Tutorial 2: Step 6 Perform Hierarchical Clustering

Perform Hierarchical Clustering

1. Click the 3-nearest neighbors dataset in the Experiments navigator (Click the Experiments tab to display the Experiments navigator). The item is highlighted.

2. Click the Hierarchical Clustering toolbar icon , or select Hierarchical Clustering from the Clustering menu, or right-click the item and select Hierarchical Clustering from the shortcut menu. The Hierarchical Clustering dialog is displayed.

3. Set parameters.

Parameter	Setting
Clustering Orientation	Cluster Samples
Data Measurements: Between Data Points	Pearson Correlation
Data Measurements: Between Clusters	Average Linkage

Note that Agglomerative (the default option) is set as the Type parameter in the Algorithm Properties group.

4. Click OK. The clustering operation is performed, and upon successful completion, a new Sample Hierarchical Clustering experiment is added to the Experiments navigator under the original dataset.

GeneLinker™ provides many different clustering algorithms, and there are other clustering methods listed under Partitional Clustering. Genes can be clustered in addition to samples by using the same command sequence as above but changing the choice of clustering orientation from Samples to Genes.

If you have automatic visualizations enabled in your user preferences, a matrix tree plot of the clustering results is displayed.