Application of ab initio theory for the prediction of acidity constants of some 1-hydroxy-9,10-anthraquinone derivatives using genetic neural network

Abstract A genetic algorithm based neural network model (GA-NN) has been applied for the prediction of the acidity constants of some recently synthesized 1-hydroxy-9,10-anthraquinone derivatives using quantum chemical descriptors. Ab initio theory was used to calculate some quantum chemical descriptors including electrostatic potentials and local charges at each atom, HOMO and LUMO energies, etc. A three-layered feed forward neural network with back-propagation of error learning algorithm was employed to model the nonlinear and complex relationships between the acidity constant of anthraquinones and their quantum chemical descriptors. The subset of descriptors, which resulted in the low prediction error, was selected by genetic algorithm. A proper model with low prediction error and high correlation coefficient was obtained. This model was applied for the prediction of the pKa of some anthraquinone derivatives, which were not used in the modeling procedure. The relative errors of prediction lower than 2% were obtained.

[1]  M. C. U. Araújo,et al.  The successive projections algorithm for variable selection in spectroscopic multicomponent analysis , 2001 .

[2]  F. Tomás-Vert,et al.  Artificial neural network applied to the discrimination of antibacterial activity by topological methods , 2000 .

[3]  Ruisheng Zhang,et al.  Neural Network-Topological Indices Approach to the Prediction of Properties of Alkene , 1997, J. Chem. Inf. Comput. Sci..

[4]  Beata Walczak,et al.  Neural networks with robust backpropagation learning algorithm , 1996 .

[5]  Emili Besalú,et al.  Quantum mechanical origin of QSAR: theory and applications , 2000 .

[6]  U Depczynski,et al.  Genetic algorithms applied to the selection of factors in principal component regression , 2000 .

[7]  H. Eslami.  Prediction of the density for natural gas and liquefied natural gas mixtures , 2001 .

[8]  Jahan B. Ghasemi,et al.  Spectrophotometric determination of acidity constants of some anthraquinones and anthrones in methanol-water mixtures. , 1993, Talanta.

[9]  Anton J. Hopfinger,et al.  4D-QSAR Analysis of a Set of Ecdysteroids and a Comparison to CoMFA Modeling , 2001, J. Chem. Inf. Comput. Sci..

[10]  S. Wold,et al.  PLS-regression: a basic tool of chemometrics , 2001 .

[11]  Emilio Benfenati,et al.  Interpretation of Quantitative Structure-Property and -Activity Relationships , 2001, J. Chem. Inf. Comput. Sci..

[12]  X. Yuan,et al.  Quantitative Structure-Activity Relationships of Organic Acids and Bases , 1996, Bulletin of environmental contamination and toxicology.

[13]  Kailin Tang,et al.  Combining PLS with GA-GP for QSAR , 2002 .

[14]  M. Shamsipur,et al.  Multicomponent acid–base titration by principal component-artificial neural network calibration , 2002 .

[15]  Bahram Hemmateenejad,et al.  QSAR study of the calcium channel antagonist activity of some recently synthesized dihydropyridine derivatives. An application of genetic algorithm for variable selection in MLR and PLS methods , 2002 .

[16]  Palanisamy Thanikaivelan,et al.  Application of quantum chemical descriptor in quantitative structure activity and structure property relationship , 2000 .

[17]  Xueguang Shao,et al.  Molecular interactions of α-cyclodextrin inclusion complexes using a genetic algorithm , 2001 .

[18]  M. Karelson,et al.  Quantum-Chemical Descriptors in QSAR/QSPR Studies. , 1996, Chemical reviews.

[19]  Elizabeth A. Peck,et al.  Introduction to Linear Regression Analysis , 2001 .

[20]  Paola Gramatica,et al.  Structure/Response Correlations and Similarity/Diversity Analysis by GETAWAY Descriptors, 2. Application of the Novel 3D Molecular Descriptors to QSAR/QSPR Studies , 2002, J. Chem. Inf. Comput. Sci..

[21]  L. Hammett,et al.  Physical organic chemistry , 1940 .

[22]  Spectrophotometric Determination of Acidity Constants of Some Anthraquinone Derivatives in Binary Methanol-Water Mixtures , 1995 .

[23]  B. T. Luke.  Comparison of three different QSAR/QSPR generation techniques , 1999 .

[24]  Andrey A. Toropov,et al.  Improved molecular descriptors to calculate boiling points based on the optimization of correlation weights of local graph invariants , 2001 .

[25]  Roberto Todeschini,et al.  Handbook of Molecular Descriptors , 2002 .

[26]  H. Sharghi,et al.  Quantitative structure-property relationship study of acidity constants of some 9,10-anthraquinone derivatives using multiple linear regression and partial least-squares procedures. , 2001, Talanta.

[27]  M. Shamsipur,et al.  Simultaneous determination of promethazine, chlorpromazine, and perphenazine by multivariate calibration methods and derivative spectrophotometry. , 2002, Journal of AOAC International.

[28]  S. Unger.  Molecular Connectivity in Structure–activity Analysis , 1987 .

[29]  John H. Kalivas,et al.  Global optimization by simulated annealing with wavelength selection for ultraviolet-visible spectrophotometry , 1989 .

[30]  Byungwhan Kim,et al.  An optimal neural network plasma model: a case study , 2001 .

[31]  Jahan B. Ghasemi,et al.  Spectrophotometric Determination of Acidity Constants of Some Recently Synthesized Anthraquinones in Methanol + Water , 1997 .

[32]  Pin Yang,et al.  Molecular modeling on recognition of sheared and normal DNA by novel metal complex Λ- and Δ-[Co(phen)2hpip]3+ , 2002 .

[33]  M. Pintore,et al.  Molecular descriptor selection combining genetic algorithms and fuzzy logic: application to database mining procedures , 2002 .

[34]  Paul Geladi,et al.  A comparison of modeling nonlinear systems with artificial neural networks and partial least squares , 1999 .

[35]  Pierre Bruneau,et al.  Search for Predictive Generic Model of Aqueous Solubility Using Bayesian Neural Nets , 2001, J. Chem. Inf. Comput. Sci..