/usr/share/perl5/Bio/Align/ProteinStatistics.pm is in libbio-perl-perl 1.6.923-1.
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 | #
# BioPerl module for Bio::Align::ProteinStatistics
#
# Please direct questions and support issues to <bioperl-l@bioperl.org>
#
# Cared for by Jason Stajich <jason-at-bioperl.org>
#
# Copyright Jason Stajich
#
# You may distribute this module under the same terms as perl itself
# POD documentation - main docs before the code
=head1 NAME
Bio::Align::ProteinStatistics - Calculate Protein Alignment statistics (mostly distances)
=head1 SYNOPSIS
use Bio::Align::ProteinStatistics;
use Bio::AlignIO;
my $in = Bio::AlignIO->new(-format => 'fasta',
-file => 'pep-104.fasaln');
my $aln = $in->next_aln;
my $pepstats = Bio::Align::ProteinStatistics->new();
$kimura = $protstats->distance(-align => $aln,
-method => 'Kimura');
print $kimura->print_matrix;
=head1 DESCRIPTION
This object is for generating various statistics from a protein
alignment. Mostly it is where pairwise protein distances can be
calculated.
=head1 REFERENCES
D_Kimura - Kimura, M. 1983. The Neutral Theory of Molecular Evolution. CUP,
Cambridge.
=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
the Bioperl mailing list. 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
of the bugs and their resolution. Bug reports can be submitted via the
web:
https://redmine.open-bio.org/projects/bioperl/
=head1 AUTHOR - Jason Stajich
Email jason-at-bioperl.org
=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::Align::ProteinStatistics;
use vars qw(%DistanceMethods $Precision $DefaultGapPenalty);
use strict;
use Bio::Align::PairwiseStatistics;
use Bio::Matrix::PhylipDist;
%DistanceMethods = ('kimura|k' => 'Kimura',
);
$Precision = 5;
$DefaultGapPenalty = 0;
use base qw(Bio::Root::Root Bio::Align::StatisticsI);
=head2 new
Title : new
Usage : my $obj = Bio::Align::ProteinStatistics->new();
Function: Builds a new Bio::Align::ProteinStatistics object
Returns : an instance of Bio::Align::ProteinStatistics
Args :
=cut
sub new {
my($class,@args) = @_;
my $self = $class->SUPER::new(@args);
$self->pairwise_stats( Bio::Align::PairwiseStatistics->new());
return $self;
}
=head2 distance
Title : distance
Usage : my $distance_mat = $stats->distance(-align => $aln,
-method => $method);
Function: Calculates a distance matrix for all pairwise distances of
sequences in an alignment.
Returns : L<Bio::Matrix::PhylipDist> object
Args : -align => Bio::Align::AlignI object
-method => String specifying specific distance method
(implementing class may assume a default)
=cut
sub distance{
my ($self,@args) = @_;
my ($aln,$method) = $self->_rearrange([qw(ALIGN METHOD)],@args);
if( ! defined $aln || ! ref ($aln) || ! $aln->isa('Bio::Align::AlignI') ) {
$self->throw("Must supply a valid Bio::Align::AlignI for the -align parameter in distance");
}
$method ||= 'Kimura';
foreach my $m ( keys %DistanceMethods ) {
if(defined $m && $method =~ /$m/i ) {
my $mtd = "D_$DistanceMethods{$m}";
return $self->$mtd($aln);
}
}
$self->warn("Unrecognized distance method $method must be one of [".
join(',',$self->available_distance_methods())."]");
return;
}
=head2 available_distance_methods
Title : available_distance_methods
Usage : my @methods = $stats->available_distance_methods();
Function: Enumerates the possible distance methods
Returns : Array of strings
Args : none
=cut
sub available_distance_methods{
my ($self,@args) = @_;
return values %DistanceMethods;
}
=head2 D - distance methods
=cut
=head2 D_Kimura
Title : D_Kimura
Usage : my $matrix = $pepstats->D_Kimura($aln);
Function: Calculate Kimura protein distance (Kimura 1983) which
approximates PAM distance
D = -ln ( 1 - p - 0.2 * p^2 )
