comparison cluster.tools/consensus.clustering.xml @ 2:b442996b66ae draft

Uploaded

2:b442996b66ae

<tool id="consensus_clustering" name="Consensus Clustering" force_history_refresh="True">
    <command interpreter="python">consensus.clustering.py
-d $dataset 
-n ${direction} 
-a ${method.algorithm} 
#if $method.algorithm == 'hc' # -m ${method.hc_distance_metric}
-i ${method.innerLinkage} 
#end if
#if $method.algorithm == 'pam' # -m ${method.pam_distance_metric}
#end if
#if $method.algorithm == 'km' # -m euclidean
#end if
-k ${kmax} 
-r ${reps} 
-f ${finalLinkage}
-o ${output} 
-h $report 
-p ${report.files_path}

</command>
    <inputs>
      <param name="dataset" type="data" format='tabular' label="Data Set" help="Specify the data matrix (tab-delimited) to be clustered"/>
      <param name="direction" type="select" label="Cluster Samples or Genes?" help="Specify the matrix dimension to cluster (see help below)">
	<option value="rows">Genes (rows)</option>
	<option value="cols" selected="true">Samples (columns)</option>
      </param>
    	
      <conditional name='method'>
	<param name="algorithm" type="select" label="Clustering Algorithm" help="Specify the cluster method to use (see help below)">
	  <option value="hc">Hierarchical Clustering</option>
	  <option value="pam" selected='true'>Partioning around Medioids</option>
	  <option value="km">K-Means Clustering</option>
	</param>
	<when value='hc'>
	  <param name="hc_distance_metric" type="select" label="Distance Metric" help="Specify the distance metric to use (see help below)">
	    <option value="cosine" selected='true'>Cosine</option>
	    <option value="abscosine">Absolute Cosine</option>
	    <option value="pearson">Pearson</option>
	    <option value="abspearson">Absolute Pearson</option>
	    <option value="spearman">Spearman</option>
	    <option value="kendall">Kendall</option>
	    <option value="euclidean">Euclidean</option>
	    <option value="maximum">Maximum</option>
	    <option value="manhattan">Manhattan (AKA city block)</option>
	    <option value="canberra">Canberra</option>
	    <option value="binary">Binary</option>
	  </param>

	  <param name="innerLinkage" type="select" label="Linkage for inner HAC " help="Specify the linkage to use during the 'inner' hierarchcial clustering (see help below)">
	    <option value="average">Average</option>
	    <option value="centroid">Centroid</option>
	    <option value="complete" selected='true'>Complete</option>
	    <option value="mcquitty">McQuitty</option>
	    <option value="median">Median</option>
	    <option value="single">Single</option>
	    <option value="ward">Ward</option>
	  </param>
    	</when>
 	<when value='pam'>
	  <param name="pam_distance_metric" type="select" label="Distance Metric" help="Specify the distance metric to use (see help below)">
	    <option value="cosine" selected='true'>Cosine</option>
	    <option value="abscosine">Absolute Cosine</option>
	    <option value="pearson">Pearson</option>
	    <option value="abspearson">Absolute Pearson</option>
	    <option value="spearman">Spearman</option>
	    <option value="kendall">Kendall</option>
	    <option value="euclidean">Euclidean</option>
	    <option value="maximum">Maximum</option>
	    <option value="manhattan">Manhattan (AKA city block)</option>
	    <option value="canberra">Canberra</option>
	    <option value="binary">Binary</option>
	  </param>
    	</when>
      </conditional>
      <param name="finalLinkage" type="select" label="Final Linkage" help="Specify the linkage to use when clustering the consensus matrix (see help below)">
	<option value="average">Average</option>
	<option value="centroid">Centroid</option>
	<option value="complete" selected='true'>Complete</option>
	<option value="mcquitty">McQuitty</option>
	<option value="median">Median</option>
	<option value="single">Single</option>
	<option value="ward">Ward</option>
      </param>
      
      
      <param name="kmax" type="integer" label="K Max" value="10" help="Maximum number of K to analyze" />
      <param name="reps" type="integer" label="Repetitions" value="500" help="Number of Sample Permutations to Repeat"/>
    	
    </inputs>
    <outputs>
      <data format="html" name="report" label="Consensus Clustering Report (HTML)"/>
      <data format="rdata" name="output" label="Consensus Clustering Data (RData)"/>
    </outputs>
<help>
.. class:: infomark
     
**Perform Consensus Clustering (Cluster Samples) on a specified data set**

----

**Parameters**

- **Data Set** - Specify the data matrix to be clustered.  Data must be formated as follows:

         * Tab-delimited
         * Use row/column headers

- **Cluster Samples or Genes** - Specify the dimension of the matrix to cluster:

         * Rows (Genes)
         * Columns (Samples)

- **Clustering Algorithm** Specify the choice of algorithm to use.  Choice of:

         * Hierarchical Clustering
         * K-Means

- **Distance Metric** Specify the choice of distance metric to use.  Choice of:

	 * Cosine (AKA uncentered pearson)
	 * Absolute Cosine (AKA uncentered pearson, absolute value)
         * Pearson (pearson correlation)
	 * Absolute Pearson (pearson correlation, absolute value)
         * Spearman (spearman correlation)
	 * Kendall (Kendall's Tau)
         * Euclidean (euclidean distance)
	 * Maximum
	 * Manhattan (AKA city block)
	 * Canberra
	 * Binary

- **Final Linkage** Specify the choice linkage to use when clustering Consensus Matrix.  Choice of:

         * Average (see documentation for R's hclust function for explanation of choices)
         * Single
         * Complete
         * Median
         * Centroid
         * McQuity
         * Ward

- **Inner Linkage** Specify the choice linkage to use when using HAC as clustering method.  Same choices as 'Final Linkage'

- **K Max** Specify the number to use for the largest K considered

- **Repititions**  Specify the number of 'bootstrap' repitions to perform to generate the consensus matrix

</help>
</tool>