Even with the same diagnosis, patients can experience very different disease courses and treatment outcomes.
While current state-of-the-art Generative AI systems primarily lean on statistical correlations for their outputs, AIRIS offers new opportunities for modelling disease progression, capturing individual variability and ultimately helping researchers understand the underlying mechanisms of complex diseases. By grounding its predictions in biological mechanisms, AIRIS aims to enable researchers to simulate disease trajectories, identify key divergence points, and uncover promising targets for intervention.
AIRIS (Mechanism-Informed Multimodal Generative AI for Causal and Dynamical Modelling in Biomedical Research) is developing a trustworthy AI collaborator that supports scientists at every stage of the research process. Rather than relying on black-box predictions, AIRIS combines multimodal data with biological knowledge to support more transparent and explainable research. By helping researchers investigate complex diseases more effectively, the EU-funded project aims to accelerate biomedical discovery and advance the future of personalised medicine.
While current tools retrieve and summarise, we're building an AI collaborator that helps scientists access and harmonise data, explore disease mechanisms, generate and test hypotheses, and design rigorous studies.
An AI Collaborator that Supports the Entire Research Cycle
At the end of this four-year project the AI collaborator will accelerate the biomedical research pipeline. Instead of spending months wrangling data and manually drafting protocols; harmonised datasets, evidence-based hypotheses, and clinical study protocols are drafted within weeks. This will give researchers more time to focus on interpreting results, designing interventions, and potentially identifying new treatment opportunities.
5 Use Cases: From Computational Models to Experimental Validation
Latest News & Insights
.jpg "McGill")
