Last active
September 27, 2015 05:08
-
-
Save epaule/1216188 to your computer and use it in GitHub Desktop.
Cufflinks FTP to Agustus hints GFF conversion (exon|intron|ep)
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/env perl | |
# | |
# convert cufflinks GTF into a Augustus hintfile | |
# | |
# seq source ep|exon|intron start stop score +/- phase grp=ID; src=E | |
my %transcripts; | |
while(<>){ | |
next unless /Cufflinks\s+exon.*transcript_id/; | |
s/"//g; | |
chomp; | |
my @c = split; | |
push @{$transcripts{$c[11]}},{seq=>$c[0],name => $c[11],start => $c[3],stop => $c[4],strand => $c[6]}; | |
} | |
while(my($k,$v)=each %transcripts){ | |
my @exons = sort {$a->{start} <=> $b->{stop}} @$v; # get them in the correct order ... just in case | |
for(my $i=0;$i<scalar(@exons);$i++){ | |
my $ex=$exons[$i]; | |
unless($i == 0){ | |
my %intron = %$ex; | |
$intron{start}=$exons[$i-1]->{stop}+1; | |
$intron{stop} =$ex->{start}-1; | |
print_gff(\%intron,'intron'); | |
} | |
if($i == 0 || $i==scalar(@exons)-1){ | |
print_gff($ex,'ep'); | |
} | |
else{ | |
print_gff($ex,'exon'); | |
} | |
} | |
} | |
sub print_gff{ | |
my ($e,$source)=@_; | |
printf "%s\tCufflinks\t$source\t%d\t%d\t.\t%s\t.\tgrp=%ssrc=W\n",$e->{seq},$e->{start},$e->{stop},$e->{strand},$e->{name}; | |
} |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment