Date Received: 22-07-2015 / Date Accepted: 03-09-2015 / Date Published: 13-06-2025
Spectral clustering algorithms have been the most effective algorithms to divide genes into groups accordingto the degree of their expression similarity. Such a grouping may suggestthat the respective genes are correlated and/or co-regulated, and subsequently indicatesthat the genes could possibly share a common biological role. In this paper,three spectral clustering algorithms were investigated: unnormalized spectral clustering, normalized spectral clustering according to Shi and Malik (2000), and normalized spectral clustering according to Ng, Jordan and Weiss (2002). The algorithms were benchmarked against each other.The performance of the three clustering algorithms wasstudied on time series expressiondata using Dynamic TimeWarping (DTW) distance in order to measure similarity betweengene expression profiles. Four different cluster validation measures were usedto evaluate the clustering algorithms: Connectivity and Silhouette Index for estimatingthe quality of clusters, Jaccard Index for evaluating the stability of a clustermethod and Rand Index for assessing the accuracy. The results were analyzedby Friedman’s test. The performance of normalized spectral clustering according to Ng, Jordan and Weiss (2002)wasdemonstratedto be the best under the Silhouetteand Rand validation indices.
