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

die "usage:perl $0 outputDir tumor" unless @ARGV==2;
my ($outputDir,$tumor)=@ARGV;
my @mmr=("MLH1","MSH2","MSH6","PMS2","EPCAM");

open OUT,">$outputDir/MMR/${tumor}_mmr.txt";
open IN, "$outputDir/mutation/${tumor}.snp.indel.Germline.anno.hg19_multianno_filtered.txt";
open MMRPRE,">$outputDir/MMR/${tumor}.mmr.pre.txt";
my $head=<IN>;

my (@content,@mmrpre);
while(<IN>){
		chomp;
		my @line=split("\t");
		next unless grep{$line[7] eq $_}@mmr;
		push @mmrpre,"$_";
        next if $line[0]!~/1|2|3/;
        my $sig=($line[0]=='1')?'致病突变':($line[0]=='2')?'疑似致病突变':'意义未明突变';
        shift @line;
        if($line[9] ne '.'){
			my $hgvs=$line[9];
			$hgvs=~/:(NM_\d+):exon\d+:(c\.\S+):(p\.\S+)$/;
			my $gene=$line[6];
			my $tr=$1;
			my $codon=$2;
			my $protein=$3;
			my $freq=(split(":",$line[-1]))[-2];
			my $muttype=($line[8]=~/nonsynonymous SNV/)?'错义突变':($line[8]=~/^frameshift/)?'移码突变':($line[8]=~/^nonframeshift/)?'非移码突变':($line[8]=~/stopgain/)?'提前终止':'未知';
			push @content,join("\t",($gene,$tr,$codon,$protein,$freq,$muttype,$sig));
		}
}

if (@content){
	print OUT "gene\ttranscript\tc_change\tp_change\tfreq\tmuttype\tsig\n";
	print OUT join("\n",@content);
}

if (@mmrpre){
	print MMRPRE $head;
	print MMRPRE join("\n",@mmrpre)."\n";
}