Over the past 15 years, the pharmaceutical industry has undergone much transformation. Drug targets (i.e., proteins associated with a particular disease process) have grown more challenging and the molecules required to hit those targets have become more complex. The industry is under tremendous pressure to reduce costs and increase the speed at which it develops and manufactures these products, while concurrently improving manufacturing robustness.
The quality by design (QbD) paradigm was introduced by the U.S. Food & Drug Administration (FDA) in 2004 and is now codified as a series of industry guidance documents. QbD provides a framework for a manufacturer to evaluate risks in process robustness.
Within the past two decades, advances in computational power have supported great leaps in data management, statistical analysis, machine learning, and data visualization. This progress has given chemical engineers the tools to use data science to accelerate innovation and discovery.
In the November AIChE Journal Perspective article, “Bayesian Probabilistic Modeling in Pharmaceutical Process Development,” Jean Tom, Jose Tabora, and Federico Lora Gonzalez (Bristol-Myers Squibb) discuss how Bayesian statistics can be used in the pharmaceutical...
Would you like to reuse content from CEP Magazine? It’s easy to request permission to reuse content. Simply click here to connect instantly to licensing services, where you can choose from a list of options regarding how you would like to reuse the desired content and complete the transaction.