Feature selection in quantitative structure-activity relationships

Current Opinion in Drug Discovery and Development

Volumn 8, Issue 3, 2005, Pages 329-333

  Walters, W Patrick ^a   Goldman, Brian B ^b  

^a VERTEX PHARMACEUTICALS   (United States)

^b NONE

Author keywords

Feature selection; QSAR; Variable selection

Indexed keywords

NEW DRUG;

ACCURACY; ALGORITHM; AUTOMATION; CHEMICAL STRUCTURE; DATA BASE; KOLMOGOROV SMIRNOV TEST; LINEAR REGRESSION ANALYSIS; QUANTITATIVE STRUCTURE ACTIVITY RELATION; REVIEW; STOCHASTIC MODEL;

ANIMALS; DRUG DESIGN; HUMANS; MODELS, CHEMICAL; MOLECULAR CONFORMATION; MOLECULAR STRUCTURE; QUANTITATIVE STRUCTURE-ACTIVITY RELATIONSHIP;

EID: 17844411481     PISSN: 13676733     EISSN: None     Source Type: Journal    
DOI: None     Document Type: Review

References (36)

1. Cristianini N, Shawe-Taylor J (Eds): An Introduction to Support Vector Machines and Other Kernel-based Learning Methods. Cambridge University Press, Cambridge, UK (2000). An excellent introduction to the theory of SVMs, including applications of SVMs to real-world problems.
2. Vapnik VN (Ed): The Nature of Statistical Learning Theory. Springer-Verlag, New York, NY, USA (2000). An advanced text pertaining to the theory of SVMs.
3. Zupan J, Gasteiger J (Eds): Neural Networks in Chemistry and Drug Design. Wiley-VCH Verlag GmbH & Co KGaA, Weinheim, Germany (1999).
4. Zupan J, Gasteiger J (Eds): Neural Networks for Chemists. Wiley-VCH Verlag GmbH & Co KGaA, Weinheim, Germany (1993).
5. Guyon I, Elisseeff A: An introduction to variable and feature selection. J Machine Learning Res (2003) 3(March):1157-1182. A review of feature selection techniques from a computer science perspective.
6. Chapelle O, Vapnik V, Bousquet O, Mukherjee S: Choosing multiple parameters for support vector machines. Machine Learning (2002) 46(1-3):131-159. Examples of using cost functions other than cross-validation for parameter tuning and feature selection.
7. Livingstone DJ, Salt DW: Judging the significance of multiple linear regression models. J Med Chem (2005) 48(3):661-663. A study of the impact of feature selection on linear regression models.
8. Hawkins DM: The problem of overfitting. J Chem Inf Comput Sci (2004) 44(1):1-12. An excellent review that details a number of factors which can lead to overfitting.
9. 2! J Mol Graph Model (2002) 20(4):269-276.
10. Lanctot JK, Putta S, Lemmen C, Greene J: Using ensembles to classify compounds for drug discovery. J Chem Inf Comput Sci (2003) 43(6):2163-2169.
11. Liu Y: A comparative study on feature selection methods for drug discovery. J Chem Inf Comput Sci (2004) 44(5):1823-1828. A comparison of effects of several feature selection methods on OSAR models.
12. Venkatraman V, Dalby AR, Yang ZR: Evaluation of mutual information and genetic programming for feature selection in QSAR. J Chem Inf Comput Sci (2004) 44(5):1686-1692.
13. Weston J, Perez-Cruz F, Bousquet O, Chapelle O, Elisseeff A, Scholkopf B: Feature selection and transduction for prediction of molecular bioactivity for drug design. Bioinformatics (2003) 19(6):764-771. Provides an example of the use of prior domain knowledge to obtain feature selection metrics.
14. Byvatov E, Schneider G: SVM-based feature selection for characterization of focused compound collections. J Chem Inf Comput Sci (2004) 44(3):993-999.
15. Rassokhin DN, Agrafiotis DK: Kolmogorov-Smimov statistic and its application in library design. J Mol Graph Model (2000) 18(4-5):368-382.
