/usr/share/perl5/Bio/Tools/Genscan.pm is in libbio-perl-perl 1.6.924-3.
This file is owned by root:root, with mode 0o644.
The actual contents of the file can be viewed below.
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 | #
# BioPerl module for Bio::Tools::Genscan
#
# Please direct questions and support issues to <bioperl-l@bioperl.org>
#
# Cared for by Hilmar Lapp <hlapp@gmx.net>
#
# Copyright Hilmar Lapp
#
# You may distribute this module under the same terms as perl itself
# POD documentation - main docs before the code
=head1 NAME
Bio::Tools::Genscan - Results of one Genscan run
=head1 SYNOPSIS
use Bio::Tools::Genscan;
$genscan = Bio::Tools::Genscan->new(-file => 'result.genscan');
# filehandle:
$genscan = Bio::Tools::Genscan->new( -fh => \*INPUT );
# parse the results
# note: this class is-a Bio::Tools::AnalysisResult which implements
# Bio::SeqAnalysisParserI, i.e., $genscan->next_feature() is the same
while($gene = $genscan->next_prediction()) {
# $gene is an instance of Bio::Tools::Prediction::Gene, which inherits
# off Bio::SeqFeature::Gene::Transcript.
#
# $gene->exons() returns an array of
# Bio::Tools::Prediction::Exon objects
# all exons:
@exon_arr = $gene->exons();
# initial exons only
@init_exons = $gene->exons('Initial');
# internal exons only
@intrl_exons = $gene->exons('Internal');
# terminal exons only
@term_exons = $gene->exons('Terminal');
# singleton exons:
($single_exon) = $gene->exons();
}
# essential if you gave a filename at initialization (otherwise the file
# will stay open)
$genscan->close();
=head1 DESCRIPTION
The Genscan module provides a parser for Genscan gene structure prediction
output. It parses one gene prediction into a Bio::SeqFeature::Gene::Transcript-
derived object.
This module also implements the Bio::SeqAnalysisParserI interface, and thus
can be used wherever such an object fits. See L<Bio::SeqAnalysisParserI>.
=head1 FEEDBACK
=head2 Mailing Lists
User feedback is an integral part of the evolution of this and other
Bioperl modules. Send your comments and suggestions preferably to one
of the Bioperl mailing lists. Your participation is much appreciated.
bioperl-l@bioperl.org - General discussion
http://bioperl.org/wiki/Mailing_lists - About the mailing lists
=head2 Support
Please direct usage questions or support issues to the mailing list:
I<bioperl-l@bioperl.org>
rather than to the module maintainer directly. Many experienced and
reponsive experts will be able look at the problem and quickly
address it. Please include a thorough description of the problem
with code and data examples if at all possible.
=head2 Reporting Bugs
Report bugs to the Bioperl bug tracking system to help us keep track
the bugs and their resolution. Bug reports can be submitted via the
web:
https://github.com/bioperl/bioperl-live/issues
=head1 AUTHOR - Hilmar Lapp
Email hlapp@gmx.net
=head1 APPENDIX
The rest of the documentation details each of the object methods. Internal methods are usually preceded with a _
=cut
# Let the code begin...
package Bio::Tools::Genscan;
use strict;
use Symbol;
use Bio::Root::Root;
use Bio::Tools::Prediction::Gene;
use Bio::Tools::Prediction::Exon;
use base qw(Bio::Tools::AnalysisResult);
my %ExonTags = ('Init' => 'Initial',
'Intr' => 'Internal',
'Term' => 'Terminal',
'Sngl' => '');
sub _initialize_state {
my ($self,@args) = @_;
# first call the inherited method!
$self->SUPER::_initialize_state(@args);
# our private state variables
$self->{'_preds_parsed'} = 0;
$self->{'_has_cds'} = 0;
# array of pre-parsed predictions
$self->{'_preds'} = [];
# seq stack
$self->{'_seqstack'} = [];
}
=head2 analysis_method
Usage : $genscan->analysis_method();
Purpose : Inherited method. Overridden to ensure that the name matches
/genscan/i.
Returns : String
Argument : n/a
=cut
#-------------
sub analysis_method {
#-------------
my ($self, $method) = @_;
if($method && ($method !~ /genscan/i)) {
$self->throw("method $method not supported in " . ref($self));
}
return $self->SUPER::analysis_method($method);
}
=head2 next_feature
Title : next_feature
Usage : while($gene = $genscan->next_feature()) {
# do something
}
Function: Returns the next gene structure prediction of the Genscan result
file. Call this method repeatedly until FALSE is returned.
The returned object is actually a SeqFeatureI implementing object.
This method is required for classes implementing the
SeqAnalysisParserI interface, and is merely an alias for
next_prediction() at present.
