perl/etc/bs/fVarScan.pl

   1 #!/usr/bin/env perl
   2 use strict;
   3 use warnings;
   4 use Data::Dump qw(ddx);
   5
   6 die "Usage: $0 <VarScan file> >out.txt\n" if @ARGV < 1;
   7 #@ARGV;
   8 my $IN = shift;
   9
  10 my @thePOS = qw(chrom position);
  11 my @SELECTED = qw(ref normal_reads1 normal_reads2 normal_var_freq normal_gt tumor_reads1 tumor_reads2 tumor_var_freq tumor_gt somatic_status tumor_reads1_plus tumor_reads2_minus);
  12 my @Print = qw(normal_reads1 normal_reads2 normal_var_freq normal_gt tumor_reads1 tumor_reads2 tumor_var_freq tumor_gt tumor_reads1_plus tumor_reads2_minus);
  13
  14 open I,'<',$IN or die "Error opening $IN: $!\n";
  15 my ($id,$flag,@tmpstr) = (0,0);
  16 my (%hash,@in);
  17 chomp(my $t = <I>);
  18 my @tt = split("\t",$t);
  19 map { s/_read(\d)$/_reads$1/ } @tt;
  20 while(<I>) {
  21         chomp;
  22         @hash{@tt} = split /\t/;
  23         @in[0,1] = @hash{@thePOS};
  24         $in[2] = [@hash{@SELECTED}];
  25         next if $in[2]->[9] ne 'Somatic';
  26         next if $in[2]->[4] ne $in[2]->[0];
  27         next if $in[2]->[1]<15 or $in[2]->[2]!=0 or ($in[2]->[5]+$in[2]->[6])<20 or $in[2]->[6]<1;
  28         my $t = $in[2]->[7];
  29         $t =~ s/%$//;
  30         next if $t < 20;
  31         next if $in[2]->[10]<1 or $in[2]->[11]<0;
  32         #ddx \@in;
  33         print join("\t",@in[0,1],join(',',@hash{qw(ref var)}),join(',',@hash{@Print})),"\n";
  34 }
  35 close I;
  36
  37 __END__
  38 1.normal组织没有一个和ref不一样的，并且深度大于20，并且正负链都有支持ref的read。
  39 2. cancer组织深度大于15，突变碱基的频率大于20%。并且正负链都有支持突变的read。
  40
  41 normal_read1 >=15, normal_read2==0; tumor_read2>1; tumor_var_freq>20%; tumor_reads2_plus>=1;   tumor_reads2_minus>=0;
  42 tumor_read1+tumor_read2 >=20.