Bringing Scalability to Metabolic Flux Analysis using Machine Learning to Accelerate LC-MS Interpretation

Metabolic Flux Analysis (MFA) is a powerful technique used to characterize metabolic phenotype driving to improved productivity in biomanufacturing. MFA is most powerful when absolute concentrations of the metabolic intermediates are measured, but doing so in practice is often impractical due to inherent limitations of conventional absolute quantitation by mass spectral analysis. Recently, advances in artificial intelligence (AI) have been applied to solving the problem of broad, untargeted, absolute quantitation in liquid chromatography-mass spectrometry (LC-MS). These new approaches extend readily to the determination of absolute concentrations of stable isotopically-labeled metabolic intermediates, offering a new tool for MFA. Dr Sam Yenne from Metalytics Inc., a company that specializes in the science of metabolic flux, has recently assessed and adopted Pyxis, a new tool for absolute quantitation of raw LC-MS data. Dr Yenne describes MFA, its utility in biopharmaceutical development, associated challenges and how Pyxis impacts those challenges.