Novel application of neural network modelling for multicomponent herbal medicine optimization

The conventional method for effective or toxic chemical substance identification of multicomponent herbal medicine is based on single component separation, which is time-consuming, labor intensive, inefficient, and neglects the interaction and integrity among the components; therefore, it is necessary to find an alternative routine to evaluate the components more efficiently and scientifically. In this study, sodium aescinate injection (SAI), obtained from different manufacturers and prepared as “components knockout” samples, was chosen as the case study. The chemical fingerprints of SAI were obtained by high-performance liquid chromatography to provide the chemical information. The effectiveness and irritation of each sample were evaluated using anti-inflammatory and irritation tests, and then “Gray correlation” analysis (GCA) was applied to rank the effectiveness and irritability of each component to provide a preliminary judgment for product optimization. The prediction model of the proportions of the expected components was constructed using the artificial neural network. The results of the GCA showed that the irritation sorting of each SAI component was in the order of B > A > G > J > I > H > D > F > E > C and the effectiveness sorting of SAI components was in the order of D > C > B > A > F > E > H > I > G > J; the predictive proportion of SAI was optimized by the BP neural network as A: B: C: D: E: F = 0.7526: 0.5005: 5.4565: 1.4149: 0.8113: 1.0642. This study provided a scientific, accurate, reliable, and efficient approach for the proportion optimization of multicomponent drugs, which has a good prospect of popularization and application in product upgrading and development of herbal medicine.

[1]  Amin Alibakshi,et al.  Strategies to develop robust neural network models: Prediction of flash point as a case study. , 2018, Analytica chimica acta.

[2]  Guoqiu Wen,et al.  An approach to fuzzy soft sets in decision making based on grey relational analysis and Dempster-Shafer theory of evidence: An application in medical diagnosis , 2015, Artif. Intell. Medicine.

[3]  Satoshi Ogawa,et al.  Antioxidant activities and structural characterization of flavonol O-glycosides from seeds of Japanese horse chestnut (Aesculus turbinata BLUME). , 2017, Food chemistry.

[4]  Jun Li,et al.  Evaluation of in Vivo Antioxidant and Immunity Enhancing Activities of Sodium Aescinate Injection Liquid , 2012, Molecules.

[5]  Agnieszka Leśniak,et al.  Prediction of site overhead costs with the use of artificial neural network based model , 2018, Archives of Civil and Mechanical Engineering.

[6]  Antaryami Mishra,et al.  Application of Artificial Neural Network modeling for optimization and prediction of essential oil yield in turmeric (Curcuma longa L.) , 2018, Comput. Electron. Agric..

[7]  E. Akkol,et al.  Beneficial effects of Aesculus hippocastanum L. seed extract on the body's own antioxidant defense system on subacute administration. , 2010, Journal of ethnopharmacology.

[8]  Shen-Jiang Hu,et al.  Dual effects of sodium aescinate on vascular tension in rat thoracic aorta. , 2010, Microvascular research.

[9]  Liying Sha,et al.  The Efficacy of Sodium Aescinate on Cutaneous Wound Healing in Diabetic Rats , 2015, Inflammation.

[10]  Dongsheng Guo,et al.  Common nature of learning between BP-type and Hopfield-type neural networks , 2015, Neurocomputing.

[11]  Yanjuan Huang,et al.  Anti-inflammatory effect of external use of escin on cutaneous inflammation: possible involvement of glucocorticoids receptor. , 2018, Chinese journal of natural medicines.

[12]  Satoshi Ogawa,et al.  Anti-obesity effects of highly polymeric proanthocyanidins from seed shells of Japanese horse chestnut (Aesculus turbinata Blume) , 2011 .

[13]  C. China Pharmacopoeia,et al.  Pharmacopoeia of the People's Republic of China , 2010 .

[14]  Franco Allegrini,et al.  Sensitivity, Prediction Uncertainty, and Detection Limit for Artificial Neural Network Calibrations. , 2016, Analytical chemistry.

[15]  Jianhui Xie,et al.  Anti-inflammatory activity of coptisine free base in mice through inhibition of NF-κB and MAPK signaling pathways. , 2017, European journal of pharmacology.

[16]  Jerzy Bieniek,et al.  Estimation of operational parameters of the counter-rotating wind turbine with artificial neural networks , 2017 .

[17]  Li Wu,et al.  Investigation on relationships between chemical spectrum and bioeffect of prepared rhubarb decoction in rats by UPLC-ESI-Q-TOF-MS method coupled with gray correlation analysis , 2017 .

[18]  W. Kong,et al.  A novel "target constituent knock-out" strategy coupled with TLC, UPLC-ELSD and microcalorimetry for preliminary screening of antibacterial constituents in Calculus bovis. , 2011, Journal of chromatography. B, Analytical technologies in the biomedical and life sciences.

[19]  Shuang-li Zheng,et al.  Effects of aescin on cytochrome P450 enzymes in rats. , 2014, Journal of ethnopharmacology.

[20]  Yaping Zhao,et al.  Aescin nanoparticles prepared using SEDS: Composition stability and dissolution enhancement , 2017 .

[21]  Lin Ye,et al.  Artificial neural network based mechanical and electrical property prediction of engineered cementitious composites , 2018, Construction and Building Materials.

[22]  Hua Chen,et al.  Fractional-order gradient descent learning of BP neural networks with Caputo derivative , 2017, Neural Networks.

[23]  Xue-song Liu,et al.  Investigation of an on-line detection method combining near infrared spectroscopy with local partial least squares regression for the elution process of sodium aescinate. , 2013, Spectrochimica acta. Part A, Molecular and biomolecular spectroscopy.

[24]  C. Sirtori.  Aescin: pharmacology, pharmacokinetics and therapeutic profile. , 2001, Pharmacological research.