GSK, Siemens and Atos built a hybrid mechanistic and AI digital twin for vaccine adjuvant manufacturing.

Vaccine development ran in siloed digital environments with few connections. The partners created a closed-loop digital twin that combines mechanical models, CFD and machine learning to predict adjuvant particle formation as parameters change. The page states real-time prediction capability and faster timelines but gives no figures.

Siemens is an industrial technology group whose Opcenter MES, automation and digital twin software are used across pharma production and process development

This sits in the Build stage of the AI use-case lifecycle: Named examples from the foundation-model labs and platforms pharma teams use to actually construct, train and generate the model or application.