Nathan S. Watson-Haigh nathanhaigh

## deinterleave_fastq.sh
#!/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)
#

## add_user_accounts.sh
#!/usr/bin/env bash

#####
# Set default command line options
#####
USERNAME_PREFIX=user
USERNAME_SUFFIX_START=1
USERNAME_SUFFIX_END=100
USERNAME_SUFFIX_ZERO_PADDING_LENGTH=4

## interleave_fastq.sh
#!/bin/bash
# Usage: interleave_fastq.sh f.fastq r.fastq > interleaved.fastq
#
# Interleaves the reads of two FASTQ files specified on the
# command line and outputs a single FASTQ file of STDOUT.
#
# Can interleave 100 million paired reads (200 million total
# reads; a 2 x 22Gbyte files), in memory (/dev/shm), in 6m54s (414s)
#
# Latest code: https://gist.github.com/4544979

## install.sh
#!/bin/bash
# You should clone this gist to obtain the installation and patch file
# and then run it locally, after changing the below settings to something
# suitable for your system. Something like this:
#   sudo apt-get install -y ssh
#   cd
#   scp -r nhaigh@bioserver:git/sysadmin/generic/gitorious_install ./
# Edit the settings below, then run the following as root:
#   cd gitorious_install && sh ./install.sh
#

## depth2bedgraph.awk
#!/usr/bin/awk
# Takes output of "samtools depth" and reformats into grouped bedgraph format:
# samtools depth -r ${loc} -Q 1 --reference $fasta $bam | mawk -f scripts/depth2bedgraph.awk > /tmp/my.bedgraph
# Example input:
#chr1     26      2
#chr1     27      2
#chr1     28      2
#chr1     29      5
#chr1     30      5
#chr1     31      5

## sra_process.sh
#!/bin/bash
# Bash script to download a bunch of *.sra files from the NCBI SRA, using
# the aspera client, and extract FASTQ data using the SRA Toolkit.

max_bandwidth_mbps=50

# These SRA files are for the durum genome
files=(
  'SRR567512.sra'
  'SRR567559.sra'

## trackList.json
"fmtDetailValue_Dbxref" : "function(dbxref){if(typeof dbxref!='string'){return dbxref}var dbid=dbxref.split(':');var prefix='';switch(dbid[0].toLowerCase()){case 'interpro':prefix='http://www.ebi.ac.uk/interpro/entry/';break;case 'pfam':prefix='http://pfam.sanger.ac.uk/family/';break;case 'reactome':prefix='http://www.reactome.org/content/detail/';break;case 'unipathway':prefix='http://www.grenoble.prabi.fr/obiwarehouse/unipathway/upa?upid=';break;case 'kegg':prefix='http://www.genome.jp/kegg-bin/show_pathway?ec';break;case 'prositepatterns':prefix='http://prosite.expasy.org/';break;case 'prositeprofiles':prefix='http://prosite.expasy.org/cgi-bin/prosite/PSView.cgi?ac=';break;case 'smart':prefix='http://smart.embl-heidelberg.de/smart/do_annotation.pl?BLAST=DUMMY&DOMAIN=';break;case 'superfamily':prefix='http://supfam.org/SUPERFAMILY/cgi-bin/scop.cgi?sunid=';dbid[1]=dbid[1].replace('SSF','');break;case 'gene3d':prefix='http://www.cathdb.info/version/latest/superfamily/';dbid[1]=dbid[2];break;case 'pirsf':prefi

## gff3_split.pl
#!/usr/bin/env perl
use strict;
use warnings;

my $bed_file = shift @ARGV;
my $suffix_fmt = '_part%01d';

open(my $bed_fh, '<', $bed_file) || die "Couldn't open BED file: $!\n";

my %cut_positions;

## update_openstack_python_apis.sh
#!/bin/bash
sudo apt-get update && sudo apt-get -y dist-upgrade

urls=(
  'https://github.com/pypa/pip.git'
  'git://github.com/openstack-dev/pbr.git'
  'git://github.com/iguananaut/d2to1.git'
  'https://github.com/kelp404/six.git'
  'https://github.com/openstack/python-glanceclient.git'
  'https://github.com/openstack/python-keystoneclient.git'

