#!/usr/bin/perl -w
use POSIX;
use Getopt::Long qw(:config bundling require_order auto_version);
use FAST;
use strict;
use vars qw($VERSION $DESC $NAME $COMMAND $DATE);
$VERSION = $FAST::VERSION;
$DESC = "Reverse complements nucleotide sequences and alignments.";
$NAME = $0;
$NAME =~ s/^.*\///;
$COMMAND = join " ",$NAME,@ARGV;
$DATE = POSIX::strftime("%c",localtime());
use constant { true => 1, false => 0 };
## DEFAULT OPTION VALUES
my $def_format = $FAST::DEF_FORMAT; # "fasta";
my $def_logname = $FAST::DEF_LOGNAME; # "FAST.log.txt";
## OPTION VARIABLES
my $man = undef; # --man
my $help = undef; # -h
my $format = $def_format; # -f
my $log = undef; # -l
my $logname = $def_logname; # -L
my $comment = undef; # -C
my $moltype = undef; # -m, force moltype
my $nobrand = undef; # -n, don't add "-rc" to identifier
GetOptions('help|h' => \$help,
'man' => \$man,
'format=s' => \$format,
'log|l' => \$log,
'logname|L=s' => \$logname,
'comment|C=s' => \$comment,
'moltype|m=s' => sub{ my (undef,$val) = @_;
die "$NAME: --moltype or -m option argument must be \"dna\", \"rna\""
unless $val =~ /dna|rna/i;
$moltype = $val;
},
'nobrand|n' => \$nobrand,
'fastq|q' => sub {$format = 'fastq';},
)
or pod2usage(2);
pod2usage(-verbose => 1) if $help;
pod2usage(-verbose => 2) if $man;
my $fromSTDIN = ((-t STDIN) ? false : true);
pod2usage("$NAME: Requires at least one argument FILE [FILE2…FILEN] unless input from STDIN.\n") if (!($fromSTDIN) && (@ARGV == 0));
pod2usage("$NAME: Requires exactly zero arguments if input is from STDIN.\n") if ($fromSTDIN && (@ARGV != 0));
&FAST::log($logname, $DATE, $COMMAND, $comment) if ($log);
my $OUT = FAST::Bio::SeqIO->newFh('-format' => $format);
my $IN;
unless (@ARGV) {
if ($moltype) {
$IN = FAST::Bio::SeqIO->new(-fh => *STDIN{IO}, '-format' => $format, '-alphabet' => $moltype);
}
else {
$IN = FAST::Bio::SeqIO->new(-fh => *STDIN{IO}, '-format' => $format);
}
}
while ($IN or @ARGV) {
if (@ARGV) {
my $file = shift (@ARGV);
unless (-e $file) {
warn "$NAME: Could not find file $file. Skipping.\n";
next;1
}
elsif ($moltype) {
$IN = FAST::Bio::SeqIO->new(-file => $file, '-format' => $format, '-alphabet' => $moltype);
}
else {
$IN = FAST::Bio::SeqIO->new(-file => $file, '-format' => $format);
}
}
if ($IN) {
while (my $seq = $IN->next_seq()) {
if ($format eq 'fastq') {
$seq->force_flush('1');
}
my $revcom = FAST::Bio::SeqUtils->revcom_with_features($seq);
unless ($nobrand) {
my $id = join '-',$seq->display_id,'rc';
$revcom->display_id($id);
}
print $OUT $revcom;
}
undef $IN;
}
}
__END__
=head1 NAME
B<fasrc> - reverse complement nucleotide sequences and alignments
=head1 SYNOPSIS
B<fasrc> [OPTIONS] [MULTIFASTA-FILE...]
=head1 DESCRIPTION
B<fasrc> takes multifasta format nucleotide sequences or alignments as
input, and generates reverse complements of those sequences as output.
Options specific to fasrc:
B<-n>, B<--nobrand> don't "brand" sequence ids with "-rc" extension
Options general to FAST:
B<-h>, B<--help> print a brief help message
B<--man> print full documentation
B<--version> print version
B<-l>, B<--log> create/append to logfile
B<-L>, B<--logname>=<string> use logfile name <string>
B<-C>, B<--comment>=<string> save comment <string> to log
B<--format>=<format> use alternative format for input
B<--moltype>=<[dna|rna|protein]> specify input sequence type
B<-q>, B<--fastq> use fastq format as input and output
=head1 INPUT AND OUTPUT
B<fasrc> is part of FAST, the FAST Analysis of Sequences Toolbox, based
on Bioperl. Most core FAST utilities expect input and return output in
multifasta format. Input can occur in one or more files or on
STDIN. Output occurs to STDOUT. The FAST utility B<fasconvert> can
reformat other formats to and from multifasta.
=head1 OPTIONS
=over 8
=item B<-n>
B<--nobrand>
This option will not append -rc to the end of the identifiers.
=item B<-h>,
B<--help>
Print a brief help message and exit.
=item B<--man>
Print the manual page and exit.
=item B<--version>
Print version information and exit.
=item B<-l>,
B<--log>
Creates, or appends to, a generic FAST logfile in the current working
directory. The logfile records date/time of execution, full command
with options and arguments, and an optional comment.
=item B<-L [string]>,
B<--logname=[string]>
Use [string] as the name of the logfile. Default is "FAST.log.txt".
=item B<-C [string]>,
B<--comment=[string]>
Include comment [string] in logfile. No comment is saved by default.
=item B<-m>,
B<--moltype=[dna|rna|protein]>
Specify the type of sequence on input (should not be needed in most
cases, but sometimes Bioperl cannot guess and complains when
processing data).
=item B<-q>
B<--fastq>
use fastq format as input and output.
=back
=head1 EXAMPLES
Take the reverse complements of sequences in file data.fas:
=over 8
B<fasrc> data.fas
=back
=head1 SEE ALSO
=over 8
=item C<man FAST>
=item C<perldoc FAST>
Introduction and cookbook for FAST
=item L<The FAST Home Page|http://compbio.ucmerced.edu/ardell/FAST>"
=back
=head1 CITING
If you use FAST, please cite I<Lawrence et al. (2015). FAST: FAST Analysis of
Sequences Toolbox.> and Bioperl I<Stajich et al.>.
=cut