Created
March 12, 2012 18:16
-
-
Save cybersiddhu/2023749 to your computer and use it in GitHub Desktop.
Fasta header of dictyBase proteins in NCBI format
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
#!/usr/bin/perl -w | |
use strict; | |
use Pod::Usage; | |
use Getopt::Long; | |
use Bio::SeqIO; | |
use Bio::PrimarySeq; | |
use IO::File; | |
my $mapfile; | |
GetOptions( | |
'h|help' => sub { pod2usage(1); }, | |
'm|map=s' => \$mapfile | |
); | |
die "no map file given\n" if !$mapfile; | |
die "no fasta file given\n" if !$ARGV[0]; | |
my $input = IO::File->new( $mapfile, 'r' ) or die "cannot open file:$!"; | |
my %id2product; | |
while ( my $line = $input->getline ) { | |
chomp $line; | |
my @data = split /\t/, $line; | |
$id2product{ $data[0] } = $data[1]; | |
} | |
$input->close; | |
my $seqio = Bio::SeqIO->new( -format => 'fasta', -file => $ARGV[0] ); | |
my $seqout = Bio::SeqIO->new( | |
-format => 'fasta', | |
-file => '>discoideum_polypeptide.fa' | |
); | |
while ( my $seq = $seqio->next_seq ) { | |
my $seqid = $seq->id; | |
my ( $protein_id, $gene_id ); | |
if ( $seqid =~ /\|/ ) { | |
( $protein_id, $gene_id ) = split /\|/, $seqid; | |
} | |
else { | |
$protein_id = $seqid; | |
my @data = split /\|/, $seq->desc; | |
$gene_id = $data[0]; | |
} | |
my $primary_seq; | |
if ( not defined $id2product{$gene_id} ) { | |
$primary_seq = Bio::PrimarySeq->new( | |
-seq => $seq->seq, | |
-id => 'gnl|dictyBase|'.$protein_id, | |
-alphabet => 'protein' | |
); | |
} | |
else { | |
$primary_seq = Bio::PrimarySeq->new( | |
-seq => $seq->seq, | |
-id => 'gnl|dictyBase|'.$protein_id.'|', | |
-description => $id2product{$gene_id}, | |
-alphabet => 'protein' | |
); | |
} | |
$seqout->write_seq($primary_seq); | |
} | |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment