File: gmod_gff3_preprocessor.pl

package info (click to toggle)
libchado-perl 1.31-6
  • links: PTS, VCS
  • area: main
  • in suites: bookworm, bullseye, sid
  • size: 44,716 kB
  • sloc: sql: 282,721; xml: 192,553; perl: 25,524; sh: 102; python: 73; makefile: 57
file content (338 lines) | stat: -rwxr-xr-x 10,322 bytes parent folder | download | duplicates (4)
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
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
#!/usr/bin/env perl
use strict;
use warnings;

use Bio::FeatureIO;
use Getopt::Long;
use FileHandle;
#use lib '/home/cain/cvs_stuff/schema/chado/lib';
#use lib '/home/scott/cvs_stuff/schema/chado/lib';
use Bio::GMOD::DB::Adapter;
use Bio::GMOD::Config;
use Bio::GMOD::DB::Config;

=head1 NAME

$0 - Prepares a GFF3 file for bulk loading into a chado database.

=head1 SYNOPSIS

  % gmod_gff_preprocessor [options] --gfffile <filename>

=head1 COMMAND-LINE OPTIONS

 --gfffile        The file containing GFF3 (optional, can read
                     from stdin)
 --outfile        The name kernel that will be used for naming result files
 --splitfile      Split the files into more manageable chunks, providing
                     an argument to control splitting
 --onlysplit      Split the files and then quit (ie, don't sort)
 --nosplit        Don't split the files (ie, only sort)
 --hasrefseq      Set this if the file contains a reference sequence line
                     (Only needed if not splitting files)
 --dbprofile      Specify a gmod.conf profile name (otherwise use default)
 --inheritance_tiers How many levels of inheritance do you expect tis file
                     to have (default: 3)

=head1 DESCRIPTION


splitfile  -- Just setting this flag to 1 will cause the file to be split 
by reference sequence.  If you provide an optional argument, it will be
further split according to these rules:

 source=1     Splits files according to the value in the source column
 source=a,b,c Puts lines with sources that match (via regular expression)
                     'a', 'b', or 'c' in a separate file
 type=a,b,c   Puts lines with types that match 'a', 'b', or 'c' in a
                     separate file

For example, if you wanted all of your analysis results to go in a separate
file, you could indicate '--splitfile type=match', and all cDNA_match,
EST_match and cross_genome_match features would go into separate files
(separate by reference sequence).

inheritence_tiers -- The number of levels of inheritance this file has. 
For example, if the file has "central dogma" genes in it (gene/mRNA/
exon,polypeptide), then it has 3.  Up to 4 is supported but the higher
the number, the more slowly it performs.  If you don't know, 3 is a 
reasonable guess.

=head2 FASTA sequence

If the GFF3 file contains FASTA sequence at the end, the sequence
will be placed in a separate file with the extension '.fasta'.  This
fasta file can be loaded separately after the split and/or sorted
GFF3 files are loaded, using the command:

  gmod_bulk_load_gff3.pl -g <fasta file name>

=head1 AUTHOR

Scott Cain E<lt>cain@cshl.orgE<gt>

Copyright (c) 2006-2007

This library is free software; you can redistribute it and/or modify
it under the same terms as Perl itself.

=cut

my (@GFFFILE, $OUTFILE, $SPLITFILE,$ONLYSPLIT,$NOSPLIT,$HASREFSEQ,
    $DBPROFILE, $INHERITANCE_TIERS);

GetOptions(
    'gfffile=s'   => \@GFFFILE,
    'outfile=s'   => \$OUTFILE,
    'splitfile=s' => \$SPLITFILE,
    'onlysplit'   => \$ONLYSPLIT,
    'nosplit'     => \$NOSPLIT,
    'hasrefseq'   => \$HASREFSEQ,
    'dbprofile=s' => \$DBPROFILE,
    'inheritance_tiers=i' => \$INHERITANCE_TIERS,
) or ( system( 'pod2text', $0 ), exit -1 );

