/usr/share/perl5/Bio/Tools/Run/TigrAssembler.pm is in libbio-perl-run-perl 1.7.1-3.
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 | # BioPerl module for Bio::Tools::Run::TigrAssembler
#
# Copyright Florent E Angly <florent-dot-angly-at-gmail-dot-com>
#
# You may distribute this module under the same terms as perl itself
#
# POD documentation - main docs before the code
=head1 NAME
Bio::Tools::Run::TigrAssembler - Wrapper for local execution of TIGR Assembler
v2
=head1 SYNOPSIS
use Bio::Tools::Run::TigrAssembler;
# Run TIGR Assembler using an input FASTA file
my $factory = Bio::Tools::Run::TigrAssembler->new( -minimum_overlap_length => 35 );
my $asm_obj = $factory->run($fasta_file, $qual_file);
# An assembly object is returned by default
for my $contig ($assembly->all_contigs) {
... do something ...
}
# Read some sequences
use Bio::SeqIO;
my $sio = Bio::SeqIO->new(-file => $fasta_file, -format => 'fasta');
my @seqs;
while (my $seq = $sio->next_seq()) {
push @seqs,$seq;
}
# Run TIGR Assembler with input sequence objects and return an assembly file
my $asm_file = 'results.tigr';
$factory->out_type($asm_file);
$factory->run(\@seqs);
# Use LIGR Assembler instead
my $ligr = Bio::Tools::Run::TigrAssembler->new(
-program_name => 'LIGR_Assembler',
-trimmed_seq => 1
);
$ligr->run(\@seqs);
=head1 DESCRIPTION
Wrapper module for the local execution of the DNA assembly program TIGR
Assembler v2.0. TIGR Assembler is open source software under The Artistic
License and available at: http://www.tigr.org/software/assembler/
This module runs TIGR Assembler by feeding it a FASTA file or sequence objects
and returning an assembly file or assembly and IO objects. When the input is
Bioperl object, sequences less than 39 bp long are filtered out since they are
not supported by TIGR Assembler.
If provided in the following way, TIGR Assembler will use additional
information present in the sequence descriptions for assembly:
>seq_name minimum_clone_length maximum_clone_length median_clone_length
clear_end5 clear_end3
or
>db|seq_name minimum_clone_length maximum_clone_length median_clone_length
clear_end5 clear_end3
e.g.
>GHIBF57F 500 3000 1750 33 587
This module also supports LIGR Assembler, a variant of TIGR Assembler:
http://sourceforge.net/projects/ligr-assembler/
=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:
http://redmine.open-bio.org/projects/bioperl/
=head1 AUTHOR - Florent E Angly
Email: florent-dot-angly-at-gmail-dot-com
=head1 APPENDIX
The rest of the documentation details each of the object methods. Internal
methods are usually preceded with a _
=cut
package Bio::Tools::Run::TigrAssembler;
use strict;
use IPC::Run;
use base qw( Bio::Root::Root Bio::Tools::Run::AssemblerBase );
our $program_name = 'TIGR_Assembler'; # name of the executable
our @program_params = (qw( minimum_percent minimum_length max_err_32 quality_file
maximum_end resort_after ));
our @program_switches = (qw( include_singlets consider_low_scores safe_merging_stop
ignore_tandem_32mers use_tandem_32mers not_random incl_bad_seq trimmed_seq ));
our %param_translation = (
'quality_file' => 'q',
'minimum_percent' => 'p',
'minimum_length' => 'l',
'include_singlets' => 's',
'max_err_32' => 'g',
'consider_low_scores' => 'L',
'maximum_end' => 'e',
'ignore_tandem_32mers' => 't',
'use_tandem_32mers' => 'u',
'safe_merging_stop' => 'X',
'not_random' => 'N',
'resort_after' => 'r',
'incl_bad_seq' => 'b',
'trimmed_seq' => 'i'
);
our $qual_param = 'quality_file';
our $use_dash = 1;
our $join = ' ';
our $asm_format = 'tigr';
our $min_len = 39;
=head2 new
Title : new
Usage : $factory->new( -minimum_percent => 95,
-minimum_length => 50,
-include_singlets => 1 );
Function: Create a TIGR Assembler factory
Returns : A Bio::Tools::Run::TigrAssembler object
Args :
TIGR Assembler options available in this module:
minimum_percent / minimum_overlap_similarity: the minimum percent identity
that two DNA fragments must achieve over their entire region of overlap in
order to be considered as a possible assembly. Adjustments are made by the
program to take into account that the ends of sequences are lower quality
and doubled base calls are the most frequent sequencing error.
minimum_length / minimum_overlap_length: the minimum length two DNA fragments
must overlap to be considered as a possible assembly (warning: this option
is not strictly respected by TIGR Assembler...)
include_singlets: a flag which indicates that singletons (assemblies made up
of a single DNA fragment) should be included in the lassie output_file - the
default is to not include singletons.
max_err_32: the maximum number + 1 of alignment errors (mismatches or gaps)
allowed within any contiguous 32 base pairs in the overlap region between
two DNA fragments in the same assembly. This is meant to split apart splice
variants which have short splice differences and would not be disqualified
by the -p minimum_percent parameter.
consider_low_scores: a flag which causes even very LOW pairwise scores to be
considered - caution using this flag may cause longer run time and a worse
assembly.
maximum_end: the maximum length at the end of a DNA fragment that does not
match another overlapping DNA fragment (sometimes referred to as overhang)
that will not disqualify a DNA fragment from becoming part of an assembly.
ignore_tandem_32mers: a flag which causes tandem 32mers (a tandem 32mer is a
32mer which occurs more than once in at least one sequence read) to be
ignored (this is now the default behavior and this flag is for backward
compatibility)
use_tandem_32mers: a flag which causes tandem 32mers to be used for pairwise
comparison opposite of the -t flag which is now the default).
safe_merging_stop: a flag which causes merging to stop when only sequences
which appear to be repeats are left and these cannot be merged based on
clone length constraints.
not_random: a flag which indicates that the DNA fragments in the input_file
should not be treated as random genomic fragments for the purpose of
determining repeat regions.
resort_after: specifies how many sequences should be merged before resorting
the possible merges based on clone constraints.
