1
# $Id: sigscan.pm,v 1.6 2006/07/04 22:23:35 mauricio Exp $
2
# BioPerl module for Bio::Tools::Run::PiseApplication::sigscan
4
# Cared for by Catherine Letondal <letondal@pasteur.fr>
6
# For copyright and disclaimer see below.
8
# POD documentation - main docs before the code
12
Bio::Tools::Run::PiseApplication::sigscan
20
Bio::Tools::Run::PiseApplication::sigscan
24
SIGSCAN Scans a sparse protein signature against swissprot (EMBOSS)
30
http://bioweb.pasteur.fr/seqanal/interfaces/sigscan.html
31
for available values):
39
Name of signature file for input (-sigin)
42
Name of sequence database to search (-database)
46
Name of (optionally grouped) scop families file for input (-targetf)
49
Minimum length (residues) of overlap required for two hits with the same code to be counted as the same hit. (-thresh)
52
Residue substitution matrix (-sub)
55
Gap insertion penalty (-gapo)
58
Gap extension penalty (-gape)
61
Select number -- N-terminal matching options (-nterm)
64
Number of hits to output (-nhits)
67
Name of signature hits file for output (-hitsf)
70
Name of signature alignments file for output (-alignf)
78
User feedback is an integral part of the evolution of this and other
79
Bioperl modules. Send your comments and suggestions preferably to
80
the Bioperl mailing list. Your participation is much appreciated.
82
bioperl-l@bioperl.org - General discussion
83
http://bioperl.org/wiki/Mailing_lists - About the mailing lists
87
Report bugs to the Bioperl bug tracking system to help us keep track
88
of the bugs and their resolution. Bug reports can be submitted via the
91
http://bugzilla.open-bio.org/
95
Catherine Letondal (letondal@pasteur.fr)
99
Copyright (C) 2003 Institut Pasteur & Catherine Letondal.
102
This module is free software; you can redistribute it and/or modify
103
it under the same terms as Perl itself.
107
This software is provided "as is" without warranty of any kind.
115
http://bioweb.pasteur.fr/seqanal/interfaces/sigscan.html
119
Bio::Tools::Run::PiseApplication
123
Bio::Tools::Run::AnalysisFactory::Pise
127
Bio::Tools::Run::PiseJob
134
package Bio::Tools::Run::PiseApplication::sigscan;
138
use Bio::Tools::Run::PiseApplication;
140
@ISA = qw(Bio::Tools::Run::PiseApplication);
145
Usage : my $sigscan = Bio::Tools::Run::PiseApplication::sigscan->new($location, $email, @params);
146
Function: Creates a Bio::Tools::Run::PiseApplication::sigscan object.
147
This method should not be used directly, but rather by
148
a Bio::Tools::Run::AnalysisFactory::Pise instance.
149
my $factory = Bio::Tools::Run::AnalysisFactory::Pise->new();
150
my $sigscan = $factory->program('sigscan');
152
Returns : An instance of Bio::Tools::Run::PiseApplication::sigscan.
