Summary
A classification of molecules depends on the descriptor set which is used to represent the compounds, and each descriptor could be regarded as one perception of a molecule. In this study we show that a combination of several classifiers that are grounded on separate descriptor sets can be superior to a single classifier that was built using all available descriptors. The task of predicting ligands of G-protein coupled receptors (GPCR) served as an example application. The perceptron, multilayer neural networks, and radial basis function (RBF) networks were employed for prediction. We developed classifiers with and without descriptor selection. Prediction accuracy was assessed by the area under the receiver operating characteristic (ROC) curve. In the case with descriptor selection both the selection and the rank order of the descriptors depended on the type and topology of the neural networks. We demonstrate that the overall prediction accuracy of the system can be improved by joining neural network classifiers of different type and topology using a “jury network” that is trained to evaluate the predictions from the individual classifiers. Seventy-one percent correct prediction of GPCR ligands was obtained.
Similar content being viewed by others
Abbreviations
- BP:
-
backpropagation algorithm
- GA:
-
genetic algorithm
- HTS:
-
high-throughput screening
- MLP:
-
multilayer neural network (multilayer perceptron)
- MSE:
-
mean square error
- QSAR:
-
quantitative structure–activity relationship
- RBF:
-
radial basis function
- ROC:
-
receiver operating characteristic curve
References
Böhm, H.-J. and Schneider, G. (Eds.) Virtual Screening for Bioactive Molecules, Wiley-VCH, Weinheim, 2000.
Muegge, I., Selection criteria for drug-like compounds, Med. Res. Rev., 23 (2003) 302–321.
Fradera, X. and Mestres, J., Guided docking approaches to structure-based design and screening, Curr. Top. Med. Chem., 4 (2004) 687–700.
Givehchi, A., Dietrich, A., Wrede, P. and Schneider, G., ChemSpaceshuttle: A tool for data mining in drug discovery by classification, projection, and 3D visualization, QSAR Comb. Sci., 5 (2003) 549–559.
The Chemical Computing Group Inc., MOE Manual, URL: http://www.chemcomp.com/Journal_of_CCG/Features/descr.htm, 2004.
Todeschini, R. and Consonni, V., Handbook of Molecular Descriptors, WILEY-VCH, Weinheim, 2000.
So, S.S. and Karplus, M., A comparative study of ligand–receptor complex binding affinity prediction methods based on glycogen phosphorylase inhibitors, J. Comp. Aided Mol. Des., 13 (1999) 243–258.
Yasri, A. and Hartsough, D., Toward an optimal procedure for variable selection and QSAR model building, J. Chem. Inf. Comp. Sci., 41 (2001) 1218–1227.
Saxena, A.K. and Prathipati, P., Comparison of MLR, PLS and GA-MLR in QSAR analysis, SAR QSAR Environ. Res., 14 (2003) 433–445.
Schneider, G. and Wrede, P., Artificial neural networks for computer-based molecular design, Prog. Biophys. Mol. Biol., 70 (1998) 175–222.
Sadowski, J., Database profiling by neural networks, in Böhm, H.-J. and Schneider, G. (Eds.), Virtual Screening for Bioactive Molecules, Wiley-VCH, Weinheim, 2000, pp. 117–130.
Zupan, J. and Gasteiger, J., Neural Networks in Chemistry and Drug Design. An Introduction, Wiley-VCH, Weinheim, 1999.
Schneider, P. and Schneider, G., Collection of bioactive reference compounds for focused library design, QSAR Comb. Sci., 22 (2003) 713–718.
Anderson, J.A., Pellionisz, A. and Rosenfield, E. (Eds.) Neurocomputing 2: Directions for Research, MIT Press, Cambridge, MA, 1990.
Churchland, P.S. and Sejnowski, T.J., The Computational Brain, MIT Press, Cambridge, MA, 1992.
Rumelhart, D.E., Hinton, G.E. and Williams, R.J., Learning internal representations by error propagation, in Rumelhart, D.E. and McClelland, J.L. (Eds.), Parallel Distributed Processing, Vol. 1, MIT Press, Cambridge, MA, 1986, pp. 318–362.
Demuth, H. and Beal, M., Neural Network Toolbox, User's Guide, Version 4, 2001.
