nathanhaigh

#!/usr/bin/perl
# Usage: gunzip -c graph.asqg.gz | asqg2dot.pl ['<node_label_regex>'] > graph.dot

use strict;
use warnings;

my $bidirected = 1;
my $highlight_vertex_regex = shift @ARGV || '';

my %vertex_labels;

nathanhaigh

#!/bin/bash
# Usage: deinterleave_fastq.sh < interleaved.fastq f.fastq r.fastq [compress]
# 
# Deinterleaves a FASTQ file of paired reads into two FASTQ
# files specified on the command line. Optionally GZip compresses the output
# FASTQ files using pigz if the 3rd command line argument is the word "compress"
# 
# Can deinterleave 100 million paired reads (200 million total
# reads; a 43Gbyte file), in memory (/dev/shm), in 4m15s (255s)
# 

nathanhaigh

#!/bin/bash
# Usage: quality_value_summary.sh < in.fastq > quality_stats.txt
# Inspired by Torsten Seemann's blog post:
# http://thegenomefactory.blogspot.com.au/2012/05/cool-use-of-unix-paste-with-ngs.html
# Inspired by:
# http://www.unix.com/shell-programming-scripting/37305-how-convert-hex-value-dec.html
paste - - - - | \
  cut -f 4 | \
  xxd -g 1 -c 1 -p | \
  grep -v '0a' | \

nathanhaigh

library Illimina_pe     200     500     ^(AGRF).*$
# Note sure if the following single-ended "library" is valid for AMOS:
library 454_se  0       0       ^(GKUZBF401|GKUZBF402|GK7W4KZ01|GK7W4KZ02|GK538RQ01|GK538RQ02|GK0HZXL01|GK0HZXL02|F196STF01|F196STF02|F4S7VAM01|F4S7VAM02|F5ZSAHT01|F5ZSAHT02|F6J8SXW01|F6J8SXW02).*$
library 454_3kb     1000    5000    ^(GK33D5G01|GK33D5G02|GK9RFDF01|GK9RFDF02|GLBLI5G01|GLBLI5G02|GLDJ2JW01|GLKV9FY01).*$
library 454_20kb    8000    32000   ^(F5XZBDV01|F5XZBDV02).*$
pair    ^(.+?)_left.*$  ^(.+?)_right.*$
pair    ^(.+?)/1.*$     ^(.+?)/2.*$

nathanhaigh

#!/usr/bin/perl
#
# Convert contigs of an ACE file into a FASTA file.
# Usage: ace2fas.pl < my.ace > my.fas
#
use strict;
use warnings;

while(<>){
  next until /^CO\s+(\S+).+?$/;  # read ACE file till next contig starts

nathanhaigh

#!/bin/bash
#
# NOTE: This may not entirely work! I couldn't quite get this working on my CentOS release 5.6 (Final) box
#
# References: http://www.freelists.org/post/mira_talk/header-file-missing-in-my-configlog,7
#             https://svn.boost.org/trac/boost/ticket/5917
#             http://permalink.gmane.org/gmane.comp.lib.boost.user/69898

####################
# Specify versions #

nathanhaigh

#!/usr/bin/perl
#
# Usage: sspace_evidence2agp.pl formattedcontigs.fasta < final.evidence > out.agp 2> out.stderr
# e.g. sspace_evidence2agp.pl intermediate_results/standard_output.formattedcontigs.fasta < standard_output.final.evidence > standard_output.agp 2> standard_output.agp.stderr
#
# What this script does:
#   1) Uses the *.final.evidence file created by SSPACE to generate an AGP v2.0 file.
#   2) Uses information in the *.formattedcontigs.fasta file to recover the original contig
#      names.
#   3) Non-positive length gaps are output as component_type=U and gap length 100, as per the

nathanhaigh

#!/bin/bash
apt-get update
apt-get -y dist-upgrade
apt-get -y install ubuntu-desktop gnome-session-fallback python-software-properties
add-apt-repository -y ppa:freenx-team
apt-get update
apt-get -y install freenx
cd /tmp
wget https://bugs.launchpad.net/freenx-server/+bug/576359/+attachment/1378450/+files/nxsetup.tar.gz
tar xzf nxsetup.tar.gz

nathanhaigh

#!/bin/bash
export WORKSHOP_NAME="ACAD"
export PARENT_DIR="/mnt"
export SUDO_USER="ubuntu"
export TRAINEE_USER="ngstrainee"
export TMPDIR=/mnt/tmp

# set the timezone
TZ="Australia/Adelaide"
echo "$TZ" > /etc/timezone

nathanhaigh

#!/bin/bash
# Usage: fastq2fasta.sh < in.fastq > out.fasta
# Taken from http://stackoverflow.com/a/10359425/1413849 and happens to
#   be able to convert 10 millions reads in 14 seconds!!
# The fastest converter I've seen!
sed -n '1~4s/^@/>/p;2~4p'