Mercurial > repos > alan-blakely > filter_by_substring_match
changeset 2:397067d90a77 draft
Deleted selected files
| author | alan-blakely |
|---|---|
| date | Thu, 21 Aug 2014 15:57:43 -0400 |
| parents | 9af08aa008de |
| children | b41c88a53578 |
| files | submatch/submatch.pl submatch/submatch.xml |
| diffstat | 2 files changed, 0 insertions(+), 90 deletions(-) [+] |
line wrap: on
line diff
--- 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 (<SEQ>){ - chomp(); - $seq[$i] = $_; - $i++; -} -while (<REP>){ - $rep[$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]"); -
--- 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 @@ - -<tool id="pmatch" name="Filter by Substring Match"> - - <description>This tool allows for partial sequences to match lines containing a larger, more complete sequence. </description> - - <command interpreter="perl">submatch.pl $sequences $report $output </command> - - <inputs> - - <param format="tabular" name="sequences" type="data" label="Tabular file containing list to filter on."/> - <param format="tabular" name="report" type="data" label="Tabular file to be filtered."/> - - </inputs> - - <outputs> - <data format="tabular" name="output" /> - </outputs> - <tests> - <test> - <param name="sequences" value="submatch_input.tab"/> - <param name="report" value="submatch_input2.tab"/> - <output name="output" file="submatch_output.tab"/> - </test> - </tests> - -<help> - - - -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. - - - - - -</help> - -</tool>