A New Variable Selection Method Based on Mutual Information Maximization by Replacing Collinear Variables for Nonlinear Quantitative Structure-Property Relationship Models

다국어 초록 (Multilingual Abstract)

Selection of the most informative molecular descriptors from the original data set is a key step for development of quantitative structure activity/property relationship models. Recently, mutual information (MI) has gained increasing attention in feature selection problems. This paper presents an effective mutual information-based feature selection approach, named mutual information maximization by replacing collinear variables (MIMRCV), for nonlinear quantitative structure-property relationship models. The proposed variable selection method was applied to three different QSPR datasets, soil degradation half-life of 47 organophosphorus pesticides, GC-MS retention times of 85 volatile organic compounds, and water-to-micellar cetyltrimethylammonium bromide partition coefficients of 62 organic compounds.The obtained results revealed that using MIMRCV as feature selection method improves the predictive quality of the developed models compared to conventional MI based variable selection algorithms.

참고문헌 (Reference)

1 Livingstone, D. J., 40 : 195-, 2000

2 Ghasemi, J., 604 : 99-, 2007

3 Sprunger, L. M., 28 : 72-, 2009

4 Tomizawa, L., 4 : 117-, 1975

5 Yan, D., 71 : 1809-, 2008

6 Cai, C. P., 40 : 417-, 1995

7 Zvinavashe, E., 75 : 1531-, 2009

8 Cortes, C., 20 : 273-, 1995

9 32. Akhlaghi, Y., 20 : 1-, 2006

10 Park, J., 5 : 305-, 1993

11 Perez-Marin, D., 72 : 28-, 2007

12 Chen, K. X., 44 : 4367-, 2009

13 Mercader, A. G., 50 : 1542-, 2010

14 Shamsipur, M., 646 : 39-, 2009

15 Jouan-Rimbaud, D., 304 : 285-, 1995

16 Ghasemi, J., 161 : 74-, 2009

17 Guptaa, V. K., 83 : 1014-, 2011

18 Ghasemi, J., 588 : 200-, 2007

19 Deswal, S., 41 : 1339-, 2006

20 Xia, B., 43 : 1489-, 2008

21 Blank, T. B., 65 : 3081-, 1993

22 Pourbasheer, E., 45 : 1087-, 2010

23 Hemmateenejad, B., 610 : 25-, 2008

24 Benoudjita, N., 74 : 243-, 2004

25 Amiri, F., 34 : 1184-, 2011

26 Liu, H., 42 : 1330-, 2009

27 Huang, D., 63 : 325-, 2005

28 Rossi, F., 80 : 215-, 2006

29 Durand, A., 595 : 72-, 2007

30 Caetano, S., 602 : 37-, 2007

31 Kojadinovic, I., 49 : 1205-, 2005

32 Kraskov, A., 69 : 066138-, 2004

33 Harald, S., 70 : 066123-, 2004

34 Despagne, F., 123 : 157-, 1998

35 Hastie, T., "The Elements of Statistical Learning" Springer-Verlag 2001

36 Vapnik, V., "Statistical Learning Theory" John Wiley 1998

37 Forst, L., "Odor and VOC Control Handbook" McGraw-Hill 3-, 1998

38 Vogue, P. A., "OSU Extension Pesticide Properties Database" National Pesticide Information Center 1994

39 Astakhov, S. A., "MILCA algorithm"

40 Eckschlager, K., "Information Theory in Analytical Chemistry" John Wiley and Sons 1994

41 Cover, T. M., "Elements of Information Theory" Wiley 2005

42 "EPA Method 8260C: Volatile organic compounds by Gas chromatography- mass/spectrometry (GC/MS)"

43 Calvert, J. G., "Chemistry for the 21st Century. The Chemistry of the Atmosphere: Its Impact on Global Change" Blackwell Scientific Publications 1994

44 FAO, "Agriculture Towards 2010" 1993