Optimization strategy based on genetic algorithms and neural networks applied to a polymerization process

The article presents a simple and general methodology, especially destined to the optimization of complex, strongly nonlinear systems, for which no extensive knowledge or precise models are available. The optimization problem is solved by means of a simple genetic algorithm, and the results are interpreted both from the mathematical point of view (the minimization of the objective function) and technological (the estimation of the achievement of individual objectives in multiobjective optimization). The use of a scalar objective function is supported by the fact that the genetic algorithm also computes the weights attached to the individual objectives along with the optimal values of the decision variables. The optimization strategy is accomplished in three stages: (1) the design and training of the neural model by a new method based on a genetic algorithm where information about the network is coded into the chromosomes; (2) the actual optimization based on genetic algorithms, which implies testing different values for parameters and different variants of the algorithm, computing the weights of the individual objectives and determining the optimal values for the decision variables; (3) the user's decision, who chooses a solution based on technological criteria. © 2007 Wiley Periodicals, Inc. Int J Quantum Chem, 2008     

Geometry optimizations of benzene clusters using a modified genetic algorithm

A modified genetic algorithm with real-number coding, non-uniform mutation and arithmetical crossover operators was described in this paper. A local minimization was used to improve the final solution obtained by the genetic algorithm. Using the exp-6-1 interatomic energy function, the modified genetic algorithm with local minimization (MGALM) was applied to the geometry optimization problem of small benzene clusters (C6H6)N(N = 2-7) to obtain the global minimum energy structures. MGALM is simple but the structures optimized are comparable to the published results obtained by parallel genetic algorithms.     

Crystal structure prediction of flexible molecules using parallel genetic algorithms with a standard force field

This article describes the application of our distributed computing framework for crystal structure prediction (CSP) the modified genetic algorithms for crystal and cluster prediction (MGAC), to predict the crystal structure of flexible molecules using the general Amber force field (GAFF) and the CHARMM program. The MGAC distributed computing framework includes a series of tightly integrated computer programs for generating the molecule's force field, sampling crystal structures using a distributed parallel genetic algorithm and local energy minimization of the structures followed by the classifying, sorting, and archiving of the most relevant structures. Our results indicate that the method can consistently find the experimentally known crystal structures of flexible molecules, but the number of missing structures and poor ranking observed in some crystals show the need for further improvement of the potential. © 2009 Wiley Periodicals, Inc. J Comput Chem, 2009     

Development of a multipopulation parallel genetic algorithm for structure solution from powder diffraction data

Previously, the genetic algorithm (GA) approach for direct-space crystal structure solution from powder diffraction data has been applied successfully in the structure determination of a range of organic molecular materials. In this article, we present a further development of our approach, namely a multipopulation parallel GA (PGA), which is shown to give rise to increased speed, efficiency, and reliability of structure solution calculations, as well as providing new opportunities for further optimizing our GA methodology. The multipopulation PGA is based on the independent evolution of different subpopulations, with occasional interaction (e.g., transfer of structures) allowed to occur between the different subpopulations. Different strategies for carrying out this interpopulation communication are considered in this article, and comparisons are made to the conventional single-population GA. The increased power offered by the PGA approach creates the opportunity for structure determination of molecular crystals of increasing complexity.     

Strategies for increasing the efficiency of a genetic algorithm for the structural optimization of nanoalloy clusters

An improved genetic algorithm (GA) is described that has been developed to increase the efficiency of finding the global minimum energy isomers for nanoalloy clusters. The GA is optimized for the example Pt12Pd12, with specific investigation of: the effect of biasing the initial population by seeding; the effect of removing specified clusters from the population ("predation"); and the effect of varying the type of mutation operator applied. These changes are found to significantly enhance the efficiency of the GA, which is subsequently demonstrated by the application of the best strategy to a new cluster, namely Pt19Pd19.     

