Neural Network Definitions of Highly Predictable Protein Secondary Structure Classes

Part of Advances in Neural Information Processing Systems 6 (NIPS 1993)

Bibtex Metadata Paper

Authors

Alan Lapedes, Evan Steeg, Robert Farber

Abstract

We use two co-evolving neural networks to determine new classes of protein secondary structure which are significantly more pre(cid:173) dictable from local amino sequence than the conventional secondary structure classification. Accurate prediction of the conventional secondary structure classes: alpha helix, beta strand, and coil, from primary sequence has long been an important problem in compu(cid:173) tational molecular biology. Neural networks have been a popular method to attempt to predict these conventional secondary struc(cid:173) ture classes. Accuracy has been disappointingly low. The algo(cid:173) rithm presented here uses neural networks to similtaneously exam(cid:173) ine both sequence and structure data, and to evolve new classes of secondary structure that can be predicted from sequence with significantly higher accuracy than the conventional classes. These new classes have both similarities to, and differences with the con(cid:173) ventional alpha helix, beta strand and coil.