17
|
1
|
|
2 <!--This is a configuration file for the integration of a CADDSuite tool into Galaxy (http://usegalaxy.org). This file was automatically generated using GalaxyConfigGenerator, so do not bother to make too many manual modifications.-->
|
|
3 <tool id="inputpartitioner" name="InputPartitioner" version="1.6">
|
|
4 <description>split QSAR data set</description>
|
|
5 <command interpreter="bash"><![CDATA[../../InputPartitioner
|
|
6 #if str( $i ) != '' and str( $i ) != 'None' :
|
|
7 -i "$i"
|
|
8 #end if
|
|
9 #if str( $o ) != '' and str( $o ) != 'None' :
|
|
10 -o "$o"
|
|
11 #end if
|
|
12 #if str( $n ) != '' and str( $n ) != 'None' :
|
|
13 -n "$n"
|
|
14 #end if
|
|
15 | tail -n 5
|
|
16 ]]></command>
|
|
17 <inputs>
|
|
18 <param name="i" optional="false" label="input data-file" type="data" format="dat"/>
|
|
19 <param name="n" optional="false" label="number of partitions" type="text" area="true" size="1x5" value=""/>
|
|
20 </inputs>
|
|
21 <outputs>
|
|
22 <data name="o" format="dat"/>
|
|
23 </outputs>
|
|
24 <help>InputPartitioner partitions a given QSAR data set into n partitions with evenly distributed response values.
|
|
25 Thus, this tool can be useful as part of a nested validation pipeline.
|
|
26 Input is a data file as generated by InputReader.
|
|
27 Output will be written to n files postfixed '_TRAIN<i>.dat' and '_TEST<i>.dat', where <i> is the ID of the resp. partition. For each of these partitions, the training set contains only those compounds that were not selected for the resp. test set.</help>
|
|
28 </tool> |