diff sam2Bed_bowtie.pl @ 21:9dcffd531c76 draft

Uploaded
author big-tiandm
date Wed, 05 Nov 2014 21:09:35 -0500
parents 07745c0958dd
children
line wrap: on
line diff
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/sam2Bed_bowtie.pl	Wed Nov 05 21:09:35 2014 -0500
@@ -0,0 +1,74 @@
+#!/usr/bin/perl -w
+#Filename:
+#Author: Tian Dongmei
+#Email: tiandm@big.ac.cn
+#Date: 2011/11/7
+#Modified:
+#Description: sam2BED 
+my $version=1.00;
+
+use strict;
+use Getopt::Long;
+
+my %opts;
+GetOptions(\%opts,"i=s","mark=s","o=s","h");
+if (!(defined $opts{i} and defined $opts{o}) || defined $opts{h}) { #necessary arguments
+&usage;
+}
+
+my $filein=$opts{'i'};
+my $fileout=$opts{'o'};
+my $mark=$opts{'mark'};
+my @sample=split/\#/,$mark;
+$mark=join"\t",@sample;
+open OUT,">$fileout"; #output file  
+print OUT "#chr\tstrand\tstart\tend\t$mark\n";
+
+open IN,"<$filein"; #input file  
+my $Tags_num=0;
+my @read_num;
+#print OUT "#chr\tstart\tend\tnum\t<=20\t21\t22\t23\t24\t>=25\n";
+while (my $aline=<IN>) {
+	chomp $aline;
+	next if($aline=~/^\@/);
+	my @tmp=split/\t/,$aline;
+	my $strand=$tmp[1];
+	my $start=$tmp[3]+1;
+	my $length=length($tmp[4]);
+	my $end=$start+$length-1;
+	my $hit=$tmp[6]+1;
+	#======express caculate weighted===================================
+		my $exp;
+		my @tempID=split/\:/,$tmp[0];
+		my @exp=split/\_/,$tempID[1];
+		pop @exp;
+		for (my $j=0;$j<@exp ;$j++) {
+			#my @tempID1=split/\=/,$tempID[$j];
+			$exp[$j]=sprintf("%.2f",$exp[$j]/$hit);
+			$read_num[$j]+=$exp[$j];
+			#print OUT "\t$exp";
+		}
+		$exp=join "\t",@exp;
+		print OUT $tmp[2],"\t",$strand,"\t",$start,"\t",$end,"\t",$exp,"\n";
+		$Tags_num++;
+
+}
+print "Total Tags numer: $Tags_num\n";
+my $read_number=join "\t",@read_num;
+print "Each sample numer: $read_number\n";
+close IN;
+close OUT;
+sub usage{
+print <<"USAGE";
+Version $version
+Usage:
+$0 -i -o
+options:
+-i input file
+-mark sampleA	sampleB	sampleC.....
+-o output file
+-h help
+USAGE
+exit(1);
+}
+