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
收藏
页码：88 / 93
页数：6
相关论文
共 50 条
  • [1] Application of support vector regression to Quantitative Structure-Activity Relationships(QSAR)
    Lu, HM
    Huang, L
    Dai, Y
    [J]. PROCEEDINGS OF THE 7TH JOINT CONFERENCE ON INFORMATION SCIENCES, 2003, : 942 - 945
  • [2] Feature selection in quantitative structure-activity relationships
    Walters, WP
    Goldman, BB
    [J]. CURRENT OPINION IN DRUG DISCOVERY & DEVELOPMENT, 2005, 8 (03) : 329 - 333
  • [3] Current approaches for choosing feature selection and learning algorithms in quantitative structure-activity relationships (QSAR)
    Khan, Pathan Mohsin
    Roy, Kunal
    [J]. EXPERT OPINION ON DRUG DISCOVERY, 2018, 13 (12) : 1075 - 1089
  • [4] Structure-activity relationships in chromatography: Retention prediction of oligonucleotides with support vector regression
    Kohlbacher, Oliver
    Quinten, Sascha
    Sturm, Marc
    Mayr, Bettina M.
    Huber, Christian G.
    [J]. ANGEWANDTE CHEMIE-INTERNATIONAL EDITION, 2006, 45 (42) : 7009 - 7012
  • [5] QUANTITATIVE STRUCTURE-ACTIVITY RELATIONSHIPS (QSAR) STUDIES OF BISBENZAMIDINES WITH ANTIFUNGAL ACTIVITY
    de Almeida, Vera L.
    Dias Lopes, Julio Cesar
    Oliveira, Sheila Rodrigues
    Donnici, Claudio L.
    Montanari, Carlos A.
    [J]. QUIMICA NOVA, 2010, 33 (07): : 1482 - 1489
  • [6] Modelling of the structure-activity quantitative relationships (QSAR) of tipifarnib analogues with antichagasic activity
    Granados-Tavera, Kevin
    Tilvez, Elkin A.
    Ahumedo-Monterrosa, Maicol
    [J]. Informacion Tecnologica, 2019, 30 (01): : 3 - 14
  • [7] Quantitative studies on Structure-Activity and Structure-Property Relationships (QSAR/QSPR)
    Gonzalez-Diaz, Humberto
    [J]. CURRENT TOPICS IN MEDICINAL CHEMISTRY, 2008, 8 (18) : 1554 - 1554
  • [8] Quantitative structure-activity relationships (QSAR):: studies of inhibitors of tyrosine kinase
    Shen, Q
    Lü, QZ
    Jiang, JH
    Shen, GL
    Yu, RQ
    [J]. EUROPEAN JOURNAL OF PHARMACEUTICAL SCIENCES, 2003, 20 (01) : 63 - 71
  • [9] On the nature, evolution and future of quantitative structure-activity relationships (QSAR) in toxicology
    Veith, GD
    [J]. SAR AND QSAR IN ENVIRONMENTAL RESEARCH, 2004, 15 (5-6) : 323 - 330
  • [10] Quantitative structure-activity relationships (QSAR) of cinnamic acid bird repellents
    Watkins, RW
    Lumley, JA
    Gill, EL
    Bishop, JD
    Langton, SD
    MacNicoll, AD
    Price, NR
    Drew, MGB
    [J]. JOURNAL OF CHEMICAL ECOLOGY, 1999, 25 (12) : 2825 - 2845
12345