LogD7.4 modeling using Bayesian regularized neural networks. assessment and correction of the errors of prediction

Journal of Chemical Information and Modeling

Volumn 46, Issue 3, 2006, Pages 1379-1387

  Bruneau, Pierre ^a   McElroy, Nathan R ^a,b  

^a ASTRAZENECA   (United Kingdom)

^b INDIANA UNIVERSITY OF PENNSYLVANIA   (United States)

Author keywords

[No Author keywords available]

Indexed keywords

COMPUTER SIMULATION; ERROR CORRECTION; IONIZATION; MATHEMATICAL MODELS; NEURAL NETWORKS;

AUTOMATIC RELEVANCE DETERMINATION (ARD); BAYESIAN REGULARIZED NEURAL NETWORKS (BRNNS); HOMOGENEOUS IONIZATION; LOGD7.4;

BIOCHEMISTRY;

ALGORITHM; ARTICLE; ARTIFICIAL NEURAL NETWORK; BAYES THEOREM;

ALGORITHMS; BAYES THEOREM; NEURAL NETWORKS (COMPUTER);

EID: 33745383499     PISSN: 15499596     EISSN: 1549960X     Source Type: Journal    
DOI: 10.1021/ci0504014     Document Type: Article

References (33)

1. Tetko, I. V.; Bruneau, P. Application of ALOGPS to Predict 1-Octanol/ Water Distribution Coefficients, logP, and logD of AstraZeneca Inhouse Database. J. Pharm. Sci. 2004, 93, 3103-3110.
2. Tetko, I. V.; Poda, G. I. Application of ALOGPS 2.1 to Predict logD Distribution Coefficient for Pfizer Proprietary Compounds. J. Med. Chem. 2004, 47, 5601-5604.
3. Morris, J. J.; Bruneau, P. Prediction of Physical Properties. In Virtual Screening for Bioactiue Molecules; Bohm, H. J., Schneider, G., Eds.; Wiley-VCH: Chichester, 2000; pp 33-58
4. Stouch, T. R.; Kenyon, J. R.; Johnson, S. R.; Xue-Qing; Doweyko, A.; Li Y. In Silico ADME/Tox: Why Models Fail. J. Comput.-Aided Mol. Des. 2003, 17, 83-92.
5. Dewitte, R. S.; Kolovanov, E. D. Predicting Molecular Physical Properties. Biotechnol. Pharm. Aspects 2004, 1, 27-52.
6. Livingstone, D. J. Theoretical Property Predictions. Curr. Topics Med. Chem. 2003, 3, 1171-1192.
7. PrologD. CompuDrug Chemistry Ltd. (www.compudrug.com).
8. Advanced Chemical Development Inc., 133 Richmond Sreet West, Suite 605, Toronto, Ontario, Canada M5H 2L3 (www.acdlabs.com).
9. a, and logD. J. Chem. Inf. Comput. Sci. 2002, 42, 796-805.
10. Krejsa, C. M.; Horwath, D.; Rogalski, S. L.; Penzotti, J. E.; Mao, B.; Barbosa, F.; Migeon, J. C. Predicting ADME Properties and Side Effects: The BioPrint Approach. Curr. Opin. Drug Discovery Dev. 2003, 6, 4.
11. http://www.lib.uchicago.edu/SCI/SCIpharm2004/2.2FrederiqueBar-bosa.pdf.
12. Bruneau, P. Search for Predictive Generic Model of Aqueous Solubility Using Bayesian Neural Nets. J. Chem. Inf. Comput. Sci. 2001, 41, 1605-1616.
13. JMP version 5.1.1. Distributed by SAS Institute Inc. http://www.JMP.com.
14. Neal, R. N. Software for Flexible Bayesian Modeling, version 99-12-06. (www.cs.toronto.ca/~radford).
15. Winkler, D. A.; Burden, F. R. Bayesian Neural Nets for Modeling in Drug Discovery. DDT:Biosilico 2004, 2, 104-111.
16. Burden, F. R.; Winkler, D. A. Robust QSAR Models Using Bayesian Regularized Neural Networks. J. Med. Chem. 1999, 42, 3183-3187.
17. Hawkins D. M. The problem of Overfitting. J. Chem. Inf. Comput. Sci. 2004, 44, 1-12
18. Hoffmann, R.; Minkin, V. I.; Carpenter B. K. Occam's Razor and Chemistry. Bull. Soc. Chim. Fr. 1996, 133, 117-130.
19. Winkler, D. A.; Burden, F. R. Modelling Blood-Brain Barrier Partitioning Using Bayesian Neural Nets. J. Mol. Graphics Modell. 2004, 22, 499-505.
20. Li, Y.; Campbell, C.; Tipping, M. Bayesian Automatic Relevance Determination Algorithms for Classifying Genetic Expression Data. Bioinformatics 2002, 18, 1332-1339.
21. Enot, D. P.; Gautier, R.; Le Marouillle, J. Y. Gaussian Process: An Efficient Technique to Solve Quantitative Structure - Property Relationship Problems. SAR QSAR. Environ. Res. 2001, 72, 461-469.
22. Burden, F. R.; Ford, M. G.; Witley, D. C.; Winkler, D. A. Use of Automatic Relevance Determination in QSAR Studies Using Bayesian Neural Nets. J. Chem. Inf. Comput. Sci. 2000, 40, 1423-1430.
23. Todeschini, R.; Consonni, V.; Pavan, M. A Distance Measure Between Models: A Tool for Similarity/Diversity Analysis of Model Populations. Chemom. Intell. Lab. Syst. 2004, 70, 55-61.
24. Xu, Y.; Gao, H. Dimension Related Distance and its Application in QSAR/QSPR Model Error Estimation. QSAR Comb. Sci. 2003, 22, 422-429.
25. Sheridan, R. P.; Feuston, B. P.; Maiorov, V. N.; Kearsley Similarity to Molecules in the Training Set Is a Good Discriminator for Prediction Accuracy in QSAR. J. Chem. Inf. Comput. Sci. 2004, 44, 1912-1928
26. i-ȳ) where y is a vector of values for a particular point, ȳ is the vector of means of each variable, and S is the covariance matrix of the variables.
27. Not published.
28. Daylight Inc., Mission Viejo, California, USA.http://www.daylight.com/ dayhtml/doc/theory/theory.smarts.html.
29. Tetko, I. V. Neural Network studies. 4. Introduction to Associative Neural Networks. J. Chem. Inf. Comput. Sci. 2002, 42, 717-728.
30. Tetko, I. V.; Tanchuk V. Y. Application of Associative Neural Networks for Prediction of Lipophilicity in ALOGPS 2.1 Program. J. Chem. Inf. Comput. Sci. 2002, 42, 1136-1145.
31. Tiño, P.; Nabney, I. T.; Williams, B. S.; Lösel, J.; Sun, Y. Nonlinear Prediction of Quantitative Structure - Activity Relationships. J. Chem. Inf. Comput. Sci. 2004, 44, 1647-1653.
32. A measurement is more likely repeated if an apparently abnormal result is obtained. Thus, high ranges in duplicated measurements do not indicate a global variability of the experimental methodology.
33. Yang, L.; Wang, P.; Jiang, Y.; Chen, J. Studying the Explanatory Capacity of Artificial Neural Networks for Understanding Environmental Chemical Quantitative Structure - Activity Relationship Models. J. Chem. Inf. Comput. Sci. ASAP, Web release October 13, 2005.