Abstract
We report a neural network modeling approach combined with genetic algorithm for prediction of experimental binding affinity to human Estrogen Receptor α and β (ER-α and ER-β) of a diverse set of chemicals. The counterpropagation artificial neural network is used as a modeling method. Structural features of ligands having the strongest influence to the binding affinities were investigated. The molecular descriptors have been selected in the variable selection procedure based on the genetic algorithm (GA). The 3D descriptors of molecular structures were calculated for the minimal energy conformation of isolated ligands. All the optimized models were tested by an internal and an external set of compounds. The models served for classification and prediction of binding affinities. The optimized models were 100% correct in the classification part, where the active molecules were separated from the inactive ones. The best predictive model of active molecules was assessed with the internal test set yielding the error in prediction RMS = 0.12, while the predictions for the external test set contain some outliers, which are ascribed to the incompatibility of individual compounds concerning the structural domain of our model. The influence of the receptor on the conformation of the ligands in the ligand–protein complex is described and discussed in the accompanying paper.
Similar content being viewed by others
Abbreviations
- CP-ANN:
-
Counterpropagation artificial neuronal network
- ER:
-
Estrogen receptor
- GA:
-
Genetic algorithm
- RBA:
-
Relative binding affinity
- RMS:
-
Root mean square error
References
Kuiper GGJM, Lemmen JG, Carlsson B, Corton JC, Safe SH, van der Saag PT, van der Burg P, Gustafsson JA (1998) Interaction of estrogenic chemicals and phytoestrogens with estrogen receptor β. Endocrinology 139: 4252–4263
Brzozowski AM, Pike ACW, Dauter Z, Hubbard RE, Bonn T, Engstrom O, Ohman L, Greene GL, Gustafsson JA, Carlquist M (1997) Molecular basis of agonism and antagonism in the oestrogen receptor. Nature 389: 753–758
Kuiper GJM, Carlsson B, Grandien K, Enmark E, Haggblad J, Nilsson S, Gustafsson JA (1997) Comparison of the ligand binding specificity and transcript tissue distribution of estrogen receptor α and β. Endocrinology 138: 863–870
Toppari J, Larsen JC, Christiansen P, Giwercman A, Grandjean P, Guillette LJ Jr, Je’gou B, Jensen TK, Jouannet P, Keiding N, Leffers H, McLachlan JA, Meyer O, Muűller J, Rajpert-De Meyts E, Scheike T, Sharpe R, Sumpter J, Skakkebæk NE (1996) Male reproductive health and environmental xenoestrogen. Environ Health Persp 104: 741–803
Elsby R, Ashby J, Sumpter J, Brooks A, Pennie W, Maggs J, Lefevre P, Odum J, Beresford N, Paton D, Park BK (2000) Obstacles to the prediction of estrogenicity from chemical structure: assay-mediated metabolic transformation and the apparent promiscuous nature of the estrogen receptor. Biochem Pharmacol 60: 1519–1530
Damstra T, Barlow S, Bergman A, Kavlock R, Van Der Kraak G (2000) Global assessment of the state-of-the-science of endocrine disruptors international in programme on chemical safety, ICPS-WHO
De Voogt P, Van Hattum B (2003) Critical factors in exposure modeling of endocrine active substances. Pure Appl Chem 75: 1933–1948
Huetz P, Kamarulzaman EE, Wahab HA, Mavri J (2004) Chemical reactivity as a tool to study carcinogenicity: reaction between estradiol and estrone 3,4-quinones ultimate carcinogens and guanine. J Chem Inf Comput Sci 44: 310–314
Rogan EG, Badawi AF, Devanesan PD, Meza JL, Edney JA, West WW, Higginbotham SM, Cavalieri EL (2003) Relative imbalances in estrogen metabolism and conjugation in breast tissue of women with carcinoma: potential biomarkers of susceptibility to cancer. Carcinogenesis 24: 697–702
Devanesan P, Todorovic R, Zhao J, Gross ML, Rogan EG, Cavalieri EL (2001) Catechol estrogen conjugates and DNA adducts in the kidney of male Syrian golden hamsters treated with 4-hydroxyestradiol: potential biomarkers for estrogen-initiated cancer. Carcinogenesis 22: 489–497
