Advanced Analytical Techniques integrated with Machine Learning for Proactive Raw material Characterization for Vaccine Production

Over the last several decades, challenges in the development, production, supply, and use of vaccines have been raised and by consequence had led to increasing concern around the world. As a result, an increase in research and innovation in the vaccine industry is needed. In this sense, one of the most critical factors in the vaccine production industry is the raw material and its quality. It is well known, that in order to obtain high yields of the target compounds in vaccines, well-characterized and homogenized raw material is needed. Hence, a raw material characterization, optimization, and control process are critical before raw materials are used in the fermentation that we can refer to as a biological process. The use of advanced analytical techniques such as Raman and Nuclear Magnetic Resonance spectroscopy are suitable alternatives to characterize complex matrix as they offer a deeply detailed composition. Furthermore, this data can be integrated with Machine Learning for better-quality control and automatization of the process. The main aim of this work is to characterize and optimize the raw material used in vaccine production through advanced analytical techniques and integrating it with Machine Learning to improve vaccine production and decrease the cost.

Faculty Supervisor:

Satinder Kaur Brar

Student:

Partner:

Sanofi

Discipline:

Life Sciences

Sector:

Health and Related Sciences & Technology; Pharmaceuticals; Biotechnology

University:

York University

Program: