Toward an optimal procedure for PC-ANN model building: Prediction of the carcinogenic activity of a large set of drugs

被引:61
作者
Hemmateenejad, B [1 ]
Safarpour, MA
Miri, R
Nesari, N
机构
[1] Shiraz Univ Med Sci, Med & Nat Prod Chem Res Ctr, Shiraz, Iran
[2] Persian Gulf Univ, Sch Basic Sci, Dept Chem, Boushehr, Iran
关键词
D O I
10.1021/ci049766z
中图分类号
R914 [药物化学];
学科分类号
100701 ;
摘要
The performances of the three novel QSAR algorithms, principal component-artificial neural network modeling method combining with three factor selection procedures named eigenvalue ranking, correlation ranking, and genetic algorithm (ER-PC-ANN, CR-PC-ANN, PC-GA-ANN, respectively), are compared by application of these model to the prediction of the carcinogenic activity of a large set of drugs (735 drugs) belonging to a diverse type of compounds. A total number of 1350 theoretical descriptors are calculated for each molecule. The matrix of calculated descriptors (with 735 x 1350 dimension) is subjected to PCA. 95% of the variances in the matrix are explained by the first 137 principal components (PC's). From the pool of 137 PC's, the factor selection methods (ER, CR, and GA) are employed to select the best set of PC's for PC-ANN modeling. In the ER-PC-ANN, the PC's are successively entered into the ANN based on their decreasing eigenvalue. In the CR-PC-ANN, the ANN is first employed to model the nonlinear relationship between each one of the PC's and the carcinogen activity separately. Then, the PC's are ranked based on their decreasing correlating ability and entered to the input layer of the network one after another. Finally, a search algorithm (i.e. genetic algorithm) is used to find the best set of PC's. Both the external and cross-validation methods are used to validate the performances of the resulting models. One is able to see that the results obtained by the PC-GA-ANN and CR-PC-ANN procedures are superior to those resulted from the EV-PC-ANN. Comparison of the results reveals that the results produced by the PC-GA-ANN algorithm are better than those produced by CR-PC-ANN. However, the difference is not significant.
引用
收藏
页码:190 / 199
页数:10
相关论文
共 60 条
[41]  
SHETH UK, 1972, INDIAN J PHARM, V4, P32
[42]   Genetic neural networks for quantitative structure-activity relationships: Improvements and application of benzodiazepine affinity for benzodiazepine/GABA(A) receptors [J].
So, SS ;
Karplus, M .
JOURNAL OF MEDICINAL CHEMISTRY, 1996, 39 (26) :5246-5256
[43]   Implementation of an ADME enabling selection and visualization tool for drug discovery [J].
Stoner, CL ;
Gifford, E ;
Stankovic, C ;
Lepsy, CS ;
Brodfuehrer, J ;
Prasad, JVNV ;
Surendran, N .
JOURNAL OF PHARMACEUTICAL SCIENCES, 2004, 93 (05) :1131-1141
[44]   A CORRELATION PRINCIPAL COMPONENT REGRESSION-ANALYSIS OF NIR DATA [J].
SUN, JG .
JOURNAL OF CHEMOMETRICS, 1995, 9 (01) :21-29
[45]   WHICH PRINCIPAL COMPONENTS TO UTILIZE FOR PRINCIPAL COMPONENT REGRESSION [J].
SUTTER, JM ;
KALIVAS, JH ;
LANG, PM .
JOURNAL OF CHEMOMETRICS, 1992, 6 (04) :217-225
[46]   Introduction to multi-layer feed-forward neural networks [J].
Svozil, D ;
Kvasnicka, V ;
Pospichal, J .
CHEMOMETRICS AND INTELLIGENT LABORATORY SYSTEMS, 1997, 39 (01) :43-62
[47]   Neural network studies .2. Variable selection [J].
Tetko, IV ;
Villa, AEP ;
Livingstone, DJ .
JOURNAL OF CHEMICAL INFORMATION AND COMPUTER SCIENCES, 1996, 36 (04) :794-803
[48]  
TODESCHINI R, 2000, HDB MOL DECRIPTORS M
[49]   Prediction of heteroaromatic amine mutagenicity by means of correlation weighting of atomic orbital graphs of local invariants [J].
Toropov, AA ;
Toropova, AP .
JOURNAL OF MOLECULAR STRUCTURE-THEOCHEM, 2001, 538 :287-293
[50]   Selective descriptor pruning for QSAR/QSPR studies using artificial neural networks [J].
Turner, JV ;
Cutler, DJ ;
Spence, I ;
Maddalena, DJ .
JOURNAL OF COMPUTATIONAL CHEMISTRY, 2003, 24 (07) :891-897