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
|
#!/usr/bin/env perl
use strict;
use warnings;
use FindBin;
use lib ("$FindBin::Bin/../PerlLib");
use Gene_obj;
use Gene_obj_indexer;
use GFF3_utils;
use Carp;
use Data::Dumper;
use Getopt::Long qw(:config posix_default no_ignore_case bundling pass_through);
my $usage = <<__EOUSAGE__;
################################################################################
#
# Required:
#
# --gff3_file <string> gff3 file w/ predicted ORFs
#
# Optional:
#
# --blast_hits <string> blast hits file
#
# --pfam_hits <string> pfam hits file
#
################################################################################
__EOUSAGE__
;
my $gff3_file;
my $blast_hits_file;
my $pfam_hits_file;
&GetOptions('gff3_file=s' => \$gff3_file,
'blast_hits=s' => \$blast_hits_file,
'pfam_hits=s' => \$pfam_hits_file,
);
unless ($gff3_file) {
die $usage;
}
main: {
my %blast_hits;
if ($blast_hits_file) {
%blast_hits = &parse_blastp_hits_file($blast_hits_file);
}
my %pfam_hits;
if ($pfam_hits_file) {
%pfam_hits = &parse_pfam_hits_file($pfam_hits_file);
}
my $gene_obj_indexer_href = {};
my $asmbl_id_to_gene_list_href = &GFF3_utils::index_GFF3_gene_objs($gff3_file, $gene_obj_indexer_href);
foreach my $asmbl_id (sort keys %$asmbl_id_to_gene_list_href) {
my @gene_ids = @{$asmbl_id_to_gene_list_href->{$asmbl_id}};
#print "ASMBL: $asmbl_id, gene_ids: @gene_ids\n";
my @gene_entries;
foreach my $gene_id (@gene_ids) {
my $gene_obj_ref = $gene_obj_indexer_href->{$gene_id};
my $model_id = $gene_obj_ref->{Model_feat_name};
my $homology_count = 0;
if ($blast_hits{$model_id}) {
$homology_count++;
}
if ($pfam_hits{$model_id}) {
$homology_count++;
}
my $struct = { gene_obj => $gene_obj_ref,
length => $gene_obj_ref->get_CDS_length(),
homology_count => $homology_count,
};
push (@gene_entries, $struct);
}
@gene_entries = sort {
$b->{homology_count} <=> $a->{homology_count}
||
$b->{length} <=> $a->{length}
} @gene_entries;
if (scalar @gene_entries > 1) {
print STDERR "ORFs prioritized as:\n";
foreach my $entry (@gene_entries) {
print STDERR "\t" . join("\t", $entry->{gene_obj}->{Model_feat_name},
"homology_count: " . $entry->{homology_count},
"len: " . $entry->{length}) . "\n";
}
}
my $best_gene_entry = shift @gene_entries;
my $gene_obj = $best_gene_entry->{gene_obj};
print $gene_obj->to_GFF3_format(source => "transdecoder") . "\n";
foreach my $remaining_gene (@gene_entries) {
print STDERR "-discarding " . $remaining_gene->{gene_obj}->{Model_feat_name} . " as not single best orf on trans\n";
}
}
exit(0);
}
## note borrowed code below from TransDecoder.predict and should consolidate. ## //FIXME
sub parse_pfam_hits_file {
my ($pfam_hits_file) = @_;
my %has_pfam_hit;
if (! -e $pfam_hits_file) {
die "Error, cannot find pfam hits file: $pfam_hits_file";
}
print "PFAM output found and processing...\n";
# capture those proteins having pfam hits
open (my $fh, $pfam_hits_file) or die "Error, cannot open file: $pfam_hits_file";
while (my $ln=<$fh>) {
next if $ln=~/^\#/;
my @x = split(/\s+/,$ln);
next unless $x[3]; # domtbl
my $orf_acc = $x[3];
$has_pfam_hit{$orf_acc} = 1;
}
close $fh;
return(%has_pfam_hit);
}
####
sub parse_blastp_hits_file {
my ($blastp_file) = @_;
unless (-e $blastp_file) {
die "Error, cannot find file $blastp_file";
}
my %blastp_hits;
open (my $fh, $blastp_file) or die "Error, cannot open file $blastp_file";
while (<$fh>) {
chomp;
my @x = split(/\t/);
my $id = $x[0];
$blastp_hits{$id} = 1;
}
close $fh;
return(%blastp_hits);
}
|
