|
2
|
1 <tool id="consensus_clustering" name="Consensus Clustering" force_history_refresh="True">
|
|
|
2 <command interpreter="python">consensus.clustering.py
|
|
|
3 -d $dataset
|
|
|
4 -n ${direction}
|
|
|
5 -a ${method.algorithm}
|
|
|
6 #if $method.algorithm == 'hc' # -m ${method.hc_distance_metric}
|
|
|
7 -i ${method.innerLinkage}
|
|
|
8 #end if
|
|
|
9 #if $method.algorithm == 'pam' # -m ${method.pam_distance_metric}
|
|
|
10 #end if
|
|
|
11 #if $method.algorithm == 'km' # -m euclidean
|
|
|
12 #end if
|
|
|
13 -k ${kmax}
|
|
|
14 -r ${reps}
|
|
|
15 -f ${finalLinkage}
|
|
|
16 -o ${output}
|
|
|
17 -h $report
|
|
|
18 -p ${report.files_path}
|
|
|
19
|
|
|
20 </command>
|
|
|
21 <inputs>
|
|
|
22 <param name="dataset" type="data" format='tabular' label="Data Set" help="Specify the data matrix (tab-delimited) to be clustered"/>
|
|
|
23 <param name="direction" type="select" label="Cluster Samples or Genes?" help="Specify the matrix dimension to cluster (see help below)">
|
|
|
24 <option value="rows">Genes (rows)</option>
|
|
|
25 <option value="cols" selected="true">Samples (columns)</option>
|
|
|
26 </param>
|
|
|
27
|
|
|
28 <conditional name='method'>
|
|
|
29 <param name="algorithm" type="select" label="Clustering Algorithm" help="Specify the cluster method to use (see help below)">
|
|
|
30 <option value="hc">Hierarchical Clustering</option>
|
|
|
31 <option value="pam" selected='true'>Partioning around Medioids</option>
|
|
|
32 <option value="km">K-Means Clustering</option>
|
|
|
33 </param>
|
|
|
34 <when value='hc'>
|
|
|
35 <param name="hc_distance_metric" type="select" label="Distance Metric" help="Specify the distance metric to use (see help below)">
|
|
|
36 <option value="cosine" selected='true'>Cosine</option>
|
|
|
37 <option value="abscosine">Absolute Cosine</option>
|
|
|
38 <option value="pearson">Pearson</option>
|
|
|
39 <option value="abspearson">Absolute Pearson</option>
|
|
|
40 <option value="spearman">Spearman</option>
|
|
|
41 <option value="kendall">Kendall</option>
|
|
|
42 <option value="euclidean">Euclidean</option>
|
|
|
43 <option value="maximum">Maximum</option>
|
|
|
44 <option value="manhattan">Manhattan (AKA city block)</option>
|
|
|
45 <option value="canberra">Canberra</option>
|
|
|
46 <option value="binary">Binary</option>
|
|
|
47 </param>
|
|
|
48
|
|
|
49 <param name="innerLinkage" type="select" label="Linkage for inner HAC " help="Specify the linkage to use during the 'inner' hierarchcial clustering (see help below)">
|
|
|
50 <option value="average">Average</option>
|
|
|
51 <option value="centroid">Centroid</option>
|
|
|
52 <option value="complete" selected='true'>Complete</option>
|
|
|
53 <option value="mcquitty">McQuitty</option>
|
|
|
54 <option value="median">Median</option>
|
|
|
55 <option value="single">Single</option>
|
|
|
56 <option value="ward">Ward</option>
|
|
|
57 </param>
|
|
|
58 </when>
|
|
|
59 <when value='pam'>
|
|
|
60 <param name="pam_distance_metric" type="select" label="Distance Metric" help="Specify the distance metric to use (see help below)">
|
|
|
61 <option value="cosine" selected='true'>Cosine</option>
|
|
|
62 <option value="abscosine">Absolute Cosine</option>
|
|
|
63 <option value="pearson">Pearson</option>
|
|
|
64 <option value="abspearson">Absolute Pearson</option>
|
|
|
65 <option value="spearman">Spearman</option>
|
|
|
