# HG changeset patch # User alan-blakely # Date 1408651063 14400 # Node ID 397067d90a7782286762cac77a8cb574862c68d2 # Parent 9af08aa008de327004829d8b159317d75744f0a1 Deleted selected files diff -r 9af08aa008de -r 397067d90a77 submatch/submatch.pl --- a/submatch/submatch.pl Thu Aug 21 12:52:21 2014 -0400 +++ /dev/null Thu Jan 01 00:00:00 1970 +0000 @@ -1,41 +0,0 @@ -#!/usr/bin/perl -w -use strict; -my (@seq, @rep, $i, $n, $l, $t); - -open (SEQ, "<$ARGV[0]"); -open (REP, "<$ARGV[1]"); -open (OUT, ">$ARGV[2]"); - - -$i=$n=$l=0; - - - -while (){ - chomp(); - $seq[$i] = $_; - $i++; -} -while (){ - $rep[$n] = $_; - $n++; - -} -while ($l < $i){ - $t=0; - while ($t < $n){ - print OUT $rep[$t] if $rep[$t] =~ /$seq[$l]/; - $t++; - } - $l++; -} - - - -close (SEQ); -close (REP); -close (OUT); - -#optional: remove duplicate lines using server-side shell command -system("sort", "-u", "-o", "$ARGV[2]", "$ARGV[2]"); - diff -r 9af08aa008de -r 397067d90a77 submatch/submatch.xml --- a/submatch/submatch.xml Thu Aug 21 12:52:21 2014 -0400 +++ /dev/null Thu Jan 01 00:00:00 1970 +0000 @@ -1,49 +0,0 @@ - - - - This tool allows for partial sequences to match lines containing a larger, more complete sequence. - - submatch.pl $sequences $report $output - - - - - - - - - - - - - - - - - - - - - - - -Each line from the list file is converted to a regular expression of the form .*LINE.* - - - -Lines from the second file that match the expression are returned. - - - - -This tool allows for partial sequences to match lines containing a larger more complete sequence. - -Example: a file containing fragment amino acid sequences is used to select corresponding lines from a peptide report. - - - - - - - -