SVM approach for predicting LogP

被引：40

作者：

Liao, Quan ^{[1
]}

Yao, Jianhua ^{[1
]}

Yuan, Shengang ^{[1
]}

机构：

[1] Chinese Acad Sci, Shanghai Inst Organ Chem, Dept Comp Chem & Chemoinformat, Shanghai 200032, Peoples R China

来源：

MOLECULAR DIVERSITY | 2006年 / 10卷 / 03期

基金：

中国国家自然科学基金;

关键词：

LogP prediction; multiple linear regression (MLR); partial least squares (PLS); support vector machines (SVM);

D O I：

10.1007/s11030-006-9036-2

中图分类号：

Q5 [生物化学]; Q7 [分子生物学];

学科分类号：

071010 [生物化学与分子生物学]; 081704 [应用化学];

摘要：

The logarithm of the partition coefficient between n-octanol and water (logP) is an important parameter for drug discovery. Based upon the comparison of several prediction logP models, i.e. Support Vector Machines (SVM), Partial Least Squares (PLS) and Multiple Linear Regression (MLR), the authors reported SVM model is the best one in this paper.

引用

页码：301 / 309

页数：9

共 32 条

[1]

[Anonymous], LIBSVM LIB SUPPORT V

[2]

Drug design by machine learning: support vector machines for pharmaceutical data analysis [J].