Decision tree-based formation of consensus protein secondary structure prediction

Motivation: Prediction of protein secondary structure provides information that is useful for other prediction methods like fold recognition and ab initio 3D prediction. A consensus prediction constructed from the output of several methods should yield more reliable results than each of the individual methods. Method: We present an approach that reveals subtle but systematic differences in the output of different secondary structure prediction methods allowing the derivation of coherent consensus predictions. The method uses a machine learning technique that builds decision trees from existing data. Results: The first results of our analysis show that consensus prediction of protein secondary structure may be improved both quantitatively and qualitatively. Availability: Our method for consensus secondary structure prediction CoDe (Consensus formation by Decision tree learning) is based on machine learning and will be integrated into the ToPLign system (Toolbox for Protein aLignment) which can be accessed at http://cartan.gmd.de/ToPLign.html. Contact: {mevissen,selbig}@gmd.de