diff tools/metag_tools/short_reads_figure_high_quality_length.xml @ 0:9071e359b9a3

Uploaded
author xuebing
date Fri, 09 Mar 2012 19:37:19 -0500
parents
children
line wrap: on
line diff
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/tools/metag_tools/short_reads_figure_high_quality_length.xml	Fri Mar 09 19:37:19 2012 -0500
@@ -0,0 +1,75 @@
+<tool id="hist_high_quality_score" name="Histogram">
+<description> of high quality score reads </description>
+
+<command interpreter="python">short_reads_figure_high_quality_length.py $input1 $output1 $input2</command>
+
+<inputs>
+<page>
+    <param name="input1" type="data" format="qualsolexa,qual454,txtseq.zip" label="Quality score file" help="No dataset? Read tip below"/>
+    <param name="input2" type="integer" size="5" value="20" label="Quality score threshold" />
+</page>
+</inputs>
+<outputs>
+  	<data name="output1" format="pdf" />
+</outputs>
+<requirements>
+	<requirement type="python-module">rpy</requirement>
+</requirements>
+<tests>
+	<test>
+		<param name="input1" value="solexa.qual" ftype="qualsolexa" />
+		<param name="input2" value="5" />
+  		<output name="output1" file="solexa_high_quality_hist.pdf" ftype="pdf"/>
+	</test>
+	<test>
+		<param name="input1" value="454.qual" ftype="qual454" />
+		<param name="input2" value="5" />
+		<output name="output1" file="454_high_quality_hist.pdf" ftype="pdf"/>
+	</test>
+</tests>
+
+<help>
+
+.. class:: warningmark
+
+To use this tool, your dataset needs to be in the *Quality Score* format. Click the pencil icon next to your dataset to set the datatype to *Quality Score* (see below for examples).
+
+-----
+
+**What it does**
+
+This tool takes Quality Files generated by Roche (454), Illumina (Solexa), or ABI SOLiD machines and builds a histogram of lengths of high quality reads.
+
+-----
+
+**Examples of Quality Data**
+
+Roche (454) or ABI SOLiD data::
+
+	&gt;seq1
+	23 33 34 25 28 28 28 32 23 34 27 4 28 28 31 21 28
+
+Illumina (Solexa) data::
+
+ 	-40 -40 40 -40	 -40 -40 -40 40	 
+ 
+-----
+
+**Note**
+
+- Quality score data::
+
+	&gt;seq1
+	23 33 34 25 28 28 28 32 23 34 27 4 28 28 31 21 28
+
+- If the threshold is set to 20:
+
+  - a low quality score 4 in the middle separated two segments of lengths 11 and 5.
+
+  - The histogram will be built based on the numbers (11, 5).
+	 	
+- For Illumina (Solexa) data, only the maximal of the 4 values will be used.
+
+
+</help>
+</tool>