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
|
#!/usr/bin/env perl
use strict;
use warnings;
use FindBin;
use lib ("$FindBin::RealBin/../PerlLib");
use Fasta_reader;
use BHStats;
my $usage = "\n\nusage: $0 transcripts.fasta\n\n";
my $fasta_file = $ARGV[0] or die $usage;
main: {
my $fasta_reader = new Fasta_reader($fasta_file);
my @all_seq_lengths;
my $number_transcripts = 0;
my $num_GC = 0;
my %component_to_longest_isoform;
my $tot_seq_len = 0;
while (my $seq_obj = $fasta_reader->next()) {
my $acc = $seq_obj->get_accession();
$number_transcripts++;
my $comp_id;
if ($acc =~ /^(.*c\d+_g\d+)/) {
$comp_id = $1;
}
elsif ($acc =~ /^(.*comp\d+_c\d+)/) {
$comp_id = $1;
}
else {
die "Error, cannot decipher gene identifier from acc: $acc";
}
my $sequence = $seq_obj->get_sequence();
my $seq_len = length($sequence);
$tot_seq_len += $seq_len;
if ( (! exists $component_to_longest_isoform{$comp_id})
||
$component_to_longest_isoform{$comp_id} < $seq_len) {
$component_to_longest_isoform{$comp_id} = $seq_len;
}
push (@all_seq_lengths, $seq_len);
while ($sequence =~ /[gc]/ig) {
$num_GC++;
}
}
print "\n\n";
print "################################\n";
print "## Counts of transcripts, etc.\n";
print "################################\n";
print "Total trinity 'genes':\t" . scalar(keys %component_to_longest_isoform) . "\n";
print "Total trinity transcripts:\t" . $number_transcripts . "\n";
my $pct_gc = sprintf("%.2f", $num_GC / $tot_seq_len * 100);
print "Percent GC: $pct_gc\n\n";
print "########################################\n";
print "Stats based on ALL transcript contigs:\n";
print "########################################\n\n";
&report_stats(@all_seq_lengths);
print "\n\n";
print "#####################################################\n";
print "## Stats based on ONLY LONGEST ISOFORM per 'GENE':\n";
print "#####################################################\n\n";
&report_stats(values %component_to_longest_isoform);
print "\n\n\n";
exit(0);
}
####
sub report_stats {
my (@seq_lengths) = @_;
@seq_lengths = reverse sort {$a<=>$b} @seq_lengths;
my $cum_seq_len = 0;
foreach my $len (@seq_lengths) {
$cum_seq_len += $len;
}
for (my $i = 10; $i <= 50; $i += 10) {
my $cum_len_needed = $cum_seq_len * $i/100;
my $N_val = &get_contigNvalue($cum_len_needed, \@seq_lengths);
print "\tContig N$i: $N_val\n";
}
print "\n";
my $median_len = &BHStats::median(@seq_lengths);
print "\tMedian contig length: $median_len\n";
my $avg_len = sprintf("%.2f", &BHStats::avg(@seq_lengths));
print "\tAverage contig: $avg_len\n";
print "\tTotal assembled bases: $cum_seq_len\n";
return;
}
sub get_contigNvalue {
my ($cum_len_needed, $seq_lengths_aref) = @_;
my $partial_sum_len = 0;
foreach my $len (@$seq_lengths_aref) {
$partial_sum_len += $len;
if ($partial_sum_len >= $cum_len_needed) {
return($len);
}
}
return -1; # shouldn't happen.
}
|
