| Authors: |
Amela Prelic, Stefan Bleuler, Philip Zimmermann, Anja Wille, Peter Bühlmann, Wilhelm Gruissem, Lars Hennig, Lothar Thiele, Eckart Zitzler |
| Abstract: |
Motivation: In recent years, there have been various efforts to overcome the limitations of standard clustering approaches for the analysis of gene expression data by grouping genes and
samples simultaneously. The underlying concept, which is often referred to as biclustering, allows to identify sets of genes sharing compatible expression patterns across subsets of samples, and
its usefulness has been demonstrated for different organisms and data sets. Several biclustering methods have been proposed in the literature; however, it is not clear how the different
techniques compare to each other with respect to the biological relevance of the clusters as well as to other characteristics such as robustness and sensitivity to noise. Accordingly, no
guidelines concerning the choice of the biclustering method are currently available. Results: First, this paper provides a methodology for comparing and validating biclustering methods that
includes a simple binary reference model. Although this model captures the essential features of most biclustering approaches, it is still simple enough to exactly determine all optimal
groupings; to this end, we propose a fast divide-and-conquer algorithm (Bimax). Second, we evaluate the performance of five salient biclustering algorithms together with the reference model and a
hierarchical clustering method on various synthetic and real data sets for Saccharomyces cerevisiae and Arabidopsis thaliana. The comparison reveals that (i) biclustering in general has
advantages over a conventional hierarchical clustering approach, that (ii) there are considerable performance differences between the tested methods, and that (iii) already the simple reference
model delivers relevant patterns within all considered settings. Availability: The data sets used, the outcomes of the biclustering algorithms, and the Bimax implementation for the reference
model are available at http://www.tik.ee.ethz.ch/sop/bimax. |
