skip to main content

Title: Neural network definitions of highly predictable protein secondary structure classes

We use two co-evolving neural networks to determine new classes of protein secondary structure which are significantly more predictable 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 computational molecular biology. Neural networks have been a popular method to attempt to predict these conventional secondary structure classes. Accuracy has been disappointingly low. The algorithm presented here uses neural networks to similtaneously examine 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 conventional alpha helix, beta strand and coil.
Authors:
 [1] ;  [2] ;  [3]
  1. Los Alamos National Lab., NM (United States)|[Santa Fe Inst., NM (United States)
  2. Toronto Univ., ON (Canada). Dept. of Computer Science
  3. Los Alamos National Lab., NM (United States)
Publication Date:
OSTI Identifier:
10121251
Report Number(s):
LA-UR--94-110; CONF-9311171--2
ON: DE94006234
DOE Contract Number:
W-7405-ENG-36
Resource Type:
Conference
Resource Relation:
Conference: Neural information processing systems (NIPS) conference,Denver, CO (United States),30 Nov - 2 Dec 1993; Other Information: PBD: [1994]
Research Org:
Los Alamos National Lab., NM (United States)
Sponsoring Org:
USDOE, Washington, DC (United States)
Country of Publication:
United States
Language:
English
Subject:
59 BASIC BIOLOGICAL SCIENCES; 99 GENERAL AND MISCELLANEOUS//MATHEMATICS, COMPUTING, AND INFORMATION SCIENCE; PROTEIN STRUCTURE; NEURAL NETWORKS; PROTEINS; ALGORITHMS 550400; 550200; 990200; GENETICS; BIOCHEMISTRY; MATHEMATICS AND COMPUTERS