This file is indexed.

/usr/bin/sam2vcf.pl is in samtools 1.7-1.

This file is owned by root:root, with mode 0o755.

The actual contents of the file can be viewed below.

  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
#!/usr/bin/env perl
#
#    Copyright (C) 2009, 2010 Genome Research Ltd.
#
#    Author: Petr Danecek <pd3@sanger.ac.uk>
#
# Permission is hereby granted, free of charge, to any person obtaining a copy
# of this software and associated documentation files (the "Software"), to deal
# in the Software without restriction, including without limitation the rights
# to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
# copies of the Software, and to permit persons to whom the Software is
# furnished to do so, subject to the following conditions:
#
# The above copyright notice and this permission notice shall be included in
# all copies or substantial portions of the Software.
#
# THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
# IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
# FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL
# THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
# LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
# FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER
# DEALINGS IN THE SOFTWARE.

# VCF specs: http://www.1000genomes.org/wiki/doku.php?id=1000_genomes:analysis:vcf3.3

use strict;
use warnings;
use Carp;

my $opts = parse_params();
do_pileup_to_vcf($opts);

exit;

#---------------

sub error
{
    my (@msg) = @_;
    if ( scalar @msg ) { croak(@msg); }
    die
        "Usage: sam2vcf.pl [OPTIONS] < in.pileup > out.vcf\n",
        "Options:\n",
        "   -h, -?, --help                  This help message.\n",
        "   -i, --indels-only               Ignore SNPs.\n",
        "   -r, --refseq <file.fa>          The reference sequence, required when indels are present.\n",
        "   -R, --keep-ref                  Print reference alleles as well.\n",
        "   -s, --snps-only                 Ignore indels.\n",
        "   -t, --column-title <string>     The column title.\n",
        "\n";
}


sub parse_params
{
    my %opts = ();

    $opts{fh_in}  = *STDIN;
    $opts{fh_out} = *STDOUT;

    while (my $arg=shift(@ARGV))
    {
        if ( $arg eq '-R' || $arg eq '--keep-ref' ) { $opts{keep_ref}=1; next; }
        if ( $arg eq '-r' || $arg eq '--refseq' ) { $opts{refseq}=shift(@ARGV); next; }
        if ( $arg eq '-t' || $arg eq '--column-title' ) { $opts{title}=shift(@ARGV); next; }
        if ( $arg eq '-s' || $arg eq '--snps-only' ) { $opts{snps_only}=1; next; }
        if ( $arg eq '-i' || $arg eq '--indels-only' ) { $opts{indels_only}=1; next; }
        if ( $arg eq '-?' || $arg eq '-h' || $arg eq '--help' ) { error(); }

        error("Unknown parameter \"$arg\". Run -h for help.\n");
    }
    return \%opts;
}

sub iupac_to_gtype
{
    my ($ref,$base) = @_;
    my %iupac = (
            'K' => ['G','T'],
            'M' => ['A','C'],
            'S' => ['C','G'],
            'R' => ['A','G'],
            'W' => ['A','T'],
            'Y' => ['C','T'],
            );
    if ( !exists($iupac{$base}) )
    {
        if ( $base ne 'A' && $base ne 'C' && $base ne 'G' && $base ne 'T' ) { error("FIXME: what is this [$base]?\n"); }
        if ( $ref eq $base ) { return ('.','0/0'); }
        return ($base,'1/1');
    }
    my $gt = $iupac{$base};
    if ( $$gt[0] eq $ref  ) { return ($$gt[1],'0/1'); }
    elsif ( $$gt[1] eq $ref ) { return ($$gt[0],'0/1'); }
    return ("$$gt[0],$$gt[1]",'1/2');
}


sub parse_indel
{
    my ($cons) = @_;
    if ( $cons=~/^-/ )
    {
        my $len = length($');
        return "D$len";
    }
    elsif ( $cons=~/^\+/ ) { return "I$'"; }
    elsif ( $cons eq '*' ) { return undef; }
    error("FIXME: could not parse [$cons]\n");
}


# An example of the pileup format:
#   1       3000011 C       C       32      0       98      1       ^~,     A
#   1       3002155 *       +T/+T   53      119     52      5       +T      *       4       1       0
#   1       3003094 *       -TT/-TT 31      164     60      11      -TT     *       5       6       0
#   1       3073986 *       */-AAAAAAAAAAAAAA       3       3       45      9       *       -AAAAAAAAAAAAAA 7       2       0
#
sub do_pileup_to_vcf
{
    my ($opts) = @_;

    my $fh_in  = $$opts{fh_in};
    my $fh_out = $$opts{fh_out};
    my ($prev_chr,$prev_pos,$prev_ref);
    my $refseq;
    my $ignore_indels = $$opts{snps_only} ? 1 : 0;
    my $ignore_snps   = $$opts{indels_only} ? 1 : 0;
    my $keep_ref      = $$opts{keep_ref} ? 1 : 0;
    my $title = exists($$opts{title}) ? $$opts{title} : 'data';

