Bioprocess digital twins are an exciting new technology that changes the way we do bioprocess development, process validation, and cGMP operations.
In 2016, Colin Harris, VP of Software Research at GE presented a tool for industrial processes that was positively fascinating — science fiction turned into reality. Colin Harris interacted with a voice-activated software to remotely mitigate damages to a wind turbine on the other side of the world. He addressed the software as “Twin” and the two calmly saved millions of dollars within seconds. This is the future, right?
Yes! Digitalization. Artificial intelligence. Data Analytics. There is a new tech wave in the process industry. Digital twins are becoming a reality in many industries. Bioprocessing is no exception.
In this article, we delve into the “Bioprocess Digital Twin” technology for bioprocessing and explore how it is changing the way we do bioprocess development, process validation, and GMP manufacturing.
What is a Bioprocess Digital Twin?
It is only a slight exaggeration to say the digital twin is a full process-assistant who has access to all historical data, present process conditions, and can simulate the future based on all effective models.
Effectively, the bioprocess digital twin is a comprehensive, integrated mathematical model of the complete process chain. It runs in real-time, incorporates development and real-time data. It feeds on PAT data, quality data, and time-series data. Digital twins make use of merged ODE, PDE and bayesian statistical models. And they can predict critical quality attributes and key performance indicators.
With this new modeling power at hand, how do leading biotech companies apply bioprocess digital twins?
Where do leading biotech’s apply bioprocess digital twins?
We generally don’t speak with digital twins to solve our bioprocessing tasks yet, as Dr. Harris did. But I don’t think that is the most important aspect. What is important is how the bioprocess digital twin helps us reduce costs and increase process robustness. Read below on how digital twins reduce process development costs, costs in process validation, and prevent expensive re-processing in manufacturing:
Digital twins cut costs in bioprocess development
For many years, biotech manufacturers have been building platform bioprocesses. Now, leading biotech companies leverage bioprocess platforms with digital twins. Digital twins organize bioprocess development, suggest experimental designs, and manages new knowledge. This drastically cuts process development costs. They can do this by combining previous platform knowledge to predict future process results. And now that the concept is growing roots, it can be used in nearly any process development.
Digital twins reduce effort in bioprocess validation
Bioprocess validation is an essential step for the commercialization of any pharmaceutical drug. And interestingly, process validation was one of the first reported applications of digital twins. Digital twins can save manufacturers millions in expenditures in a number of aspects ranging from reducing the number of required PPQ runs to setting a robust control strategy.
- In process characterization studies, biopharma companies set acceptance criteria and normal operating ranges using digital twins, well-aligned with the FDA’s Quality by Design Initiative.
- During process performance qualification (PPQ), biopharma companies calculate the necessary number of PPQ batches for validation, leveraging digital twin models to justify reduced PPQ run numbers.
- Over the course of continued process verification (CVP), biopharma companies leverage digital twins to set alert limits, predict changes, and react to trends.
For more information on leading biopharma use of digital twins in process validation, see the following article by Boehringer Ingelheim, Versatis and Exputec.
Digital twins reduce out of spec events and supports problem solving in cGMP manufacturing
Digital twins represent a universal tool for the full lifecycle of a bioprocess. They are born out of platform processes. They mature within process development and process validation. Finally, they arrive in GMP manufacturing where they unfold their full potential:
- Better specs, less out of spec events (OOS): the simulations will predict Bulk Substrate and Finished Product specification variation better than individual unit operation models. With these simulations, precise specifications and control limits can be estimated not only for the intermediates, but for the end results. This will result in less deviations and OOSs.
- Seamlessly predicts the future based on past data and present simulations: The historical data, the present data, and the models combine together within the simulation to give the most precise prediction possible, given the complexity of bioprocesses.
- Continuously improves itself: Machine learning algorithms can be easily incorporated to take in new production data and improve the models, thus allowing for increasingly precise models over time.
- Faster problem solving: atypical outcomes can be traced back through the simulations to investigate potential special cause variation, whether univariate or multivariate.
What do you need to build and run a digital twin?
Bioprocess digital twins leverage data from process development, design of experiments and manufacturing, therefore a scalable, asset-centric data foundation for both manufacturing and development data is critical. To build digital bioprocess twins, you need asset connectivity, statistical analytics, and mechanistic modelling in one environment. To that end, we have created inCyght software, the first bioprocess IoT software platform. inCyght software organizes bioprocess data and analytics workflows and is the ideal environment capable of executing bioprocess digital twins.
Interested? Just talk to one of our bioprocess data scientists today. We can walk through the different data sources and support you in the creation of your bioprocess digital twins.