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     

基于遗传算法的手性毛细管电泳分离中多指标同时优化

将功效函数法结合遗传算法用于碱性药物肾上腺素的手性毛细管电泳的多指标同时优化.以均匀设计安排了4因素(电解质浓度、pH值、手性试剂浓度和分离电压)6水平实验,建立了峰分离度、迁移时间和灵敏度与实验因素间的多元线性回归方程.为获得毛细管电泳评价指标的同时优化,采用Derringer功效函数法,建立了总功效函数与实验因素的定量关系.采用实数编码的遗传算法搜寻总功效函数的最大值,获得了多个优化分离条件,在这些分离条件下得到的总功效函数与均匀试验设计中最佳条件相比,平均提高了10.4%,获得了三指标同时优化的结果.     

Biologically driven neural platform invoking parallel electrophoretic separation and urinary metabolite screening

This work reveals a computational framework for parallel electrophoretic separation of complex biological macromolecules and model urinary metabolites. More specifically, the implementation of a particle swarm optimization (PSO) algorithm on a neural network platform for multiparameter optimization of multiplexed 24-capillary electrophoresis technology with UV detection is highlighted. Two experimental systems were examined: (1) separation of purified rabbit metallothioneins and (2) separation of model toluene urinary metabolites and selected organic acids. Results proved superior to the use of neural networks employing standard back propagation when examining training error, fitting response, and predictive abilities. Simulation runs were obtained as a result of metaheuristic examination of the global search space with experimental responses in good agreement with predicted values. Full separation of selected analytes was realized after employing optimal model conditions. This framework provides guidance for the application of metaheuristic computational tools to aid in future studies involving parallel chemical separation and screening. Adaptable pseudo-code is provided to enable users of varied software packages and modeling framework to implement the PSO algorithm for their desired use.     

Application of Artificial Neural Network and Multiple Linear Regression Retention Models for Optimization of Separation in Ion Chromatography by Using Several Criteria Functions

This work focuses on problems regarding empirical retention modelling and optimization of separation in ion chromatography. Influences of eluent flow rate and concentration of eluent competing ion (OH^–) on separation of seven inorganic anions (fluoride, chloride, nitrite, sulphate, bromide, nitrate, and phosphate) were investigated. Artificial neural networks and multiple linear regression retention models in combination with several criteria functions were used and compared in global optimization process. It can be seen that general recommendations for optimization of separation in ion chromatography is application of chromatography exponential function criterion in combination with artificial neural networks retention model.     

Optimization of transmission near infrared spectrometry procedures for quality control of pesticide formulations

The use of different response functions to be optimized in the frame of the use of near infrared spectrometry for quality control of active principles in agrochemical formulations has been evaluated. Both, simple functions, based on parameters like sensitivity, repeatability, accuracy, signal to noise ratio, limit of detection or sample throughput, and a complex function, considering all the aforementioned aspects, were employed in the development of a new method for Iprodione determination in agrochemicals. Optimization strategies were based on the previous screening of the most important instrumental factors like number of cumulated scans, nominal resolution, mirror velocity and zero filling factor, based on a two-level full factorial design and on the search for the optimum conditions using central composite designs. Data found evidenced the influence of the response function on the optimum values of experimental conditions and could be employed as a general guide to evaluate the experimental factors in routine use of near infrared spectrometry. Finally the optimized method for Iprodione has been applied to the determination of Diuron and results found compared with those obtained by a conventional approach.     

Optimization by orthogonal array design of ion-pair HPLC separation of the enzymatic hydrolysis products of yeast RNA

<正>The separation of enzymatic hydrolysis products of yeast RNA by ion-pair HPLC was studied.A modified chromatographic response function(MCRF) was proposed to appraise the effectiveness of chromatographic separation.This function takes the number of peaks,resolution and the retention time of the last peak into consideration.It shows advantages for optimization of HPLC separation of complex mixtures.An orthogonal array design was used to separate the hydrolysate of yeast RNA and the optimal chromatographic conditions were obtained.     

Optimising mobile phase composition, its flow-rate and column temperature in HPLC using taboo search

A chemometric methodology is proposed to study the separation of seven p-hydroxybenzoic esters in reversed phase liquid chromatography (RPLC). Fifteen experiments were found to be necessary to find a mathematical model which linked a novel chromatographic response function (CRF) with the column temperature, the water fraction in the mobile phase and its flow rate. The CRF optimum was determined using a new algorithm based on Glover's taboo search (TS). A flow-rate of 0.9 ml min(-1) with a water fraction of 0.64 in the ACN-water mixture and a column temperature of 10 degrees C gave the most efficient separation conditions. The usefulness of TS was compared with the pure random search (PRS) and simplex search (SS). As demonstrated by calculations, the algorithm avoids entrapment in local minima and continues the search to give a near-optimal final solution. Unlike other methods of global optimisation, this procedure is generally applicable, easy to implement, derivative free, conceptually simple and could be used in the future for much more complex optimisation problems.     

