Supplemental File S2. perl scripts used to filter for genotype likelihood and strand bias.

#!/usr/bin/perl
use strict;
use warnings;

###script to filter VCF file for calls where the minimum difference between genotype likelihoods (PL) is less than 21. 

my ($input, $output) = @ARGV; #input and output

open (IN, "<$input") or die "cant open $input - $!";
open (OUT, ">$output") or die "cant write to $output - $!";

my $PL_threshold = "21";

while ( <IN> ){
    my $row = $_;
    my @output_array = ();
    if ($row =~ m/^#/) { #ignore header rows
	  print OUT "$row";
	}      
    if ($row !~ m/^#/) { 
        my @cells = split; 
        foreach my $cell (@cells){
            if ($cell !~ m/^.\/./) {
		@output_array = (@output_array, $cell);
	    }	    
	    if ($cell =~ m/(.\/.):(\d+,\d+,\d+|\d+,\d+,\d+,\d+,\d+,\d+|\d+,\d+,\d+,\d+,\d+,\d+,\d+,\d+,\d+,\d+):(\d+):(\d+):(\d+):(\d+,\d+|\d+,\d+,\d+|\d+,\d+,\d+,\d+)/) {   
		my @PL_array = (split(/,/,$2));
		my @sorted_PL = sort { $a <=> $b } @PL_array;
		my $PL_diff = ($sorted_PL[1]-$sorted_PL[0]);
		if ($PL_diff > $PL_threshold) {
		    @output_array = (@output_array, $cell);
		}
		if ($PL_diff <= $PL_threshold) {
		    my $new_cell = "./.:$2:$3:$4:$5:$6";
		    @output_array = (@output_array, $new_cell);
		}		    
            }
	    elsif ($cell =~m/(.\/.):(\d+):(\d+):(\d+):(\d+,\d+|\d+,\d+,\d+|\d+,\d+,\d+,\d+)/) {
		    @output_array = (@output_array, $cell);
	    } 
        }
       print OUT join ("\t",@output_array,"\n");
       @output_array = ();
    }
}
close IN;
close OUT;


###script to filter VCF file for calls which show evidence of statistically significant strand bias (SP, p > 0.05).

my ($input, $output) = @ARGV; #input and output in the command line

open (IN, "<$input") or die "cant open $input - $!";
open (OUT, ">$output") or die "cant write to $output - $!";

my $SP_threshold = "13"; #translates to p > 0.05

while ( <IN> ){
    my $row = $_;
    my @output_array = ();
    if ($row =~ m/^#/) { 
	  print OUT "$row";
	}      
    if ($row !~ m/^#/) { 
        my @cells = split; 
        foreach my $cell (@cells){

            if ($cell !~ m/^.\/./) {	
		@output_array = (@output_array, $cell);
	    }          	    
	    if ($cell =~ m/(.\/.):(\d+,\d+,\d+|\d+,\d+,\d+,\d+,\d+,\d+|\d+,\d+,\d+,\d+,\d+,\d+,\d+,\d+,\d+,\d+):(\d+):(\d+):(\d+):(\d+,\d+|\d+,\d+,\d+|\d+,\d+,\d+,\d+)/) {   
		if ($5 < $SP_threshold) {				  
		    @output_array = (@output_array, $cell);
		}
		elsif ($5 >= $SP_threshold) {				  
		    my $new_cell = "./.:$2:$3:$4:$5:$6";
		    @output_array = (@output_array, $new_cell);
		}		    
            }
	    elsif ($cell =~m/(.\/.):(\d+):(\d+):(\d+):(\d+,\d+|\d+,\d+,\d+|\d+,\d+,\d+,\d+)/) {
		if ($4 < $SP_threshold) {
		    @output_array = (@output_array, $cell);
		}
		elsif ($4 >= $SP_threshold) {
		    my $new_cell = "./.:$2:$3:$4:$5";
		    @output_array = (@output_array, $new_cell);
		}
	    }
        }
       print OUT join ("\t",@output_array,"\n");	
       @output_array = ();
    }
}

close IN;
close OUT;


###Examples of genotype formats:
##VARIANT site format:
#GT:PL:DP:DV:SP:DPR	1/1:237,57,0:19:19:0:0,19
#GT:PL:DP:DV:SP:DPR	1/1:221,37,0,224,57,231:20:19:0:1,19,0
#GT:PL:DP:DV:SP:DPR	1/2:60,3,0,60,3,60,60,3,60,60:1:1:0:0,1,0,0
#GT:PL:DP:DV:SP:DPR	1/1:142,18,0,142,18,142,142,18,142,142:6:6:0:0,6,0,0
##INVARIANT site format:
#GT:DP:DV:SP:DPR	0/0:24:0:0:24,0	or 0/0:42:1:0:41,1,0 or 0/0:42:1:0:41,1,0,0