changeset 5:04079c34452a draft

planemo upload for repository https://github.com/HegemanLab/VKMZ commit 3e37abe007f126480b9b748ad5322755445ac95b-dirty

--- a/README	Wed May 30 18:35:57 2018 -0400
+++ b/README	Thu May 31 12:06:20 2018 -0400
@@ -63,6 +63,8 @@
     * Sets root directory for database file path
   * `--polarity`
     * Set polarity for all samples overriding input files
+  * `--unique`
+    * Remove features with multiple predictions
   * `--no-plot`
     * Disable html output
 

--- a/vkmz.py	Wed May 30 18:35:57 2018 -0400
+++ b/vkmz.py	Thu May 31 12:06:20 2018 -0400
@@ -35,7 +35,8 @@
   inputSubparser.add_argument('--directory', nargs='?', default='', type=str, help='Define directory of tool.')
   inputSubparser.add_argument('--polarity', '-p', choices=['positive','negative'], help='Force polarity mode. Ignore variables in input file.')
   inputSubparser.add_argument('--no-adjustment', '-na', action='store_true', help='Use flag to turn off polarity based mass adjustment. This flag should always be used if reprocessing data generated by VKMZ.')
-  inputSubparser.add_argument('--multiprocessing', '-m', action='store_true', help='Use flag to turn on multiprocessing.')
+  inputSubparser.add_argument('--unique', '-u', action='store_true', help='Set flag to only output features which have a single match.')
+  inputSubparser.add_argument('--multiprocessing', '-m', action='store_true', help='Set flag to turn on multiprocessing.')
   inputSubparser.add_argument('--plottype', '-t', nargs='?', default='scatter-2d', choices=['scatter-2d', 'scatter-3d'], help='Select plot type.')
   inputSubparser.add_argument('--size',     '-s', nargs='?', default=5, type=int, help='Set maxium size of plot symbols.')
   inputSubparser.add_argument('--size-algorithm', '-a', nargs='?', default=0, type=int, choices=[0,1], help="Symbol size algorithm selector. Algorithm 0 sets all symbols to the maxium size. Algorithm 2 determines a features symbol size by it's log intensity.")
@@ -48,6 +49,8 @@
 
 vkPolarity = getattr(args, "polarity")
 
+vkUnique = getattr(args, "unique")
+
 vkMultiprocessing = getattr(args, "multiprocessing")
 
 vkNoAdjustment = getattr(args, "no_adjustment")
@@ -103,6 +106,8 @@
   if prediction != -1:
     feature[2] = mass
     predictions = predictNeighbors(mass, uncertainty, prediction)
+    if vkUnique and len(predictions) > 1:
+      return
     feature.append(predictions) # feature[5]
     predictionClosest = predictions[0]
     formula = predictionClosest[1]

--- a/vkmz.xml	Wed May 30 18:35:57 2018 -0400
+++ b/vkmz.xml	Thu May 31 12:06:20 2018 -0400
@@ -1,4 +1,4 @@
-<tool id="VKMZ" name="VKMZ" version="1.1">
+<tool id="VKMZ" name="VKMZ" version="1.1.1">
 
   <description>metabolomics formula prediction and van Krevelen diagram generation</description>
   
@@ -34,6 +34,9 @@
     --output vkmz
     --error $prediction.error
     --database $prediction.database_type.database
+    #if $prediction.unique=="True":
+      --unique
+    #end if
     --size $diagram.size
     --size-algorithm $diagram.sizealgorithm
     --directory $__tool_directory__/
@@ -81,6 +84,7 @@
           <param name="database" label="Database" type="data" format="tabular" help="Select a custom tabular database" />
         </when>
       </conditional>
+      <param name="unique" label="Unique matches" type="boolean" truevalue="True" help="Only output features with a single prediction" />
     </section>
     <section name="diagram" title="Diagram Options" expanded="true">
       <param name="size" label="Minimum Maker Size" type="integer" value="5" min="0" help="Set the base size of diagram's markers" />
@@ -163,6 +167,8 @@
 
 *Database* can be set to heuristically generated databases for unlabeled and labeled chemcials [2] or to a custom database.
 
+*Unique matches* removes features from the output which have multiple predictions. Low mass molecules are less affected by this filter than high mass molecules.
+
 **Diagram Options**
 
 Predicted features are plotted as markers. The size of each marker is determined by the minimum marker size and a marker size algorithm. The marker size algorithms use minimum marker size as a variable.