#########################################################################
# Fetch the sequence surrounded the miRNA loci from a one line fasta 
# genome file
# Chen et. al
#########################################################################

#!/usr/bin/perl -w

use strict;

my$inFile=$ARGV[0];
my$genomeFile=$ARGV[1];
my$size=$ARGV[2];
my$header=1;

open(INFILE, "<$inFile")||die "cannot open $inFile:$!";
while (my$line=<INFILE>){
	if($header==1){
		$header++;
		next;
	}
	chomp $line;
	my($query_seq, $database_seq, $perc_id, $align_len, $mismatch, $gap, $q_start, $q_stop, $db_start, $db_stop, $e_val, $bit_score)=split "\t", $line;
	#find midpoint of database start and stop points
	my$midPoint=int(($db_stop+$db_start)/2);
	#get startpoint for substring
	my$startPoint=$midPoint-100;
	#make sure starting point is not negative
	if($startPoint<0){
		$startPoint=0;
	}
	open(GENOMEFILE, "<$genomeFile")||die "cannot open $genomeFile:$!";
	my$store=0;
	my$keepSeq;
	while (my$line=<GENOMEFILE>){
		my$flankingDist=$size;
		if($line=~/$database_seq\n/){
			$store=1;
			next;
		}
		if($store==1){
			#make sure substring does not go past length of sequence
			chomp $line;
			my$seqLength=length $line;
			if(($startPoint+$flankingDist)>$seqLength){
				$flankingDist=$seqLength-$startPoint;
			}
			my$flankingSeq=substr $line, $startPoint, $flankingDist;
			print "$query_seq\t$database_seq\t$flankingSeq\n";
			print "$flankingDist\n";
			$store=0;
		}
		
	}
	close GENOMEFILE;

}
close(INFILE);