The Consortium for Biomedical Research and Artificial Intelligence in Neurodegeneration (C-BRAIN), a global collaboration of academic researchers, pharmaceutical companies, and philanthropic organisations of which Washington University School of Medicine in St. Louis is a founding member, launched three open-source AI tools to accelerate research aimed at developing new treatments for Alzheimer’s disease and other neurodegenerative diseases. Announced at the Alzheimer’s Association International Conference in London, the tools synthesise Alzheimer’s and neuroscience literature, surface insights from unpublished and so-called “dark” or hidden data, and provide peer review-style feedback for researchers. WashU Medicine led the formation of the 17-member consortium.

C-BRAIN’s mission is to build an “AI Biomedical Research Scientist” that works alongside human researchers to address a persistent challenge: more than 99 per cent of Alzheimer’s drug candidates fail in clinical trials. Despite decades of research, vital scientific knowledge remains fragmented across millions of published papers, massive complex datasets, and unpublished research results. AI provides scientists the capability to harness all this information toward a shared goal.

“Leveraging the AI revolution with scientists’ ability to generate enormous amounts of research results has created an incredible opportunity,” said Randall J. Bateman, MD, the Charles F. and Joanne Knight Distinguished Professor of Neurology at WashU Medicine, one of the world’s leading Alzheimer’s researchers and the director and founder of C-BRAIN. “The brain is immensely complex, but artificial intelligence inspired by the human brain can find relationships within massive amounts of data that a single human mind simply cannot hold. We expect that discoveries made over the next few years will be breakthroughs that wouldn’t be possible without AI.”

Bateman anticipates that C-BRAIN’s AI Scientist will accelerate the pace of discovery many times over by boosting the efficiency and effectiveness of Alzheimer’s disease and neurodegeneration research.

Open-sourcing an AI-powered toolbox

C-BRAIN’s work to date places three interrelated, open-source AI tools into the hands of the global research community:

AI Literature and Data Synthesis: Synthesises Alzheimer’s and neuroscience literature using advanced retrieval methods, helping researchers evaluate hypotheses faster than manual review allows.

Dark Data Analyser: Surfaces insights from unpublished data and negative results contributed by academic and pharmaceutical members, helping researchers avoid repeating failed experiments.

Reviewer Three: A critical reasoning agent that provides scientifically grounded, peer review-style feedback on grant proposals, manuscripts and experimental designs.

“It is antithetical to science that we would develop AI tools that function as an uninterpretable black box,” Bateman said. “By delivering an entirely open system, scientists worldwide can look at the code, analyse it, test it, improve on it, and collectively find where the flaws are. These tools are built for scientists, by scientists, and are owned by the scientific community.”