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

die "usage:perl $0 outputDir tumor" unless @ARGV==2;
my ($outputDir,$tumor)=@ARGV;
my @hhr1=("ATM","BARD1","BRCA1","BRCA2","BRIP1","CDK12","CHEK1","CHEK2","FANCL","PALB2","RAD51B","RAD51C","RAD51D","RAD54L");
my @hrr2=("PPP2R2A","ARID1A","ATR","ATRX","BAP1","BLM","FANCA","FANCC","FANCD2","FANCE","FANCF","FANCG","FANCI","MDC1","MRE11","NBN","PTEN","RAD50","RAD51","XRCC2");
my @hrr3=("ATM","BARD1","BRCA1","BRCA2","BRIP1","CDK12","CHEK1","CHEK2","FANCL","PALB2","PPP2R2A","RAD51B","RAD51C","RAD51D","RAD54L","ARID1A","ATR","ATRX","BAP1","BLM","FANCA","FANCC","FANCD2","FANCE","FANCF","FANCG","FANCI","MDC1","MRE11","NBN","PTEN","RAD50","RAD51","XRCC2");

open OUT,">$outputDir/HRR/${tumor}_hrr.txt";
open IN1, "$outputDir/mutation/${tumor}.snp.indel.Germline.anno.hg19_multianno_filtered.txt";
open HRRPRE, ">$outputDir/HRR/${tumor}.hrr.pre.txt";
my $head=<IN1>;
my (@content,@hrrpre);
while(<IN1>){
	chomp;
	my @line=split("\t");
	next unless grep{$line[7] eq $_}@hrr3;
	push @hrrpre,$_;
	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]))[4];
		my $freq=(split(":",$line[-2]))[-2];
		my $FREQ=$freq=~s/%//r;
		next if $FREQ<10;
		my $genotype=($FREQ<=90?"杂合型":"纯合型");
#		$freq=join("",($freq*100,'%'));
		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,$protein,$genotype,$muttype,$sig));
	}
}

open IN2, "$outputDir/mutation/${tumor}.snp.indel.Somatic.annoall.hg19_multianno_filtered.txt";
<IN2>;
while(<IN2>){
	chomp;
	my @line=split("\t");
	next if $line[0] ne '1';
	next unless grep{$line[7] eq $_}@hrr3;
	push @hrrpre,$_;
	my $sig;
	if($line[17]=~/pathogenic|Affects|association|Conflicting|sensitivity|drug|other|risk|protective|Uncertain|not_provided|\./i){
                if($line[17]=~/Likely_pathogenic|drug/i){
                        $sig="疑似致病突变";
                }elsif($line[17]=~/pathogenic/i and $line[17]!~/Conflicting/i){
                        $sig="致病突变";
                }else{
                        $sig="意义未明突变";
                }
    }
	
	next unless $sig;
	shift @line;
	if($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]))[4];
		my $freq=(split(":",$line[-2]))[-2];
#		my $FREQ=$freq=~s/%//r;
#		next if $FREQ<3;
#		$freq=join("",($freq*100,'%'));
		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':($line[8]=~/stopgain/)?'提前终止':'未知';
		if(grep{$gene eq $_}@hrr1 and ($sig eq "致病突变" or $sig eq "疑似致病突变")){
			$sig="I级";
		}elsif(grep{$gene eq $_}@hrr2 and ($sig eq "致病突变" or $sig eq "疑似致病突变")){
			$sig="II级";
		}else{
			$sig="III级";
		}
		push @content,join("\t",($gene,$tr,$codon,$protein,$muttype,$freq,$sig));
	}
}

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

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