Skip to main content
Presentation
GA-Facilitated Knowledge Discovery and Pattern Recognition Optimization Applied to the Biochemistry of Protein Solvation
Lecture Notes in Computer Science
  • Michael R. Peterson, Wright State University - Main Campus
  • Travis E. Doom, Wright State University - Main Campus
  • Michael L. Raymer, Wright State University - Main Campus
Document Type
Conference Proceeding
Publication Date
6-1-2004
Catalog Record
Catalog Record
Abstract
The authors present a GA optimization technique for cosine-based k-nearest neighbors classification that improves predictive accuracy in a class-balanced manner while simultaneously enabling knowledge discovery. The GA performs feature selection and extraction by searching for feature weights and offsets maximizing cosine classifier performance. GA-selected feature weights determine the relevance of each feature to the classification task. This hybrid GA/classifier provides insight to a notoriously difficult problem in molecular biology, the correct treatment of water molecules mediating ligand binding to proteins. In distinguishing patterns of water conservation and displacement, this method achieves higher accuracy than previous techniques. The data mining capabilities of the hybrid system improve the understanding of the physical and chemical determinants governing favored protein-water binding.
Comments

Presented at the Genetic and Evolutionary Computation Conference, Seattle, WA, June 26-30, 2004.

DOI
10.1007/978-3-540-24854-5_43
Citation Information
Michael R. Peterson, Travis E. Doom and Michael L. Raymer. "GA-Facilitated Knowledge Discovery and Pattern Recognition Optimization Applied to the Biochemistry of Protein Solvation" Lecture Notes in Computer Science Vol. 3102 (2004) p. 426 - 437 ISSN: 9783540223443
Available at: http://works.bepress.com/michael_raymer/13/