@GFFFILE = split(/,/,join(',',@GFFFILE));

$DBPROFILE ||='default';

$INHERITANCE_TIERS ||= 3;

my ($split_on_source, $split_on_type, $split_on_ref);
if ($SPLITFILE) {
    if ($SPLITFILE and $SPLITFILE !~ /=/ and $SPLITFILE == 1) {
        $split_on_ref = 1;
    } 
    else {
        my @splits = split /;/, $SPLITFILE;
        for (@splits) {
            my ($tag, $value) = split /=/;
            $value            =~ s/,/|/g;
            if ($tag eq 'source') {
                $split_on_source = $value;
            }
            elsif ($tag eq 'type') {
                $split_on_type   = $value;
            }
            else {
                die "unsupported splitfile tag: $tag\n";
            }
        }
    }
}


my %has_ref_seq;
my @gfffiles;
for my $GFFFILE (@GFFFILE) {
  $GFFFILE  ||='-';
  $OUTFILE  ||="$GFFFILE.out.gff3";
  my $FASTA = "$OUTFILE.fasta";

  if ($SPLITFILE && !$NOSPLIT) {

    open GFFIN, "<", $GFFFILE or die "couldn't open $GFFFILE for reading: $!";
    open FASTA, ">", $FASTA or die " couldn't open $FASTA for writing: $!";

    my $fasta_flag = 0;
    my %files;
    while ( <GFFIN> ) {
        if (/^##FASTA/) {
            $fasta_flag = 1;
            print FASTA;
            next;
        } elsif ($fasta_flag) {
            print FASTA;
            next;
        }
        next if /^#/;
        my @la = split /\t/;

        (warn "ignored gff line: $_" && next) if (scalar @la != 9);

        my $has_ref_seq;
        chomp $la[8];
        if ( $la[8] =~ /ID=([^;]+);*.*$/ ) {
            my $id = $1;
            if ( $id eq $la[0] ) {
                $has_ref_seq = $id;
            } 
        }

        if ( $split_on_source && $split_on_source eq 1 ) {
            my $source = $la[1];
            my $filename = "$la[0].$la[1].$OUTFILE";
            unless ( defined $files{ $filename } ) {
                $files{ $filename } = new FileHandle $filename, "w";
                push @gfffiles, $filename;
            }
            $files{ $filename }->print( $_ );

            push @{$has_ref_seq{ $filename }}, $has_ref_seq if $has_ref_seq;
        }
        elsif ( $split_on_source && $la[1] =~ /$split_on_source/) {
            my $filename = "$la[0].source.$OUTFILE";
            unless ( defined $files{ $filename } ) {
                $files{ $filename } = new FileHandle $filename, "w";
                push @gfffiles, $filename;
            }
            $files{ $filename }->print( $_ );

            push @{$has_ref_seq{ $filename }}, $has_ref_seq if $has_ref_seq;
        }
        elsif ( $split_on_type && $la[2] =~ /$split_on_type/) {
            my $filename = $la[0].'.type.'.$OUTFILE;
            unless ( defined $files{ $filename } ) {
                $files{ $filename } = new FileHandle $filename, "w";
                push @gfffiles, $filename;
            } 
            $files{ $filename }->print( $_ );
 
            push @{$has_ref_seq{ $filename }}, $has_ref_seq if $has_ref_seq;
        }
        else {
            my $filename = $la[0].'.'.$OUTFILE;
            unless ( defined $files{ $filename } ) {
                $files{ $filename } = new FileHandle $filename, "w";
                push @gfffiles, $filename;
            }
            $files{ $filename }->print( $_ );

            push @{$has_ref_seq{ $filename }}, $has_ref_seq if $has_ref_seq; 
        }
    } 

    for my $key (keys %files) {
        $files{$key}->close;
    }
  }
  else {
    push @gfffiles, $GFFFILE;
    push @{ $has_ref_seq{ $GFFFILE } }, $GFFFILE if $HASREFSEQ;
  }