    print $fh_out
        qq[##fileformat=VCFv3.3\n],
        qq[##INFO=DP,1,Integer,"Total Depth"\n],
        qq[##FORMAT=GT,1,String,"Genotype"\n],
        qq[##FORMAT=GQ,1,Integer,"Genotype Quality"\n],
        qq[##FORMAT=DP,1,Integer,"Read Depth"\n],
        qq[#CHROM\tPOS\tID\tREF\tALT\tQUAL\tFILTER\tINFO\tFORMAT\t$title\n]
        ;

    while (my $line=<$fh_in>)
    {
        chomp($line);
        my (@items) = split(/\t/,$line);
        if ( scalar @items<8 )
        {
            error("\nToo few columns, does not look like output of 'samtools pileup -c': $line\n");
        }
        my ($chr,$pos,$ref,$cons,$cons_qual,$snp_qual,$rms_qual,$depth,$a1,$a2) = @items;
        $ref  = uc($ref);
        $cons = uc($cons);

        my ($alt,$gt);
        if ( $ref eq '*' )
        {
            # An indel is involved.
            if ( $ignore_indels )
            {
                $prev_ref = $ref;
                $prev_pos = $pos;
                $prev_chr = $chr;
                next;
            }

            if (!defined $prev_chr || $chr ne $prev_chr || $pos ne $prev_pos)
            {
                if ( !$$opts{refseq} ) { error("Cannot do indels without the reference.\n"); }
                if ( !$refseq ) { $refseq = Fasta->new(file=>$$opts{refseq}); }
                $ref = $refseq->get_base($chr,$pos);
                $ref = uc($ref);
            }
            else { $ref = $prev_ref; }

            # One of the alleles can be a reference and it can come in arbitrary order. In some
            #   cases */* can be encountered. In such a case, look in the additional columns.
            my ($al1,$al2) = split(m{/},$cons);
            if ( $al1 eq $al2 && $al1 eq '*' ) { $al1=$a1; $al2=$a2; }
            my $alt1 = parse_indel($al1);
            my $alt2 = parse_indel($al2);
            if ( !$alt1 && !$alt2 ) { error("FIXME: could not parse indel:\n", $line); }
            if ( !$alt1 )
            {
                $alt=$alt2;
                $gt='0/1';
            }
            elsif ( !$alt2 )
            {
                $alt=$alt1;
                $gt='0/1';
            }
            elsif ( $alt1 eq $alt2 )
            {
                $alt="$alt1";
                $gt='1/1';
            }
            else
            {
                $alt="$alt1,$alt2";
                $gt='1/2';
            }
        }
        else
        {
            if ( $ignore_snps || (!$keep_ref && $ref eq $cons) )
            {
                $prev_ref = $ref;
                $prev_pos = $pos;
                $prev_chr = $chr;
                next;
            }

            # SNP
            ($alt,$gt) = iupac_to_gtype($ref,$cons);
        }

        print $fh_out "$chr\t$pos\t.\t$ref\t$alt\t$snp_qual\t0\tDP=$depth\tGT:GQ:DP\t$gt:$cons_qual:$depth\n";

        $prev_ref = $ref;
        $prev_pos = $pos;
        $prev_chr = $chr;
    }
}


#------------- Fasta --------------------
#
# Uses samtools to get a requested base from a fasta file. For efficiency, preloads
#   a chunk to memory. The size of the cached sequence can be controlled by the 'size'
#   parameter.
#
package Fasta;

use strict;
use warnings;
use Carp;

sub Fasta::new
{
    my ($class,@args) = @_;
    my $self = {@args};
    bless $self, ref($class) || $class;
    if ( !$$self{file} ) { $self->throw(qq[Missing the parameter "file"\n]); }
    $$self{chr}  = undef;
    $$self{from} = undef;
    $$self{to}   = undef;
    if ( !$$self{size} ) { $$self{size}=10_000_000; }
    bless $self, ref($class) || $class;
    return $self;
}

sub read_chunk
{
    my ($self,$chr,$pos) = @_;
    my $to = $pos + $$self{size};
    my $cmd = "samtools faidx $$self{file} $chr:$pos-$to";
    my @out = `$cmd`;
    if ( $? ) { $self->throw("$cmd: $!"); }
    my $line = shift(@out);
    if ( !($line=~/^>$chr:(\d+)-(\d+)/) ) { $self->throw("Could not parse: $line"); }
    $$self{chr}  = $chr;
    $$self{from} = $1;
    $$self{to}   = $2;
    my $chunk = '';
    while ($line=shift(@out))
    {
        chomp($line);
        $chunk .= $line;
    }
    $$self{chunk} = $chunk;
    return;
}

sub get_base
{
    my ($self,$chr,$pos) = @_;
    if ( !$$self{chr} || $chr ne $$self{chr} || $pos<$$self{from} || $pos>$$self{to} )
    {
        $self->read_chunk($chr,$pos);
    }
    my $idx = $pos - $$self{from};
    return substr($$self{chunk},$idx,1);
}

sub throw
{
    my ($self,@msg) = @_;
    croak(@msg);
}