Example :
Returns : A Bio::Tools::Prediction::Gene object.
Args :
=cut
sub next_feature {
my ($self,@args) = @_;
# even though next_prediction doesn't expect any args (and this method
# does neither), we pass on args in order to be prepared if this changes
# ever
return $self->next_prediction(@args);
}
=head2 next_prediction
Title : next_prediction
Usage : while($gene = $genscan->next_prediction()) {
# do something
}
Function: Returns the next gene structure prediction of the Genscan result
file. Call this method repeatedly until FALSE is returned.
Example :
Returns : A Bio::Tools::Prediction::Gene object.
Args :
=cut
sub next_prediction {
my ($self) = @_;
my $gene;
# if the prediction section hasn't been parsed yet, we do this now
$self->_parse_predictions() unless $self->_predictions_parsed();
# get next gene structure
$gene = $self->_prediction();
if($gene) {
# fill in predicted protein, and if available the predicted CDS
#
my ($id, $seq);
# use the seq stack if there's a seq on it
my $seqobj = pop(@{$self->{'_seqstack'}});
if(! $seqobj) {
# otherwise read from input stream
($id, $seq) = $self->_read_fasta_seq();
# there may be no sequence at all, or none any more
if($id && $seq) {
$seqobj = Bio::PrimarySeq->new('-seq' => $seq,
'-display_id' => $id,
'-alphabet' => "protein");
}
}
if($seqobj) {
# check that prediction number matches the prediction number
# indicated in the sequence id (there may be incomplete gene
# predictions that contain only signals with no associated protein
# and CDS, like promoters, poly-A sites etc)
$gene->primary_tag() =~ /[^0-9]([0-9]+)$/;
my $prednr = $1;
if($seqobj->display_id() !~ /_predicted_\w+_$prednr\|/) {
# this is not our sequence, so push back for next prediction
push(@{$self->{'_seqstack'}}, $seqobj);
} else {
$gene->predicted_protein($seqobj);
# CDS prediction, too?
if($self->_has_cds()) {
($id, $seq) = $self->_read_fasta_seq();
$seqobj = Bio::PrimarySeq->new('-seq' => $seq,
'-display_id' => $id,
'-alphabet' => "dna");
$gene->predicted_cds($seqobj);
}
}
}
}
return $gene;
}
=head2 _parse_predictions
Title : _parse_predictions()
Usage : $obj->_parse_predictions()
Function: Parses the prediction section. Automatically called by
next_prediction() if not yet done.
Example :
Returns :
=cut
sub _parse_predictions {
my ($self) = @_;
my $gene;
my $seqname;
while(defined($_ = $self->_readline())) {
if(/^\s*(\d+)\.(\d+)/) {
# exon or signal
my $prednr = $1;
my $signalnr = $2; # not used presently
if(! defined($gene)) {
$gene = Bio::Tools::Prediction::Gene->new(
'-primary' => "GenePrediction$prednr",
'-source' => 'Genscan');
}
# split into fields
chomp();
my @flds = split(' ', $_);
# create the feature object depending on the type of signal
my $predobj;
my $is_exon = grep {$_ eq $flds[1];} (keys(%ExonTags));
if($is_exon) {
$predobj = Bio::Tools::Prediction::Exon->new();
} else {
# PolyA site, or Promoter
$predobj = Bio::SeqFeature::Generic->new();
}
# set common fields
$predobj->source_tag('Genscan');
$predobj->score($flds[$#flds]);
$predobj->strand((($flds[2] eq '+') ? 1 : -1));
my ($start, $end) = @flds[(3,4)];
if($predobj->strand() == 1) {
$predobj->start($start);
$predobj->end($end);
} else {
$predobj->end($start);
$predobj->start($end);
}
# add to gene structure (should be done only when start and end
# are set, in order to allow for proper expansion of the range)
if($is_exon) {
# first, set fields unique to exons
$predobj->start_signal_score($flds[8]);
$predobj->end_signal_score($flds[9]);
$predobj->coding_signal_score($flds[10]);
$predobj->significance($flds[11]);
$predobj->primary_tag($ExonTags{$flds[1]} . 'Exon');
$predobj->is_coding(1);
# Figure out the frame of this exon. This is NOT the frame
# given by Genscan, which is the absolute frame of the base
# starting the first predicted complete codon. By comparing
# to the absolute frame of the first base we can compute the
# offset of the first complete codon to the first base of the
# exon, which determines the frame of the exon.
my $cod_offset;
if($predobj->strand() == 1) {
$cod_offset = $flds[6] - (($predobj->start()-1) % 3);
