#!/usr/bin/perl
use warnings;
use strict;
use FindBin qw($RealBin);
use Getopt::Long;
#####################################################################################
# Copyright Copyright 2010-17 Simon Andrews #
# #
# This file is part of FastQC. #
# #
# FastQC is free software; you can redistribute it and/or modify #
# it under the terms of the GNU General Public License as published by #
# the Free Software Foundation; either version 3 of the License, or #
# (at your option) any later version. #
# #
# FastQC is distributed in the hope that it will be useful, #
# but WITHOUT ANY WARRANTY; without even the implied warranty of #
# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the #
# GNU General Public License for more details. #
# #
# You should have received a copy of the GNU General Public License #
# along with FastQC; if not, write to the Free Software #
# Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA #
#####################################################################################
# Check to see if they've mistakenly downloaded the source distribution
# since several people have made this mistake
if (-e "$RealBin/uk/ac/babraham/FastQC/FastQCApplication.java") {
die "This is the source distribution of FastQC. You need to get the compiled version if you want to run the program\n";
}
my $delimiter = ':';
if ($^O =~ /Win/) {
$delimiter = ';';
}
if ($ENV{CLASSPATH}) {
$ENV{CLASSPATH} .= "$delimiter$RealBin$delimiter$RealBin/sam-1.103.jar$delimiter$RealBin/jbzip2-0.9.jar$delimiter$RealBin/cisd-jhdf5.jar";
}
else {
$ENV{CLASSPATH} = "$RealBin$delimiter$RealBin/sam-1.103.jar$delimiter$RealBin/jbzip2-0.9.jar$delimiter$RealBin/cisd-jhdf5.jar";
}
# We need to find the java interpreter. We'll start from the assumption that this
# is included in the path.
my $java_bin = "java";
# We might have bundled a jre with the installation. If that's the case then we'll
# use the interpreter which is bundled in preference to the system one.
# Windows first
if (-e "$RealBin/jre/bin/java.exe") {
$java_bin = "$RealBin/jre/bin/java.exe";
}
# Linux
elsif (-e "$RealBin/jre/bin/java") {
$java_bin = "$RealBin/jre/bin/java";
}
# OSX
elsif (-e "$RealBin/jre/Contents/Home/bin/java") {
$java_bin = "$RealBin/jre/Contents/Home/bin/java";
}
my @java_args;
my @files;
if ($^O =~/darwin/) {
# Add the OSX specific options to use a standard OSX menu bar
# and set the program name to something sensible.
push @java_args, '-Xdock:name=FastQC';
push @java_args, "-Xdock:icon=$RealBin/../Resources/seqmonk.icns";
push @java_args, '-Dapple.laf.useScreenMenuBar=true';
}
# We now need to scan the command line for switches which we're going
# to pass on to the main java program.
my $version;
my $help;
my $outdir;
my $unzip;
my $format;
my $contaminant;
my $adapter;
my $limits;
my $threads;
my $quiet;
my $nogroup;
my $expgroup;
my $casava;
my $nano;
my $nofilter;
my $kmer_size;
my $temp_directory;
my $min_length;
my $dup_length;
my $result = GetOptions('version' => \$version,
'help' => \$help,
'quiet' => \$quiet,
'nogroup' => \$nogroup,
'expgroup' => \$expgroup,
'outdir=s' => \$outdir,
'extract!' => \$unzip,
'format=s' => \$format,
'threads=i' => \$threads,
'kmers=i' => \$kmer_size,
'casava' => \$casava,
'nano' => \$nano,
'nofilter' => \$nofilter,
'contaminants=s' => \$contaminant,
'adapters=s' => \$adapter,
'limits=s' => \$limits,
'dir=s' => \$temp_directory,
'java=s' => \$java_bin,
'min_length=i' => \$min_length,
'dup_length=i' => \$dup_length,
);
# Check the simple stuff first
if ($help) {
# Just print the help and exit
print while(<DATA>);
exit;
}
if ($version) {
push @java_args ,"-Dfastqc.show_version=true";
}
# Now parse any additional options
if ($outdir) {
unless(-e $outdir and -d $outdir) {
die "Specified output directory '$outdir' does not exist\n";
}
push @java_args ,"-Dfastqc.output_dir=$outdir";
}
if ($contaminant) {
unless (-e $contaminant and -r $contaminant) {
