MACHINE LEARNING CONTRIBUTIONS IN BIOPHARMACEUTICALS

MACHINE LEARNING CONTRIBUTIONS IN BIOPHARMACEUTICALS

Bhavna Venkatakrishnan, Swadha Singh

R.V College of Engineering, B.E Final Year Students

ABSTRACT

Machine learning (ML) has made significant contributions to the biopharmaceutical field, and its applications are increasing in quality, design-based development and manufacturing of biologics, reflecting the huge potential of bioprocess automation.We are still in the early stages in terms of  direct support.This hinders the process from  development to production. However, the accumulation of extensive production data has led to a significant increase in the use of ML-based models instead of traditional multivariate data analysis techniques. This trend is primarily driven by the introduction of advanced process analytical techniques to monitor biopharmaceutical process variables and quality attributes in real-time.To create accurate, flexible, and powerful predictive models that can address analysis, monitoring, and control problems in the biopharmaceutical field, taking into account the complexity and multidimensionality of  bioproduct design, bioprocess development, and product manufacturing data.

 ML-based approaches are increasingly being used. The purpose of this article is to provide a comprehensive overview of  current applications of ML solutions in the design, monitoring, control and optimization of monoclonal antibody upstream, downstream and product formulation processes.Finally, this article details the key challenges associated with the use of the bioprocess itself, process data, and  machine learning models in the development and manufacturing of monoclonal antibody processes.

Keywords

Biopharmaceuticals, Machine learning, Upstream Downstream, Bioprocesses.