# Possible values are -2, -1, 0, 1, 2. -1 and -2 correspond
# to offsets 2 and 1, resp. Offset 3 is the same as 0.
$cod_offset += 3 if($cod_offset < 1);
} else {
# On the reverse strand the Genscan frame also refers to
# the first base of the first complete codon, but viewed
# from forward, which is the third base viewed from
# reverse.
$cod_offset = $flds[6] - (($predobj->end()-3) % 3);
# Possible values are -2, -1, 0, 1, 2. Due to the reverse
# situation, {2,-1} and {1,-2} correspond to offsets
# 1 and 2, resp. Offset 3 is the same as 0.
$cod_offset -= 3 if($cod_offset >= 0);
$cod_offset = -$cod_offset;
}
# Offsets 2 and 1 correspond to frame 1 and 2 (frame of exon
# is the frame of the first base relative to the exon, or the
# number of bases the first codon is missing).
$predobj->frame(3 - $cod_offset);
# then add to gene structure object
$gene->add_exon($predobj, $ExonTags{$flds[1]});
} elsif($flds[1] eq 'PlyA') {
$predobj->primary_tag("PolyAsite");
$gene->poly_A_site($predobj);
} elsif($flds[1] eq 'Prom') {
$predobj->primary_tag("Promoter");
$gene->add_promoter($predobj);
}
next;
}
if(/^\s*$/ && defined($gene)) {
# current gene is completed
$gene->seq_id($seqname);
$self->_add_prediction($gene);
$gene = undef;
next;
}
if(/^(GENSCAN)\s+(\S+)/) {
$self->analysis_method($1);
$self->analysis_method_version($2);
next;
}
if(/^Sequence\s+(\S+)\s*:/) {
$seqname = $1;
next;
}
if(/^Parameter matrix:\s+(\S+)/i) {
$self->analysis_subject($1);
next;
}
if(/^Predicted coding/) {
$self->_has_cds(1);
next;
}
/^>/ && do {
# section of predicted sequences
$self->_pushback($_);
last;
};
}
$self->_predictions_parsed(1);
}
=head2 _prediction
Title : _prediction()
Usage : $gene = $obj->_prediction()
Function: internal
Example :
Returns :
=cut
sub _prediction {
my ($self) = @_;
return unless(exists($self->{'_preds'}) && @{$self->{'_preds'}});
return shift(@{$self->{'_preds'}});
}
=head2 _add_prediction
Title : _add_prediction()
Usage : $obj->_add_prediction($gene)
Function: internal
Example :
Returns :
=cut
sub _add_prediction {
my ($self, $gene) = @_;
if(! exists($self->{'_preds'})) {
$self->{'_preds'} = [];
}
push(@{$self->{'_preds'}}, $gene);
}
=head2 _predictions_parsed
Title : _predictions_parsed
Usage : $obj->_predictions_parsed
Function: internal
Example :
Returns : TRUE or FALSE
=cut
sub _predictions_parsed {
my ($self, $val) = @_;
$self->{'_preds_parsed'} = $val if $val;
if(! exists($self->{'_preds_parsed'})) {
$self->{'_preds_parsed'} = 0;
}
return $self->{'_preds_parsed'};
}
=head2 _has_cds
Title : _has_cds()
Usage : $obj->_has_cds()
Function: Whether or not the result contains the predicted CDSs, too.
Example :
Returns : TRUE or FALSE
=cut
sub _has_cds {
my ($self, $val) = @_;
$self->{'_has_cds'} = $val if $val;
if(! exists($self->{'_has_cds'})) {
$self->{'_has_cds'} = 0;
}
return $self->{'_has_cds'};
}
=head2 _read_fasta_seq
Title : _read_fasta_seq()
Usage : ($id,$seqstr) = $obj->_read_fasta_seq();
Function: Simple but specialised FASTA format sequence reader. Uses
$self->_readline() to retrieve input, and is able to strip off
the traling description lines.
Example :
Returns : An array of two elements.
=cut
sub _read_fasta_seq {
my ($self) = @_;
my ($id, $seq);
local $/ = ">";
my $entry = $self->_readline();
if($entry) {
$entry =~ s/^>//;
# complete the entry if the first line came from a pushback buffer
while($entry !~ />$/) {
last unless $_ = $self->_readline();
$entry .= $_;
}
# delete everything onwards from an intervening empty line (at the
# end there might be statistics stuff)
$entry =~ s/\n\n.*$//s;
# id and sequence
if($entry =~ /^(\S+)\n([^>]+)/) {
$id = $1;
$seq = $2;
} else {
$self->throw("Can't parse Genscan predicted sequence entry");
}
$seq =~ s/\s//g; # Remove whitespace
}
return ($id, $seq);
}
1;
|