Feature selection of support vector regression for Quantitative Structure-Activity Relationships (QSAR)

被引：0

作者：

Huang, L ^{[1
]}

Lu, HM ^{[1
]}

Dai, Y ^{[1
]}

机构：

[1] Univ Illinois, Dept Bioengn MC063, Chicago, IL 60607 USA

来源：

METMBS'03: PROCEEDINGS OF THE INTERNATIONAL CONFERENCE ON MATHEMATICS AND ENGINEERING TECHNIQUES IN MEDICINE AND BIOLOGICAL SCIENCES | 2003年

关键词：

QSAR; support vector regression; feature selection; grid search; linear programs;

D O I：

暂无

中图分类号：

R19 [保健组织与事业（卫生事业管理）];

学科分类号：

摘要：

Predicting the biological activity of a compound from its chemical structure is a fundamental problem in drug design. The Support Vector (SV) Machine regression is one of the powerful machine learning methods developed for this purpose in Quantitative Structure-Activity Relationships (QSAR) Analysis. A procedure based on linear programming is proposed for feature selection of SV regression. This new approach demonstrates favorable behavior in comparison with Partial Least Squares (PLS) regression method and a hybrid procedure of combining (1) genetic programming and (2) a neural network for several real compound data.

引用

页码：88 / 93

页数：6

共 14 条

[1] Broad patterns of gene expression revealed by clustering analysis of tumor and normal colon tissues probed by oligonucleotide arrays [J].

Alon, U ;

Barkai, N ;

Notterman, DA ;

Gish, K ;

Ybarra, S ;

Mack, D ;

Levine, AJ .

PROCEEDINGS OF THE NATIONAL ACADEMY OF SCIENCES OF THE UNITED STATES OF AMERICA, 1999, 96 (12) :6745-6750

[2] PLS regression methods [J].

Höskuldsson, Agnar .

Journal of Chemometrics, 1988, 2 (03) :211-228

[3]

APPELL M, 2002, ANAL BINDING COCAINE

[4]

Bradley P. S., 1998, INFORMS Journal on Computing, V10, P209, DOI 10.1287/ijoc.10.2.209

[5] Bagging predictors [J].

Breiman, L .

MACHINE LEARNING, 1996, 24 (02) :123-140

[6]

DAI Y, 2002, P 2002 INT C MATH EN

[7]

DEMIRIZ A, IN PRESS COMPUTING S

[8]

Dunn III W. J., 1989, TETRAHEDRON COMPUT M, V2, P349, DOI DOI 10.1016/0898-5529(89)90004-3

[9] Support vector machine classification and validation of cancer tissue samples using microarray expression data [J].

Furey, TS ;

Cristianini, N ;

Duffy, N ;

Bednarski, DW ;

Schummer, M ;

Haussler, D .

BIOINFORMATICS, 2000, 16 (10) :906-914

[10] APPLICATION OF GENETIC FUNCTION APPROXIMATION TO QUANTITATIVE STRUCTURE-ACTIVITY-RELATIONSHIPS AND QUANTITATIVE STRUCTURE-PROPERTY RELATIONSHIPS [J].

ROGERS, D ;

HOPFINGER, AJ .

JOURNAL OF CHEMICAL INFORMATION AND COMPUTER SCIENCES, 1994, 34 (04) :854-866

← 1 2 →