157
my ($class, $location, $email, @params) = @_;
158
my $self = $class->SUPER::new($location, $email);
160
# -- begin of definitions extracted from /local/gensoft/lib/Pise/5.a/PerlDef/sigscan.pm
162
$self->{COMMAND} = "sigscan";
163
$self->{VERSION} = "5.a";
164
$self->{TITLE} = "SIGSCAN";
166
$self->{DESCRIPTION} = "Scans a sparse protein signature against swissprot (EMBOSS)";
168
$self->{OPT_EMAIL} = 0;
170
$self->{CATEGORIES} = [
172
"protein:3d structure",
175
$self->{DOCLINK} = "http://www.uk.embnet.org/Software/EMBOSS/Apps/sigscan.html";
177
$self->{_INTERFACE_STANDOUT} = undef;
178
$self->{_STANDOUT_FILE} = undef;
180
$self->{TOP_PARAMETERS} = [
190
$self->{PARAMETERS_ORDER} = [
193
"input", # input Section
194
"sigin", # Name of signature file for input (-sigin)
195
"database", # Name of sequence database to search (-database)
196
"targetf", # Name of (optionally grouped) scop families file for input (-targetf)
197
"required", # required Section
198
"thresh", # Minimum length (residues) of overlap required for two hits with the same code to be counted as the same hit. (-thresh)
199
"sub", # Residue substitution matrix (-sub)
200
"gapo", # Gap insertion penalty (-gapo)
201
"gape", # Gap extension penalty (-gape)
202
"nterm", # Select number -- N-terminal matching options (-nterm)
203
"output", # output Section
204
"nhits", # Number of hits to output (-nhits)
205
"hitsf", # Name of signature hits file for output (-hitsf)
206
"alignf", # Name of signature alignments file for output (-alignf)
212
"sigscan" => 'String',
214
"input" => 'Paragraph',
216
"database" => 'Sequence',
217
"targetf" => 'InFile',
218
"required" => 'Paragraph',
219
"thresh" => 'Integer',
224
"output" => 'Paragraph',
225
"nhits" => 'Integer',
226
"hitsf" => 'OutFile',
227
"alignf" => 'OutFile',
239
"perl" => '" -sigin=$value"',
242
"perl" => '" -database=$value -sformat=fasta"',
245
"perl" => '" -targetf=$value"',
250
"perl" => '" -thresh=$value"',
253
"perl" => '" -sub=$value"',
256
"perl" => '" -gapo=$value"',
259
"perl" => '" -gape=$value"',
262
"perl" => '" -nterm=$value"',
267
"perl" => '" -nhits=$value"',
270
"perl" => '" -hitsf=$value"',
273
"perl" => '" -alignf=$value"',
276
"perl" => '" -auto -stdout"',
279
"perl" => '"sigscan"',
284
$self->{FILENAMES} = {
311
$self->{BY_GROUP_PARAMETERS} = [
336
$self->{ISHIDDEN} = {
357
$self->{ISCOMMAND} = {
377
$self->{ISMANDATORY} = {
399
"input" => "input Section",
400
"sigin" => "Name of signature file for input (-sigin)",
401
"database" => "Name of sequence database to search (-database)",
402
"targetf" => "Name of (optionally grouped) scop families file for input (-targetf)",
403
"required" => "required Section",
404
"thresh" => "Minimum length (residues) of overlap required for two hits with the same code to be counted as the same hit. (-thresh)",
405
"sub" => "Residue substitution matrix (-sub)",
406
"gapo" => "Gap insertion penalty (-gapo)",
407
"gape" => "Gap extension penalty (-gape)",
408
"nterm" => "Select number -- N-terminal matching options (-nterm)",
409
"output" => "output Section",
410
"nhits" => "Number of hits to output (-nhits)",
411
"hitsf" => "Name of signature hits file for output (-hitsf)",
412
"alignf" => "Name of signature alignments file for output (-alignf)",
417
$self->{ISSTANDOUT} = {
439
"input" => ['sigin','database','targetf',],
440
"required" => ['thresh','sub','gapo','gape','nterm',],
441