16. Lin TM, Li MT, Tsai KC: Implementing the Fisher's discriminant ratio in a k-means clustering algorithm for feature selection and data set trimming. J Chem Inf Comput Sci (2004) 44(1):76-87.
17. Wegner JK, Frohlich H, Zell A: Feature selection for descriptor based classification models. 2. Human intestinal absorption (HIA). J Chem Inf Comput Sci (2004) 44(3):931-939.
18. Wegner JK, Frohlich H, Zell A: Feature selection for descriptor based classification models. 1. Theory and GA-SEC algorithm. J Chem Inf Comput Sci (2004) 44(3):921-930.
19. Wegner JK, Zell A: Prediction of aqueous solubility and partition coefficient optimized by a genetic algorithm based descriptor selection method. J Chem Inf Comput Sci (2003) 43(3):1077-1084.
20. Bender A, Mussa HY, Glen RC, Reiling S: Molecular similarity searching using atom environments, information-based feature selection, and a naïve Bayesian classifier. J Chem Inf Comput Sci (2004) 44(1):170-178.
21. KDD Cup (2001): University of Wisconsin, Madison, WI, USA (2001). http://www.cs.wisc.edu/~dpage/kddcup2001/
22. Baumann K, Stiefl N: Validation tools for variable subset regression. J Comput Aid Mol Des (2005) 18(7-9):549-562. Presents a number of interesting metrics for assessing the quality of a QSAR model.
23. Devillers J (Ed): Genetic Algorithms in Molecular Modeling. Academic Press, London, UK (1996).
24. Goldberg DE (Ed): Genetic Algorithms in Search, Optimization, and Machine Learning. Addison-Wesley, Reading, MA, USA (1989).
25. Cho SJ, Hermsmeier MA: Genetic algorithm guided selection: Variable selection and subset selection. J Chem Inf Comput Sci (2002) 42(4):927-936.
26. Liu SS, Yin CS, Wang LS: Combined MEDV-GA-MLR method for QSAR of three panels of steroids, dipeptides and COX-2 inhibitors. J Chem Inf Comput Sci (2002) 42(3):749-756.
27. Saxena AK, Prathipati P: Comparison of MLR, PLS and GA-MLR in QSAR analysis. SAR QSAR Environ Res (2003) 14(5-6):433-445.
28. Gao H, Lajiness MS, Van Drie J: Enhancement of binary QSAR analysis by a GA-based variable selection method. J Mol Graph Model (2002) 20(4):259-268.
29. Yasri A, Hartsough D: Toward an optimal procedure for variable selection and QSAR model building. J Chem Inf Comput Sci (2001) 41(5):1218-1227.
30. Laarhoven PJ, Aarts EH (Eds): Simulated Annealing: Theory and Applications. Kluwer Academic Publishers, Boston, MA, USA (1987).
31. Zheng W, Tropsha A: Novel variable selection quantitative structure-property relationship approach based on the k-nearest-neighbor principle. J Chem Inf Comput Sci (2000) 40(1):185-194.
32. Agrafiotis DK, Cedeno W: Feature selection for structure-activity correlation using binary particle swarms. J Med Chem (2002) 45(5):1098-1107.
33. Cedeno W, Agrafiotis DK: Using particle swarms for the development of QSAR models based on k-nearest neighbor and kernel regression. J Comput Aid Mol Des (2003) 17(2-4):255-263.
34. Izrailev S, Agrafiotis DK: Variable selection for QSAR by artificial ant colony systems. SAR QSAR Environ Res (2002) 13(3-4):417-423.
35. Guyon I, Weston J, Barnhill S, Vapnik V: Gene selection for cancer classification using support vector machines. Machine Learning (2002) 46(1-3):389-422.
36. Xue Y, Li ZR, Yap CW, Sun LZ, Chen X, Chen YZ: Effect of molecular descriptor feature selection in support vector machine classification of pharmacokinetic and toxicological properties of chemical agents. J Chem Inf Comput Sci (2004) 44(5):1630-1638.