Premium
Application of genetic algorithm‐kernel partial least square as a novel non‐linear feature selection method: partitioning of drug molecules
Author(s) -
Noorizadeh H.,
Sobhan Ardakani S.,
Ahmadi T.,
Mortazavi S. S.,
Noorizadeh M.
Publication year - 2013
Publication title -
drug testing and analysis
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 1.065
H-Index - 54
eISSN - 1942-7611
pISSN - 1942-7603
DOI - 10.1002/dta.275
Subject(s) - kernel (algebra) , quantitative structure–activity relationship , genetic algorithm , feature selection , partial least squares regression , algorithm , selection (genetic algorithm) , cross validation , feature (linguistics) , computer science , artificial intelligence , mathematics , pattern recognition (psychology) , biological system , machine learning , combinatorics , biology , linguistics , philosophy
Genetic algorithm (GA) and partial least squares (PLS) and kernel PLS (KPLS) techniques were used to investigate the correlation between immobilized liposome chromatography partitioning (log Ks) and descriptors for 65 drug compounds. The models were validated using leave‐group‐out cross validation LGO‐CV. The results indicate that GA‐KPLS can be used as an alternative modelling tool for quantitative structure‐property relationship (QSPR) studies. Copyright © 2011 John Wiley & Sons, Ltd.