Abstract
Quality by Design (QbD) guided process development is time & cost effective only if knowledge is transferred from one scale to the other (vertical knowledge transfer) one project to the next (horizontal knowledge transfer). Today knowledge is transferred across scales and molecules when assessing the technical risks. However, this form of knowledge transfer is limited and despite the wide spread of platform processes, to some degree the process needs to be developed de novo for every new drug or vaccine candidate.
Hybrid modeling and transfer learning have the potential to transfer knowledge between scales and processes of different molecules much more effectively. In particular, we propose to use an embedding technology to transfer knowledge and a digital twin as a knowledge transfer vehicle. Used consistently this has the potential to reduce the number of experiments by up to 80%.
Hybrid modeling and transfer learning have the potential to transfer knowledge between scales and processes of different molecules much more effectively. In particular, we propose to use an embedding technology to transfer knowledge and a digital twin as a knowledge transfer vehicle. Used consistently this has the potential to reduce the number of experiments by up to 80%.
| Original language | English |
|---|---|
| Title of host publication | Digitally Driven Biotechnology: 4th DTU Bioengineering symposium |
| Number of pages | 1 |
| Publisher | DTU Bioengineering |
| Publication date | 2023 |
| Pages | 16-16 |
| Publication status | Published - 2023 |
| Event | 4th DTU Bioengineering symposium - Kgs. Lyngby, Denmark Duration: 26 Oct 2023 → 26 Oct 2023 |
Conference
| Conference | 4th DTU Bioengineering symposium |
|---|---|
| Country/Territory | Denmark |
| City | Kgs. Lyngby |
| Period | 26/10/2023 → 26/10/2023 |
