Automated learning of a detector for the cores of α-helices in protein sequences via genetic programming

Author

Handley, Simon

Author_Institution

Dept. of Comput. Sci., Stanford Univ., CA, USA

fYear

1994

fDate

27-29 Jun 1994

Firstpage

474

Abstract

The author used J.R. Koza´s (1992) genetic programming to evolve programs that classified contiguous regions of proteins as being α-helix cores or not. He snipped positive and negative examples of α-helix core regions out of a set of 90 proteins. These proteins were chosen from the Brookhaven Protein Data Bank to be non-homologous. The fitness of the programs was defined as the correlation coefficient between the observed and the predicted α-helicity of the above regions. The fittest program produced by the genetic programming system that predicted the training set at least as well as the testing set had a correlation of 0.4818 between the observed classifications and the classifications predicted by the program (on the proteins in the testing set)

Keywords

biology computing; chemistry computing; factographic databases; genetic algorithms; information services; macromolecules; proteins; search problems; α-helices; α-helix cores; Brookhaven Protein Data Bank; automated learning; contiguous regions; core regions; correlation coefficient; fittest program; genetic programming; predicted α-helicity; protein sequences; training set; Amino acids; Computer science; Crystallography; Detectors; Energy states; Genetic programming; Proteins; Sequences; Solvents; System testing;

fLanguage

English

Publisher

ieee

Conference_Titel

Evolutionary Computation, 1994. IEEE World Congress on Computational Intelligence., Proceedings of the First IEEE Conference on

Conference_Location

Orlando, FL

Print_ISBN

0-7803-1899-4

Type

conf

DOI

10.1109/ICEC.1994.349904

Filename

349904