Artificial neural networks for quantification in unresolved capillary electrophoresis peaks

The application of the combination of experimental design (ED) and artificial neural networks (ANNs) for the quantification of overlapped peaks in capillary zone electrophoresis is described. When the total separation cannot be achieved by separation techniques, the use of ED-ANN can be a suitable approach. The unstability of EOF causes peak shift that has to be corrected in order to apply ED-ANN methods. In this work, normalization procedure of electropherograms with consequent application of ANNs for quantification purpose was developed. Both, spectra and electropherograms can be used as multivariate data. In general, both kinds of data were found to be suitable for unresolved peaks quantification by ED-ANN approach.     

Quantitative determination of paraffin oil in blood by capillary gas chromatography

A capillary gas chromatographic method is described for the quantitative determination of liquid paraffin in blood. Paraffin is extracted from blood into n-heptane. After solvent evaporation and dissolution of the residue in 100–200 μl n-heptane one μl is injected into a gas chromatograph fitted with a fused silica capillary column (Permabond® OV-1-CB-0.1, 10 m × 0.32 mm i.d.) and flame ionization detector. Analysis is performed by using an oven program [50°C (3 min)?285°C (5 min), rise 10%min]. The sensitivity (1.5 ng hexadecane) and the reproducibility prove the applicability of the method for the determination of liquid paraffin in blood and for the study of the stability of the liquid paraffin hollow fiber membranes used in an extracorporeal liver support system.     

Madaline网络用于分光光度法同时测定铜钴镍的研究

采用4－（2－吡啶偶氮）－间苯二酚（PAR）－Cu,Co,Ni显色体系，应用Madline神经网络原理，对于吸收光谱严重重叠的三组分金属配合物体系同时进行含量测定，Cu^2 ,Co^2 ,Ni^2 的平均回收率分别为94％，101％，102％，实验表明，该法具有训练速度快，预测结果准确度良好等特点，有望成为多组分分析的有效方法之一。     

用人工神经网络预测催化精馏塔开工过程的研究

催化精馏是使化学反应过程和精馏分离过程结合在一起,是伴有化学反应的新型特殊精馏过程.“反应精馏”概念自20年代提出以来,从30年代到60年代初,研究都是对特定体系的工艺探索;70年代后,研究扩展到非均相催化反应体系,出现了非均相催化精馏过程,成为了反应精馏的一个重要分支;     

Recent developments on creation of artificial metalloenzymes

Organic synthesis using biocatalysts has been developed over many years and is still a prominent area of research. In this context, various hybrid biocatalysts composed of a synthetic metal complex catalyst and a protein scaffold (i.e. “artificial metalloenzymes”) have been constructed. One of the most recent research areas in biocatalysts-mediated synthesis is CC bond/cleavage, the most important type of reaction in organic chemistry. Some of the artificial enzymes were applied to in-cell reactions as well as in vitro systems. The effects of the structural fluctuation in biomacromolecules on their functions have also been realized. This review article includes recent research examples of artificial metalloenzymes used to CC bond formation/cleavage. As a perspective, we also focus on how we apply protein dynamics factor for the creation of new generation artificial metalloenzymes.     

Unraveling the mystery of efficacy in Chinese medicine formula: New approaches and technologies for research on pharmacodynamic substances

Traditional Chinese medicine (TCM) is the key to unlock treasures of Chinese civilization. TCM and its compound play a beneficial role in medical activities to cure diseases, especially in major public health events such as novel coronavirus epidemics across the globe. The chemical composition in Chinese medicine formula is complex and diverse, but their effective substances resemble “mystery boxes”. Revealing their active ingredients and their mechanisms of action has become focal point and difficulty of research for herbalists. Although the existing research methods are numerous and constantly updated iteratively, there is remain a lack of prospective reviews. Hence, this paper provides a comprehensive account of existing new approaches and technologies based on previous studies with an in vitro to in vivo perspective. In addition, the bottlenecks of studies on Chinese medicine formula effective substances are also revealed. Especially, we look ahead to new perspectives, technologies and applications for its future development. This work reviews based on new perspectives to open horizons for the future research. Consequently, herbal compounding pharmaceutical substances study should carry on the essence of TCM while pursuing innovations in the field.     

Modeling of the relationship between electroosmotic flow and separation parameters in capillary zone electrophoresis using artificial neural networks and experimental design

The prediction of migration time of electroosmotic flow (EOF) marker was achieved by applying artificial neural networks (ANN) model based on principal component analysis (PCA) and standard normal distribution simulation to the input variables. The voltage of performance, the temperature in the capillary, the pH and the ionic strength of background electrolytes (BGE) were applied as the input variables to ANN. The range of the performance voltage studied was from 15 to 27 kV, and that of the temperature in the capillary was from 20 to 30 °C. For the pH values studied, the range was from 5.15 to 8.04. The range of the ionic strength investigated in this paper was from 0.040 to 0.097. The prediction abilities of ANN with different pre-processing procedure to the input variables were compared. Under the same performance conditions, the average prediction error of the migration time of the EOF marker was 5.46% with RSD = 1.76% according to 10 parallel runs of the optimized ANN structure by the proposed approach, and that of the 10 parallel predictions of the optimal ANN structure for the different performance conditions was 12.95% with RSD = 2.29% according to the proposed approach. The study showed that the proposed method could give better predicted results than other approaches discussed.     

Optimization of the Microwave-Assisted Saponification and Extraction of Organic Pollutants from Marine Biota Using Experimental Design and Artificial Neural Networks

Several improvements in sample pretreatment for the determination of organic pollutants (i.e. n-alkanes, polycyclic aromatic hydrocarbons, PAHs) in marine biota (mussels) are presented. The use of liquid nitrogen and homogenization of the samples are shown to be an alternative to the time consuming liophilization step required for the analysis of biota samples. Microwave-assisted hydrolysis and extraction are combined to isolate organic pollutants (19 n-alkanes and 27 PAHs) from biota matrices. Experimental design (ED) and artificial neural networks (ANNs) were used to optimize the experimental conditions. NIST-CRM 2978 was used to test the validity of the developed method which shows a good agreement with certified values.     

Application of an artificial neural network (ANN) and piezoelectric chemical sensor array for identification of volatile organic compounds

A piezoelectric chemical sensor array was developed using four quartz crystals. Gas chromatographic stationary phases were used as sensing materials and the array was connected to an artificial neural network (ANN). The application of the ANN method proved to be particularly advantageous if the measured property (mass, concentration, etc.) should not be connected exactly to the signal of the transducers of the piezoelectric sensor. The optimum structure of neural network was determined by a trial and error method. Different structures were tried with several neurons in the hidden layer and the total error was calculated. The optimum values of primary weight factors, learning rate (η=0.15), momentum term (μ=0.9), and the sigmoid parameter (β=1) were determined. Finally, three hidden neurons and 900 training cycles were applied. After the teaching process the network was used for identification of taught analytes (acetone, benzene, chloroform, pentane). Mixtures of organic compounds were also analysed and the ANN method proved to be a reliable way of differentiating the sensing materials and identifying the volatile compounds.