🔬 At the Bioprocessing Summit, Richard D. Braatz described a testbed for continuous manufacturing of monoclonal antibodies.
🧪 Optimal analytics are necessary to optimize the system, but it can be challenging to select the right tools.
💡 Braatz and his team tested smart process analytics (SPA) software for manufacturing monoclonal antibodies.
✅ SPA software automatically selects data analytics/machine learning tools based on specific characteristics of the data and process.
🔬 Smart process data analytics software has the potential to be widely applied to biomanufacturing processes.
Introduction:
Richard D. Braatz, a professor at MIT, presented a fully instrumented testbed for the end-to-end integrated and continuous manufacturing of monoclonal antibodies. This system relies on analytics to optimize the process. However, selecting the right analytics package for bioprocessing can be challenging due to the lack of complete understanding and quantification of biological processes. Braatz and his colleagues have explored the use of smart process analytics (SPA) software, which automatically selects data analytics/machine learning tools based on specific characteristics of the data and expert domain knowledge of the process.
- Complete understanding and quantification of biological processes is lacking in bioprocessing.
- Selecting the right analytics package for bioprocessing is complex and requires expertise.
- Smart process analytics (SPA) software can automatically select data analytics/machine learning tools based on specific characteristics of the data and expert domain knowledge of the process.
- The capability of smart process data analytics software enables wide application to biomanufacturing processes.
Conclusion:
The use of smart process analytics (SPA) software shows promise in bioprocessing for the manufacturing of monoclonal antibodies. By automatically selecting data analytics/machine learning tools based on specific characteristics of the data and expert domain knowledge of the process, this software can enhance the optimization of biomanufacturing processes. Further research and development in this area could lead to improved control and efficiency in bioprocessing.