## gist:5589673
#!/bin/bash
# First setup everything needed for connecting to it via an NX connection
wget https://gist.github.com/nathanhaigh/4007406/raw/40717e3031bec9efccc3dfcc38c3a50c222d29d9/NXServer.sh
chmod +x NXServer.sh
./NXServer.sh

apt-get -y install libreoffice-java-common htop sysstat git xclip dos2unix

wget http://mirror.ctan.org/systems/texlive/tlnet/install-tl-unx.tar.gz
tar xzf install-tl-unx.tar.gz && rm install-tl-unx.tar.gz
	#!/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)
	#
	#!/usr/bin/env bash

	#####
	# Set default command line options
	#####
	USERNAME_PREFIX=user
	USERNAME_SUFFIX_START=1
	USERNAME_SUFFIX_END=100
	USERNAME_SUFFIX_ZERO_PADDING_LENGTH=4
	#!/bin/bash
	# Usage: interleave_fastq.sh f.fastq r.fastq > interleaved.fastq
	#
	# Interleaves the reads of two FASTQ files specified on the
	# command line and outputs a single FASTQ file of STDOUT.
	#
	# Can interleave 100 million paired reads (200 million total
	# reads; a 2 x 22Gbyte files), in memory (/dev/shm), in 6m54s (414s)
	#
	# Latest code: https://gist.github.com/4544979
	#!/bin/bash
	# You should clone this gist to obtain the installation and patch file
	# and then run it locally, after changing the below settings to something
	# suitable for your system. Something like this:
	# sudo apt-get install -y ssh
	# cd
	# scp -r nhaigh@bioserver:git/sysadmin/generic/gitorious_install ./
	# Edit the settings below, then run the following as root:
	# cd gitorious_install && sh ./install.sh
	#
	#!/usr/bin/awk
	# Takes output of "samtools depth" and reformats into grouped bedgraph format:
	# samtools depth -r ${loc} -Q 1 --reference $fasta $bam \| mawk -f scripts/depth2bedgraph.awk > /tmp/my.bedgraph
	# Example input:
	#chr1 26 2
	#chr1 27 2
	#chr1 28 2
	#chr1 29 5
	#chr1 30 5
	#chr1 31 5
	#!/bin/bash
	# Bash script to download a bunch of *.sra files from the NCBI SRA, using
	# the aspera client, and extract FASTQ data using the SRA Toolkit.

	max_bandwidth_mbps=50

	# These SRA files are for the durum genome
	files=(
	'SRR567512.sra'
	'SRR567559.sra'
	#!/usr/bin/env perl
	use strict;
	use warnings;

	my $bed_file = shift @ARGV;
	my $suffix_fmt = '_part%01d';

	open(my $bed_fh, '<', $bed_file) \|\| die "Couldn't open BED file: $!\n";

	my %cut_positions;
	#!/bin/bash
	sudo apt-get update && sudo apt-get -y dist-upgrade

	urls=(
	'https://github.com/pypa/pip.git'
	'git://github.com/openstack-dev/pbr.git'
	'git://github.com/iguananaut/d2to1.git'
	'https://github.com/kelp404/six.git'
	'https://github.com/openstack/python-glanceclient.git'
	'https://github.com/openstack/python-keystoneclient.git'
	#!/bin/bash
	# First setup everything needed for connecting to it via an NX connection
	wget https://gist.github.com/nathanhaigh/4007406/raw/40717e3031bec9efccc3dfcc38c3a50c222d29d9/NXServer.sh
	chmod +x NXServer.sh
	./NXServer.sh

	apt-get -y install libreoffice-java-common htop sysstat git xclip dos2unix

	wget http://mirror.ctan.org/systems/texlive/tlnet/install-tl-unx.tar.gz
	tar xzf install-tl-unx.tar.gz && rm install-tl-unx.tar.gz