Abstract
Undoubtedly, computer aided drug design (CADD) has gained important position in medicinal chemistry thanks to balancing random approaches to discovery of new drugs by prioritizing rational insight into the development process. From many CADD methods, quantitative structure activity relationships (QSAR), which are able to exploit chemical and biological information hidden in chemical structures through utilization of numerous machine learning and artificial intelligence methods, are expected to provide the necessary assistance in mechanistic interpretation and prediction of biological activities. In the present work, 56 derivatives of a natural adjuvant euodenine A, which occurs in Euodia asteridula, were selected for a QSAR study with the use of artificial neural networks (ANN). Since building of robust QSAR models is still a challenging research area, several methods had to be utilized to achieve a robust solution. Among various backpropagation based algorithms, much effort has been devoted to research of an optimal brain surgeon (OBS) method, which attempts to prune unimportant ANN elements according to the second derivation of the output signal error with respect to the weights. Herein, the performance of OBS in QSAR analyses is discussed and compared with other ANN learning methods.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsReferences
George, S., Nair, S.A., Venkataraman, R., Baby, S.: Chemical composition, antibacterial and anticancer activities of volatile oil of Melicope denhamii leaves. Nat. Prod. Res. 29, 1959–1962 (2015)
Neve, J.E., Wijesekera, H.P., Duffy, S., Jenkins, I.D., Ripper, J.A., Teague, S.J., Campitelli, M., Garavelas, A., Nikolakopoulos, G., Le, P.V., de, A.L.P., Pham, N.B., Shelton, P., Fraser, N., Carroll, A.R., Avery, V.M., McCrae, C., McCrae, C.: Euodenine A: a small-molecule agonist of human TLR4. J. Med. Chem. 57, 1252–1275 (2014)
Waisser, K., Dolezal, R., Palat, K., Cizmarik, J., Kaustova, J.: QSAR study of antimycobacterial activity of quaternary ammonium salts of piperidinylethyl esters of alkoxysubstituted phenylcarbamic acids. Folia Microbiol. 51, 21–24 (2006)
Nesmerak, K., Dolezal, R., Hudska, V., Bartl, J., Sticha, M., Waisser, K.: Quantitative structure-electrochemistry relationship of 1-Phenyl-5-benzyl-sulfanyltetrazoles and their electrooxidation as a metabolic model. Electroanalysis 22, 2117–2122 (2010)
Maggi, G., Giaccone, G., Donadio, M., Ciuffreda, L., Dalesio, O., Leria, G., Trifiletti, G., Casadio, C., Palestro, G., Mancuso, M., et al.: Thymomas. A review of 169 cases, with particular reference to results of surgical treatment. Cancer 58, 765–776 (1986)
May, R., Dandy, G., Maier, H.: Review of input variable selection methods for artificial neural networks. In: Kenji, S. (ed.) ANN-MABA, InTech (2011). doi:10.5772/16004
Sabo, D., Yu, X.-H.: A new pruning algorithm for neural network dimension analysis. 2008 IEEE, pp. 3313–3318, (2008). doi:10.1109/IJCNN.2008.4634268
Hassibi, B., Stork, D.G.: Second order derivatives for network pruning: Optimal brain surgeon. In: Cowan, J.D. et al. (ed.) NIPS 1993, pp. 164–171, Morgan Kaufmann (1993)
LeCun, Y., Denker, J.S., Solla, S.A., Howard, R.E., Jackel, L.D.: Optimal brain damage. In: Touretzky, D. (ed.) NIPS 1989, 2, pp. 598–605, Morgan Kaufman (1990)
Hassibi, B., Stork, D.G., Wolff, G.J.: Optimal brain surgeon and general network pruning. IEEE ICNN 1, 293–299 (1993). doi:10.1109/ICNN.1993.298572
Acknowledgements
This work was supported by project “Smart Solutions for Ubiquitous Computing Environments” FIM UHK, Czech Republic (under ID: UHK-FIM-SP-2016-2102). The work was also supported by: Czech Science Foundation (GA15-11776S), the IT4Innovations Centre of Excellence project (CZ.1.05/1.1.00/02.0070), and the MŠMT project (LM2011033).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2016 Springer International Publishing Switzerland
About this paper
Cite this paper
Dolezal, R., Trejbal, J., Mesicek, J., Milanov, A., Racakova, V., Krenek, J. (2016). Designing QSAR Models for Promising TLR4 Agonists Isolated from Euodia Asteridula by Artificial Neural Networks Enhanced by Optimal Brain Surgeon. In: Nguyen, N., Iliadis, L., Manolopoulos, Y., Trawiński, B. (eds) Computational Collective Intelligence. ICCCI 2016. Lecture Notes in Computer Science(), vol 9876. Springer, Cham. https://doi.org/10.1007/978-3-319-45246-3_26
Download citation
DOI: https://doi.org/10.1007/978-3-319-45246-3_26
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-45245-6
Online ISBN: 978-3-319-45246-3
eBook Packages: Computer ScienceComputer Science (R0)