Application of Stable Isotopes with Machine Learning Techniques for Identifying Aconiti Lateralis Radix Praeparata (Fuzi) Geographical Origins

Performance evaluation of E-nose and E-tongue combined with machine learning for qualitative and quantitative assessment of bear bile powder

Bear bile powder (BBP) is a valuable animal-derived product with a huge adulteration problem on market. It is a crucially important task to identify BBP and its counterfeit. Electronic sensory technologies are the inheritance and development of traditional empirical identification. Considering that each drug has its own specific odor and taste characteristics, electronic tongue (E-tongue), electronic nose (E-nose) and GC-MS were used to evaluate the aroma and taste of BBP and its common counterfeit. Two active components of BBP, namely tauroursodeoxycholic acid (TUDCA) and taurochenodeoxycholic acid (TCDCA) were measured and linked with the electronic sensory data. The results showed that bitterness was the main flavor of TUDCA in BBP, saltiness and umami were the main flavor of TCDCA. The volatiles detected by E-nose and GC-MS were mainly aldehydes, ketones, alcohols, hydrocarbons, carboxylic acids, heterocyclic, lipids, and amines, mainly earthy, musty, coffee, bitter almond, burnt, pungent odor descriptions. Four different machine learning algorithms (backpropagation neural network, support vector machine, K-nearest neighbor, and random forest) were used to identify BBP and its counterfeit, and the regression performance of these four algorithms was also evaluated. For qualitative identification, the algorithm of random forest has shown the best performance, with 100% accuracy, precision, recall and F1-score. Also, the random forest algorithm has the best R² and the lowest RMSE in terms of quantitative prediction.

Multidimensional isotope analysis of carbon, hydrogen, and oxygen as a tool for traceability of lactose in drug products

Lactose is one of the most commonly used pharmaceutical excipients. Depending on manufactures, the properties of lactose are very different, which could impact the pharmacokinetic behavior of drug products. Therefore, it is very important to trace the origin of pharmaceutical lactose in drug products which is valuable for prescription analysis. In this study, the carbon, hydrogen and oxygen isotope ratios (δ¹³C, δ²H and δ¹⁸O) of thirty-four lactose from seven manufacturers were analyzed by elemental analysis-stable isotope ratio mass spectrometry (EA-IRMS). One-way analysis of variance (ANOVA) and Duncan's test indicated significant differences in isotope ratios of lactose from different origins. To identify the lactose manufacturer, a discrimination model was generated through linear discriminant analysis (LDA). Based on this model, the manufacturers of lactose used in three drug products were successfully identified. Our results suggested that the multidimensional analysis of δ¹³C, δ²H and δ¹⁸O of lactose provided a fast and effective method to trace the lactose manufacturer. In conclusion, this method can be used to analyze the prescription of the drug product quickly, which could speed up the development of generic drug product.

Rapid discrimination of the authenticity and geographical origin of bear bile powder using stable isotope ratio and elemental analysis

Bear bile powder (BBP) is one of the most famous traditional Chinese medicines derived from animals. It has a long history of medicinal use and is widely used in the treatment of hepatobiliary and ophthalmic diseases. Due to its similar morphological characterizations and chemical composition compared with other bile powders, it is difficult to accurately identify its authenticity. In addition, there are very few methods that could analyze the geographical origins of BBP. In this study, elemental analysis isotope ratio mass spectrometry (EA-IRMS) and inductively coupled plasma mass spectrometry (ICP-MS) were used to determine stable isotope ratios and elemental contents, respectively. Combined these variables with chemometrics, the discrimination models were established successfully for identifying the authenticity and geographical origins of BBP. Meanwhile, the discrimination markers were identified by calculating the variable importance for the projection (VIP) value of each variable. A total of 13 discrimination markers (δ¹³C, δ¹⁵N, C, Li, Mg, K, Ca, Cr, Ni, Zn, As, Se, and Sr) were used to further establish the fingerprint of BBP. According to similarity analysis, the authenticity and geographical origins of BBP could be identified without chemometrics. In conclusion, the present study established a reliable method for authenticity identification and origin traceability of BBP, which will provide references for the quality control of bile medicines.