How Machine Learning and Gas Chromatography-Ion Mobility Spectrometry Form an Optimal Team for Benchtop Volatilomics

Abstract

This invited feature article discusses the potential of gas chromatography-ion mobility spectrometry (GC-IMS) as a point-of-need alternative for volatilomics. Furthermore, the capabilities and versatility of machine learning (ML) (chemometric) techniques used in the framework of GC-IMS analysis are also discussed. Modern ML techniques allow for addressing advanced GC-IMS challenges to meet the demands of modern chromatographic research. We will demonstrate workflows based on available tools that can be used with a clear focus on open-source packages to ensure that every researcher can follow our feature article. In addition, we will provide insights and perspectives on the typical issues of the GC-IMS along with a discussion of the process necessary to obtain more reliable qualitative and quantitative analytical results.