ACO-Based bayesian network ensembles for the hierarchical classification of ageing-related proteins

摘要: The task of predicting protein functions using computational techniques is a major research area in the field bioinformatics. Casting into classification problem makes it challenging, since classes (functions) to be predicted are hierarchically related, and can have more than one function. One approach produce set local classifiers; each responsible for discriminating between subset certain level hierarchy. In this paper we tackle hierarchical fashion, by learning an ensemble Bayesian network classifiers class hierarchy combining their outputs with four alternative methods: a) selecting best classifier, b) majority voting, c) weighted d) constructing meta-classifier. built ABC-Miner, our recently introduced Ant-based Classification algorithm. We use different types representations learn models. empirically evaluate proposed methods on ageing-related dataset created research.