From 2015 to 2023: How Machine Learning Aids Natural Product Analysis

Abstract In recent years, conventional chemistry techniques have faced significant challenges due to their inherent limitations, struggling to cope with the increasing complexity of and volume of data generated in contemporary research endeavors. Computational methodologies represent robust tools in the field of chemistry, offering the capacity to harness potent machine learning (ML) models to yield insightful analytical outcomes. This review examines the integration of machine learning into natural product chemistry from 2015 to 2023, highlighting its potential to overcome the inherent limitations of traditional chemical techniques. We present a structured approach that matches specific natural product challenges—such as component determination, concentration prediction, and classification—with suitable ML models, including regression, classification, and dimension reduction methods. Our objective is to illustrate how ML pipelines, from data preprocessing to model evaluation, enhance both qualitative and quantitative analyses, providing a comprehensive framework, with the potential catalyze a transformation in the field of natural product analysis.