BIOINFORMATICS<-->STRUCTURE
Jerusalem, Israel, November 17-21, 1996

Abstract


Exploring the limits of secondary structure prediction

Jonathan M. Levin

Unite de Bioinformatique, INRA, 78352 Jouy-en-Josas, France

jon@glycine.jouy.inra.fr


This poster presents a simple and robust secondary structure prediction scheme, Simpa96 (Levin 1996), based on an updated version of the nearest neighbour method (Levin and Garnier, 1988).
Using a larger data base, the Blosum 62 substitution matrix and a regularization algorithm the three state prediction accuracy is increased by 4.7% points to 67.7% for a single sequence and up to 72.8% when using multiple alignments. The increase in prediction accuracy with respect to the previous version can be almost entirely ascribed to the 7 fold increase in the size of the data base. A more detailed analysis of the results shows that badly predicted regions of a protein sequence are randomly distributed throughout the data base and that the goal of perfect secondary structure predictions by methods which use only local sequence information is illusory.

References
Levin J.M. 1996 Submitted.
Levin J.M. and Garnier J. 1988 Biochim. Biophys. Acta 955: 283-295


Back to the Abstract Index.