Hierarchical clustering is used to group similar objects into “clusters”. In the beginning, each row and/or column is considered a cluster. In hierarchical clustering, the two most similar clusters are combined and continue to combine until all objects are in the same cluster. Hierarchical clustering produces a tree (called a dendogram) that shows the hierarchy of the clusters. This allows for exploratory analysis to see how the microarrays group together based on similarity of features. Hierarchical clustering is considered an unsupervised clustering method. Unsupervised clustering does not take any of the experimental variables such as treatment, phenotype, tissue, etc. into account while clustering, whereas supervised clusters does consider experimental variables when clustering. Partek offers an alternative to Hierarchical clustering in the form of K-Means clustering and Self-Organizing Map. You can read a more in depth description of how Partek performs these different forms for clustering analysis in Chapter 8 Hierarchical & Partitioning Clustering of the Partek Manual. The Partek user’s manual is embedded in Partek Genomics Suite under Help > On-Line Help.
|