diff short_reads_figure_score.xml @ 0:b52b9c7aabd9 draft default tip

Imported from capsule None

--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/short_reads_figure_score.xml	Mon May 19 12:35:00 2014 -0400
@@ -0,0 +1,87 @@
+<tool id="quality_score_distribution" name="Build base quality distribution" version="1.0.2">
+<description></description>
+<requirements>
+    <requirement type="package" version="2.11.1">fontconfig</requirement>
+    <requirement type="package" version="1.0.3">rpy</requirement>
+    <requirement type="package" version="2.11.0">R</requirement>
+</requirements>
+<command interpreter="python">short_reads_figure_score.py $input1 $output1 </command>
+<inputs>
+<page>
+    <param name="input1" type="data" format="qualsolexa, qual454" label="Quality score file" help="No dataset? Read tip below"/>
+</page>
+</inputs>
+
+<outputs>
+  	<data name="output1" format="png" />
+</outputs> 
+<tests>
+	<test>
+		<param name="input1" value="solexa.qual" ftype="qualsolexa" />
+  		<output name="output1" file="solexaScore.png" ftype="png" />
+	</test>
+	<test>
+		<param name="input1" value="454.qual" ftype="qual454" />
+		<output name="output1" file="454Score.png" ftype="png" />
+	</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 graph showing score distribution like the one below. Such graph allows you to perform initial evaluation of data quality in a single pass.
+
+-----
+
+**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	 
+ 
+-----
+
+**Output example**
+
+Quality scores are summarized as boxplot (Roche 454 FLX data):
+
+.. image:: short_reads_boxplot.png
+
+where the **X-axis** is coordinate along the read and the **Y-axis** is quality score adjusted to comply with the Phred score metric. Units on the X-axis depend on whether your data comes from Roche (454) or Illumina (Solexa) and ABI SOLiD machines:
+
+  - For Roche (454) X-axis (shown above) indicates **relative** position (in %) within reads as this technology produces reads of different lengths;
+  - For Illumina (Solexa) and ABI SOLiD X-axis shows **absolute** position in nucleotides within reads.
+  
+Every box on the plot shows the following values::
+
+       o     &lt;---- Outliers
+       o
+      -+-    &lt;---- Upper Extreme Value that is no more 
+       |           than box length away from the box   
+       |
+    +--+--+  &lt;---- Upper Quartile
+    |     |
+    +-----+  &lt;---- Median
+    |     |
+    +--+--+  &lt;---- Lower Quartile 
+       |
+       |
+      -+-    &lt;---- Lower Extreme Value that is no more
+                   than box length away from the box
+       o     &lt;---- Outlier
+ 
+ 
+     
+</help>
+</tool>