Abstract
Many commercially available software programs claim similar efficiency and accuracy as variable selection tools. Genetic algorithms are commonly used variable selection methods where most relevant variables can be differentiated from ‘less important’ variables using evolutionary computing techniques. However, different vendors offer several algorithms, and the puzzling question is: which one is the appropriate method of choice? In this study, several genetic algorithm tools (e.g. GFA from Cerius2, QuaSAR-Evolution from MOE and Partek’s genetic algorithm) were compared. Stepwise multiple linear regression models were generated using the most relevant variables identified by the above genetic algorithms. This procedure led to the successful generation of Quantitative Structure–activity Relationship (QSAR) models for (a) proprietary datasets and (b) the Selwood dataset.
Similar content being viewed by others
References
C. Hansch A.R. Steward (1964) J. Med. Chem., 44 691
C. Hansch R.M. Muir T. Fujita P.P. Maloney F. Geiger M. Streich (1963) J. Am. Chem. Soc., 85 1817
G.M. Keseru (2003) Mol. Div., 7 1
U. Norinder T. Hogberg (2002) Textbook of Drug Design and Discovery Taylor & Francis New York, NY
R. Todeschini V. Consonni (Eds) (2000) Handbook of Molecular Descriptors Wiley-VCH Weinheim, Germany
D.M. Hawkins (2004) J. Chem. Inf. Comput. Sci., 44 1
S. Wold (1991) Quant. Struct.-Act. Relat., 10 191
R.D. Cramer ParticleIII (1993) Perspect. Drug Discov. Design, 1 269
D.L. Selwood D.J. Livingstone J.C. Comley A.B. O’Dowd A.T. Hudson P. Jackson K.S. Jandu V.S. Rose J.N. Stables (1990) J. Med. Chem., 33 136
D.C. Whitley M.G. Ford D.J. Livingstone (2000) J. Chem. Inf. Comput. Sci., 40 1160
D.J. Livingstone E. Rahr (1989) Quant. Struct.-Act. Relat., 8 103
O. Kikuch (1987) Quant. Struct.-Act. Relat., 6 179
J.M. Sutter S.L. Dixon P.C. Jurs (1995) J. Chem. Inf. Comput. Sci., 35 77
B.H. Sumida A.I. Houston J.M. McNamara W.D. Hamilton (1990) J. Theor. Biol., 147 59
Rogers, D., In Proceedings of the Fourth International Conference on Genetic Algorithms, San Diego, CA, 1991.
R. Leardi R. Boggia M. Terrile (1992) J. Chemometr., 6 267
M. Mitchell (Eds) (1999) An Introduction to Genetic Algorithm The MIT Press London, UK
B.T. Luke (1994) J. Chem. Inf. Comput. Sci., 34 1279
Accelrys, Cerius2, San Diego, CA, 2003.
ChemicalComputingGroup, MOE, Quebec, Canada, 2003.
Partek, Partek Pro, St. Charles, MO, 2003.
P. Chavatte S. Yous C. Marot N. Baurin D. Lesieur (2001) J. Med. Chem., 44 3223
A. Cavalli E. Poluzzi F. Ponti ParticleDe M. Recanatini (2002) J. Med. Chem., 45 3844
J.H. Holland (Eds) (1975) Adaptation in Natural and Artificial Systems The MIT Press Cambridge, MA
H. Kubinyi (1994) Quant. Struct.-Act. Relat., 13 285
D. Rogers (1992) Adv. Neural Inform. Process. Syst., 4 1088
D. Rogers A.J. Hopfinger (1994) J. Chem. Inf. Comput. Sci., 34 854
J.H. Friedman (1991) Ann. Statist., 19 1
ChemicalComputingGroup, Svl Exchange Webpage. http://svl.chemcomp.com/, 2003.
S. Schefzick C. Kibbey M.P. Bradley (2004) J. Comb. Chem., 6 916
Wold, S., In v.d. Waterbeemd H. (Ed.), QSAR: Chemometric Methods in Molecular Design, Verlag-Chemie, Weinheim, Germany, 1994.
S.J. Cho M.A. Hermsmeier (2002) J. Chem. Inf. Comput. Sci., 42 927
H. Kubinyi (1994) Quant. Struct.-Act. Relat., 13 393
C.L. Waller M.P. Bradley (1999) J. Chem. Inf. Comput. Sci., 39 345
J.W. McFarland D.J. Gans (1994) Quant. Struct.-Act. Relat., 13 11
Todeschini, R., Dragon, Milan, Italy, 2003.
Pearlman, R.S., Tripos Inc., St. Louis, MO.
The QSAR and Modelling Society. http://www.ndsu.nodak.edu/qsar_soc/, 2003.
M. Kendall (Eds) (1955) Rank Correlation Methods Charles Griffin and Co. London, UK
M.B. Brown J.K. Benedetti (1977) J. Am. Stat. Assoc., 72 309
A. Agresti (Eds) (1990) Categorical Data Analysis John Wiley & Sons, Inc. New York
R. Todeschini V. Consonni M. Pavan (2004) Chemometr. Intell. Lab. Syst., 70 55
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Schefzick, S., Bradley, M. Comparison of commercially available genetic algorithms: GAs as variable selection tool. J Comput Aided Mol Des 18, 511–521 (2004). https://doi.org/10.1007/s10822-004-5322-1
Received:
Accepted:
Issue Date:
DOI: https://doi.org/10.1007/s10822-004-5322-1