Hagan, M.T., Demuth, H.B. and Beale, M.H., Neural Network Design, PWS Publishing, Boston, MA, 1996.
Hagan, M.T. and Menhaj, M., Training feedforward networks with the Marquardt algorithm, IEEE Trans. Neural Networks, 5 (1994) 989–993.
Goldberg, D.E., Genetic Algorithms in Search, Optimization and Machine Learning, Addison Wesley, MA, 1989.
Leardi, R., Genetic algorithms in chemometrics and chemistry: A review, J. Chemometr., 15(7) (2001) 559–569.
Leardi, R., Application of genetic algorithm-PLS for feature selection in spectral data sets, J. Chemometr., 14(5–6) (2000) 643–655.
Leardi, R., Boggia, R. and Terrile, M., Genetic algorithms for a strategy for feature selection, J. Chemometr., 14(5–6) (2000) 643–655.
Weber, L., Practical approaches to evolutionary design, in Böhm, H.-J., Schneider, G. (Eds.), Virtual Screening for Bioactive Molecules, Wiley-VCH, Weinheim, 2000, pp. 187–205.
Zweig, M.H. and Campbell, G., Receiver-operating characteristic (ROC) plots: A fundamental evaluation tool in clinical medicine, Clin. Chem., 39 (1993) 561–577.
Griner, P.F., Mayewski, R.J., Mushlin, A.I. and Greenland, P., Selection and interpretation of diagnostic tests and procedures, Ann. Int. Med., 94 (1981) 555–600.
Hanley, J.A. and McNeil, B.J., The meaning and use of the area under a receiver operating characteristic (ROC) curve, Radiology, 143 (1982) 29–36.
Hanley, J.A. and McNeil, B.J., A method of comparing the areas under receiver operating characteristic curves derived from the same cases, Radiology, 148 (1983) 839–843.
Metz, C.E., Basic principles of ROC analysis, Semin. Nuclear Med., 8 (1978) 283–298.
Karwath, A. and King, R.D., Homology induction: The use of machine learning to improve sequence similarity searches, BMC Bioinform., 3(11) (2002).
Broberg, P., Statistical methods for ranking differentially expressed genes, Genome Biol., 4(R41) (2003).
Chen, S., Cowan, C.F.N. and Grant, P.M., Orthogonal least squares learning algorithm for radial basis function networks, IEEE Trans. Neural Networks, 2(2) (1991) 302–309.
Moody, J. and Darken, C.J., Fast learning in networks of locally-tuned processing units, Neural Comput., 1–2 (1989) 281–294.
Broomhead, D.S. and Lowe, D., Multivariable functional interpolation and adaptive networks, Complex Sys., 2 (1988) 321–355.
Powell, M.J.D., Radial basis function for multivariate interpolation: A review, in Cox, M.G. and Mason, J.C. (Eds.), Algorithm for the Approximation of Function and Data, Oxford University Press, New York, 1985, pp. 143–167.
Musavi, M.T., Ahmed, W., Chan, K.H., Faris, K.B. and Hummels, D.M., On the training of radial basis function classifiers, Neural Networks, 5 (1992) 595–603.
Bishop, C., Neural Networks for Pattern Recognition, Oxford University Press, Oxford, 1995.
Poggio, T. and Girosi, F., A Theory of Networks for Approximation and Learning, Massachussets Institute of Technology, AI Lab, Cambridge, MA, 1989.
Schwenker, F., Kestler, H.A. and Palm, G., Three learning phases for radial-basis-function networks, Neural Networks, 14 (2001) 439–458.
Cichocki, A. and Unbehauen, R., Neural Networks for Optimization and Signal Processing, John Wiley and Sons, New York, 1993.
Kohonen, T., Self-Organizing Maps, Springer, Berlin, 1995.
Givehchi, A. and Schneider, G., Impact of descriptor vector scaling on classification drugs and nondrugs with artificial neural networks, J. Mol. Model, 10 (2004) 204–211.
Park, H., Amari, S. and Fukumizu, K., Adaptive natural gradient learning algorithms for various stochastic models, Neural Networks, 13 (2000) 755–764.
Biganzoli, E., Boracchi, P., Mariani, L. and Marubini, E., Feed forward neural networks for the analysis of censored survival data: A partial logistic regression approach, Stat. Med., 17 (1998) 116–186.
