Mercurial > repos > kkonganti > cfsan_bettercallsal

comparison 0.5.0/bin/fasta_join.pl @ 1:365849f031fd

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
"planemo upload"
author kkonganti
date Mon, 05 Jun 2023 18:48:51 -0400
parents
children
comparison
equal deleted inserted replaced
0:a4b1ee4b68b1 1:365849f031fd
1 #!/usr/bin/env perl
2
3 # Kranti Konganti
4 # Takes in a gzipped multi-fasta file
5 # and joins contigs by 10 N's
6
7 use strict;
8 use warnings;
9 use Cwd;
10 use Bio::SeqIO;
11 use Getopt::Long;
12 use File::Find;
13 use File::Basename;
14 use File::Spec::Functions;
15
16 my ( $in_dir, $out_dir, $suffix, @uncatted_genomes );
17
18 GetOptions(
19 'in_dir=s' => \$in_dir,
20 'out_dir=s' => \$out_dir,
21 'suffix=s' => \$suffix
22 ) or die usage();
23
24 $in_dir = getcwd if ( !defined $in_dir );
25 $out_dir = getcwd if ( !defined $out_dir );
26 $suffix = '_genomic.fna.gz' if ( !defined $suffix );
27
28 find(
29 {
30 wanted => sub {
31 push @uncatted_genomes, $File::Find::name if ( $_ =~ m/$suffix$/ );
32 }
33 },
34 $in_dir
35 );
36
37 if ( $out_dir ne getcwd && !-d $out_dir ) {
38 mkdir $out_dir || die "\nCannot create directory $out_dir: $!\n\n";
39 }
40
41 open( my $geno_path, '>genome_paths.txt' )
42 || die "\nCannot open file genome_paths.txt: $!\n\n";
43
44 foreach my $uncatted_genome_path (@uncatted_genomes) {
45 my $catted_genome_header = '>' . basename( $uncatted_genome_path, $suffix );
46 $catted_genome_header =~ s/(GC[AF]\_\d+\.\d+)\_*.*/$1/;
47
48 my $catted_genome =
49 catfile( $out_dir, $catted_genome_header . '_scaffolded' . $suffix );
50
51 $catted_genome =~ s/\/\>(GC[AF])/\/$1/;
52
53 print $geno_path "$catted_genome\n";
54
55 open( my $fh, "gunzip -c $uncatted_genome_path |" )
56 || die "\nCannot create pipe for $uncatted_genome_path: $!\n\n";
57
58 open( my $fho, '|-', "gzip -c > $catted_genome" )
59 || die "\nCannot pipe to gzip: $!\n\n";
60
61 my $seq_obj = Bio::SeqIO->new(
62 -fh => $fh,
63 -format => 'Fasta'
64 );
65
66 my $joined_seq = '';
67 while ( my $seq = $seq_obj->next_seq ) {
68 $joined_seq = $joined_seq . 'NNNNNNNNNN' . $seq->seq;
69 }
70
71 $joined_seq =~ s/NNNNNNNNNN$//;
72 $joined_seq =~ s/^NNNNNNNNNN//;
73
74 # $joined_seq =~ s/.{80}\K/\n/g;
75 # $joined_seq =~ s/\n$//;
76 print $fho $catted_genome_header, "\n", $joined_seq, "\n";
77
78 $seq_obj->close();
79 close $fh;
80 close $fho;
81 }
82
83 sub usage {
84 print
85 "\nUsage: $0 [-in IN_DIR] [-ou OUT_DIR] [-su Filename Suffix for Header]\n\n";
86 exit;
87 }
88