Simple ensemble methods are competitive with state-of-the-art data integration methods for gene function prediction
Matteo Ré, Giorgio Valentini;
JMLR W&CP 8:98-111, 2010.
Several works showed that biomolecular data integration is a key issue
to improve the prediction of gene functions. Quite surprisingly only
little attention has been devoted to data integration for gene
function prediction through ensemble methods. In this work we show
that relatively simple ensemble methods are competitive and in some
cases are also able to outperform state-of-the-art data integration
techniques for gene function prediction.