Sprinkhuizen-Kuyper, I.G. and Boers, E.J.W., The error surface of the 2-2-1 XOR network: The finite stationary points, Neural Networks, 11 (1998) 683–690.
Polhill, J.G. and Weir, M.K., An approach to guaranteeing generalisation in neural networks, Neural Networks, 14 (2001) 1035–1048.
Hamey, L.G.C., XOR has no local minima: A case study in neural network error surface analysis, Neural Networks, 11 (1998) 669–681.
Schneider, G., Evolutionary molecular design in virtual fitnet landscape, in Böhm, H.-J. and Schneider, G. (Eds.), Virtual Screening for Bioactive Molecules, Wiley-VCH, Weinheim, 2000, pp. 161–186.
Byvatov, E., Fechner, U., Sadowski, J. and Schneider, G., Comparison of support vector machine and artificial neural network systems for drug/nondrug classification, J. Chem. Inf. Comput. Sci., 43 (2003) 1882–1889.
Hemmateenejad, B., Akhond, M., Miri, R. and Shamsipur, M., Genetic algorithm applied to the selection of factors in principal component-artificial neural networks: Application to QSAR study of calcium channel antagonist activity of 1,4-dihydropyridines (nifedipine analogous), J. Chem. Inf. Comput. Sci., 43 (2003) 1328–1334.
McClelland, H.E. and Jurs, P., Quantitative structure–property relationships for the prediction of vapor pressures of organic compounds from molecular structures, J. Chem. Inf. Comput. Sci., 40 (2000) 967–975.
Tetko, I.V., Villa, A.E. and Livingstone, D.J., Neural network studies. 2. Variable selection, J. Chem. Inf. Comput. Sci., 36 (1996) 794–803.
Gasteiger, J. and Marsali, M., Iterative partial equalization of orbital electronegativity: A rapid access to atomic charges, Tetrahedron, 36 (1980) 3219–3288.
Wildman, S.A. and Crippen, G.M., Prediction of physiochemical parameters by atomic contributions, J. Chem. Inf. Comput. Sci., 39 (1999) 868–873.
Balaban, A.T., Highly discriminating distance-based topological index, Chem. Phys. Lett., 89 (1982) 399–404.
Wegner, J.K. and Zell, A., Prediction of aqueous solubility and partition coefficient optimized by a genetic algorithm based descriptor selection method, J. Chem. Inf. Comput. Sci., 43 (2003) 1077–1084.
Balakin, K.V., Tkachenko, S.E., Lang, S.A., Okun, I., Ivashchenko, A.A. and Savchuk, N.P., Property-based design of GPCR-targeted library, J. Chem. Inf. Comput. Sci., 42 (2002) 1332–1342.
Ajay, A., Walters, W.P. and Murcko, M.A., Can we learn to distinguish between “drug-like” and “nondrug-like” molecules?, J. Med. Chem., 41 (1998) 3314–3324.
Sadowski, J. and Kubinyi, H., A scoring scheme for discriminating between drugs and nondrugs, J. Med. Chem., 41 (1998) 3325–3329.
Fechner, U. and Schneider, G., Evaluation of distance metrics for ligand-based similarity searching, Chembiochem, 5 (2004) 538–540.
Hert, J., Willett, P., Wilton, D.J., Acklin, P., Azzaoui, K., Jacoby, E. and Schuffenhauer, A., Comparison of fingerprint-based methods for virtual screening using multiple bioactive reference structures, J. Chem. Inf. Comput. Sci., 44 (2004) 1177–1785.
Lam, R.L. and Welch, W.J., Comparison of methods based on diversity and similarity for molecule selection and the analysis of drug discovery data, Methods Mol. Biol., 275 (2004) 301–316.
Byvatov, E. and Schneider, G., SVM-based feature selection for characterization of focused compound collections, J. Chem. Inf. Comput. Sci., 44 (2004) 993–999.
Byvatov, E. and Schneider, G., Support vector machine applications in bioinformatics, Appl. Bioinform., 2 (2003) 67–77.
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Givehchi, A., Schneider, G. Multi-space classification for predicting GPCR-ligands. Mol Divers 9, 371–383 (2005). https://doi.org/10.1007/s11030-005-6293-4
Received:
Accepted:
Issue Date:
DOI: https://doi.org/10.1007/s11030-005-6293-4