/usr/bin/interpolate_sam.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 | #!/usr/bin/env perl
#
# Copyright (C) 2009 Genome Research Ltd.
#
# Author: Heng Li <lh3@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.
use strict;
use warnings;
###Builds interpolated pileup from SAM file
##@description counts bases between paired ends and piles up single end reads.
##@output, uses a #header for the RNAME and then the number of reads per base
##@author sm8@sanger.ac.uk, Stephen B. Montgomery
##@caveats
##Requires RNAME to have format as per example
## chromosome:NCBI36:18:1:76117153:1
## supercontig::NT_113883:1:137703:1
## clone::AC138827.3:1:149397:1
##Expects simple CIGAR characters, M, I and D
##Expects SAM file to be sorted.
##Expects 0x0010 to mark second read in PE file (as has been the observed case from MAQ output) (important for line 77)
##Verify and read in SAM file
my $sam_file = $ARGV[0];
if(!defined($sam_file)) { die("No sam file defined on arg 1"); }
unless(-f $sam_file) { die("Sam file does not exist: $sam_file"); }
open(SAM, $sam_file) || die("Cannot open sam file");
##Globals
my $current_location = ""; ##Current RNAME being processed
my $current_size = 0; ##Size of sequence region being processed
my $current_position = 1; ##Current base being processed
my $open = 0; ##Number of open reads (PE reads that have not been closed)
my %close = (); ##Hash of closing positions, when the current_position gets to this position it subtracts the
##contained value from those open and deletes the indexed position from the hash
while (my $line = <SAM>) {
my @tokens = split /\t/, $line;
if ($current_location ne $tokens[2]) { ##Start a new sequence region
for (my $i = $current_position; $i <= $current_size; $i++) { ##Close the previous sequence region
if (defined($close{$i})) {
$open = $open - $close{$i};
delete $close{$i};
}
print $open . "\n";
}
if ($current_location ne "") {
print "\n";
}
##Initiate a new sequence region
my @location_tokens = split /:/, $tokens[2];
$current_position = 1;
$current_location = $tokens[2];
$current_size = $location_tokens[4];
$open = 0;
%close = ();
print "#" . $tokens[2] . "\n";
##Print pileup to just before the first read (will be 0)
for (my $current_position = 1; $current_position < $tokens[3]; $current_position++) {
print $open . "\n";
}
$current_position = $tokens[3];
} else { ##Sequence region already open
if ($tokens[3] > $current_position) { ##If the new read's position is greater than the current position
##cycle through to catch up to the current position
for (my $i = $current_position; $i < $tokens[3]; $i++) {
if (defined($close{$i})) {
$open = $open - $close{$i};
delete $close{$i};
}
print $open . "\n";
}
$current_position = $tokens[3];
}
}
$open++; ##Increment the number of open reads
if (($tokens[1] & 0x0080 || $tokens[1] & 0x0040) && $tokens[1] & 0x0010 && $tokens[1] & 0x0002) { ##if second read of mate pair, add close condition
$open--;
my $parsed_cig = &parseCigar($tokens[5]);
my $seq_region_end = $tokens[3] + $parsed_cig->{'M'} + $parsed_cig->{'D'} - 1;
if (!defined($close{$seq_region_end + 1})) { $close{$seq_region_end + 1} = 0; }
$close{$seq_region_end + 1} = $close{$seq_region_end + 1} + 1;
} elsif (!($tokens[1] & 0x0001) || !($tokens[1] & 0x0002)) { ##if unpaired, add close condition
my $parsed_cig = &parseCigar($tokens[5]);
my $seq_region_end = $tokens[3] + $parsed_cig->{'M'} + $parsed_cig->{'D'} - 1;
if (!defined($close{$seq_region_end + 1})) { $close{$seq_region_end + 1} = 0; }
$close{$seq_region_end + 1} = $close{$seq_region_end + 1} + 1;
} else {
#do nothing
}
}
for (my $i = $current_position; $i <= $current_size; $i++) { ##Finish up the last sequence region
if (defined($close{$i})) {
$open = $open - $close{$i};
delete $close{$i};
}
print $open . "\n";
}
print "\n";
close(SAM);
exit(0);
##reads and tokenizes simple cigarline
sub parseCigar() {
my $cigar_line = shift;
$cigar_line =~ s/([0-9]*[A-Z]{1})/$1\t/g;
my @cigar_tokens = split /\t/, $cigar_line;
my %parsed = ('M' => 0,
'I' => 0,
'D' => 0);
my @events = ();
for(my $i = 0; $i < scalar(@cigar_tokens); $i++) {
if ($cigar_tokens[$i] =~ /([0-9]+)([A-Z]{1})/g) {
if (!defined($parsed{$2})) { $parsed{$2} = 0; }
my $nt = $2;
if ($nt ne "M" && $nt ne "D" && $nt ne "I") { $nt = "M"; }
$parsed{$nt} += $1;
my %event_el = ("t" => $nt,
"n" => $1);
push @events, \%event_el;
}
}
$parsed{'events'} = \@events;
return \%parsed;
}
|