LIGR Assembler has the same options as TIGR Assembler, and the following:
incl_bad_seq: keep all sequences including potential chimeras and splice variants
trimmed_seq: indicates that the sequences are trimmed. High quality scores will be
given on the whole sequence length instead of just in the middle)
=cut
sub new {
my ($class,@args) = @_;
my $self = $class->SUPER::new(@args);
$self->_set_program_options(\@args, \@program_params, \@program_switches,
\%param_translation, $qual_param, $use_dash, $join);
*minimum_overlap_length = \&minimum_length;
*minimum_overlap_similarity = \&minimum_percent;
$self->program_name($program_name) if not defined $self->program_name();
$self->_assembly_format($asm_format);
return $self;
}
=head2 out_type
Title : out_type
Usage : $factory->out_type('Bio::Assembly::ScaffoldI')
Function: Get/set the desired type of output
Returns : The type of results to return
Args : Desired type of results to return (optional):
'Bio::Assembly::IO' object
'Bio::Assembly::ScaffoldI' object (default)
The name of a file to save the results in
=cut
=head2 run
Title : run
Usage : $factory->run($fasta_file);
Function: Run TIGR Assembler
Returns : - a Bio::Assembly::ScaffoldI object, a Bio::Assembly::IO
object, a filename, or undef if all sequences were too small to
be usable
Returns : Assembly results (file, IO object or assembly object)
Args : - sequence input (FASTA file or sequence object arrayref)
- optional quality score input (QUAL file or quality score object
arrayref)
=cut
=head2 _run
Title : _run
Usage : $assembler->_run()
Function: Make a system call and run Newbler
Returns : An assembly file
Args : - FASTA file, SFF file and MID, or analysis dir and MID
- optional QUAL file
=cut
sub _run {
my ($self, $fasta_file, $qual_file) = @_;
# Setup needed files and filehandles first
my ($output_fh, $output_file ) = $self->_prepare_output_file( );
my ($scratch_fh, $scratch_file) = $self->io->tempfile( -dir => $self->tempdir() );
my ($stderr_fh, $stderr_file ) = $self->io->tempfile( -dir => $self->tempdir() );
# Get program executable
my $exe = $self->executable;
# Get command-line options
my $options = $self->_translate_params();
# Usage: TIGR_Assembler [options] scratch_file < input_file > output_file
my @program_args = ( $exe, @$options, $scratch_file );
my $stdin = $fasta_file;
my $stdout = $output_file;
my $stderr = $stderr_file;
my @ipc_args = ( \@program_args,
'<', $fasta_file,
'>', $output_file,
'2>', $stderr_file );
# Print command for debugging
if ($self->verbose() >= 0) {
my $cmd = '';
$cmd .= join ( ' ', @program_args );
for ( my $i = 1 ; $i < scalar @ipc_args ; $i++ ) {
my $element = $ipc_args[$i];
my $ref = ref($element);
my $value;
if ( $ref && $ref eq 'SCALAR') {
$value = $$element;
} else {
$value = $element;
}
$cmd .= " $value";
}
$self->debug( "$exe command = $cmd\n" );
}
# Execute command
eval {
IPC::Run::run(@ipc_args) || die("There was a problem running $exe: $!");
};
if ($@) {
$self->throw("$exe call crashed: $@");
}
$self->debug(join("\n", "$exe STDERR", $stderr_file)) if $stderr_file;
# TIGR Assembler's stderr reports a lot more than just errors
# Close filehandles
close($scratch_fh);
close($output_fh);
close($stderr_fh);
# Import assembly
return $output_file;
}
=head2 _remove_small_sequences
Title : _remove_small_sequences
Usage : $assembler->_remove_small_sequences(\@seqs, \@quals)
Function: Remove sequences below a threshold length
Returns : a new sequence object array reference
a new quality score object array reference
Args : sequence object array reference
quality score object array reference (optional)
=cut
# Aliasing function _prepare_input_sequences to _remove_small_sequences
*_prepare_input_sequences = \&_remove_small_sequences;
sub _remove_small_sequences {
my ($self, $seqs, $quals) = @_;
# The threshold length, $min_len, has been registered as a global variable
my @new_seqs;
my @new_quals;
if (ref($seqs) =~ m/ARRAY/i) {
my @removed;
my $nof_seqs = scalar @$seqs;
for my $i (1 .. $nof_seqs) {
my $seq = $$seqs[$i-1];
if ($seq->length >= $min_len) {
push @new_seqs, $seq;
if ($quals) {
my $qual = $$quals[$i-1];
push @new_quals, $qual;
}
} else {
push @removed, $seq->id;
}
}
if (scalar @removed > 0) {
$self->warn("The following sequences were removed because they are smaller".
" than $min_len bp: @removed\n");
}
}
return \@new_seqs, \@new_quals;
}
1;
|