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
|
#!/usr/bin/env perl
use strict;
use warnings;
use lib ("/usr/lib/trinityrnaseq/PerlLib");
use Fasta_reader;
use Nuc_translator;
use Data::Dumper;
use Getopt::Long qw(:config posix_default no_ignore_case bundling pass_through);
my $usage = <<__EOUSAGE__;
###################################################
#
# Required:
#
# --genome_fa <string> genome fasta file
#
# --flattened_gff <string> flattened gff file
#
# Optional:
#
# --no_revcomp do not revcomp reverse strand transcripts
#
###################################################
__EOUSAGE__
;
my $genome_fa;
my $flattened_gff;
my $NO_REVCOMP_FLAG = 0;
my $help_flag;
&GetOptions ( 'h' => \$help_flag,
'genome_fa=s' => \$genome_fa,
'flattened_gff=s' => \$flattened_gff,
'no_revcomp' => \$NO_REVCOMP_FLAG,
);
if ($help_flag) {
die $usage;
}
unless ($genome_fa && $flattened_gff) {
die $usage;
}
main: {
my $fasta_reader = new Fasta_reader($genome_fa);
my %seqs = $fasta_reader->retrieve_all_seqs_hash();
my %gene_to_transcripts = &parse_gff($flattened_gff);
unless (%gene_to_transcripts) {
die "Error, no gff records parsed. Be sure to use the flattened gff file";
}
#die Dumper(\%gene_to_transcripts);
foreach my $gene (keys %gene_to_transcripts) {
my @transcripts = keys %{$gene_to_transcripts{$gene}};
my $transcript_counter = 0;
foreach my $transcript (@transcripts) {
$transcript_counter += 1;
my @regions = @{$gene_to_transcripts{$gene}->{$transcript}};
@regions = sort {$a->{lend}<=>$b->{lend}} @regions;
my $trans_seq = "";
my @path_coords;
foreach my $region (@regions) {
my $lend = $region->{lend};
my $rend = $region->{rend};
my $chr = $region->{chr};
my $exon_number = $region->{exon_number};
my $seg_len = $rend - $lend + 1;
my $seq_seg = substr($seqs{$chr}, $lend-1, $seg_len);
push (@path_coords, [$exon_number, length($trans_seq)+1, length($trans_seq) + length($seq_seg)]);
$trans_seq .= $seq_seg;
}
if ($regions[0]->{orient} eq '-' && ! $NO_REVCOMP_FLAG) {
# revcomp everthing
$trans_seq = &reverse_complement($trans_seq);
my $trans_len = length($trans_seq);
foreach my $path_coord (@path_coords) {
my $new_rend = $trans_len - $path_coord->[1] + 1;
my $new_lend = $trans_len - $path_coord->[2] + 1;
($path_coord->[1], $path_coord->[2]) = ($new_lend, $new_rend);
}
@path_coords = sort {$a->[1]<=>$b->[1]} @path_coords;
}
## construct header
my @path_text;
foreach my $path_coord (@path_coords) {
my ($exon_number, $lend, $rend) = @$path_coord;
$lend--;
$rend--;
push (@path_text, "$exon_number:$lend-$rend");
}
my $header = ">${gene}_i${transcript_counter} path=[" . join(" ", @path_text) . "]";
print "$header\n$trans_seq\n";
}
}
exit(0);
}
####
sub parse_gff {
my ($gff_file) = @_;
my %gene_to_transcripts;
open(my $fh, $gff_file) or die $!;
while (<$fh>) {
chomp;
my @x = split(/\t/);
my $chr = $x[0];
my $feat_type = $x[2];
my $lend = $x[3];
my $rend = $x[4];
my $orient = $x[6];
my $info = $x[8];
unless ($feat_type eq "exonic_part") { next; }
$info =~ /transcripts \"([^\"]+)\";.*\s+exonic_part_number \"(\d+)\"; gene_id \"([^\"]+)\"/ or die "Error, cannot parse $info";
my $transcripts_list = $1;
my $exonic_part_number = $2;
my $gene_id = $3;
my $region_struct = { chr => $chr,
lend => $lend,
rend => $rend,
orient => $orient,
exon_number => $exonic_part_number,
};
my @transcripts = split(/\+/, $transcripts_list);
foreach my $transcript (@transcripts) {
push (@{$gene_to_transcripts{$gene_id}->{$transcript}}, $region_struct);
}
}
close $fh;
return(%gene_to_transcripts);
}
|
