Genetic Programming for Improved Data Mining: Application to the Biochemistry of Protein Interactions

Michael L. Raymer; William F. Punch; Erik D. Goodman; Leslie A. Kuhn

Genetic Programming for Improved Data Mining: Application to the Biochemistry of Protein Interactions

Michael L. Raymer, William F. Punch, Erik D. Goodman, Leslie A. Kuhn

Wright State University

Research output: Contribution to conference › Presentation

Abstract

We have previously shown how a genetic algorithm (GA) can be used to perform "data mining," the discovery of particular/important data within large datasets, by finding optimal data classifications using known examples. However, these approaches, while successful, limited data relationships to those that were "fixed" before the GA run. We report here on an extension of our previous work, substituting a genetic program (GP) for a GA. The GP could optimize data classification, as did the GA, but could also determine the functional relationships among the features. This gave improved performance and new information on important relationships among features. We discuss the overall approach, and compare the effectiveness of the GA vs. GP on a biochemistry problem, the determination of the involvement of bound water molecules in protein interactions.

Original language	American English
State	Published - Jan 1 1996
Event	Proceedings of the First Annual Conference on Genetic Programming - Duration: Jan 1 1996 → …

Conference

Conference	Proceedings of the First Annual Conference on Genetic Programming
Period	1/1/96 → …

Disciplines

Bioinformatics
Communication
Communication Technology and New Media
Computer Sciences
Databases and Information Systems
Life Sciences
OS and Networks
Physical Sciences and Mathematics
Science and Technology Studies
Social and Behavioral Sciences

Access to Document

http://www.kuhnlab.bmb.msu.edu/publication_papers/pdf/garage96-04-01.pdf

Cite this

@conference{9c9579be81804e5da35bd5a3297231f5,

title = "Genetic Programming for Improved Data Mining: Application to the Biochemistry of Protein Interactions",

abstract = " We have previously shown how a genetic algorithm (GA) can be used to perform {"}data mining,{"} the discovery of particular/important data within large datasets, by finding optimal data classifications using known examples. However, these approaches, while successful, limited data relationships to those that were {"}fixed{"} before the GA run. We report here on an extension of our previous work, substituting a genetic program (GP) for a GA. The GP could optimize data classification, as did the GA, but could also determine the functional relationships among the features. This gave improved performance and new information on important relationships among features. We discuss the overall approach, and compare the effectiveness of the GA vs. GP on a biochemistry problem, the determination of the involvement of bound water molecules in protein interactions.",

author = "Raymer, {Michael L.} and Punch, {William F.} and Goodman, {Erik D.} and Kuhn, {Leslie A.}",

year = "1996",

month = jan,

day = "1",

language = "American English",

note = "Proceedings of the First Annual Conference on Genetic Programming ; Conference date: 01-01-1996",

}

TY - CONF

T1 - Genetic Programming for Improved Data Mining: Application to the Biochemistry of Protein Interactions

AU - Raymer, Michael L.

AU - Punch, William F.

AU - Goodman, Erik D.

AU - Kuhn, Leslie A.

PY - 1996/1/1

Y1 - 1996/1/1

N2 - We have previously shown how a genetic algorithm (GA) can be used to perform "data mining," the discovery of particular/important data within large datasets, by finding optimal data classifications using known examples. However, these approaches, while successful, limited data relationships to those that were "fixed" before the GA run. We report here on an extension of our previous work, substituting a genetic program (GP) for a GA. The GP could optimize data classification, as did the GA, but could also determine the functional relationships among the features. This gave improved performance and new information on important relationships among features. We discuss the overall approach, and compare the effectiveness of the GA vs. GP on a biochemistry problem, the determination of the involvement of bound water molecules in protein interactions.

AB - We have previously shown how a genetic algorithm (GA) can be used to perform "data mining," the discovery of particular/important data within large datasets, by finding optimal data classifications using known examples. However, these approaches, while successful, limited data relationships to those that were "fixed" before the GA run. We report here on an extension of our previous work, substituting a genetic program (GP) for a GA. The GP could optimize data classification, as did the GA, but could also determine the functional relationships among the features. This gave improved performance and new information on important relationships among features. We discuss the overall approach, and compare the effectiveness of the GA vs. GP on a biochemistry problem, the determination of the involvement of bound water molecules in protein interactions.

UR - https://corescholar.libraries.wright.edu/knoesis/84

UR - http://www.kuhnlab.bmb.msu.edu/publication_papers/pdf/garage96-04-01.pdf

M3 - Presentation

T2 - Proceedings of the First Annual Conference on Genetic Programming

Y2 - 1 January 1996

ER -

Genetic Programming for Improved Data Mining: Application to the Biochemistry of Protein Interactions

Abstract

Conference

Disciplines

Access to Document

Other files and links

Cite this