AISB Network Expands Federated OpenFold3 Initiative with Three New Pharma Contributors

BERLIN, Germany, October 1, 2025 - Apheris GmbH announced today the expansion of the Federated OpenFold3 Initiative from the AI Structural Biology (AISB) Network. Astex Pharmaceuticals, Bristol Myers Squibb, and Takeda are joining founding members AbbVie and Johnson & Johnson to fine-tune OpenFold3 on proprietary structural data from multiple pharmaceutical companies, in collaboration with Mohammed AlQuraishi’s Lab at Columbia University.

Participating parties of the Federated OpenFold3 Initiative bring together structurally-derived data at a scale not previously achieved, enabling OpenFold3 to be fine-tuned on uniquely rich proprietary datasets while preserving confidentiality and protecting intellectual property. Each partner is contributing data from several thousand experimentally determined protein–small molecule structures, creating one of the most diverse datasets assembled for model training in drug discovery.

The project is powered by Apheris’ federated computing platform, which enables collaboration without moving or exposing sensitive data. By pooling these datasets, the initiative aims to improve OpenFold3’s accuracy in predicting protein–ligand interactions — a critical step in small molecule drug discovery. OpenFold3 is being developed by the the AlQuraishi Lab at Columbia University, which is collaborating directly in this initiative.

“At Astex we see structural biology and computation as inseparable in modern drug discovery,” said Paul Mortenson, Senior Director, Computational Chemistry and Informatics, Astex. “By contributing data from our small molecule–protein structures to a federated effort, we can help ensure models like OpenFold3 better reflect the challenges medicinal chemists face every day, while keeping proprietary science protected.”

“At Bristol Myers Squibb, our AI and machine learning strategy is deeply embedded in our R&D framework, guiding everything from target prioritization to predictive molecule design and patient segmentation. Through this federated learning initiative, we’re bringing together diverse structural datasets from multiple pharmaceutical companies to advance predictive models for small molecule discovery in ways no single organization could achieve alone," said Payal Sheth, Vice President, Discovery Biotherapeutics & Lead Discovery and Optimization, Bristol Myers Squibb. "These efforts strengthen our ability to accelerate the development of transformational therapies for patients.”

“The Federated OpenFold3 Initiative is a powerful example of how pharmaceutical companies can come together to develop AI tools that improve the development of novel therapies for patients,” said Hans Bitter, Head of Computational Science and Data Strategy at Takeda. “We are excited to be joining the AI Structural Biology (AISB) Network and providing additional data to support the refinement of OpenFold3. This promising prediction tool, focused on identifying and predicting binding affinities of small molecule-protein and antibody-antigen interactions, could be transformative in how we discover and develop small molecule therapeutics.”

“In drug discovery, no single company has enough data to solve the hardest problems alone,” said Robin Röhm, Co-founder and CEO of Apheris. “Federated learning allows the industry to overcome this barrier. With the AISB Network, we’re showing that it is possible to combine the power of pharma datasets without ever moving or exposing them. The AISB Network will run several initiatives across both small and large molecules, and together these efforts are changing how AI models for drug discovery are developed.”

About the AI Structural Biology (AISB) Network

The AISB Network is an industry-led network focused on advancing AI in drug discovery. Within a secure federated computing paradigm, its long-term vision is to accelerate molecular design by achieving predictive precision comparable to experimental methods like X-ray crystallography. One of its flagship projects is the Federated OpenFold3 Initiative, conducted in collaboration with the AlQuraishi Lab at Columbia University. In parallel, the network is scoping further initiatives across both small and large molecules.

About Apheris GmbH

Apheris powers federated life sciences data networks, addressing the challenge of accessing proprietary data locked in silos due to IP and privacy constraints. The Apheris platform provides a federated computing infrastructure with built-in governance, security, and privacy controls, enabling cross-company collaborations that preserve confidentiality. For more information, visit: www.apheris.com.

Press contact: press@apheris.com