changeset 5:de26b312c0d2 draft

planemo upload for repository https://gitlab.com/paulklemm_PHD/proteinortho commit b4d8b8da2a259973c9ad90e4b9d1a3e22ae4348f

--- a/proteinortho_macros.xml	Tue Nov 22 16:50:38 2022 +0000
+++ b/proteinortho_macros.xml	Fri Jun 16 20:52:56 2023 +0000
@@ -1,6 +1,6 @@
 <?xml version="1.0"?>
 <macros>
-   <token name="@TOOL_VERSION@">6.1.2</token>
+   <token name="@TOOL_VERSION@">6.2.3</token>
    <token name="@WRAPPER_VERSION@">1</token>
    <token name="@PROFILE@">20.09</token>
    <xml name="citations">
@@ -12,12 +12,10 @@
     <xml name="requirements">
         <requirements>
             <requirement type="package" version="@TOOL_VERSION@">proteinortho</requirement>
-            <!-- blast, blat, and last are not in the biopython requirements
-                 diamond is, but latest version does not work: https://gitlab.com/paulklemm_PHD/proteinortho/-/issues/55 -->
-            <requirement type="package" version="2.0.15">diamond</requirement>
+            <requirement type="package" version="2.1.4">diamond</requirement>
             <requirement type="package" version="2.13.0">blast</requirement>
             <requirement type="package" version="377">ucsc-blat</requirement>
-            <requirement type="package" version="1418">last</requirement>
+            <requirement type="package" version="1422">last</requirement>
         </requirements>
     </xml>
     <xml name="version_command">

--- a/proteinortho_summary.xml	Tue Nov 22 16:50:38 2022 +0000
+++ b/proteinortho_summary.xml	Fri Jun 16 20:52:56 2023 +0000
@@ -7,9 +7,6 @@
     <expand macro="version_command"/>
     <command detect_errors="exit_code"><![CDATA[
         export TERM=dumb &&
-        ## TODOs:
-        ## - check if 2>&1 can be removed https://gitlab.com/paulklemm_PHD/proteinortho/-/merge_requests/9
-        ## - include output0.tsv as Galaxy output?
         proteinortho_summary.pl 
             $queryfile
             #if $queryfile2:
@@ -19,6 +16,7 @@
             | awk '/^$/ && !f{f=1;next}1' ## remove potentially present 1st empty line
             | awk 'BEGIN{i=0} /^$/{i+=1}{print > ("output" i ".tsv")}' ## split file at empty lines
         &&
+        mv output0.tsv '$distribution' &&
         mv output1.tsv '$adjacencyMat' &&
         mv output2.tsv '$average1paths' &&
         mv output3.tsv '$adjacencyMatSquared' &&
@@ -29,14 +27,20 @@
         <param name="queryfile2" type="data" format="tabular" optional="true" label="(optional) A second orthology-pairs / RBH file" help="If you provide a second file, then difference is calculated (GRAPH - second GRAPH)"/>
     </inputs>
     <outputs>
+        <data name="distribution" format="tabular" label="${tool.name} on ${on_string}: Protein-Group distribution"/>
         <data name="adjacencyMat" format="tabular" label="${tool.name} on ${on_string}: Adjacency Matrix"/>
         <data name="average1paths" format="tabular" label="${tool.name} on ${on_string}: Average number of Edges"/>
         <data name="adjacencyMatSquared" format="tabular" label="${tool.name} on ${on_string}: Matrix of 2-paths"/>
         <data name="average2paths" format="tabular" label="${tool.name} on ${on_string}: Average number of 2-paths"/>
     </outputs>
     <tests>
-        <test expect_num_outputs="4">
+        <test expect_num_outputs="5">
             <param name="queryfile" value="result.proteinortho-graph"/>
+            <output name="distribution">
+                <assert_contents>
+                    <has_text text="%"/>
+                </assert_contents>
+            </output>
             <output name="adjacencyMat">
                 <assert_contents>
                     <has_text text="18"/>
@@ -66,7 +70,7 @@
                 </assert_contents>
             </output>
         </test>
-        <test expect_num_outputs="4">
+        <test expect_num_outputs="5">
             <param name="queryfile" value="result.proteinortho-graph"/>
             <param name="queryfile2" value="result.blast-graph"/>
             <output name="average2paths">
@@ -77,6 +81,15 @@
                 </assert_contents>
             </output>
         </test>
+        <test expect_num_outputs="5">
+            <param name="queryfile" value="result.blast-graph"/>
+            <output name="average2paths">
+                <assert_contents>
+                    <has_text text="115.2"/>
+                    <has_text text="TERM" negate="true"/>
+                </assert_contents>
+            </output>
+        </test>
     </tests>
     <help><![CDATA[proteinortho summary
 
@@ -84,6 +97,8 @@
 
 proteinortho_summary : Summaries the (orthology-pairs/RBH) file(s) to determine how well the species are connected to each other.
 
+ * **Protein-Group distribution** (for orthology-pairs) : This report contains overal statistics about the output. (i) Number of groups that contains at least p% input species (with p ranging between 0 and 100). (ii) number of groups for each input species.
+
  * **Adjacency Matrix** : How well are the species connected to each other directly.
 
  * **Average number of Edges** : Averaged number of connections for each species.
@@ -92,7 +107,6 @@
 
  * **Average number of 2-paths** : The average number of 2-paths for each species. If a species is not well connected to all the other species, it will result in a low average.
 
-
 If you supply a second orthology-pairs/RBH then the difference is calculated for all 4 outputs.
 
 E.g. given the RBH and the orthology-pairs of the same run : The outputs show how much the clustering removed from the initial reciprocal best hit graph.