Modelling blood-brain barrier partitioning using Bayesian neural nets

被引:72
作者
Winkler, DA
Burden, FR
机构
[1] CSIRO, Clayton 3169, Australia
[2] Monash Univ, Sch Chem, Monash 3800, Australia
[3] Scimetrics, Blackburn, Australia
关键词
QSAR; blood-brain barrier; ARD; neural net; ADMET; Bayesian methods;
D O I
10.1016/j.jmgm.2004.03.010
中图分类号
Q5 [生物化学];
学科分类号
071010 ; 081704 ;
摘要
We have employed three families of molecular molecular descriptors, together with Bayesian regularized neural nets, to model the partitioning of a diverse range of drugs and other small molecules across the blood-brain barrier (BBB). The relative efficacy of each descriptors class is compared, and the advantages of flexible, parsimonious, model free mapping methods, like Bayesian neural nets, illustrated. The relative importance of the molecular descriptors for the most predictive BBB model were determined by use of automatic relevance determination (ARD), and compared with the important descriptors from other literature models of BBB partitioning. (C) 2004 Elsevier Inc. All rights reserved.
引用
收藏
页码:499 / 505
页数:7
相关论文
共 36 条
[1]  
ABBOTT MJ, 1996, MOL MED TODAY MAR, P106
[2]   HYDROGEN-BONDING .33. FACTORS THAT INFLUENCE THE DISTRIBUTION OF SOLUTES BETWEEN BLOOD AND BRAIN [J].
ABRAHAM, MH ;
CHADHA, HS ;
MITCHELL, RC .
JOURNAL OF PHARMACEUTICAL SCIENCES, 1994, 83 (09) :1257-1268
[3]   Drug discovery [J].
Brennan, MB .
CHEMICAL & ENGINEERING NEWS, 2000, 78 (23) :63-+
[4]   New QSAR methods applied to structure-activity mapping and combinatorial chemistry [J].
Burden, FR ;
Winkler, DA .
JOURNAL OF CHEMICAL INFORMATION AND COMPUTER SCIENCES, 1999, 39 (02) :236-242
[5]   Robust QSAR models using Bayesian regularized neural networks [J].
Burden, FR ;
Winkler, DA .
JOURNAL OF MEDICINAL CHEMISTRY, 1999, 42 (16) :3183-3187
[6]   A chemically intuitive molecular index based on the eigenvalues of a modified adjacency matrix [J].
Burden, FR .
QUANTITATIVE STRUCTURE-ACTIVITY RELATIONSHIPS, 1997, 16 (04) :309-314
[7]   A quantitative structure-activity relationships model for the acute toxicity of substituted benzenes to Tetrahymena pyriformis using Bayesian-regularized neural networks [J].
Burden, FR ;
Winkler, DA .
CHEMICAL RESEARCH IN TOXICOLOGY, 2000, 13 (06) :436-440
[8]   Use of automatic relevance determination in QSAR studies using Bayesian neural networks [J].
Burden, FR ;
Ford, MG ;
Whitley, DC ;
Winkler, DA .
JOURNAL OF CHEMICAL INFORMATION AND COMPUTER SCIENCES, 2000, 40 (06) :1423-1430
[9]  
BURDEN FR, 1998, MOL MODELLING PREDIC
[10]  
Calder J A, 1994, Drug Des Discov, V11, P259