On the use of PLS and N-PLS in MIA-QSAR: Azole antifungals

被引:34
作者
Goodarzi, Mohammad [2 ,3 ]
Freitas, Matheus P. [1 ]
机构
[1] Univ Fed Lavras UFLA, Dept Quim, BR-37200000 Lavras, MG, Brazil
[2] Azad Univ, Fac Sci, Dept Chem, Arak, Iran
[3] Azad Univ, Young Researchers Club, Arak, Iran
关键词
MIA-QSAR; PLS regression; N-PLS regression; Antifungals; IMAGE-BASED APPROACH; MULTIVARIATE QSAR; MULTILINEAR PLS; DERIVATIVES; SERIES; AGENTS;
D O I
10.1016/j.chemolab.2008.11.007
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
The antifungal activities of a series of azole derivatives have been modeled by using MIA (multivariate image analysis) descriptors. Two regression methods were applied to correlate such descriptors with the activities column vector: bilinear (classical) and multilinear (N-way) partial least squares-PLS and WKS, respectively. The PLS-based model for this series of compounds demonstrated higher predictive ability than the N-PLS-based model, in opposition to some published results for other series of compounds. The activities block was taken in logarithmic scale (pMiC(90(cpd))/pMIC(90(bifonazole))) and the statistical performance of both models was found to be significantly better than the CoMFA analysis previously established. (C) 2008 Elsevier B.V. All rights reserved.
引用
收藏
页码:59 / 62
页数:4
相关论文
共 22 条