Interpreting computational neural network quantitative structure-activity relationship models: A detailed interpretation of the weights and biases

Journal of Chemical Information and Modeling

Volumn 45, Issue 4, 2005, Pages 1109-1121

  Guha, Rajarshi ^a   Stanton, David T ^b   Jurs, Peter C ^a  

^a PENNSYLVANIA STATE UNIVERSITY   (United States)

^b PROCTER AND GAMBLE COMPANY   (United States)

Author keywords

[No Author keywords available]

Indexed keywords

COMPUTATIONAL METHODS; MATHEMATICAL MODELS; MATHEMATICAL TRANSFORMATIONS; STATISTICAL METHODS; TRANSFER FUNCTIONS; TREES (MATHEMATICS);

COMPUTATIONAL NEURAL NETWORKS (CNN); NEURONS; NONLINEAR TRANSFORMS; STATISTICAL MODELS;

NEURAL NETWORKS;

ORGANIC COMPOUND;

ALGORITHM; ARTICLE; ARTIFICIAL NEURAL NETWORK; CHEMICAL STRUCTURE; DATA BASE; DRUG EFFECT; METHODOLOGY; PHYSIOLOGY; QUANTITATIVE STRUCTURE ACTIVITY RELATION; RESEARCH; SKIN ABSORPTION; STATISTICAL MODEL;

ALGORITHMS; DATABASES; MODELS, STATISTICAL; MOLECULAR STRUCTURE; NEURAL NETWORKS (COMPUTER); ORGANIC CHEMICALS; QUANTITATIVE STRUCTURE-ACTIVITY RELATIONSHIP; RESEARCH; SKIN ABSORPTION;

EID: 23844539732     PISSN: 15499596     EISSN: 1549960X     Source Type: Journal    
DOI: 10.1021/ci050110v     Document Type: Article

References (43)

