Combining protein secondary structure prediction models with ensemble methods of optimal complexity

Many sophisticated methods are currently available to perform protein secondary structure prediction. Since they are frequently based on di,erent principles, and di,erent knowledge sources, signi>cant bene>ts can be expected from combining them. However, the choice of an appropriate combiner appears to be an issue in its own right. The >rst di@culty to overcome when combining prediction methods is over>tting. This is the reason why we investigate the implementation of Support Vector Machines to perform the task. A family of multi-class SVMs is introduced. Two of these machines are used to combine some of the current best protein secondary structure prediction methods. Their performance is consistently superior to the performance of the ensemble methods traditionally used in the >eld. They also outperform the decomposition approaches based on bi-class SVMs. Furthermore, initial experimental evidence suggests that their outputs could be processed by the biologist to perform higher-level treatments. c © 2003 Elsevier B.V. All rights reserved.