QM/NN QSPR models with error estimation: Vapor pressure and LogP

被引:81
作者
Beck, B [1 ]
Breindl, A [1 ]
Clark, T [1 ]
机构
[1] Univ Erlangen Nurnberg, Comp Chem Ctr, D-91052 Erlangen, Germany
来源
JOURNAL OF CHEMICAL INFORMATION AND COMPUTER SCIENCES | 2000年 / 40卷 / 04期
关键词
D O I
10.1021/ci990131n
中图分类号
O6 [化学];
学科分类号
0703 ;
摘要
QSPR models for logP and vapor pressures of organic compounds based on neural net interpretation of descriptors derived from quantum mechanical (semiempirical MO; AM1) calculations are presented. The models are cross-validated by dividing the compound set into several equal portions and training several individual multilayer feedforward neural nets (trained by the back-propagation of errors algorithm), each with a different portion as test set. The results of these nets are combined to give a mean predicted property value and a standard deviation. The performance of two models, for logP and the vapor pressure at room temperature, is analyzed, and the reliability of the predictions is tested.
引用
收藏
页码:1046 / 1051
页数:6
相关论文
共 44 条
[1]   AN ALGORITHM FOR THE LOCATION OF TRANSITION-STATES [J].
BAKER, J .
JOURNAL OF COMPUTATIONAL CHEMISTRY, 1986, 7 (04) :385-395
[2]  
BARICIC P, 1999, REGISTRY PHYSICOCHEM
[3]   Enhanced 3D-databases: A fully electrostatic database of AM1-optimized structures [J].
Beck, B ;
Horn, A ;
Carpenter, JE ;
Clark, T .
JOURNAL OF CHEMICAL INFORMATION AND COMPUTER SCIENCES, 1998, 38 (06) :1214-1217
[4]   THE NATURAL ATOMIC ORBITAL POINT-CHARGE MODEL FOR PM3 - MULTIPOLE MOMENTS AND MOLECULAR ELECTROSTATIC POTENTIALS [J].
BECK, B ;
RAUHUT, G ;
CLARK, T .
JOURNAL OF COMPUTATIONAL CHEMISTRY, 1994, 15 (10) :1064-1073
[5]   Some biological applications of semiempirical MO theory [J].
Beck, B ;
Clark, T .
PERSPECTIVES IN DRUG DISCOVERY AND DESIGN, 1998, 9-11 :131-159
[6]  
Benson S.W., 1968, THERMOCHEMICAL KINET
[7]   A NEW METHOD FOR THE ESTIMATION OF PARTITION-COEFFICIENT [J].
BODOR, N ;
GABANYI, Z ;
WONG, CK .
JOURNAL OF THE AMERICAN CHEMICAL SOCIETY, 1989, 111 (11) :3783-3786
[8]   Prediction of the n-octanol/water partition coefficient, logP, using a combination of semiempirical MO-calculations and a neural network [J].
Breindl, A ;
Beck, B ;
Clark, T ;
Glen, RC .
JOURNAL OF MOLECULAR MODELING, 1997, 3 (03) :142-155
[9]  
CHALK AJ, UNPUB
[10]   A combined semiempirical MO neural net technique for estimating C-13 chemical shifts [J].
Clark, T ;
Rauhut, G ;
Breindl, A .
JOURNAL OF MOLECULAR MODELING, 1995, 1 (01) :22-35