Optimization of neural models using evaluation of biological activity of chemical substances as an example

Maciej Szaleniec¹, Ryszard Tadeusiewicz², Andrzej Skoczowski³

¹Instytut Katalizy i Fizykochemii Powierzchni PAN, 30-239 Kraków, ul. Niezapominajek 8.
²AGH University of Science and Technology, Kraków, Poland.
³Instytut Fizjologii Roślin im. Franciszka Górskiego PAN, 30-239 Kraków, ul. Niezapominajek 21.

DOI:

https://doi.org/10.7494/cmms.2006.2.0101

Abstract:

Neural networks (NNs) are tools that are very frequently successfully applied in the modeling of various phenomena and processes. This is due to combination of characteristic for NNs wide approximation capabilities (manifesting especially in nonlinear modeling tasks) with their flexibility and high performance in fitting the model to the real data during the learning process. Taken together these features make NNs one of the best modeling tools available. However, it is a common practice to achieve success with neural network technique in a modeling of particular system while confining the research only to neural model selection, optimization of parameters and validation of the NN performance goodness. Frequently, neural models predictions are analyzed and compared with other modeling techniques or other neural systems. In this paper we provide a complementary approach to the above-mentioned scheme. We took one non-trivial modeling task as an example (i.e. prediction of biological activity of chemical compounds based on their structure and properties) and studied various types of neural networks in order to determine the optimal type of NN, which deals with modeling problem in the most efficient way. We analyzed both linear and non-linear neural networks of MLP and GRNN type. In non-linear MLP systems the linear or non-linear output layers were tested. Moreover a hybrid neural system was developed that joins results of architecture optimization of MLP and GRNN. The paper addresses also the issue of input parameters selection, optimal number of hidden neurons and data representation, especially in terms of an output results. A dozen or so thousands of neural models were developed, providing a rich dataset for assessment of neural networks usefulness. It seems that such a comparative study can be of a high value for other researchers using neural systems in modeling studies. It should allow to chose a type and size of NN used based less on arbitrary and more on rational basis. Our results provide also better understanding into the character and cause-result relationship of processes that take place in neural networks

Cite as:

Szaleniec, M., Tadeusiewicz, R., Skoczowski, A. (2006). Optimization of neural models using evaluation of biological activity of chemical substances as an example. Computer Methods in Materials Science, 6(2), 65 – 80. https://doi.org/10.7494/cmms.2006.2.0101

Article (PDF):

Keywords:

References:

Cigizoglu, H. K. Alp, M., 2006, Generalized regression neural network in modelling river sediment yield, Adv. Eng. Soft., 37, 63 – 68.

Fogelman, S., Blumenstein, M., Zhao, H. 2006, Estimation of chemical oxygen demand by ultraviolet spectroscopic profiling and artificial neural networks, Neural Comput. Appl., 15, 197 – 203.

Hartono, P.; Hashimoto, S., 2005, Learning with ensemble of linear perceptrons. Artificial Neural Networks: Formal Models and their Applications ICANN 2005 15th International Conference, Proceedings, Part II Lec. Notes Comp. Sci., eds, Duch, W., Kacprzyk, J., Oja, E., Zadrozny, S., Springer-Verlag, Berlin, 3697, 115 – 120.

Hong, L., Chunsheng, Y., 2006, Specifying distributed multi agent systems in chemical reaction metaphor, Appl. Intell., 24, 155 – 168.

Lang, B., 2005, Monotonic multi layer perceptron networks as universal approximators. Artificial Neural Networks: Formal Models and their Applications ICANN 2005 15th International Conference, Proceedings, Part II Lec. Notes Comp. Sci., eds, Duch, W., Kacprzyk, J., Oja, E., Zadrozny, S., Springer-Verlag, Berlin, 3697, 31 – 37.

Mei, H., Zhou, Y., Liang, G., Zhiliang, L. 2005, Support vector machine applied in QSAR modeling, Chinese Sci. Bull., 50, 2291 –2296.

Pianese, C., Arsie, I., Sorrentino, M., 2006, A procedure to enhance identification of recurrent neural networks for simulating air fuel ratio dynamics in SI engines, Eng. Appl. Artif. Intel., 19, 65 – 77.

Plewczynski, D., Spieser, S.A.H., Koch, U., 2006, Assessing different classification methods for virtual screening, J. Chem. Inf. Mod., 46, 1098 – 1106.

Raji, U. , Mashor, M. Y., Ali, A. N., Adom, A. H., Sadullah, A. F., 2005, HMLP, MLP and recurrent networks for carbon monoxide concentrations forecasting: a comparison studies, WSEAS Transactions on Systems, 4, 812 – 820.

Szaleniec M., Goclon J., Witko M., Tadeusiewicz R., 2006a, Application of artificial neural networks and DFT-based parameters for prediction of reaction kinetics of ethylbenzene dehydrogenase, J. Comput., Aid. Mol. Des., 20, 1573-4951.

Szaleniec M., Witko M., Tadeusiewicz R., 2006b, Prediction of the ethylbenzene dehydrogenase reaction kinetics by comparative molecular field analysis (COMFA) and artificial neural network’s systems basing on DFT parameters. Materiały XXXVIII Ogólnopolskiego Kolokwium Katalitycznego, ed, Mokrzycki L., Instytut Katalizy i Fizykochemii Powierzchni PAN, Kraków, 215–217.

Weiss, Y., Schölkopf B., Platt J., eds, 2006, Advances in Neural Information Processing Systems 18, The MIT Press, Cambridge.

Yixing, L., Yuzhang, W., Shilie, W., Yonghong, W., 2006, Application of artificial neural network in countercurrent spray saturator, Advances in Neural Networks ISNN 2006. Proc. 3rd Int. Symp. on Neural Networks, Lec. Notes Comp. Sci., eds, Wang, J., Yi, Z., Zurada, J.M., Lu, B. L., Yin, H., Springer-Verlag, Berlin, 3973, 1277 – 1282.

Zhang, J., Sun, J., 2004, Automatic classification of MRI images for three dimensional volume reconstruction by using general regression neural networks, Conf. Rec. 2003 IEEE Nuc. Sci. Sym., 5, 3188 -3189.