66 <option value="kendall">Kendall</option>
|
|
|
67 <option value="euclidean">Euclidean</option>
|
|
|
68 <option value="maximum">Maximum</option>
|
|
|
69 <option value="manhattan">Manhattan (AKA city block)</option>
|
|
|
70 <option value="canberra">Canberra</option>
|
|
|
71 <option value="binary">Binary</option>
|
|
|
72 </param>
|
|
|
73 </when>
|
|
|
74 </conditional>
|
|
|
75 <param name="finalLinkage" type="select" label="Final Linkage" help="Specify the linkage to use when clustering the consensus matrix (see help below)">
|
|
|
76 <option value="average">Average</option>
|
|
|
77 <option value="centroid">Centroid</option>
|
|
|
78 <option value="complete" selected='true'>Complete</option>
|
|
|
79 <option value="mcquitty">McQuitty</option>
|
|
|
80 <option value="median">Median</option>
|
|
|
81 <option value="single">Single</option>
|
|
|
82 <option value="ward">Ward</option>
|
|
|
83 </param>
|
|
|
84
|
|
|
85
|
|
|
86 <param name="kmax" type="integer" label="K Max" value="10" help="Maximum number of K to analyze" />
|
|
|
87 <param name="reps" type="integer" label="Repetitions" value="500" help="Number of Sample Permutations to Repeat"/>
|
|
|
88
|
|
|
89 </inputs>
|
|
|
90 <outputs>
|
|
|
91 <data format="html" name="report" label="Consensus Clustering Report (HTML)"/>
|
|
|
92 <data format="rdata" name="output" label="Consensus Clustering Data (RData)"/>
|
|
|
93 </outputs>
|
|
|
94 <help>
|
|
|
95 .. class:: infomark
|
|
|
96
|
|
|
97 **Perform Consensus Clustering (Cluster Samples) on a specified data set**
|
|
|
98
|
|
|
99 ----
|
|
|
100
|
|
|
101 **Parameters**
|
|
|
102
|
|
|
103 - **Data Set** - Specify the data matrix to be clustered. Data must be formated as follows:
|
|
|
104
|
|
|
105 * Tab-delimited
|
|
|
106 * Use row/column headers
|
|
|
107
|
|
|
108 - **Cluster Samples or Genes** - Specify the dimension of the matrix to cluster:
|
|
|
109
|
|
|
110 * Rows (Genes)
|
|
|
111 * Columns (Samples)
|
|
|
112
|
|
|
113 - **Clustering Algorithm** Specify the choice of algorithm to use. Choice of:
|
|
|
114
|
|
|
115 * Hierarchical Clustering
|
|
|
116 * K-Means
|
|
|
117
|
|
|
118 - **Distance Metric** Specify the choice of distance metric to use. Choice of:
|
|
|
119
|
|
|
120 * Cosine (AKA uncentered pearson)
|
|
|
121 * Absolute Cosine (AKA uncentered pearson, absolute value)
|
|
|
122 * Pearson (pearson correlation)
|
|
|
123 * Absolute Pearson (pearson correlation, absolute value)
|
|
|
124 * Spearman (spearman correlation)
|
|
|
125 * Kendall (Kendall's Tau)
|
|
|
126 * Euclidean (euclidean distance)
|
|
|
127 * Maximum
|
|
|
128 * Manhattan (AKA city block)
|
|
|
129 * Canberra
|
|
|
130 * Binary
|
|
|
131
|
|
|
132 - **Final Linkage** Specify the choice linkage to use when clustering Consensus Matrix. Choice of:
|
|
|
133
|
|
|
134 * Average (see documentation for R's hclust function for explanation of choices)
|
|
|
135 * Single
|
|
|
136 * Complete
|
|
|
137 * Median
|
|
|
138 * Centroid
|
|
|
139 * McQuity
|
|
|
140 * Ward
|
|
|
141
|
|
|
142 - **Inner Linkage** Specify the choice linkage to use when using HAC as clustering method. Same choices as 'Final Linkage'
|
|
|
143
|
|
|
144 - **K Max** Specify the number to use for the largest K considered
|
|
|
145
|
|
|
146 - **Repititions** Specify the number of 'bootstrap' repitions to perform to generate the consensus matrix
|
|
|
147
|
|
|
148 </help>
|
|
|
149 </tool>
|
