Application of multiple sequence alignment profiles to improve protein secondary structure prediction

The effect of training a neural network secondary structure prediction algo rithm with different types of multiple sequence alignment profiles derived from the same sequences, is shown to provide a range of accuracy from 70.5% to 76.4%. The best accuracy of 76.4% (standard deviation 8.4%), is 3.1% (Q (3)) and 4.4% (SOV2) better than the PHD algorithm run on the same set of 4 06 sequence non-redundant proteins that were not used to train either metho d. Residues predicted by the new method with a confidence value of 5 or gre ater, have an average Q(3) accuracy of 84%, and cover 68% of the residues. Relative solvent accessibility based on a two state model, for 25, 5, and 0 % accessibility are predicted at 76.2, 79.8, and 86.6% accuracy respectivel y. The source of the improvements obtained from training with different rep resentations of the same alignment data are described in detail. The new Jn et prediction method resulting from this study is available in the Jpred se condary structure prediction server, and as a stand-alone computer program from: http:/barton.ebi.ac.uk/.Proteins 2000; 40:502-511. (C) 2000 Wiley-Lis s, Inc.