FABIA: Factor Analysis for Bicluster Acquisition
Description
Biclustering by "Factor Analysis for Bicluster
Acquisition" (FABIA). FABIA is a model-based technique for
biclustering, that is clustering rows and columns
simultaneously. Biclusters are found by factor analysis where
both the factors and the loading matrix are sparse. FABIA is a
multiplicative model that extracts linear dependencies between
samples and feature patterns. It captures realistic
non-Gaussian data distributions with heavy tails as observed in
gene expression measurements. FABIA utilizes well understood
model selection techniques like the EM algorithm and
variational approaches and is embedded into a Bayesian
framework. FABIA ranks biclusters according to their
information content and separates spurious biclusters from true
biclusters. The code is written in C.