|
0
|
1 <tool id="partiton_clust" name="Partition Clustering" force_history_refresh="True">
|
|
|
2 <command interpreter="python">partition.py
|
|
|
3 -d $dataset
|
|
|
4 ${dist_obj}
|
|
|
5 -n ${direction}
|
|
|
6 -a $alg_cond.algorithm
|
|
|
7 #if $alg_cond.algorithm == 'pam' # -m ${alg_cond.distance_metric}
|
|
|
8 #end if
|
|
|
9 -k ${numk}
|
|
|
10 -o ${output}
|
|
|
11
|
|
|
12 </command>
|
|
|
13 <inputs>
|
|
|
14 <param name="dataset" type="data" format='tabular' label="Data Set" help="Specify the data matrix (tab-delimited) to be clustered"/>
|
|
|
15 <param name="dist_obj" type="boolean" label="Distance Object (R dist object)?" truevalue="-D" falsevalue="" checked="False" help="Check if the matrix contains the pairwise distances between a set of objects"/>
|
|
|
16
|
|
|
17 <param name="direction" type="select" label="Cluster Columns or Rows?" help="Specify the matrix dimension to cluster (see help below)">
|
|
|
18 <option value="cols">Columns (Samples)</option>
|
|
|
19 <option value="rows" selected='true'>Rows (Genes)</option>
|
|
|
20 </param>
|
|
|
21
|
|
|
22 <conditional name='alg_cond'>
|
|
|
23 <param name="algorithm" type="select" label="PAM or K-means?" help="Specify the partition cluster method to use (see help below)">
|
|
|
24 <option value="km">K-means</option>
|
|
|
25 <option value="pam" selected='true'>PAM</option>
|
|
|
26 </param>
|
|
|
27 <when value='pam'>
|
|
|
28 <param name="distance_metric" type="select" label="Distance Metric" help="Specify the distance metric to use (see help below)">
|
|
|
29 <option value="cosine" selected='true'>Cosine</option>
|
|
|
30 <option value="abscosine">Absolute Cosine</option>
|
|
|
31 <option value="pearson">Pearson</option>
|
|
|
32 <option value="abspearson">Absolute Pearson</option>
|
|
|
33 <option value="spearman">Spearman</option>
|
|
|
34 <option value="kendall">Kendall</option>
|
|
|
35 <option value="euclidean">Euclidean</option>
|
|
|
36 <option value="maximum">Maximum</option>
|
|
|
37 <option value="manhattan">Manhattan (AKA city block)</option>
|
|
|
38 <option value="canberra">Canberra</option>
|
|
|
39 <option value="binary">Binary</option>
|
|
|
40 </param>
|
|
|
41 </when>
|
|
|
42 </conditional>
|
|
|
43 <param name="numk" type="integer" label="Number of Clusters" value="50" help="Specify the number of clusters to use"/>
|
|
|
44
|
|
|
45 </inputs>
|
|
|
46 <outputs>
|
|
|
47 <data format="rdata" name="output" label="Partition Clustering Data (RData)"/>
|
|
|
48 </outputs>
|
|
|
49 <help>
|
|
|
50 .. class:: infomark
|
|
|
51
|
|
|
52 **Perform Partition Clustering (Cluster Samples) on a specified data set**
|
|
|
53
|
|
|
54 ----
|
|
|
55
|
|
|
56 **Parameters**
|
|
|
57
|
|
|
58 - **Data Set** - Specify the data matrix to be clustered. Data must be formated as follows:
|
|
|
59
|
|
|
60 * Tab-delimited
|
|
|
61 * Use row/column headers
|
|
|
62
|
|
|
63 - **Distance Object** Specify whether or not the data set is a pairwise distance matrix
|
|
|
64
|
|
|
65 - **Cluster Samples or Genes** - Specify the dimension of the matrix to cluster:
|
|
|
66
|
|
|
67 * Rows (Genes)
|
|
|
68 * Columns (Samples)
|
|
|
69
|
|
|
70 - **PAM or K-means?** Specify which partition clustering method to use - users have choice of:
|
|
|
71
|
|
|
72 * PAM (Partition Around Mediods)
|
|
|
73 * K-means
|
|
|
74
|
|
|
75 - **Distance Metric** Specify the distance metric to use. Note, this is ONLY AVAILABLE IF PAM IS THE ALGORITHM BEING USED. Choice of:
|
|
|
76
|
|
|
77 * Cosine (AKA uncentered pearson)
|
|
|
78 * Absolute Cosine (AKA uncentered pearson, absolute value)
|
|
|
79 * Pearson (pearson correlation)
|
|
|
80 * Absolute Pearson (pearson correlation, absolute value)
|
|
|
81 * Spearman (spearman correlation)
|
|
|
82 * Kendall (Kendall's Tau)
|
|
|
83 * Euclidean (euclidean distance)
|
|
|
84 * Maximum
|
|
|
85 * Manhattan (AKA city block)
|
|
|
86 * Canberra
|
|
|
87 * Binary
|
|
|
88
|
|
|
89
|
|
|
90 - **Number of Clusters** Specify the number of clusters to use
|
|
|
91
|
|
|
92 </help>
|
|
|
93 </tool>
|
