|
3
|
1 <tool id="rnaseq_feature_selection" name="RNASeq Feature Selection (High Variance Filter)" force_history_refresh="True">
|
|
1
|
2 <command interpreter="python">rnaseq.feature.selection.py
|
|
|
3 -d $dataset
|
|
|
4 -z ${z_transform}
|
|
|
5 -m ${var_method}
|
|
|
6 -p ${perc_pass}
|
|
|
7 -o ${output}
|
|
|
8
|
|
|
9 </command>
|
|
|
10 <inputs>
|
|
|
11 <param name="dataset" type="data" format='tabular' label="RNASeq Data Set"/>
|
|
|
12 <param name="z_transform" type='select' display="radio" label="Z-transform data?" help="Specify whether or not to Z-transform the rows (mean=0, sd=1)">
|
|
|
13 <option value="yes" selected='true' >Yes</option>
|
|
|
14 <option value="no">No</option>
|
|
|
15 </param>
|
|
|
16 <param name="var_method" type="select" label="Variance Metric for Genes" help="Specify Metric to use for calculating Gene Variance" >
|
|
|
17 <option value="mad">Median Absolute Deviation (MAD)</option>
|
|
|
18 <option value="maxad">Maximum Absolute Deviation (Max AD)</option>
|
|
|
19 <option value="sd">Standard Deviation (SD)</option>
|
|
|
20 </param>
|
|
|
21 <param name="perc_pass" type="float" label="Total number of features to keep" help="Use value >= 1 to indicate exact number of genes. Use value in 0-1 range to specify percentage" value="1500"/>
|
|
|
22 </inputs>
|
|
|
23 <outputs>
|
|
3
|
24 <data format="tabular" name="output" label="High Variance Filtered RNASeq Data"/>
|
|
1
|
25 </outputs>
|
|
|
26 <help>
|
|
|
27 .. class:: infomark
|
|
|
28
|
|
|
29 **RNASeq Feature Selection** - Tool to filter an RNASeq matrix to select the most variant features
|
|
|
30
|
|
|
31 **OUTPUT:** A new matrix containing only the most variant feaures
|
|
|
32
|
|
|
33 ----
|
|
|
34
|
|
|
35 **Parameters**
|
|
|
36
|
|
|
37 - **Z-transform data?** - Specify whether or not to Z-transform the rows (mean=0, sd=1)
|
|
8
|
38 - **Variance Metric for Genes** - Specify Metric to use for calculating Gene Variance. Choice of
|
|
1
|
39
|
|
|
40 * Median Absolute Deviation (MAD)
|
|
|
41 * Maximum Absolute Deviation - similar to MAD, but uses the _Maximum_, instead of the Median Absolute Deviatioin
|
|
|
42 * Standard Deviation
|
|
|
43
|
|
8
|
44
|
|
|
45 - **Percentage of Samples Passing** Percent of samples with an IPL that passes the threshold. Choice of
|
|
1
|
46
|
|
|
47 * Integer Value - indicate the exact number of genes that are to be kept
|
|
|
48 * Real Value in [0,1] - indicate the percentage of genes that are to be kept
|
|
|
49
|
|
|
50 </help>
|
|
|
51 </tool>
|