"sub" => ['EPAM60','EPAM60','EPAM290','EPAM290','EPAM470','EPAM470','EPAM110','EPAM110','EBLOSUM50','EBLOSUM50','EPAM220','EPAM220','EBLOSUM62-12','EBLOSUM62-12','EPAM400','EPAM400','EPAM150','EPAM150','EPAM330','EPAM330','EBLOSUM55','EBLOSUM55','EPAM30','EPAM30','EPAM260','EPAM260','EBLOSUM90','EBLOSUM90','EPAM440','EPAM440','EPAM190','EPAM190','EPAM370','EPAM370','EPAM70','EPAM70','EPAM480','EPAM480','EPAM120','EPAM120','EDNAMAT','EDNAMAT','EPAM300','EPAM300','EBLOSUM60','EBLOSUM60','EPAM230','EPAM230','EBLOSUM62','EBLOSUM62','EPAM410','EPAM410','EPAM160','EPAM160','EPAM340','EPAM340','EBLOSUM65','EBLOSUM65','EPAM40','EPAM40','EPAM270','EPAM270','EPAM450','EPAM450','EPAM380','EPAM380','EPAM80','EPAM80','EPAM490','EPAM490','EBLOSUM30','EBLOSUM30','EBLOSUMN','EBLOSUMN','EPAM200','EPAM200','EPAM130','EPAM130','EBLOSUM35','EBLOSUM35','EPAM310','EPAM310','EBLOSUM70','EBLOSUM70','EPAM10','EPAM10','EPAM240','EPAM240','EPAM420','EPAM420','EPAM170','EPAM170','EBLOSUM75','EBLOSUM75','EPAM350','EPAM350','EPAM280','EPAM280','EPAM50','EPAM50','EPAM460','EPAM460','EPAM390','EPAM390','EPAM90','EPAM90','EPAM100','EPAM100','EBLOSUM40','EBLOSUM40','EPAM210','EPAM210','EPAM140','EPAM140','EBLOSUM45','EBLOSUM45','EPAM320','EPAM320','EBLOSUM80','EBLOSUM80','EPAM500','EPAM500','EPAM20','EPAM20','EPAM250','EPAM250','EPAM430','EPAM430','EPAM180','EPAM180','EBLOSUM85','EBLOSUM85','EPAM360','EPAM360',],
442
"nterm" => ['1','Align anywhere and allow only complete signature-sequence fit','2','Align anywhere and allow partial signature-sequence fit','3','Use empirical gaps only',],
443
"output" => ['nhits','hitsf','alignf',],
450
$self->{SEPARATOR} = {
456
"sub" => './EBLOSUM62',
461
"hitsf" => 'test.hits',
462
"alignf" => 'test.align',
467
"init" => { "perl" => '1' },
468
"input" => { "perl" => '1' },
469
"sigin" => { "perl" => '1' },
470
"database" => { "perl" => '1' },
471
"targetf" => { "perl" => '1' },
472
"required" => { "perl" => '1' },
473
"thresh" => { "perl" => '1' },
474
"sub" => { "perl" => '1' },
475
"gapo" => { "perl" => '1' },
476
"gape" => { "perl" => '1' },
477
"nterm" => { "perl" => '1' },
478
"output" => { "perl" => '1' },
479
"nhits" => { "perl" => '1' },
480
"hitsf" => { "perl" => '1' },
481
"alignf" => { "perl" => '1' },
482
"auto" => { "perl" => '1' },
494
$self->{WITHPIPEOUT} = {
505
$self->{WITHPIPEIN} = {
529
$self->{ISSIMPLE} = {
549
$self->{PARAMFILE} = {
555
"The gap insertion penalty is the score taken away when a gap is created. The best value depends on the choice of comparison matrix. The default value assumes you are using the EBLOSUM62 matrix for protein sequences, and the EDNAMAT matrix for nucleotide sequences. Allowed values: Floating point number from 1.0 to 100.0",
558
"The gap extension, penalty is added to the standard gap penalty for each base or residue in the gap. This is how long gaps are penalized. Usually you will expect a few long gaps rather than many short gaps, so the gap extension penalty should be lower than the gap penalty. An exception is where one or both sequences are single reads with possible sequencing errors in which case you would expect many single base gaps. You can get this result by setting the gap open penalty to zero (or very low) and using the gap extension penalty to control gap scoring. Allowed values: Floating point number from 0.0 to 10.0",
563
$self->{SCALEMIN} = {
567
$self->{SCALEMAX} = {
571
$self->{SCALEINC} = {
579
# -- end of definitions extracted from /local/gensoft/lib/Pise/5.a/PerlDef/sigscan.pm
583
$self->_init_params(@params);
590
1; # Needed to keep compiler happy