Accurate Prediction Of Absorption Energies Of Small Organic Molecules: Neural Network And Support Vector Machine Methods

Absorption energy is a significant physical property for a molecule, which implies inherent structure information and electronic properties. The accurate prediction the absorption energy is one of the important topics in computational chemistry. Quantum chemistry is a fundamental subject studying properties and interactions of molecules. In the past decades, it has been developed remarkably on its primary theories and methods. One of the Holy Grails of quantum mechanical calculation is to predict properties of matter prior to experiments, to examine the physical properties or processes that are inaccessible by experiments. Despite their success, the results of quantum mechanical calculation contain inherent numerical errors caused by various intrinsic approximations, in particular for complex systems. During the last 10 years, many statistical correction approaches were employed to improve the results of quantum chemical method. After the theoretical calculation of the properties of molecules, statistical correction approaches can be used to determine the quantitative relationship between the calculated and experimental results. These statistical correction approaches mainly include multiple linear regression (MLR) or nonlinear methods et al.In the present work, neural network and least squares support vector machine have been applied to improve the calculation accuracy of quantum chemical methods for absorption energies of 160 small organic molecules. With general descriptors, these combined methods can greatly eliminate the systemic errors of theoretical calculation due to ignoring the electron correlation and using small basis set, and will be a novel tool for predicting the properties of the molecules.Our work has been focus on following aspects:1. The combination of genetic algorithm and back propagation neural network correction approach (GABP) has successfully improved the calculation accuracy of the absorption energies after quantum chemical methods calculated UV-visible absorption spectra of 160 small organic molecules. Firstly, the GABP1 is introduced to determine the quantitative relationship between the experimental results and calculations obtained by using quantum chemical methods. After GABP1 correction, the root-mean-square (RMS) deviations of the calculated absorption energies reduce from 0.32, 0.95 and 0.46 eV to 0.14, 0.19 and 0.18 eV for B3LYP/6-31G(d), B3LYP/STO-3G and ZINDO methods, respectively. The corrected results of B3LYP/6-31G(d)-GABP1 are in good agreement with experimental results.2. The GABP2 is introduced to determine the quantitative relationship between the results of B3LYP/6-31G(d)-GABP1 method and calculations of the low accuracy methods (B3LYP/STO-3G and ZINDO). After GABP2 correction, the RMS deviations of the calculated absorption energies reduce to 0.20 and 0.19 eV for B3LYP/STO-3G and ZINDO methods, respectively. The results show that the RMS deviations after GABP1 and GABP2 correction are similar for B3LYP/STO-3G and ZINDO methods. Thus, the B3LYP/6-31G(d)-GABP1 is a better method to predict absorption energies and can be used as the approximation of experimental results where the experimental results are unknown or uncertain by experimental methods.3. This GABP may be used for predicting absorption energies of larger organic molecules that are unavailable by experimental methods and by high accuracy theoretical methods with lager basis sets. Thus, this method is a realiable tool to predict absorption energies.4. We enlarge the descriptors according to the data set. After multiple linear regression, 8 descriptors are selected as the proper physical descriptors.5. In this paper we introduce least squares support vector machine (LS-SVM) to improve the calculation accuracy of density functional theory. Upon the LS-SVM approach, the RMS deviations of the B3LYP/6-31G(d) calculated absorption energies of 160 organic molecules are reduced from 0.32 eV to 0.11 eV. Comparison of the MLR and LS-SVM values demonstrates the feasibility and effectiveness of the LS-SVM approach. And, the LS-SVM correction on top of the B3LYP/6-31G(d) results is a better method to predict absorption energies and can be used as the approximation of experimental results when the experimental results are limited to measurement with very high accuracy. LS-SVM greatly extends the reliability and applicability of the B3LYP/6-31G(d) method.