We power federated data networks
Proprietary life sciences data is stored in private data repositories due to IP and privacy concerns.
But data from the public domain lacks diversity to build ML models that achieve the required accuracy and generalizability.
We address this challenge: collaboratively train higher-quality models on data of multiple parties - while keeping data IP and confidentiality protected.
Join the ADMET Network
Expand the applicability domain and accuracy of ADMET prediction models
Customize globally trained models to your proprietary chemical spaces
Join the AISB Network
Build and use state-of-the-art protein-complex prediction models
Collaboratively develop predictive models for small-molecule and large-molecule drug discovery
Build your own network
Advance life sciences research with governed access to distributed, multi-modal healthcare data
Work collaboratively across boundaries while ensuring compliance
Powering the AISB Network to Revolutionize AI Drug Discovery
Apheris provides the tech layer for the Artificial Intelligence Structural Biology (AISB) Network, an unprecedented collaboration among AbbVie, Astex, AstraZeneca, Boehringer Ingelheim, Johnson & Johnson, Sanofi and Takeda aimed at transforming AI drug discovery. State-of-the-art AI models will be trained and evaluated on unique data from multiple biopharma companies without exposing proprietary information.
A Gateway to better models in life sciences
Gain access to higher-quality and more generalizable models. Join secure, federated, privacy-first data networks or build your own. The Apheris Gateway provides granular data privacy controls, model IP protection, and integrates with your existing tooling.
Maintain complete control over users, models and their access to your data. Adapt to new research protocols swiftly with full governance and minimal hassle.
Trusted by our customers and partners
What our customers and partners say about us
Through the AISB Network we can collaborate on data with other pharma partners, exploring the hypothesis that each of our internal data sets will be highly complementary when training AI models. The result could be transformative in how we advance AI-driven drug discovery to develop better medicines faster.