loading page

Smart Process Analytics for the End-to-End Batch Manufacturing of Monoclonal Antibodies
  • +7
  • Richard Braatz,
  • Moo Sun Hong,
  • Fabian Mohr,
  • Chris D. Castro,
  • Benjamin T. Smith,
  • Jacqueline Wolfrum,
  • Stacy Springs,
  • Anthony Sinskey,
  • Roger A. Hart,
  • Tom Mistretta
Richard Braatz
Massachusetts Institute of Technology Department of Chemical Engineering

Corresponding Author:braatz@mit.edu

Author Profile
Moo Sun Hong
Massachusetts Institute of Technology Department of Chemical Engineering
Author Profile
Fabian Mohr
Massachusetts Institute of Technology Department of Chemical Engineering
Author Profile
Chris D. Castro
Amgen Inc San Francisco
Author Profile
Benjamin T. Smith
Amgen Inc San Francisco
Author Profile
Jacqueline Wolfrum
Massachusetts Institute of Technology
Author Profile
Stacy Springs
Massachusetts Institute of Technology
Author Profile
Anthony Sinskey
Massachusetts Institute of Technology
Author Profile
Roger A. Hart
Amgen Inc San Francisco
Author Profile
Tom Mistretta
Amgen Inc San Francisco
Author Profile

Abstract

For many modern biopharmaceutical processes, manufacturers develop data-driven models using data analytics/machine learning (DA/ML) methods. The challenge is how to select the best methods for a specific dataset to construct the most accurate and reliable model. This article describes the application of smart process data analytics software to industrial end-to-end biomanufacturing datasets for monoclonal antibody production to automate the determination of the best DA/ML tools for model construction and process understanding. The application demonstrates that smart process data analytics software captures product- and process-specific characteristics for two different monoclonal antibody productions. This study provides tools that can be widely applied to biomanufacturing processes for root cause analysis, prediction, and control.