ABSTRACT
In this study, rapid evaporative ionization mass spectrometry(REIMS) fingerprints of 388 samples of roots of Pulsatilla chinensis(PC) and its common counterfeits, roots of P. cernua and roots of Anemone tomentosa were analyzed based on REIMS combined with machine learning. The samples were determined by REIMS through dry burning, and the REIMS data underwent cluster analysis, similarity analysis(SA), and principal component analysis(PCA). After dimensionality reduction by PCA, the data were analyzed by similarity analysis and self-organizating map(SOM), followed by modeling. The results indicated that the REIMS fingerprints of the samples showed the characteristics of variety differences and the SOM model could accurately distinguish PC, P. cernua, and A. tomentosa. REIMS combined with machine learning algorithm has a broad application prospect in the field of traditional Chinese medicine.
Subject(s)
Medicine, Chinese Traditional , Algorithms , Anemone , Machine LearningABSTRACT
A method of thin-layer fingerprinting chromatogram of artificial cow-bezoar was established with the developing solvent consisting of cyclohexane, ethyl acetate, acetic acid and methanol (2∶7∶1∶2), and 10% sulfuric acid ethanol solution sprayed as colour-developing agent. After heated at 105 ℃, TLC was recorded as an image in ultraviolet light at 366 nm which was converted into grayscale. By the gray value extracted from the grayscale, the multivariate data obtained from TLC of samples could be analyzed by chemometric method. The results indicated that samples from different manufacturers could be distinguished by this method and some specific bands were found out. All in one, this simple and practical method was suitable for the evaluation of quality difference.