A new global public-private partnership using artificial intelligence (AI) to accelerate drug discovery is launching with UCL as one of the lead academic partners.
The five-year project has a budget of more than €60 million, funded by the European Union and industry partners through the Innovative Health Initiative (IHI).
The LIGAND-AI consortium brings together 18 partners across nine countries to generate large open, high-quality datasets of how molecules (ligands) bind to proteins, and use them to train AI models capable of predicting candidate molecules as suitable binders for thousands of human proteins for use in medications.
Led by Pfizer and the Structural Genomics Consortium (SGC), the consortium of experts across academia, the life sciences industry, technology companies, and research organisations will investigate thousands of proteins relevant to existing and unmet disease areas including rare, neurological, and oncological (cancer) conditions, to generate open and accessible, high-quality, AI-ready data at scale as a public resource.
Early drug discovery is a long, expensive, and uncertain process. Scientists spend years testing thousands of molecules to find just one that binds to a disease-related protein. LIGAND-AI aims to change this by combining advanced laboratory technologies with computational methods to create a seamless pipeline from experiment to prediction. The consortium will generate billions of data points using complementary screening technologies, enabling researchers worldwide to develop, train and benchmark AI models that predict molecular interactions.
UCL is the lead academic partner in the UK, working alongside universities in Canada and Germany. The UCL team, led by Professors Matthew Todd and Nicola Burgess-Brown (both UCL School of Pharmacy), will be spearheading the community aspects of the open science project, seeking donations of protein samples and machine learning models from across the globe, and driving the creation and expansion of these researcher networks.
Professor Todd said: "Machine learning will accelerate the discovery of new medicines. But for that to happen, we need very large, high quality, public datasets so that we can train the algorithms effectively. This project helps to generate that dataset of how billions of molecules bind human proteins - experimentally, in the lab. This will help everyone develop better predictive models for drug discovery, including UCL's many industry neighbours in King's Cross.
"As a global, open science project we're encouraging potential partners to be in touch, particularly in the areas of protein science and machine learning."
Professor Aled Edwards (University of Toronto), CEO of the Structural Genomics Consortium and project coordinator, said: "This project brings together scientists and companies from across disciplines within an open science ecosystem. It is heartening to see these diverse scientific communities coalesce around a common vision to generate and share valuable chemical data openly with the world."
Beyond data generation, LIGAND-AI will foster an open discovery ecosystem by inviting the scientific community to co-develop and refine predictive models through open challenges and benchmarking campaigns. All data generated through LIGAND-AI will be shared to ensure they are findable, accessible, interoperable, and reusable by the global scientific community. By integrating expertise in protein science, structural biology, chemistry, and machine learning, the project will build a dynamic network where experimental and computational discoveries evolve together, ensuring that progress is cumulative, transparent, and accessible.
By establishing a shared, open-science infrastructure for AI-driven drug discovery, LIGAND-AI will not only advance early-stage research but also train a new generation of interdisciplinary scientists fluent in both computation and experimentation. The project represents a major step towards the Structural Genomics Consortium's "Target 2035" aim to discover chemical modulators for every human protein by the year 2035.
