UHPLC-UV-Q-Orbitrap HRMS combined with machine learning algorithms reveals the chemical markers of Euodiae Fructus among closely related cultivars

Abstract

Euodiae Fructus (EF, the fruit of Tetradium ruticarpum) belongs to the family Rutaceae which has a complex genetic background, making classification a challenge. In order to classify the three closely related cultivars (small flower EF, medium flower EF, and big flower EF) and simplify the identification procedure in the future, an approach integrating ultra-high performance liquid chromatography-ultraviolet spectrum-hybrid quadrupole-Orbitrap high resolution mass spectrometry (UHPLC-UV-Q-Orbitrap HRMS) with machine learning algorithms was developed. Orthogonal partial least squares-discriminant analysis (OPLS-DA) and random forest (RF) were used to assort the processed EF products and select the chemical markers to differentiate among the three EF cultivars, respectively. Then the thresholds of classification were determined using the eXtreme Gradient Boosting (XGboost) model based on the quantitative data of chemical markers by the UHPLC-Q-Orbitrap HRMS. The results demonstrated that the approach successfully discriminated among three closely related cultivars of EF, and five chemical markers (neochlorogenic acid, (+)-catechin, chlorogenic acid, dehydroevodiamine, and limonin) were selected. Thresholds were obtained to classify the three cultivars. If the content of neochlorogenic acid was greater than 7.52 mg/g, the sample belonged to small flower EF, otherwise, it belonged to medium flower EF or big flower EF. Furthermore, if the content of dehydroevodiamine was greater than 3.84 mg/g, the sample was medium flower EF, otherwise, it was big flower EF. In general, this research provides a novel strategy for the discrimination of Euodiae Fructus cultivars to avoid misapplication and possible side effects.