Biochemical process optimization via statistical methods: A mini review

Abstract

Biochemical process optimization is now a crucial topic for research and development. Statistical approaches are currently being used by researchers to more effectively optimize the process, reduce waste and unpredictability, improve product quality, and increase process effectiveness. Current advancements in this field include the use of machine learning techniques and the Design of Experiments (DoE). The significance of statistical approaches as useful instruments for process optimization in biochemical research is highlighted in this work. The Taguchi Method, Response Surface Methodology (RSM), and Artificial Neural Networks (ANN) combined with Genetic Algorithm (GA) are three popular approaches that are focused for further comparison. The study presents an overview of each technique, investigates how it might be applied to optimization, examines its benefits and drawbacks, and identifies its main distinctions.