Class CAST_Clustering

Object

Clustering

CAST_Clustering

public class CAST_Clustering
extends Clustering

An instance of the CAST_Clustering class represents a clustering (i.e., grouping or partitioning) of a collection of genes using the CAST (cluster affinity search technique) clustering method.

Field Summary

Fields inherited from class Clustering

clusters, experiments, genes

Constructor Summary

Constructors

Constructor and Description
CAST_Clustering(String fileName, double affinityThreshold) Creates an initially empty CAST_Clustering.

Method Summary

Modifier and Type	Method and Description
int	addGenesWithHighAffinity(Cluster current) Adds to the specified Cluster all unassigned genes that are closer to the genes in the Cluster, on average, than the affinity threshold.
void	cast() Performs CAST clustering.
static void	main(String[] args) The main method creates a Clustering based on gene and experiment data from a tab-delimited text file.
int	removeGenesWithLowAffinity(Cluster current) Removes from the specified Cluster any genes that are farther from the genes in the Cluster, on average, than the affinity threshold.

Methods inherited from class Clustering

getExperimentNamesFromFile, getGeneInformationFromFile, getNumClusters, getNumExperiments, getNumGenes, toString

Methods inherited from class Object

clone, equals, finalize, getClass, hashCode, notify, notifyAll, wait, wait, wait

Constructor Detail

CAST_Clustering

public CAST_Clustering(String fileName,
                       double affinityThreshold)

Creates an initially empty CAST_Clustering.

A set of genes and experiments are determined from the specified String representing the name of a file. Genes and experiments are read-in from the tab-delimited file. Initially, the constructed CAST_Clustering is empty, i.e., none of the genes are assigned to clusters.

Parameters:

fileName - the name of a tab-delimited text file containing gene and experiment data

affinityThreshold - the distance between any gene and the other genes in its cluster, on average, must be at least this threshold value

Method Detail

addGenesWithHighAffinity

public int addGenesWithHighAffinity(Cluster current)

Adds to the specified Cluster all unassigned genes that are closer to the genes in the Cluster, on average, than the affinity threshold.

Parameters:

current - the Cluster to add genes to

Returns:

an int indicating the number of genes added to the cluster

removeGenesWithLowAffinity

public int removeGenesWithLowAffinity(Cluster current)

Removes from the specified Cluster any genes that are farther from the genes in the Cluster, on average, than the affinity threshold.

Parameters:

current - the Cluster to remove genes from

Returns:

an int indicating the number of genes removed from the cluster

cast

public void cast()

Performs CAST clustering.

Repeast the following until all genes are assigned to some cluster. Chooses a gene not already assigned to a cluster and assigns it to a new cluster. Then, iteratively (1) adds to the new cluster any unassigned genes that are closer to the genes in the new cluster, on average, than the affinity threshold and (2) removes from the new cluster any genes that are farther from the genes in the new cluster, on average, than the affinity threshold.

main

public static void main(String[] args)

The main method creates a Clustering based on gene and experiment data from a tab-delimited text file.

The clustering is determined using CAST clustering. The text file and the affinity threshold are specified as command line arguments. The computed set of clusters is output to standard output (and can be redirected to a file).

Parameters:

args - an array of Strings representing any command line arguments