Metabolic profiling using principal component analysis, discriminant partial least squares, and genetic algorithms

The aim of this study was to evaluate evolutionary variable selection methods in improving the classification of ¹H nuclear magnetic resonance (NMR) metabonomic profiles, and to identify the metabolites that are responsible for the classification. Human plasma, urine, and saliva from a group of 150 healthy male and female subjects were subjected to ¹H NMR-based metabonomic analysis. The ¹H NMR spectra were analyzed using two pattern recognition methods, principal component analysis (PCA) and partial least square discriminant analysis (PLS-DA), to identify metabolites responsible for gender differences. The use of genetic algorithms (GA) for variable selection methods was found to enhance the classification performance of the PLS-DA models. The loading plots obtained by PCA and PLS-DA were compared and various metabolites were identified that are responsible for the observed separations. These results demonstrated that our approach is capable of identifying the metabolites that are important for the discrimination of classes of individuals of similar physiological conditions.     

Identifying clusters as low-lying mimina--efficiency of stochastic and genetic algorithms using inexpensive electronic structure levels

Molecular candidates possessing unconventional chemical bonding paradigms (e.g., boron wheels, molecular stars, and multicenter bonding) have attracted a great deal of attention by the computational community. The viability of such systems is necessarily assessed through the identification of the lowest lying energy forms of a given chemical composition on the potential energy surface (PES). Although dozens of search algorithms have been developed, only a few are general and simple enough to become standard everyday procedures for this purpose. The simple random search and genetic algorithm (GA) are among these: but how do these approaches perform on typical isomeric searches? The performance of three specific variants for the ab initio exploration of the PES of prototype planar tetracoordinated and hypercoordinated carbon-containing systems C₂Al₄ and CB₆²⁻ are compared. The advantages of preoptimizing with a low-cost semiempirical method (e.g., PM6) together with the most cost-efficient GA-based variant are discussed, and the trends verified by the isomer search of the larger Si₅Li₇⁺ clusters. © 2011 Wiley Periodicals, Inc. J Comput Chem, 2011     

Convergence and error estimation in free energy calculations using the weighted histogram analysis method

The weighted histogram analysis method (WHAM) has become the standard technique for the analysis of umbrella sampling simulations. In this article, we address the challenges (1) of obtaining fast and accurate solutions of the coupled nonlinear WHAM equations, (2) of quantifying the statistical errors of the resulting free energies, (3) of diagnosing possible systematic errors, and (4) of optimally allocating of the computational resources. Traditionally, the WHAM equations are solved by a fixed-point direct iteration method, despite poor convergence and possible numerical inaccuracies in the solutions. Here, we instead solve the mathematically equivalent problem of maximizing a target likelihood function, by using superlinear numerical optimization algorithms with a significantly faster convergence rate. To estimate the statistical errors in one-dimensional free energy profiles obtained from WHAM, we note that for densely spaced umbrella windows with harmonic biasing potentials, the WHAM free energy profile can be approximated by a coarse-grained free energy obtained by integrating the mean restraining forces. The statistical errors of the coarse-grained free energies can be estimated straightforwardly and then used for the WHAM results. A generalization to multidimensional WHAM is described. We also propose two simple statistical criteria to test the consistency between the histograms of adjacent umbrella windows, which help identify inadequate sampling and hysteresis in the degrees of freedom orthogonal to the reaction coordinate. Together, the estimates of the statistical errors and the diagnostics of inconsistencies in the potentials of mean force provide a basis for the efficient allocation of computational resources in free energy simulations.     

Rivality index neighbourhood algorithm with density and distances weighted schemes for the building of robust QSAR classification models with high reliable applicability domain

The rivality index (RI) is a normalized distance measurement between a molecule and their first nearest neighbours providing a robust prediction of the activity of a molecule based on the known activity of their nearest neighbours. Negative values of the RI describe molecules that would be correctly classified by a statistic algorithm and, vice versa, positive values of this index describe those molecules detected as outliers by the classification algorithms. In this paper, we have described a classification algorithm based on the RI and we have proposed four weighted schemes (kernels) for its calculation based on the measuring of different characteristics of the neighbourhood of molecules for each molecule of the dataset at established values of the threshold of neighbours. The results obtained have demonstrated that the proposed classification algorithm, based on the RI, generates more reliable and robust classification models than many of the more used and well-known machine learning algorithms. These results have been validated and corroborated by using 20 balanced and unbalanced benchmark datasets of different sizes and modelability. The classification models generated provide valuable information about the molecules of the dataset, the applicability domain of the models and the reliability of the predictions.     

