| 1 |
#!/usr/bin/env perl |
| 2 |
# Convert colour-space FASTA sequences to nucleotide FASTA sequences. |
| 3 |
# Written by Shaun Jackman <[email protected]>. |
| 4 |
# Usage: cstofasta data.csfa >data.fa |
| 5 |
|
| 6 |
use strict; |
| 7 |
use Getopt::Long; |
| 8 |
use Pod::Usage; |
| 9 |
|
| 10 |
my %opt; |
| 11 |
GetOptions(\%opt, qw'help man'); |
| 12 |
pod2usage(-verbose => 1) if $opt{help}; |
| 13 |
pod2usage(-verbose => 2) if $opt{man}; |
| 14 |
|
| 15 |
my %table = ( |
| 16 |
'A' => ['A', 'C', 'G', 'T'], |
| 17 |
'C' => ['C', 'A', 'T', 'G'], |
| 18 |
'G' => ['G', 'T', 'A', 'C'], |
| 19 |
'T' => ['T', 'G', 'C', 'A'] |
| 20 |
); |
| 21 |
|
| 22 |
sub cs_to_nt($$) |
| 23 |
{ |
| 24 |
my $seed = shift; |
| 25 |
my $cs = shift; |
| 26 |
for (my $i = 0; $i < length $cs; $i++) { |
| 27 |
my $p = \substr($cs, $i, 1); |
| 28 |
$$p = $seed = $table{$seed}[$$p]; |
| 29 |
} |
| 30 |
return $cs; |
| 31 |
} |
| 32 |
|
| 33 |
my ($id, $comment); |
| 34 |
while (<>) { |
| 35 |
chomp; |
| 36 |
if (/^[ACGT]/) { |
| 37 |
my $seed = substr $_, 0, 1, ''; |
| 38 |
print "$id$comment\n", |
| 39 |
substr(cs_to_nt($seed, $_), 1), |
| 40 |
"\n"; |
| 41 |
} elsif (/^[0123]/) { |
| 42 |
for my $seed (qw'A C G T') { |
| 43 |
print "${id}_$seed$comment\n$seed", |
| 44 |
cs_to_nt($seed, $_), "\n"; |
| 45 |
} |
| 46 |
} elsif (/^>/) { |
| 47 |
($id, $comment) = split ' ', $_, 2; |
| 48 |
$comment = ' ' . $comment if $comment; |
| 49 |
} elsif (/^#/) { |
| 50 |
print "$_\n"; |
| 51 |
} else { |
| 52 |
die "error: what is `$_'"; |
| 53 |
} |
| 54 |
} |
| 55 |
|
| 56 |
=pod |
| 57 |
|
| 58 |
=head1 NAME |
| 59 |
|
| 60 |
abyss-cstont - convert colour-space FASTA sequences to nucleotide FASTA sequences |
| 61 |
|
| 62 |
=head1 SYNOPSIS |
| 63 |
|
| 64 |
B<cstofasta> F<data.csfa> >F<data.fa> |
| 65 |
|
| 66 |
=head1 DESCRIPTION |
| 67 |
|
| 68 |
Either reads or contigs may be converted from colour-space sequences |
| 69 |
to nucleotide sequences. If the first character of the input sequence |
| 70 |
is not a nucleotide, each colour-space contig will be converted to |
| 71 |
four nucleotide contigs, one for each possible starting nucleotide. |
| 72 |
|
| 73 |
=head1 EXAMPLE |
| 74 |
|
| 75 |
$ printf '>1\nA0000' |abyss-cstont |
| 76 |
>1 |
| 77 |
AAA |
| 78 |
|
| 79 |
$ printf '>1\n0000' |abyss-cstont |
| 80 |
>1_A |
| 81 |
AAAAA |
| 82 |
>1_C |
| 83 |
CCCCC |
| 84 |
>1_G |
| 85 |
GGGGG |
| 86 |
>1_T |
| 87 |
TTTTT |
| 88 |
|
| 89 |
=head1 AUTHOR |
| 90 |
|
| 91 |
Written by Shaun Jackman. |
| 92 |
|
| 93 |
=head1 REPORTING BUGS |
| 94 |
|
| 95 |
Report bugs to <[email protected]>. |
| 96 |
|
| 97 |
=head1 COPYRIGHT |
| 98 |
|
| 99 |
Copyright 2009 Canada's Michael Smith Genome Science Centre |
| 100 |
|
| 101 |
=head1 SEE ALSO |
| 102 |
|
| 103 |
L<ABYSS(1)> |
| 104 |
|
| 105 |
http://www.bcgsc.ca/platform/bioinfo/software/abyss |