( $file, $fa ) = @_;

    my ( $refId, $seq );
    open I, $file or die "Cannot open file : $file\n";

    $/ = ">"; <I>; $/ = "\n";
    while ( <I> ) {

ShujiaHuang

### Read Fa sequence ###
sub ReadFaSeq {

    my ( $file, $fa ) = @_;

    my ( $refId, $seq );
    open I, $file or die "Cannot open file : $file\n";

    $/ = ">"; <I>; $/ = "\n";
    while ( <I> ) {

ShujiaHuang

#!/bin/sh
# Just copy and paste the lines below (all at once, it won't work line by line!)
# MAKE SURE YOU ARE HAPPY WITH WHAT IT DOES FIRST! THERE IS NO WARRANTY!
# https://gist.github.com/mxcl/1173223
function abort {
  echo "$1"
  exit 1
}

set -e

ShujiaHuang

#!/bin/bash

# If you adapt this script for your own use, you will need to set these two variables based on your environment.
# SV_DIR is the installation directory for SVToolkit - it must be an exported environment variable.
# SV_TMPDIR is a directory for writing temp files, which may be large if you have a large data set.
#export SV_DIR=`cd .. && pwd`
SV_DIR=/home/siyang/bin/software_pip/svtoolkit
SV_TMPDIR=

runDir=

ShujiaHuang

#Author : Shujia Huang
#Date : 2010/11/27
#!/usr/bin/perl -w
use strict;

use warnings;

my ( $file, $outfile_prefix, @bin_num ) = @ARGV;
my %region2num = ( "1000upstream" => 0, "first-exon" => 1, "intron"         => 2,
				   "mid-exon"     => 3, "last-exon"  => 4, "1000downstream" => 5 );

ShujiaHuang

#!/usr/bin/perl

use warnings;

use strict;

use PerlIO::gzip;

die "perl $0 <.gz file in> <.gz file out>" unless @ARGV==2;