}
exit(0) if $ONLYSPLIT;

my $gmod_conf = Bio::GMOD::Config->new();
my $db_conf   = Bio::GMOD::DB::Config->new($gmod_conf, $DBPROFILE);
my $db        = Bio::GMOD::DB::Adapter->new(
                    dbuser  => $db_conf->user,
                    dbpass  => $db_conf->password || '',
                    dbhost  => $db_conf->host,
                    dbport  => $db_conf->port,
                    dbname  => $db_conf->name,
                    notransact => 1, 
                    skipinit   => 1,
                );

$db->sorter_create_table;
for my $gfffile (@gfffiles) {
    $db->sorter_delete_from_table;

    my $outfile = $gfffile.'.sorted';
    my $fasta   = "$outfile.fasta";

    open IN, "<", $gfffile or die "couldn't open $gfffile for reading: $!\n";

    my $fasta_flag = 0;
    print STDERR "Sorting the contents of $gfffile ...\n";
    while( <IN> ) {
        if (/^##FASTA/) {
            $fasta_flag = 1;
            open FASTA, 
                 ">", $fasta or die "couldn't open $fasta for writing: $!\n";

            #print FASTA "##gff-version 3\n";
            #print FASTA;
            #print FASTA "\n";  #extra cr works around bug in Bio::FeatureIO::gff
            next;
        }
        elsif ($fasta_flag) {
            print FASTA;
            next;
        }
        my $line       = $_;
        my @line_array = split /\t/, $line;

        if ($line =~ /^#/ or scalar @line_array != 9) {
            next;
        }

        my $refseq = $line_array[0];

        my ($id, @parents,@derives_froms);
        if ( $line_array[8] =~ /ID=([^;]+);*.*$/ ) {
            $id = $1;
            chomp $id;
        }
        if ( $line_array[8] =~ /Parent=([^;]+);*.*$/ ) {
            @parents       = split /,/, $1;
        }
        if ( $line_array[8] =~ /Derives_from=([^;]+);*.*$/ ) {
            @derives_froms = split /,/, $1;
        }

        if (@parents > 0 || @derives_froms > 0) {
            for my $parent ( (@parents,@derives_froms) ) {
                chomp $parent;
                $db->sorter_insert_line($refseq, $id, $parent, $line);
            }
        }
        elsif ($id) {
            $db->sorter_insert_line($refseq, $id, undef, $line);
        }
        else {
            $db->sorter_insert_line($refseq, undef, undef, $line);
        }
    }
    close IN;
    close FASTA if $fasta_flag;

    print STDERR "Writing sorted contents to $outfile ...\n";
    open OUT,">", $outfile or die "couldn't open $outfile for writing: $!\n";

#to print:
#   -get ref seqs (refseq == id)
#   -get things with no parent

    print OUT "##gff-version 3\n";

    my @refseqs = $db->sorter_get_refseqs();
    for my $refseq (@refseqs) {
        print OUT $refseq;      #already has the line feed
    }

    my @no_parents = $db->sorter_get_no_parents();
    for my $no_parent (@no_parents) {
        print OUT $no_parent;
    }
    @no_parents = '';

    if ($INHERITANCE_TIERS >= 2) {
        my @second_tiers = $db->sorter_get_second_tier();
        for my $second_tier (@second_tiers) {
            print OUT $second_tier;
        }
    }

    if ($INHERITANCE_TIERS >= 3) {
        my @third_tiers = $db->sorter_get_third_tier();
        for my $third_tier (@third_tiers) {
            print OUT $third_tier;
        }
    }

#yes, four tiers can happen, like transposible_element->te_gene->mRNA->exon
    if ($INHERITANCE_TIERS >= 4) {
        my @forth_tiers = $db->sorter_get_fourth_tier();
        for my $fourth_tier (@forth_tiers) {
            print OUT $fourth_tier;
        }
    }

    close OUT;

}