A genetic approach for building different alphabets for peptide and protein classification

• Main Authors: Lumini Alessandra, Nanni Loris
• Format: Article
• Language: English
• Published: BMC 2008-01-01
• Series: BMC Bioinformatics
• Online Access: http://www.biomedcentral.com/1471-2105/9/45

<p>Abstract</p> <p>Background</p> <p>In this paper, it is proposed an optimization approach for producing reduced alphabets for peptide classification, using a Genetic Algorithm. The classification task is performed by a multi-classifier system where each classifier (Linear or Radial Basis function Support Vector Machines) is trained using features extracted by different reduced alphabets. Each alphabet is constructed by a Genetic Algorithm whose objective function is the maximization of the area under the ROC-curve obtained in several classification problems.</p> <p>Results</p> <p>The new approach has been tested in three peptide classification problems: HIV-protease, recognition of T-cell epitopes and prediction of peptides that bind human leukocyte antigens. The tests demonstrate that the idea of training a pool classifiers by reduced alphabets, created using a Genetic Algorithm, allows an improvement over other state-of-the-art feature extraction methods.</p> <p>Conclusion</p> <p>The validity of the novel strategy for creating reduced alphabets is demonstrated by the performance improvement obtained by the proposed approach with respect to other reduced alphabets-based methods in the tested problems.</p>