QbD‐oriented development and validation of a bioanalytical method for nevirapine with enhanced liquid–liquid extraction and chromatographic separation

The present studies describe the systematic quality by design (QbD)‐oriented development and validation of a simple, rapid, sensitive and cost‐effective reversed‐phase HPLC bioanalytical method for nevirapine in rat plasma. Chromatographic separation was carried out on a C₁₈ column using isocratic 68:9:23% v/v elution of methanol, acetonitrile and water (pH 3, adjusted by orthophosphoric acid) at a flow rate of 1.0 mL/min using UV detection at 230 nm. A Box–Behnken design was applied for chromatographic method optimization taking mobile phase ratio, pH and flow rate as the critical method parameters (CMPs) from screening studies. Peak area, retention time, theoretical plates and peak tailing were measured as the critical analytical attributes (CAAs). Further, the bioanalytical liquid–liquid extraction process was optimized using an optimal design by selecting extraction time, centrifugation speed and temperature as the CMPs for percentage recovery of nevirapine as the CAA. The search for an optimum chromatographic solution was conducted through numerical desirability function. Validation studies performed as per the US Food and Drug Administration requirements revealed results within the acceptance limit. In a nutshell, the studies successfully demonstrate the utility of analytical QbD approach for the rational development of a bioanalytical method with enhanced chromatographic separation and recovery of nevirapine in rat plasma. Copyright © 2015 John Wiley & Sons, Ltd.     

Computer-Assisted Optimization of pH and Ion Concentration Selectivity in HPLC Using a Mixture Design Simplex Method

Abstract

A computer-assisted mixture design simplex method is presented for optimization of two-factor (pH and ion concentration) simultaneous selectivity for the optimal separation in reversed-phase HPLC. The method is based on two-factor selectivity rectangle concept with a special polynomial estimated from nine preliminary runs. Then connect to general simplex method for optimization. Double criteria simulation system (DCSS) is established for the measurement of chromatographic performance by this method. The validity of the optimization strategy is proved by applying it to an actual mixture and as compared with the general simplex method about thirty eight experiments can be omitted.     

Constrained optimization of a preparative ion-exchange step for antibody purification

Today, the optimization of chromatographic separation is usually based on experimental work and rule of thumb. The process and analytical technology (PAT) initiative, of the US Food and Drug Administration, has provided the opportunity of using model-based approach when designing downstream processing of pharmaceutical substances. A nonlinear chromatography model was used in this study to optimize a preparative ion-exchange separation step involving two components. Separation was simulated with the general rate model employing Langmuir kinetics. Optimization was performed with an indirect method allowing constraints on the purity, thus avoiding sub-optimization, which can lead to noisy objective functions. The six decision variables used in the optimizations were flow rate, loading volume, initial salt concentration in the elution, final salt concentration in the linear elution gradient and the two cut points. A graphical representation of the effect of the decision variables on the objective function was used to verify that the optimization had converged to the true optimum. The optimal operating points, using productivity and yield separately as objective functions, were found and compared with the product of productivity and yield as objective function. The optimum obtained with this objective function had a lower productivity, than the productivity function, but much higher yield, which makes it a good substitute for a cost function.     

POEM: Parameter Optimization using Ensemble Methods: application to target specific scoring functions

In computational biology processes such as docking, binding, and folding are often described by simplified, empirical models. These models are fitted to physical properties of the process by adjustable parameters. An appropriate choice of these parameters is crucial for the quality of the models. Locating the best choices for the parameters is often is a difficult task, depending on the complexity of the model. We describe a new method and program, POEM (Parameter Optimization using Ensemble Methods), for this task. In POEM we combine the DOE (Design Of Experiment) procedure with ensembles of different regression methods. We apply the method to the optimization of target specific scoring functions in molecular docking. The method consists of an iterative procedure that uses alternate evaluation and prediction steps. During each cycle of optimization we fit an approximate function to a defined loss function landscape and improve the quality of this fit from cycle to cycle by constantly augmenting our data set. As test applications we fitted the FlexX and Screenscore scoring functions to the kinase and ATPase protein classes. The results are promising: Starting from random parameters we are able to locate parameter sets which show superior performance compared to the original values. The POEM approach converges quickly and the approximated loss function landscapes are smooth, thus making the approach a suitable method for optimizations on rugged landscapes.     