die "Contaminant file '$contaminant' did not exist, or could not be read\n";
}
push @java_args ,"-Dfastqc.contaminant_file=$contaminant";
}
if ($adapter) {
unless (-e $adapter and -r $adapter) {
die "Adapters file '$adapter' did not exist, or could not be read\n";
}
push @java_args ,"-Dfastqc.adapter_file=$adapter";
}
if ($limits) {
unless (-e $limits and -r $limits) {
die "Limits file '$limits' did not exist, or could not be read\n";
}
push @java_args ,"-Dfastqc.limits_file=$limits";
}
if ($temp_directory) {
unless (-e $temp_directory and -d $temp_directory and -w $temp_directory) {
die "Temp directory '$temp_directory' doesn't exist, or can't be written to\n";
}
push @java_args, "-Djava.io.tmpdir=$temp_directory";
}
if ($min_length) {
push @java_args ,"-Dfastqc.min_length=$min_length";
}
if ($dup_length) {
push @java_args ,"-Dfastqc.dup_length=$dup_length";
}
if ($threads) {
if ($threads < 1) {
die "Number of threads must be a positive integer";
}
push @java_args ,"-Dfastqc.threads=$threads";
my $memory = 250 * $threads;
unshift @java_args,"-Xmx${memory}m";
}
else {
unshift @java_args,'-Xmx250m';
}
if ($kmer_size) {
unless ($kmer_size =~ /^\d+$/) {
die "Kmer size '$kmer_size' was not a number";
}
if ($kmer_size < 2 or $kmer_size > 10) {
die "Kmer size must be in the range 2-10";
}
push @java_args,"-Dfastqc.kmer_size=$kmer_size";
}
if ($quiet) {
push @java_args ,"-Dfastqc.quiet=true";
}
if ($casava) {
push @java_args ,"-Dfastqc.casava=true";
}
if ($nano) {
push @java_args ,"-Dfastqc.nano=true";
}
if ($nofilter) {
push @java_args ,"-Dfastqc.nofilter=true";
}
if ($nogroup) {
push @java_args ,"-Dfastqc.nogroup=true";
}
if ($expgroup) {
if ($nogroup) {
die "You can't specify both --expgroup and --nogroup in the same run\n";
}
push @java_args ,"-Dfastqc.expgroup=true";
}
if (defined $unzip) {
if ($unzip) {
$unzip = 'true';
}
else {
$unzip = 'false';
}
push @java_args,"-Dfastqc.unzip=$unzip";
}
if ($format) {
unless ($format eq 'bam' || $format eq 'sam' || $format eq 'fastq' || $format eq 'sam_mapped' || $format eq 'bam_mapped') {
die "Unrecognised sequence format '$format', acceptable formats are bam,sam,bam_mapped,sam_mapped and fastq\n";
}
push @java_args,"-Dfastqc.sequence_format=$format";
}
if ($java_bin ne 'java') {
warn "Java is $java_bin\n";
# $java_bin =~ s/\\/\//g;
unless (-e $java_bin) {
die "Couldn't find java interpreter at '$java_bin'";
}
# if ($java_bin =~ / /) {
# $java_bin = "\"$java_bin\"";
# }
}
# We've found that on systems with large numbers of CPUs, and especially on systems
# where IO contention can occur, that the program can consume large amounts of CPU
# during parallel garbage collection. Since interactive performance isn't really
# important when running non-interactively we'll limit the GC to using only a single
# thread if running with a list of filenames
if (@ARGV) {
push @java_args,"-XX:ParallelGCThreads=1";
}
foreach (@ARGV) {
if (/^\-D/) {
push @java_args,$_;
}
else {
push @files,$_;
}
}
# This is set internally as well, but on some JREs it doesn't
# pick up the internally set value properly, so we'll set it
# outside as well which should work.
if (@files or $version or $help) {
push @java_args, "-Djava.awt.headless=true";
}
#warn "Running 'exec $java_bin,@java_args, \"uk.ac.babraham.FastQC.FastQCApplication\", @files, CLASSPATH is $ENV{CLASSPATH}";
if ($java_bin ne 'java') {
system $java_bin,@java_args, "uk.ac.babraham.FastQC.FastQCApplication", @files;
}
else {
exec $java_bin,@java_args, "uk.ac.babraham.FastQC.FastQCApplication", @files;
}
__DATA__
FastQC - A high throughput sequence QC analysis tool
SYNOPSIS
fastqc seqfile1 seqfile2 .. seqfileN
fastqc [-o output dir] [--(no)extract] [-f fastq|bam|sam]
[-c contaminant file] seqfile1 .. seqfileN
DESCRIPTION
FastQC reads a set of sequence files and produces from each one a quality
control report consisting of a number of different modules, each one of
which will help to identify a different potential type of problem in your
data.
