- Tight Clustering:
George C. Tseng and Wing H. Wong. (2003) Tight Clustering: A Resampling-based Approach for Identifying Stable and Tight Patterns in Data. Biometrics. (To Appear).
Interactive software download: (under construction) manual snapshots download
This program contains a robust resampling method, called Tight Clustering, to finding stable and tight patterns (clusters), especially useful in microarray data analysis. It does not force assigning all genes into clusters nor estimate the number of clusters a priori. The program also has other traditional clustering methods including hierarchical cluster, K-means, SOM and PCA. Many interactive tools in heatmap are developed. Please email to request a current trial version (firstname.lastname@example.org).
Note: The program requires installation of Microsoft .NET framework.
Command-line software download: download
This version is meant for researchers who wish to work on exploratory analysis of multiple datasets or multiple parameters in tight clustering.
Multiple command lines can be edited in notepad or wordpad before pasting to the Command Prompt window (MS-DOS).
The resulting clustering results can be viewed from TreeView afterwards.
Note: The program is written in C++ and does not need Microsoft .NET framework.