Application of Multilinear Gradient Elution for Optimization of Separation of Chlorophenols Using Derringer’s Desirability Function

Multilinear gradient elution was applied for the simultaneous optimization of resolution and analysis times of nine chlorophenols separated by HPLC. The first relationship of ln k versus φ was determined using the isocratic retention time for each analyte. For prediction of gradient retention times of analytes, the fundamental equation of gradient elution was numerically solved. Then a grid search program was used to simulate chromatograms under each new condition. Two different chromatographic goals, analysis time and minimum distance between adjacent peaks, were evaluated simultaneously using Derringer’s desirability function for each chromatogram. The sigmoid function was used to transform the optimization criteria to desirability values. Under optimal conditions, a good agreement was observed between predicted and experimental values of the chromatographic response function when analysis time was less than 40 min.     

黄芪中黄酮类组分的高效液相色谱分离条件的快速优化

以黄芪为研究对象,对黄芪中乙酸乙酯部位的化学成分进行了高效液相色谱分析并对其色谱操作条件进行了快速优化。根据几个线性梯度下的保留时间来计算各组分的保留参数,然后利用重叠分辨图法确定其最佳分析条件。在选定的最佳条件下各组分分离情况良好。利用梯度保留时间计算保留参数比较方便快速,并可以有效地避免以往等度线性回归法遇到的峰识别问题。该方法更适用于实际复杂样品色谱分析条件的优化。     

回归正交评价指标智能筛选法用于色谱分离条件的快速优化

建立了一种可用于色谱分离条件快速优化的回归正交评价指标智能筛选法。以串行色谱响应函数作为色谱条件优化指标,利用回归正交试验设计建立回归模型,并通过最优解智能筛选程序对综合性优化指标进行筛选,最终实现色谱分离条件的最优化。结果表明:实验测定值与预测值的平均相对偏差为0.18%,优化结果理想。     

Optimization of a hybrid chromatography-crystallization process for the separation of Tröger's base enantiomers

This paper presents an analysis of a hybrid process consisting of simulated moving bed (SMB) chromatography and crystallization and studies its performance for the separation of the Tr?ger's base enantiomers. The SMB is simulated using a detailed model including column efficiency, thus, implying a proper evaluation of the effect of column size on column efficiency and separation performance. The crystallization operations are accounted for through material balances, assuming equilibrium between enantiopure crystals and mother liquor. A genetic algorithm is used to optimize the combined process, using proper definitions of objective functions. Multi-objective optimization of this hybrid process for productivity and evaporation cost in terms of operating parameters, column length, and SMB feed concentration shows an optimum SMB purity value as a trade off between increased SMB performance and recycle of the mother liquor.     

Predicting and evaluating separation quality of micellar electrokinetic capillary chromatography by artificial neural networks

Computer-aided optimization of micellar electrokinetic capillary chromatography (MEKC) separations was demonstrated by artificial neural networks (ANNs) using a Levenberg-Marquardt algorithm and an orthogonal experimental design. A novel criterion, named Q, for evaluating the separation quality of MEKC was firstly presented, which considered both separation selectivity and analysis time. MEKC separation conditions of seven plant hormones were then simulated and optimized using ANNs based on this novel criterion. The result was further compared to that obtained using ANNs based on a traditionally used criterion of overall normalization resolution (named r). Finally, the separation under optimum conditions predicted by ANNs using the criterion Q was compared to, and proved to be better than that obtained by empirical step-by-step optimization procedures. This method may also be adapted to other separation methods due to its generality.     

Application of the iodine-azide postcolumn reaction in RP-HPLC for the determination of thioguanine in urine

The study focuses on the analysis of a sensitive, selective, and simple postcolumn detection method for thioguanine determination, based on the sensitizing induction of thioguanine on iodine-azide reaction and the combination technique of HPLC. The analysis was accomplished in the optimum conditions for iodine-azide detection system and HPLC separation. The values for the linear range, the LOD, and DOQ amounted to 0.8-1.7, 0.4, and 0.5 nmol/mL urine, respectively.     

小波神经网络-遗传算法用于2-(9-咔唑)乙基氯甲酸酯衍生化氨基酸的胶束电动力学色谱分离优化

将小波神经网络和遗传算法应用到2-(9-咔唑)-乙基氯甲酸酯衍生化氨基酸的胶束电动力学色谱分离优化。小波神经网络结合正交试验设计用于分离过程的多因素模型建立。以训练好的小波神经网络模型为目标函数,采用实数编码的遗传算法搜寻确定最佳分离条件,在此条件下分离得到的归一化分离度积与正交试验设计中最佳条件相比,提高了12．5％。