The Application of Untargeted Metabolomics Using UHPLC-HRMS and Chemometrics for Authentication of Horse Milk Adulterated with Cow Milk

Horse milk (HM) is one of the high-quality milks which is highly potential to be adulterated with lower price milk such as cow milk (CM) to get economic profit. This study aimed to develop an analytical method based on an untargeted metabolomics approach using ultrahigh-performance liquid chromatography-high-resolution mass spectrometry (UHPLC-HRMS) for HM authentication. The untargeted metabolomics results showed that HM and CM consist of different metabolite composition. Combined with chemometrics of principal component analysis (PCA), the developed method could distinguish pure HM, pure CM, and adulterated HM. Classification analysis using orthogonal projections to latent structure-discriminant analysis (OPLS-DA) successfully discriminated pure HM and adulterated HM in two separate classes without misclassification with a good of fitness (R2X = 0.771; R2Y = 0.999) and good predictivity (Q2 = 0.990). Metabolite’s analysis found that ceramide (d18:1/24:1(15Z)), N-hexacosanoylglycine, and DG(16:1(9Z)/18:3(9Z, 12Z, 15Z)/0:0) could be used as a potential marker of HM. In contrast, metabolites of 1-O-(1Z-tetradecenyl)-2-(9Z-octadecenoyl)-sn-glycerol and 1,3-dihydroxy-2-propanyl (11Z,14Z)-11,14-icosadienoate were found to be potential markers of CM. Analysis using partial least square (PLS) and orthogonal PLS (OPLS) successfully predict the adulterant concentration (CM) in HM with high accuracy (R2 > 0.990). Good precision was obtained as demonstrated by the low value of root mean square error of estimation (RMSEE) and root mean square error of cross-validation (RMSECV) in both models. It can be concluded that untargeted metabolomics using UHPLC-HRMS in combination with chemometrics could be used as a powerful analytical method for horse milk authentication.