French start-up Bioptimus has announced that its H-optimus-o biology reference artificial intelligence (AI) foundation model has been wholly integrated into Proscia’s Concentriq Embeddings software platform, with the aim of enabling quicker and more efficient breakthroughs in AI development for therapeutic research.

H-optimus-o is one of the largest open-source AI foundation models available at the moment – having 1.1 billion possible parameters – and is one of the few solely designed for pathology. Having been trained on data sets of over 500,000 pathology slides, Bioptimus claims that the model can be applied to a variety of different tasks including model development for AI-driven research, drug development and diagnostics.

David Cahané, co-founder and general manager at Bioptimus, stated that “H-optimus-0 has set new benchmarks in AI performance, delivering best-in-class results. Our mission is to empower the scientific community and we are excited to discover what will be built on top of our cutting-edge histology foundation model. By integrating H-optimus-0 into Concentriq Embeddings, Proscia’s users now have access to a powerful tool that accelerates AI model development and drives breakthroughs not only in precision medicine, but also for therapeutic research and development.”

The Concentriq platform, meanwhile, allows researchers to store data at every point in the clinical pipeline, as well as offering AI models for the data’s enrichment and analysis. The two companies suggest that introducing H-optimus-o will further enhance the platform’s usefulness for researchers.

David West, CEO at Proscia, added,: “From Concentriq Embeddings to our real-world data offering, we are committed to giving life sciences and patholog y teams the tools they need to advance the next precision therapies and diagnostics. Adding Bioptimus’ H-optimus-0 to Concentriq Embeddings will help our users rapidly build high-performing algorithms at scale and unlock the promise of AI-driven therapeutic research and development.”