Robust Multiclass Feature Selection for the Authentication of Honey Botanical Origin via Nontargeted LC-MS Analysis

Honey is one of the most frequently frauded foods due to the high market price of certain kinds of monofloral honey. Traditional authentication methods involving pollen or targeted analysis have limitations that can be manipulated by fraudsters. Nontargeted analysis of honey via liquid chromatography-mass spectrometry (LC-MS) can provide data on thousands of chemical features. However, most studies that train machine learning models for food authentication have sample sizes in the tens or hundreds, which introduces the problem of overfitting when working with such a large feature-to-sample ratio. Herein, a recursive feature elimination (RFE) pipeline was developed specifically to address the challenges of optimizing the honey chemical fingerprint for multiclass machine learning classifiers on a limited number of samples with imperfect labels. A support vector machine was used for both RFE and classification to reduce the 2028 nontargeted features down to just 54 features (a 97.3% reduction) without any loss of classification performance. The resulting model was a 6-class classifier, capable of identifying monofloral blueberry, buckwheat, clover, goldenrod, linden, or other honey with a nested cross-validation Matthews correlation coefficient (MCC) of 0.803 ± 0.046. The development of a <i>k</i>-nearest neighbors filter and the decision to continue the RFE process beyond the iteration with the highest classification score were instrumental in achieving this outcome. This work shows a complete pipeline that automates feature selection from nontargeted LC-MS spectra when working with a limited number of samples and imperfect labels. This process can also be expanded to other food groups and spectral data.