Comparative study of kinetic modeling for the oxidative coupling of methane by genetic and marquardt algorithms

Overall kinetic studies on the oxidative coupling of methane, OCM, have been conducted in a tubular fixed bed reactor, using perovskite titanate as the reaction catalyst. The appropriate operating conditions were found to be: temperature 750-775 ℃, total feed flow rate of 160 ml/min, CH4/O2 ratio of 2 and GHSV of 100 min-1. Under these conditions, C2 yield of 28% was achieved. Correlations of the kinetic data have been performed with lumped rate equations for C2 and COx formation as functions of temperature, O2 and CH4 partial pressures. Six models have been selected among the common lumped kinetic models. The selected models have been regressed with the experimental data which were obtained from the Catatest system by genetic algorithm in order to obtain optimized parameters. The kinetic coefficients in the overall reactions were optimized by different numerical optimization methods such as: the Levenberg-Marquardt and genetic algorithms and the results were compared with one another. It has been found that the Santamaria model is in good agreement with the experimental data. The Arrhenius parameters of this model have been obtained by linear regression. It should be noted that the Marquardt algorithm is sensitive to the first guesses and there is possibility to trap in the relative minimum.     

Ab initio protein fold prediction using evolutionary algorithms: influence of design and control parameters on performance

True ab initio prediction of protein 3D structure requires only the protein primary structure, a physicochemical free energy model, and a search method for identifying the free energy global minimum. Various characteristics of evolutionary algorithms (EAs) mean they are in principle well suited to the latter. Studies to date have been less than encouraging, however. This is because of the limited consideration given to EA design and control parameter issues. A comprehensive study of these issues was, therefore, undertaken for ab initio protein fold prediction using a full atomistic protein model. The performance and optimal control parameter settings of twelve EA designs where first established using a 15-residue polyalanine molecule-design aspects varied include the encoding alphabet, crossover operator, and replacement strategy. It can be concluded that real encoding and multipoint crossover are superior, while both generational and steady-state replacement strategies have merits. The scaling between the optimal control parameter settings and polyalanine size was also identified for both generational and steady-state designs based on real encoding and multipoint crossover. Application of the steady-state design to met-enkephalin indicated that these scalings are potentially transferable to real proteins. Comparison of the performance of the steady state design for met-enkephalin with other ab initio methods indicates that EAs can be competitive provided the correct design and control parameter values are used.     

运用模糊神经网络表达和预测链烷烃pVT性质

采用一种基于遗传算法的新型模糊神经网络方法研究链烷烃类化合物的pVT性质。该方法综合神经网络、遗传算法与模糊系统三种柔性智能计算技术的优点,具有良好的学习能力,不易陷入局部最小区域,学习速度较快,网络知识以模糊语言变量的形式加以表达,易于理解。用分子连接性指数对24种链烷烃化合物结构和pVT数据进行学习,进而预测另外14种未知化合物的pVT性质,较好地揭示出化合物分子结构与pVT性质之间的关系,并给出了良好的关联与预测结果。     

Global optimization of atomic and molecular clusters using the space-fixed modified genetic algorithm method

A modified genetic algorithm approach has been applied to atomic Ar clusters and molecular water clusters up to (H₂O)₁₃. Several genetic operators are discussed which are suitable for real-valued space-fixed atomic coordinates and Euler angles. The performance of these operators has been systematically investigated. For atomic systems, it is found that a mix of operators containing a coordinate-averaging operator is optimal. For angular coordinates, the situation is less clear. It appears that inversion and two-point crossover operators are the best choice. © 1997 John Wiley & Sons, Inc. J Comput Chem 18: 1233–1244     

Dynamical properties and thermal rate coefficients for the Na + HF reaction using genetic algorithm

The genetic algorithm optimization technique (GAOT) was used to build a new potential energy surface (PES) to the Na + HF → NaF + H reaction. Quasi‐Classical Trajectories and Transition State Theory methods were used to obtain the dynamical properties and thermal rate coefficients (TRCs), respectively, of this new PES. These features were compared with the dynamical properties and TRCs available in the literature. It was found that the GAOT PES agrees very well with other PESs, in which the maximum difference found is smaller than 1.0 Ų for the cross‐sections. These results endow the GAOT approach as a method to build PESs of reactive scattering processes. © 2009 Wiley Periodicals, Inc. Int J Quantum Chem, 2010