Researchers at a Hackathon used AlphaGenome to search for the genetic causes of 29 undiagnosed diseases.Credit: Peter Kováč/Alamy
When more than 100 researchers voluntarily locked themselves in a room last year to tackle some of the hardest conditions in medicine, they turned to artificial intelligence.
As part of an effort, called the Undiagnosed Hackathon, to crack 29 undiagnosed conditions researchers deployed AlphaGenome — an AI model developed by Google DeepMind in London that was described in Nature on 28 January1.
AlphaGenome — an AI tool that was made available to scientists last year — can predict the diverse effects of mutations in non-coding DNA sequences, including how they might affect the activity of nearby genes.
Deciphering the 98% of the human genome that does not code for proteins is one of biology’s grand challenges. Mutations in these sequences are especially vexing to researchers seeking to uncover the genetic basis for rare, often fatal diseases.
“These are variants that, to be quite honest, often get triaged,” says Eric Klee, a bioinformatician at the Mayo Clinic in Rochester, Minnesota, who co-led the Undiagnosed Hackathon in September last year.
Undiagnosed rare diseases
The three-day event at the Mayo Clinic in Rochester, as well as two previous hackathons in Europe, were organized by the Wilhelm Foundation — a charity in Brottby, Sweden, that advocates for families affected by undiagnosed rare diseases. The charity was founded by Helene and Mikk Cederroth, who lost three of their four children to an undiagnosed disease, and named the foundation after their eldest son, who died at the age of 16.
Around 350 million people have an undiagnosed rare condition, but only a fraction can be diagnosed using existing technologies such as genome sequencing. “If you don’t have a diagnosis, you are left behind,” says Helene Cederroth.
DeepMind’s new AlphaGenome AI tackles the ‘dark matter’ in our DNA
Efforts to diagnose rare diseases tend to focus on mutations in protein-coding regions of the genome, known as the exome. To see if AlphaGenome could help to interpret the effects non-coding variants, Klee tested its prediction for a variant that he and his colleagues had linked to an individual’s diagnosis, before the September 2025 hackathon.
Experimental work showed that the mutation altered gene expression in cardiac cells, but not in neural cells, which was in line with the symptoms the individual experienced. AlphaGenome’s predictions of the variant’s effects supported this conclusion, Klee says.
