The AI foundation model supports biomolecular co-folding studies to improve structural reasoning in drug discovery research.
Aureka, a biotech company headquartered in the US and China, has launched the Open Drug Discovery Engine (OpenDDE), an open-source foundation model developed specifically for biomolecular co-folding studies in drug discovery research. The model is designed to serve as the structural reasoning core for next-generation drug discovery systems, modelling interactions across proteins, nucleic acid, small molecule ligands, and other biomolecular compounds, thereby supporting AI-assisted drug discovery.
Unlike many AI models used for drug discovery, which are proprietary, OpenDDE is an open-source model. The company describes it as an all-atom platform that simulates every atom in a biological system rather than relying on simplified molecular representations.
This current version supports structural prediction, antibody-antigen interaction modelling and drug discovery studies. The company also aims to develop the platform and adding features like de novo molecular design, binding affinity prediction, ensemble modelling of conformations, structure-conditioned optimisation and experimental feedback loops.
According to Aureka, OpenDDE is part of a broader AI-native drug discovery platform that combines foundation models, compute infrastructure, molecular design, high-throughput functional validation, closed-loop optimisation, and asset data room generation.
Will Hua, Head of AI Research at Aureka, said, “The release of the co-folding module is a ‘first small step’ for Aureka as it works towards ‘a real drug discovery engine,’ at a time when biomolecular foundation models are ‘entering the scaling era.’”
The company is also integrating the model with a high-throughput automated wet-lab platform to build a dry-wet closed-loop drug discovery system.
Hua added, “OpenDDE is not a complete drug discovery engine yet. It has flaws, but it forms a foundation layer. By connecting biomolecular modelling with physical wet lab validation, we hope to make therapeutic discovery more scalable, reproducible, and accessible.”
