diff w4mkmeans.xml @ 1:02cafb660b72 draft

planemo upload for repository https://github.com/HegemanLab/w4mkmeans_galaxy_wrapper/tree/master commit f600ce8a783df16e49272341dce0fc6bbc299b0a

--- a/w4mkmeans.xml	Tue Aug 08 15:30:38 2017 -0400
+++ b/w4mkmeans.xml	Wed Aug 09 18:06:55 2017 -0400
@@ -1,5 +1,5 @@
-<tool id="w4mkmeans" name="Kmeans_for_W4M" version="0.98.1">
-  <description>Calculate K-means for dataMatrix features or samples</description>
+<tool id="w4mkmeans" name="w4mKmeans" version="0.98.3">
+  <description>Calculate K-means for W4M dataMatrix features or samples</description>
 
   <requirements>
     <requirement type="package" version="3.3.2">r-base</requirement>
@@ -14,18 +14,19 @@
   <command detect_errors="aggressive"><![CDATA[
     Rscript $__tool_directory__/w4mkmeans_wrapper.R
       tool_directory $__tool_directory__
+      algorithm '$algorithm'
+      categorical_prefix '$categoricalPrefix'
       data_matrix_path '$dataMatrix_in'
-      variable_metadata_path '$variableMetadata_in'
-      sample_metadata_path '$sampleMetadata_in'
-      ksamples '$ksamples'
-      kfeatures '$kfeatures'
       iter_max '$iter_max'
+      kfeatures '$kfeatures'
+      ksamples '$ksamples'
       nstart '$nstart'
-      algorithm '$algorithm'
+      sampleMetadata_out '$sampleMetadata_out'
+      sample_metadata_path '$sampleMetadata_in'
       scores_out '$scores_out'
-      sampleMetadata_out '$sampleMetadata_out'
+      slots "\${GALAXY_SLOTS:-1}"
       variableMetadata_out '$variableMetadata_out'
-      slots "\${GALAXY_SLOTS:-1}"
+      variable_metadata_path '$variableMetadata_in'
     ; echo exit code $?
   ]]></command>
 
@@ -33,11 +34,12 @@
     <param name="dataMatrix_in" label="Data matrix file" type="data" format="tabular" help="variable x sample, decimal: '.', missing: NA, mode: numerical, separator: tab" />
     <param name="sampleMetadata_in" label="Sample metadata file" type="data" format="tabular" help="sample x metadata columns, separator: tab" />
     <param name="variableMetadata_in" label="Variable metadata file" type="data" format="tabular" help="variable x metadata columns, separator: tab" />
+    <param name="categoricalPrefix" label="prefix for cluster names " type="text" value="k" help="[categorical_prefix] Some tools require non-numeric values to discern categorical data; e.g., enter 'k' here to prepend 'k' to cluster numbers in the output; default 'k'." />
     <param name="ksamples" label="K value(s) for samples" type="text" value = "0" help="[ksamples] Single K or comma-separated Ks for samples, or 0 for none." />
     <param name="kfeatures" label="K value(s) for features" type="text" value = "0" help="[kfeatures] Single K or comma-separated Ks for features (variables), or 0 for none." />
     <param name="iter_max" label="Max number of iterations" type="text" value = "10" help="[iter_max] The maximum number of iterations allowed; default 10." />
     <param name="nstart" label="Number of random sets" type="text" value = "1" help="[nstart] How many random sets should be chosen; default 1." />
-    <param name="algorithm" label="Algorithm for clustering" type="select" value = "Hartigan-Wong" help="[algorithm] K-means clustering algorithm, default 'Hartigan-Wong'; alternatives 'Lloyd', 'MacQueen'; 'Forgy' is a synonym for 'Lloyd', see references for further info.">
+    <param name="algorithm" label="Algorithm for clustering" type="select" value = "Hartigan-Wong" help="[algorithm] K-means clustering algorithm, default 'Hartigan-Wong'; alternatives 'Lloyd', 'MacQueen'; 'Forgy' is a synonym for 'Lloyd', see stats::kmeans reference for further info.">
       <option value="Forgy">Forgy</option>
       <option value="Hartigan-Wong" selected="True">Hartigan-Wong</option>
       <option value="Lloyd">Lloyd</option>
@@ -52,7 +54,7 @@
   </outputs>
 
   <tests>
-        <test>
+    <test>
       <param name="dataMatrix_in" value="input_dataMatrix.tsv"/>
       <param name="sampleMetadata_in" value="input_sampleMetadata.tsv"/>
       <param name="variableMetadata_in" value="input_variableMetadata.tsv"/>
@@ -176,6 +178,10 @@
 
   - maximum number of iterations per calculation (see https://stat.ethz.ch/R-manual/R-devel/library/stats/html/kmeans.html).
 
+**categorical_prefix** - character(s) to add as prefix to category number (default = 'k')
+
+  - some tools treat only non-numeric data as categorical; this prefix ('k' by default) ensures that clusters data will be treated as categorical; an empty string is permitted here if desired (and succeeding tools accept integers as categorical data).
+
 ------------
 Output files
 ------------
@@ -232,7 +238,8 @@
 NEWS
 ----
 
-August 2017, Version 0.98.1 - First release
+- August 2017, Version 0.98.3 - Add (optional) prefix to category numbers for downstream tools that treat only non-numeric data as categorical.
+- August 2017, Version 0.98.1 - First release
 
 ---------
 Citations