chrM:307	0	AGCGGGGA	129
chrM:307	0	AGCGGGGA	130
chrM:307	0	AGCGGGGA	129
chrM:308	0	AGCGGGGA	129
chrM:308	0	AGCGGGGA	130
chrM:308	0	AGCGGGGA	129
chrM:309	0	AGCGGGGA	129
chrM:309	0	AGCGGGGA	130
chrM:309	0	AGCGGGGA	129
chrM:307	0	TCAAAATG	130
chrM:308	0	TCAAAATG	130
chrM:309	0	TCAAAATG	130
chrM:307	0	TCACGGTG	130
chrM:308	0	TCACGGTG	130
chrM:309	0	TCACGGTG	130
chrM:307	0	TCAGCCTG	129
chrM:308	0	TCAGCCTG	129
chrM:309	0	TCAGCCTG	129
chrM:307	0	TCAGGGAG	130
chrM:308	0	TCAGGGAG	130
chrM:309	0	TCAGGGAG	130
chrM:307	1	TCAGGGTG	106
chrM:307	2	TCAGGGTG	130
chrM:307	2	TCAGGGTG	129
chrM:308	1	TCAGGGTG	106
chrM:308	2	TCAGGGTG	130
chrM:308	2	TCAGGGTG	129
chrM:309	1	TCAGGGTG	106
chrM:309	2	TCAGGGTG	130
chrM:309	2	TCAGGGTG	129

##</code><code>##

chrM:307	0	AGCGGGGA	130     #-->Line1
chrM:307	0	TCAAAATG	130     #-->Line2
chrM:307	0	TCACGGTG	130     #-->Line3
chrM:307	0	TCAGGGAG	130     #-->Line4
chrM:307	2	TCAGGGTG	130     #-->Line5
chrM:307	0	AGCGGGGA	129     #-->Line6
chrM:307	0	AGCGGGGA	129     #-->Line7
chrM:307	0	TCAGCCTG	129     #-->Line8
chrM:307	2	TCAGGGTG	129     #-->Line9
chrM:307	1	TCAGGGTG	106     #-->Line10

##</code><code>##

CLUSTER
chrM:307	0	AGCGGGGA	130     #--> Select, first line sorted by col3, col2, col4(rev sort)    # Line1
chrM:307	0	AGCGGGGA	129     #--> Select line with similar UMI  (NO mismatch)                # Line6
chrM:307	0	AGCGGGGA	129     #--> Select line with similar UMI  (NO mismatch)                # Line7
CLUSTER
chrM:307	0	TCAAAATG	130     #--> Now selected, Second line sorted by col3, col2, col4(rev sort)  #Line2 # NO similar UMI, 1 line cluster
CLUSTER
chrM:307	0	TCACGGTG	130     #--> Now selected, Third line sorted by col3, col2, col4(rev sort)  # Line3
chrM:307	0	TCAGGGAG	130     #--> Select line with similar UMI  (Two mismatch with line3 UMI)    # Line4
chrM:307	2	TCAGGGTG	130     #--> Select line with similar UMI  (One mismatch with line3 UMI)    # Line5
chrM:307	2	TCAGGGTG	129     #--> Select line with similar UMI  (One mismatch with line3 UMI)    # Line9
chrM:307	1	TCAGGGTG	106     #--> Select line with similar UMI  (One mismatch with line3 UMI)    # Line10
CLUSTER
chrM:307	0	TCAGCCTG	129     #--> Now selected, line#8 sorted by col3, col2, col4(rev sort)      #Line8, make single line cluster
CLUSTER
....and so on for next chr positions...

##</code><code>##

CLUSTER
chrM:307	1	TCAGGGTG	106
chrM:307	2	TCAGGGTG	130
chrM:307	2	TCAGGGTG	129
chrM:307	0	TCAGGGAG	130
chrM:307	0	TCAGCCTG	129
chrM:307	0	TCACGGTG	130
CLUSTER
chrM:307	0	TCAAAATG	130
CLUSTER
chrM:307	0	AGCGGGGA	129
chrM:307	0	AGCGGGGA	130
chrM:307	0	AGCGGGGA	129
CLUSTER
chrM:308	1	TCAGGGTG	106
chrM:308	2	TCAGGGTG	130
chrM:308	2	TCAGGGTG	129
chrM:308	0	TCAGGGAG	130
chrM:308	0	TCAGCCTG	129
chrM:308	0	TCACGGTG	130
CLUSTER
chrM:308	0	TCAAAATG	130
CLUSTER
chrM:308	0	AGCGGGGA	129
chrM:308	0	AGCGGGGA	130
chrM:308	0	AGCGGGGA	129
CLUSTER
chrM:309	1	TCAGGGTG	106
chrM:309	2	TCAGGGTG	130
chrM:309	2	TCAGGGTG	129
chrM:309	0	TCAGGGAG	130
chrM:309	0	TCAGCCTG	129
chrM:309	0	TCACGGTG	130
CLUSTER
chrM:309	0	TCAAAATG	130
CLUSTER
chrM:309	0	AGCGGGGA	129
chrM:309	0	AGCGGGGA	130
chrM:309	0	AGCGGGGA	129
CLUSTER

##</code><code>##

#!/usr/bin/env/perl

#use strict;
#use warnings;

my $InSam = $ARGV[0];
my $SampleID = $ARGV[1];
chomp $InSam;
chomp $SampleID;


open(DATA, "$InSam") || die "Can't open $InSam: $!\n";
open my $OFILE, '>', $SampleID.'.cluster_ChrPos.txt' or die "Cannot create file for output: $!";

use strict;
my %seen=();
my @flds;
my $UMI;

my @cluster_ChrPos;
while (<DATA>)
{
chomp;
@flds=split /\t/;

my $POS;




	if ($seen{$flds[0]}++)
		{
				$UMI=$flds[2];
				my @subpats;
				for my $i (0..length($UMI)-1) {
				for my $j ($i+1..length($UMI)-1) {
				my $subpat = join('',
				substr($UMI, 0, $i),
				'.',  # or '\\w'
				substr($UMI, $i+1, $j-$i-1),
				'.',  # or '\\w'
				substr($UMI, $j+1),
				);
				push @subpats, $subpat;
				}
				}

				my $pat = join('|', @subpats);
						
		if($flds[0] =~ m/"$pat"/)
			{
			#print "$pat\t$flds[0]";
			push (@cluster_ChrPos, "$_");
			push (@cluster_ChrPos, "\n");
			}
		else
			{
			#push (@cluster_ChrPos, "DELIMIT\n");
			push (@cluster_ChrPos, "$_");
			push (@cluster_ChrPos, "\n");	
			}
		}	
		else
			{
			push (@cluster_ChrPos, "DELIMIT\n");
			push (@cluster_ChrPos, "$_");
			push (@cluster_ChrPos, "\n");
			}
}
push (@cluster_ChrPos, "DELIMIT");

print  $OFILE  "@cluster_ChrPos\n";
print  "@cluster_ChrPos\n";
close $OFILE;
close DATA;