Test fixes and first attampt to clean up short read tools

tools/metag_tools/short_reads_figure_score.py

@@ -230,7 +230,7 @@ def __main__():
     if (tmp_varied_length is False):
         r.boxplot(score_matrix,xlab="location in read length",main=title)
     else:
-        r.boxplot(score_matrix,xlab="percentage in read length",xaxt="n",main=title)
+        r.boxplot(score_matrix,xlab="position within read (% of total length)",xaxt="n",main=title)
         x_old_range = []
         x_new_range = []
         step = 100/number_of_points 

tools/metag_tools/short_reads_figure_score.xml

@@ -5,7 +5,7 @@
 
 <inputs>
 <page>
-    <param name="input1" type="data" format="qualityscore, txtseq.zip" label="Quality score file" />
+    <param name="input1" type="data" format="qualityscore, txtseq.zip" label="Quality score file" help="No dataset? Read tip below"/>
 </page>
 </inputs>
 
@@ -28,39 +28,59 @@
 
 .. class:: warningmark
 
-Your file needs to be a specific Galaxy **qualityscore** datatype (unless it is in zip format). Please click on the pencil symbol in the history panel to change the file format. 
+**TIP**. To use this tool your dataset needs to be in *Quality Score* format. Click pencil icon next to your dataset to set datatype to *Quality Score* (see below for examples of quality scores).
 
 -----
 
 **What it does**
 
-This tool takes quality score files and outputs a pdf file showing score distribution.
-
-Currently, the tool accepts two file formats: 
-
-- fasta: for **454** data
-- tabular: for **Solexa** data. Only take the maximal value from each 4 quality scores.
-
-You can also upload your files in a zip file format and use this tool.
+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.
 
 -----
 
-**Example**
+**Examples of Quality Data**
 
-454 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
 
-Solexa data::
+Illumina (Solexa) data::
 
- 	-40  -40   40  -40	 -40  -40  -40   40	 -40  -40   40  -40	  40  -40  -40  -40	 -40  -40  -40   40	  
+ 	-40 -40 40 -40	 -40 -40 -40 40	 
  
-boxplot::
+-----
 
-    For showing purpose, this figure is not generated from the above examples.
+**Output example**
+
+Quality scores are summarized as boxplot:
 
 .. image:: ../static/images/short_reads_boxplot.png
 
+where the X-axis is coordiante 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
+                   that box length away from the box
+       o     &lt;---- Outlier
+ 
+ 
+     
 </help>
 </tool>

tools/taxonomy/find_diag_hits.xml

@@ -1,8 +1,8 @@
 <tool id="find_diag_hits" name="Find" version="1.0.0">
     <description>diagnostic hits</description>
-    <command interpreter="python">find_diag_hits.py $input $id_col $rank_list $out_format $out_file1</command>
+    <command interpreter="python">find_diag_hits.py $input1 $id_col $rank_list $out_format $out_file1</command>
     <inputs>
-        <param format="taxonomy" name="input" type="data" label="Find diagnostic hits in"/>
+        <param format="taxonomy" name="input1" type="data" label="Find diagnostic hits in"/>
         <param name="id_col" type="data_column" data_ref="input" numerical="False" label="Select column with sequence id" />
         <param name="rank_list" type="select" display="checkboxes" multiple="true" label="select taxonomic ranks">
             <option value="superkingdom">Superkingdom</option>
@@ -37,7 +37,7 @@
     </outputs>
       <tests>
     <test>
-      <param name="input" value="taxonomyGI.dat"/>
+      <param name="input1" value="taxonomyGI.dat" type="taxonomy"/>
       <param name="id_col" value="1" />
       <param name="rank_list" value="order,genus" />
       <param name="out_format" value="counts" />

tools/taxonomy/t2t_report.xml

@@ -9,7 +9,7 @@
     </outputs>
       <tests>
     <test>
-      <param name="input" value="taxonomyGI.dat"/>
+      <param name="input" value="taxonomyGI.dat" ftype="taxonomy"/>
       <output name="out_file1" file="t2t_report.dat"/>
     </test>
   </tests>