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
|
#! /usr/bin/env perl
# This file is part of the Grinder package, copyright 2009-2012
# Florent Angly <florent.angly@gmail.com>, under the GPLv3 license
=head1 NAME
average_genome_size - Calculate the average genome size (in bp) of species in a Grinder library
=head1 DESCRIPTION
Calculate the average genome size (in bp) of species in a Grinder library given
the library composition and the full-genomes used to produce it.
=head1 REQUIRED ARGUMENTS
=over
=item <db_fasta>
FASTA file containing the full-genomes used to produce the Grinder library.
=for Euclid:
db_fasta.type: readable
=item <rank_file>
Grinder rank file that describes the library composition.
=for Euclid:
rank_file.type: readable
=back
=head1 COPYRIGHT
Copyright 2009-2012 Florent ANGLY <florent.angly@gmail.com>
Grinder is free software: you can redistribute it and/or modify
it under the terms of the GNU General Public License (GPL) as published by
the Free Software Foundation, either version 3 of the License, or
(at your option) any later version.
Grinder 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 Grinder. If not, see <http://www.gnu.org/licenses/>.
=head1 BUGS
All complex software has bugs lurking in it, and this program is no exception.
If you find a bug, please report it on the SourceForge Tracker for Grinder:
L<http://sourceforge.net/tracker/?group_id=244196&atid=1124737>
Bug reports, suggestions and patches are welcome. Grinder's code is developed
on Sourceforge (L<http://sourceforge.net/scm/?type=git&group_id=244196>) and is
under Git revision control. To get started with a patch, do:
git clone git://biogrinder.git.sourceforge.net/gitroot/biogrinder/biogrinder
=cut
use strict;
use warnings;
use Getopt::Euclid qw( :minimal_keys );
average_genome_size($ARGV{'db_fasta'}, $ARGV{'rank_file'});
exit;
sub average_genome_size {
my ( $db_fasta, $rank_file ) = @_;
# Calculate the average genome size of a Grinder simulated random library
# Read size of the genomes
my ($gen_size) = get_sequence_size($db_fasta);
my $nof_gens = scalar(keys(%$gen_size));
# Read relative abundance of the genomes
my $gen_rel_ab = read_rel_ab($rank_file);
# Calculate average
my ($avg_gen_size, $gen_size_stdev, $gen_size_stderr)
= avg_genome_size($gen_rel_ab, $gen_size, $nof_gens);
# Display results
print "$avg_gen_size bp\n";
return 1;
}
sub get_sequence_size {
# Get the size of sequences in a FASTA file
# Input: path to FASTA file containing metagenomic sequences
# Output: hashref of sequence sizes indexed by sequence ID,
# number of nucleotides,
# length of smallest sequence
# hashref of sequence names indexed by sequence ID
my $fasta = shift;
my ($sizes, $nof_bp, $min_length, $names) = ({}, 0, undef, {});
my ($id, $name, $length) = (undef, '', 0);
if (not -f $fasta) {
die "Error: '$fasta' does not seem to be a valid file\n";
}
open(FASTAIN, $fasta) || die("Error: could not read file '$fasta': $!");
while (my $line = <FASTAIN>) {
chomp $line;
if ($line =~ m/^>(\S+)\s*(.*)$/) {
# Save old sequence, start new sequence
$id && _save_seq($sizes,\$nof_bp,\$min_length,$names,$id,$name,$length);
($id, $name, $length) = ($1, $2, 0);
} elsif ($line =~ m/^\s*$/) { # Line to ignore
next;
} else { # Continuation of current sequence
$length += length($line);
}
}
# Save last sequence
$id && _save_seq($sizes,\$nof_bp,\$min_length,$names,$id,$name,$length);
close FASTAIN;
return $sizes, $nof_bp, $min_length, $names;
sub _save_seq {
my ($sizes, $nof_bp, $min_length, $names, $id, $name, $length) = @_;
$$sizes{$id} = $length;
$$nof_bp += $length;
$$min_length = $length if ((!defined $$min_length)||($length<$$min_length));
$$names{$id} = $name;
}
}
sub read_rel_ab {
my $rank_file = shift;
open(IN, $rank_file) || die("Could not read file '$rank_file': $!");
my %rel_ab;
for my $line (<IN>) {
if ($line =~ m/^#/) {
# Comment line to ignore
next;
#} elsif ($line =~ m/^(\S+)\s+(\S+)\s+(\S+)$/) {
} elsif ($line =~ m/^(.+)\t(.+)\t(.+)$/) {
# Data to keep
my $rank = $1;
my $id = $2;
my $ab = $3/100; # between 0 and 1
$rel_ab{$id} = $ab;
} else {
# Unknown format to ignore
warn "Skipping unknown line format:\n$line";
next;
}
}
close IN;
return \%rel_ab;
}
sub avg_genome_size {
my ($gen_rel_ab, $gen_size, $nof_gens) = @_;
#my ($spectrum, $nof_hits) = @_;
my $avg = 0;
my $stdev = 0;
my $stderr = 0;
for my $genome (keys %$gen_size) {
my $size = $$gen_size{$genome};
my $ab = $$gen_rel_ab{$genome};
next if not defined $ab;
my $tmp = $ab * $size;
$avg += $tmp;
$stdev += $tmp * $size;
}
$stdev = sqrt($stdev - $avg**2); # sigma = sqrt( E(X^2) - E(X)^2 )
$stderr = $stdev;
$stdev /= sqrt($nof_gens) unless ($nof_gens == 0);
return $avg, $stdev, $stderr;
}
|
