We think of cluster analysis as class discovery. That is, we assume that there is an unknown mapping called clustering structure that assigns a class label to each observation, and the goal of cluster analysis is to estimate this clustering structure, that is, to estimate the number of clusters...

We analyze a series of publicly available controlled experiments (Latin square) on Affymetrix high-density oligonucleotide microarrays using a simple physical model of the hybridization process. We plot for each gene the signal intensity vs. the hybridization free energy of RNA/DNA duplexes in...

We study spatiotemporal patterns produced by small-world networks of biologically motivated nonlinear oscillators from a data-analysis perspective. It is shown that the connectivity levels of such systems can be reconstructed by analyzing heterogeneity and fluctuation content of the patterns....