diff Scan_IUPAC_output_each_match.xml @ 0:b67ea47730d3 draft

Version 1.0.1.
author pjbriggs
date Wed, 21 Mar 2018 06:39:41 -0400
parents
children
line wrap: on
line diff
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/Scan_IUPAC_output_each_match.xml	Wed Mar 21 06:39:41 2018 -0400
@@ -0,0 +1,96 @@
+<?xml version="1.0" encoding="utf-8"?>
+<tool id="fasta_scan_iupac_each" name="IUPAC scan and output each match" version="@VERSION@">
+  <description>Returns all matches to a given IUPAC in GFF format</description>
+  <macros>
+    <import>motif_tools_macros.xml</import>
+  </macros>
+  <expand macro="requirements" />
+  <command><![CDATA[
+  perl $__tool_directory__/Scan_IUPAC_output_each_match.pl $iupac $fasta $output $label $strand
+  ]]></command>
+  <inputs>
+    <param name="iupac" type="text" label="IUPAC string" value="e.g. WGATAR" help="Enter an IUPAC string." size="20"/>
+    <param format="fasta" name="fasta" type="data" label="FASTA file" help="Select a FASTA file containing the sequences to be scanned."/>
+    <param name="label" type="text" label="Attribute in GFF output" value="IUPAC_or_name" help="The label will be included at the end (attibute) section of each GFF line. This could be the IUPAC string used or the name of the motif." size="20"/>
+    <param name="strand" type="select" label="Select sequence strands to scan" help="Scan either both strands or only the forward strand.">
+      <option value="0">Scan both strands</option>
+      <option value="1">Only scan forward strand</option>
+    </param>
+  </inputs>
+  <outputs>
+    <data format="gff" name="output" />
+  </outputs>
+  <tests>
+    <test>
+      <param name="iupac" value="WGATAR" />
+      <param name="fasta" value="phix.fa" />
+      <param name="label" value="IUPAC_or_name" />
+      <param name="strand" value="0" />
+      <output name="output" file="iupac_each_match.gff" />
+    </test>
+  </tests>
+
+  <help>
+.. class:: infomark
+
+**What it does**
+
+This tool will find all matches to a DNA pattern in the input DNA sequence, represented by an IUPAC string. The matches are non-overlapping, so searching with 'TTTT' in 'TTTTTTTT' will find two hits to the IUPAC. The output is in GFF format and the last 'attribute' field can be specified using the 'Label' option.
+
+IUPAC = Nucleotide(s):
+
+A = A
+ 
+C = C
+
+G = G
+
+T = T
+
+M = A/C
+
+R = A/G
+
+W = A/T
+
+S = C/G
+
+Y = C/T
+
+K = G/T
+
+V = A/C/G
+
+H = A/C/T
+
+D = A/G/T
+
+B = C/G/T
+
+N = A/C/G/T
+ 
+----
+
+.. class:: infomark
+
+**Options**
+
+'IUPAC string' - can be entered as upper- or lower-case as the tool will force them to become upper-case, but will only accept the IUPAC codes listed above.
+
+'Attribute in GFF output' - the last field of each GFF line 'attribute' can be specified using the 'Label' option, this should only include letters/numbers, but without spaces.
+
+'Select sequence strands to scan' - Only scanning the forward strand of the input sequence is useful if the IUPAC is a palindrome (e.g. CANNTG).
+
+----
+
+.. class:: infomark
+
+**Credits**
+
+This Galaxy tool has been developed within the Bioinformatics Core Facility at the University of Manchester. It runs the Scan_IUPAC_output_each_match.pl Perl script that was written by Ian Donaldson.
+
+Please kindly acknowledge both this Galaxy tool and Scan_IUPAC_output_each_match.pl if you use it.
+  </help>
+
+</tool>
+