#!/usr/bin/perl
##
# Jalview - A Sequence Alignment Editor and Viewer ($$Version-Rel$$)
# Copyright (C) $$Year-Rel$$ The Jalview Authors
#
# This file is part of Jalview.
#
# Jalview 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.
#
# Jalview 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 Jalview. If not, see .
# The Jalview Authors are detailed in the 'AUTHORS' file.
##
use strict;
use warnings;
my %annotLines;
my %featureids;
my @fields;
while (<>) {
($_=~/^\#/) and next;
my @fields = split /\s+/, $_;
if (scalar @fields) {
(defined $annotLines{$fields[1]}) or $annotLines{$fields[1]}=[];
# this is the tab-separated set of fields forming a jalview annotation line
# we only use sequence IDs, not numbers
my $line = [$fields[2],$fields[0],"-1", $fields[3], $fields[4], $fields[2]];
$featureids{$fields[2]}="FF0000"; # red is the colour.
my $attribs = {};
if (scalar @fields>5) {
$attribs->{"gff:score"}=$fields[5];
(scalar @fields>6) and $attribs->{"gff:strand"}=$fields[6];
(scalar @fields>7) and $attribs->{"gff:frame"}=$fields[7];
if (scalar @fields>8) {
for (my $i=7; ($i+1)<(scalar @fields); $i+=2) {
$attribs->{"gff:".$fields[$i]} = $fields[$i+1];
}
}
}
push @{$annotLines{$fields[1]}}, [$line, $attribs];
}
}
foreach my $labels (keys %featureids) {
print "$labels\t".$featureids{$labels}."\n";
}
foreach my $labels (keys %annotLines) {
print "STARTGROUP\t".$labels."\n";
foreach my $annot (@{$annotLines{$labels}}) {
# bare minimum is written - no attributes/links yet.
print "".(join "\t",@{$annot->[0]})."\n";
}
print "ENDGROUP\t".$labels."\n";
}
=pod
=head1 NAME
gff2annot.pl
=head2 SYNOPSIS
gff2annot.pl [one or more files containing gff annotation]
Generates a nominally usable Jalview Annotation file on B from arbitrary GFF annotation lines.
=head2 DESCRIPTION
This script will generate a jalview features file on standard out, from a set of GFF annotation lines input from STDIN and/or any provided filenames.
For a series of GFF annotation lines looking like :
EseqIdE EsourceE EnameE EstartE EendE [EscoreE EstrandE EframeE [EAttributeE EAttribute-Value]]
The script will generate a seuqence features file on B where annotation with a particular B