1. Stanton, D. T. On the physical interpretation of QSAR models. J. Chem. Inf. Comput. Sci. 2003, 43, 1423-1433.
2. Guha, R.; Jurs, P. C. The development of linear, ensemble and nonlinear models for the prediction and interpretation of the biological activity of a set of pdgfr inhibitors. J. Chem. Inf. Comput. Sci. 2004, 44, 2179-2189.
3. Guha, R.; Jurs, P. C. The development of QSAR models to predict and interpret the biological activity of artemisinin analogues. J. Chem. Inf. Comput. Sci. 2004, 44, 1440-1449.
4. Breiman, L. Random forests. Mach. Learning 2001, 45, 5-32.
5. Breiman, L.; Friedman, J. H.; Olshen, R. A.; Stone, C. J. Classification and Regression Trees; Wads worth: Belmont, CA, 1984.
6. Rusinko, A. I.; Farmen, M. W.; Lambert, C. G.; Brown, P. L.; Young, S. S. Analysis of a Large Structure/Biological Activity Data Set using Recursive Partitioning. J. Chem. Inf. Comput. Sci. 1999, 39, 1017-1026.
7. Hawkins, D. M.; Musser, B. J. One Tree or a Forest? Alternative Dendrographics Models. Comput. Sci. Stat. 1998, 30, 543-542.
8. Chipman, H. A.; George, E. I.; McCulloch, R. E. Making Sense of a Forest of Trees. Comput. Sci. Stat. 1998, 30, 84-92.
9. Urbanek, S. Exploring Statistical Forests, In Proc. 2002 Joint Statistical Meeting, 2002; Mira DP, in press.
10. Castro, J. L.; Mantas, C. J.; Benitez, J. M. Interpretation of artificial neural networks by means of fuzzy rules. IEEE Trans. Neural Networks 2002, 13, 101-116.
11. Limin, F. Rule generation from neural networks. IEEE Trans. Syst., Man Cybernetics 1994, 24, 1114-1124.
12. Bologna, G. Rule extraction from linear combinations of dimlp neural networks. In Proc. Sixth Brazilian Symposium on Neural Networks; 2000.
13. Yao, S.; Wei, C.; He, Z. Evolving fuzzy neural networks for extracting rules. In Fuzzy Systems, Proc. Fifth IEEE Intl. Conf.; 1996.
14. Tickle, A. B.; Golea, M.; Hayward, R.; Diederich, J. The truth is in there: current issues in extracting rules from trained feedforward artificial neural networks. In Neural networks, Intl. Conf.; 1997.
15. Sato, M.; Tsukimoto, H. Rule extraction from neural networks via decision tree induction. In Neural networks, Intl. Joint Conf.; 2001.
16. Gupta, A.; Park, S.; Lam, S. M. Generalized analytic rule extraction for feedforward neural networks. IEEE Trans. Knowledge Data Eng. 1999, 11, 985-991.
17. Chastrette, M.; Zakarya, D.; Peyraud, J. F. Structure-musk odor relationships for tetralins and indans using neural networks (on the contribution of descriptors to the classification). Eur. J. Med. Chem. 1994, 29, 343-348.
18. Hervás, C.; Silva, M.; Serrano, J. M.; Orejuela, E. Heuristic extraction of rules in pruned artificial neural network models used for quantifying highly overlapping chromatographic peaks. J. Chem. Inf. Comput. Sci. 2004, 44, 1576-1584.
19. Mak, B.; Blanning, R. W. An empirical measure of element contribution in neural networks. IEEE Trans. Syst., Man Cybernetics C 1998, 28, 561-564.
20. Haykin, S. Neural Networks; Prentice Hall: New York, 2001.
21. Hornik, K. Some new results on neural network approximation. Neural Networks 1993, 6, 1069-1072.
22. Garson, D. Interpreting neural network connection strengths. AI Expert 1991, 47-51.
23. Yoon, Y.; Guimaraes, T.; Swales, G. Integrating artificial neural networks with rule-based expert systems. Decis. Support Syst. 1994, 11, 497-507.
24. Sutter, J. M.; Dixon, S. L.; Jurs, P. C. Automated descriptor selection for quantitative structure-activity relationships using generalized simulated annealing. J. Chem. Inf. Comput. Sci. 1995, 35, 77-84.
25. Metropolis, N.; Rosenbluth, A. W.; Rosenbluth, M.; Teller, A. H.; Teller, E. Equation of state calculations by fast computing machines. J. Chem. Phys. 1953, 21, 1087-1092.
26. Goll, E. S.; Jurs, P. C. Prediction of the normal boiling points of organic compounds from molecular structures with a computational neural network model. J. Chem. Inf. Comput. Sci. 1999, 39, 974-983.
27. Guha, R.; Jurs, P. C. Interpreting Computational Neural Network QSAR Models: A Measure of Descriptor Importance. J. Chem. Inf. Model. 2005, 45, 800-806.
28. Stanton, D. T.; Mattioni, B. E.; Knittel, J. J.; Jurs, P. C. Development and use of hydrophobic surface area (HSA) descriptors for computer assisted quantitative structure-activity and structure-property relationships. J. Chem. Inf. Comput. Sci. 2004, 44, 1010-1023.
29. Patel, H.; Berge, W. T.; Cronin, M. T. D. Quantitative structure-activity relationships (QSARs) for the prediction of skin permeation of exogenous chemicals. Chemosphere 2002, 48, 603-613.
30. Mattioni, B. E. The development of quantitative structure-activity relationship models for physical property and biological activity prediction of organic compounds. Ph.D. Thesis, Pennsylvania State University, University Park, PA, 2003.
31. Gratten, J. A.; Abraham, M. H.; Bradbury, M. W.; Chadha, H. S. Molecular factors influencing drug transfer across the blood0brain barrier. J. Pharm. Pharmacol. 1997, 49, 1211-1216.
32. Audus, K. L.; Chikhale, P. J.; Miller, D. W.; Thompson, S. E.; Borchardt, R. T. Brain uptake of drugs: The influence of chemical and biological factors. Adv. Drug Res. 1992, 23, 1-64.
33. Ishibuchi, H.; Nii, M.; Tanaka, K. Fuzzy-arithmetic-based approach for extracting positive and negative linguistic rules from trained neural networks. In Fuzzy Systems Conference Proc., IEEE International, 1999.
34. Chen, P. C. Y.; Mills, J. K. Modeling of neural networks in feedback systems using describing functions. In Neural networks, International Conference; 1997.
35. Siu, K.-Y.; Roychowdhury, V.; Kailath, T. Rational approximation, harmonic analysis and neural networks. In Neural networks, Intl. Joint Conf.; 1992.
36. Fu, X.; Wang, L. Rule extraction by genetic algorithms based on a simplified RBF neural network. In Evolutionary computation, Proc. of the 2001 Congress on; 2001.
37. Stanton, D. T.; Jurs, P. C. Development and use of charged partial surface area structural descriptors in computer assissted quantitative structure property relationship studies. Anal. Chem. 1990, 62, 2323-2329.
38. Balaban, A. T. Higly discriminating distance based topological index. Chem. Phys. Lett. 1982, 89, 399-404.
39. Kier, L. B.; Hall, L. H. Molecular Connectivity in Chemistry and Drug Research; Academic Press: New York, 1976.
40. Kier. L. B.; Hall, L. H.; Murray, W. J. Molecular Connectivity 1: relationship to local anesthesia. J. Pharm. Sci. 1975, 64.
41. Kier, L. B.; Hall, L. H. Molecular connectivity in structure activity analysis; John Wiley & Sons: New York, 1986.
42. Kier, L. B.; Hall, L. H. Molecular Connectivity VII: specific treatment to heteroatoms. J. Pharm. Sci. 1976, 65, 1806-1809.
43. Randic, M. On molecular idenitification numbers. J. Chem. Inf. Comput. Sci. 1984, 24, 164-175.