Returns : L<Bio::Matrix::PhylipDist>
Args : L<Bio::Align::AlignI>
=cut
# Kimura, M. 1983. The Neutral Theory of Molecular Evolution. CUP, Cambridge.
sub D_Kimura{
my ($self,$aln) = @_;
return 0 unless $self->_check_arg($aln);
# ambiguities ignored at this point
my (@seqs,@names,@values,%dist);
my $seqct = 0;
foreach my $seq ( $aln->each_seq) {
push @names, $seq->display_id;
push @seqs, uc $seq->seq();
$seqct++;
}
my $len = $aln->length;
my $precisionstr = "%.$Precision"."f";
for( my $i = 0; $i < $seqct-1; $i++ ) {
# (diagonals) distance is 0 for same sequence
$dist{$names[$i]}->{$names[$i]} = [$i,$i];
$values[$i][$i] = sprintf($precisionstr,0);
for( my $j = $i+1; $j < $seqct; $j++ ) {
my ($scored,$match) = (0,0);
for( my $k=0; $k < $len; $k++ ) {
my $m1 = substr($seqs[$i],$k,1);
my $m2 = substr($seqs[$j],$k,1);
if( $m1 ne '-' && $m2 ne '-' ) {
# score is number of scored bases (alignable bases)
# it could have also come from
# my $L = $self->pairwise_stats->number_of_comparable_bases($pairwise);
# match is number of matches weighting ambiguity bases
# as well
$match += _check_ambiguity_protein($m1,$m2);
$scored++;
}
}
# From Felsenstein's PHYLIP documentation:
# This is very quick to do but has some obvious
# limitations. It does not take into account which amino
# acids differ or to what amino acids they change, so some
# information is lost. The units of the distance measure
# are fraction of amino acids differing, as also in the
# case of the PAM distance. If the fraction of amino acids
# differing gets larger than 0.8541 the distance becomes
# infinite.
my $D = 1 - ( $match / $scored );
if( $D < 0.8541 ) {
$D = - log ( 1 - $D - (0.2 * ($D ** 2)));
$values[$j][$i] = $values[$i][$j] = sprintf($precisionstr,$D);
} else {
$values[$j][$i] = $values[$i][$j] = ' NaN';
}
# fwd and rev lookup
$dist{$names[$i]}->{$names[$j]} = [$i,$j];
$dist{$names[$j]}->{$names[$i]} = [$i,$j];
# (diagonals) distance is 0 for same sequence
$dist{$names[$j]}->{$names[$j]} = [$j,$j];
$values[$j][$j] = sprintf($precisionstr,0);
}
}
return Bio::Matrix::PhylipDist->new(-program => 'bioperl_PEPstats',
-matrix => \%dist,
-names => \@names,
-values => \@values);
}
# some methods from EMBOSS distmat
sub _check_ambiguity_protein
{
my ($t1,$t2) = @_;
my $n = 0;
if( $t1 ne 'X' && $t1 eq $t2 ) {
$n = 1.0;
} elsif( (($t1 eq 'B' && $t2 =~ /[DN]/ ) ||
($t2 eq 'B' && $t1 =~ /[DN]/ )) ||
(($t1 eq 'Z' && $t2 =~ /[EQ]/) ||
($t2 eq 'Z' && $t1 =~ /[EQ]/ ))) {
$n = 0.5;
} elsif ( $t1 eq 'X' && $t2 eq 'X' ) {
$n = 0.0025;
} elsif( $t1 eq 'X' || $t2 eq 'X' ) {
$n = 0.05;
}
return $n;
}
=head2 Data Methods
=cut
=head2 pairwise_stats
Title : pairwise_stats
Usage : $obj->pairwise_stats($newval)
Function:
Returns : value of pairwise_stats
Args : newvalue (optional)
=cut
sub pairwise_stats{
my ($self,$value) = @_;
if( defined $value) {
$self->{'_pairwise_stats'} = $value;
}
return $self->{'_pairwise_stats'};
}
sub _check_arg {
my($self,$aln ) = @_;
if( ! defined $aln || ! $aln->isa('Bio::Align::AlignI') ) {
$self->warn("Must provide a Bio::Align::AlignI compliant object to Bio::Align::DNAStatistics");
return 0;
} elsif( $aln->get_seq_by_pos(1)->alphabet ne 'protein' ) {
$self->warn("Must provide a protein alignment to Bio::Align::ProteinStatistics, you provided a " . $aln->get_seq_by_pos(1)->alphabet);
return 0;
}
return 1;
}
1;
|