If no files to process are specified on the command line then the program
will start as an interactive graphical application. If files are provided
on the command line then the program will run with no user interaction
required. In this mode it is suitable for inclusion into a standardised
analysis pipeline.
The options for the program as as follows:
-h --help Print this help file and exit
-v --version Print the version of the program and exit
-o --outdir Create all output files in the specified output directory.
Please note that this directory must exist as the program
will not create it. If this option is not set then the
output file for each sequence file is created in the same
directory as the sequence file which was processed.
--casava Files come from raw casava output. Files in the same sample
group (differing only by the group number) will be analysed
as a set rather than individually. Sequences with the filter
flag set in the header will be excluded from the analysis.
Files must have the same names given to them by casava
(including being gzipped and ending with .gz) otherwise they
won't be grouped together correctly.
--nano Files come from nanopore sequences and are in fast5 format. In
this mode you can pass in directories to process and the program
will take in all fast5 files within those directories and produce
a single output file from the sequences found in all files.
--nofilter If running with --casava then don't remove read flagged by
casava as poor quality when performing the QC analysis.
--extract If set then the zipped output file will be uncompressed in
the same directory after it has been created. By default
this option will be set if fastqc is run in non-interactive
mode.
-j --java Provides the full path to the java binary you want to use to
launch fastqc. If not supplied then java is assumed to be in
your path.
--noextract Do not uncompress the output file after creating it. You
should set this option if you do not wish to uncompress
the output when running in non-interactive mode.
--nogroup Disable grouping of bases for reads >50bp. All reports will
show data for every base in the read. WARNING: Using this
option will cause fastqc to crash and burn if you use it on
really long reads, and your plots may end up a ridiculous size.
You have been warned!
--min_length Sets an artificial lower limit on the length of the sequence
to be shown in the report. As long as you set this to a value
greater or equal to your longest read length then this will be
the sequence length used to create your read groups. This can
be useful for making directly comaparable statistics from
datasets with somewhat variable read lengths.
--dup_length Sets a length to which the sequences will be truncated when
defining them to be duplicates, affecting the duplication and
overrepresented sequences plot. This can be useful if you have
long reads with higher levels of miscalls, or contamination with
adapter dimers containing UMI sequences.
-f --format Bypasses the normal sequence file format detection and
forces the program to use the specified format. Valid
formats are bam,sam,bam_mapped,sam_mapped and fastq
-t --threads Specifies the number of files which can be processed
simultaneously. Each thread will be allocated 250MB of
memory so you shouldn't run more threads than your
available memory will cope with, and not more than
6 threads on a 32 bit machine
-c Specifies a non-default file which contains the list of
--contaminants contaminants to screen overrepresented sequences against.
The file must contain sets of named contaminants in the
form name[tab]sequence. Lines prefixed with a hash will
be ignored.
-a Specifies a non-default file which contains the list of
--adapters adapter sequences which will be explicity searched against
the library. The file must contain sets of named adapters
in the form name[tab]sequence. Lines prefixed with a hash
will be ignored.
-l Specifies a non-default file which contains a set of criteria
--limits which will be used to determine the warn/error limits for the
various modules. This file can also be used to selectively
remove some modules from the output all together. The format
needs to mirror the default limits.txt file found in the
Configuration folder.
-k --kmers Specifies the length of Kmer to look for in the Kmer content
module. Specified Kmer length must be between 2 and 10. Default
length is 7 if not specified.
-q --quiet Supress all progress messages on stdout and only report errors.
-d --dir Selects a directory to be used for temporary files written when
generating report images. Defaults to system temp directory if
not specified.
BUGS
Any bugs in fastqc should be reported either to simon.andrews@babraham.ac.uk
or in www.bioinformatics.babraham.ac.uk/bugzilla/