Integrating metabolome dynamics and process data to guide cell line selection in biopharmaceutical process development.

Abstract in brief

• This study focuses on improving the selection process of mammalian cell lines for producing therapeutic antibodies by integrating metabolomics data with process information using machine learning, which helps predict cell line performance early in development.
• By analyzing how metabolic profiles change over time during cultivation, the approach can accurately forecast product yield (titer) and identify key biomarkers associated with high-performing cell lines, speeding up research and development.
• Ultimately, the integration of biological and process data provides deeper insights into cell physiology, enabling more efficient cell line selection and supporting the development of more stable and productive biopharmaceutical manufacturing processes.]