The specifics:
PopEVE analyzes mutation patterns across hundreds of thousands of species and then calibrates the results against databases of healthy human genomes.
Researchers applied the model to 31,000 children with severe developmental disorders, solving roughly one-third of cases that had gone undiagnosed.
The study flagged over 120 genes with no known connection to the illnesses, two dozen of which outside teams have since verified.
DeepMind's AlphaMissense flags 44% of people as carrying dangerous variants, popEVE drops that figure to 11% after reducing false positives.
Researchers applied the model to 31,000 children with severe developmental disorders, solving roughly one-third of cases that had gone undiagnosed.
The study flagged over 120 genes with no known connection to the illnesses, two dozen of which outside teams have since verified.
DeepMind's AlphaMissense flags 44% of people as carrying dangerous variants, popEVE drops that figure to 11% after reducing false positives.
There is still a lot to learn about our genome and the causes of uncommon genetic disorders, but models like PopEVE are helping to unravel the mystery by revealing genes that no one knew to look for and providing accurate diagnoses to families who have been waiting years for answers.