Liu HX, Papa E, Gramatica P (2006) QSAR prediction of estrogen activity for a large set of diverse chemicals under the guidance of OECD principles. Chem Res Toxicol 19: 1540–1548
Zupan J, Novič M, Ruisanchez I (1997) Kohonen and counter-propagation artificial neural networks in analytical chemistry. Chemometr Intell Lab 38: 1–23
Katritzky AR, Lobanov VS, Karelson M (1996) CODESSA reference manual, version 2.0. University of Florida
Stewart JJP (1989) MOPAC 6.0 program package. QCPE, No 455
CambridgeSoft Corporation, http://www.cambridgesoft.com
Halgren TA (1996) Merck molecular force field: I. Basis, form, scope, parameterization and performance of MMFF94. J Comp Chem 17: 490–519
Walters P, Stahl (Copyright (C) (1992–1996) M BABEL: Babel version 1.3
Dewar MJS, Zoebisch EG, Healy EF, Stewart J-JP (1985) The development and use of quantum-mechanical molecular- models.76. AM1 – a new general purpose quantum-mechanichal molecular-model. J Am Chem Soc 107: 3902–3909
Stewart JJP (1989) Optimization of parameters for semi-empirical methods I-method. J Comp Chem 10:209–220, (b) Stewart JJP (1989) Optimization of parameters for semi-empirical methods II-applications. J Comp Chem 10:221–264
Hecht-Nielsen R (1987) Counterpropagation networks. Appl Optics 26: 4979–4984
Zupan J, Gasteiger J (1999) Neural networks in chemistry and drug design, 2nd edn. Wiley-VCH, Weinheim
Kohonen T (1988) Self-organization and associative memory. Springer-Verlag, Berlin
Davis L (1991) Handbook of genetic algorithms. Van Nostrand Reinhold, New York
Hibbert (1993) Genetic algorithm in chemistry. Chemometr Intell Lab 19: 277–293
Harris HA, Bapat AR, Gonder DS, Frail DE (2002) The ligand binding profiles of estrogen receptors alpha and beta are species dependent. Steroids 67: 379–384
Physical Properties Database (PHYSPROP) available from: http://www.syrres.com/esc/physprop.htm
KOW WIN v1.66, on-line demo. Available from: http://www.syrres.com/esc/kowwin.htm, http://www.logp.com/
Katritzky AR, Lobanov VS, Karelson M (1994) Comprehensive descriptors for structural and statistical analysis reference manual, version 2.0. Gainesville
COD to Table Program Package, Center for Computational Science, University of Trieste
Novič M, Zupan J (1995) Investigation of infrared spectra-structure correlation using Kohonen and Counter-propagation neural network. J Chem Inf Comput Sci 35: 454–466
Marini F, Roncaglioni A, Novič M (2005) Variable selection and interpretation in structure-affinity correlation modeling of estrogen receptor binders. J Chem Inf Model 45: 1507–1519
Sun J, Baudry J, Katzenellenbogen JA, Katzenellenbogen BS (2003) Molecular basis for the subtype discrimination of the estrogen receptor β selective ligand. Diarylpropionitrile. Mol Endocrinol 17: 247–258
Sun J, Huang YR, Harrington WR, Sheng S, Katzenellenbogen JA, Katzenellenbogen BS (2002) Antagonists selective for estrogen receptor α. Endocrinology 143: 941–947
Katzenellenbogen JA, Muthyala R, Katzenellenbogen BS (2003) Nature of the ligand-binding pocket of estrogen receptor α and β: the search for subtypeselective ligands and implications for the prediction of estrogenic activity. Pure Appl Chem 75: 2397–2403
Maran E, Novič M, Barbieri P, Zupan J (2004) Application of counterpropagation artificial neural network for modeling properties of fish antibiotics. SAR QSAR Environ Res 15: 469–480
Roncaglioni A, Novič M, Vračko M, Benfenati E (2004) Classification of potential endocrine disrupters on the basis of molecular structure using a nonlinear modeling method. J Chem Inf Model 44: 300–309
Author information
Authors and Affiliations
Corresponding author
Electronic supplementary material
Rights and permissions
About this article
Cite this article
Boriani, E., Spreafico, M., Benfenati, E. et al. Structural features of diverse ligands influencing binding affinities to Estrogen α and Estrogen β receptors. Part I: molecular descriptors calculated from minimal energy conformation of isolated ligands. Mol Divers 11, 153–169 (2007). https://doi.org/10.1007/s11030-008-9069-9
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11030-008-9069-9