By Kostis Konstantinou • April 6, 2026
Jerusalem, 6 April, 2026 (TPS-IL) — Researchers at the Hebrew University of Jerusalem announced they have created an artificial intelligence tool that can greatly reduce the time needed to find the genetic causes of rare diseases. This process often takes years and leaves many patients without answers.
The tool, called EvORanker, examines how genes have evolved across more than 1,000 species to determine which gene is most likely responsible for a patient’s symptoms, according to a study published in Genetics in Medicine.
Rare disease diagnosis is often described as a “diagnostic odyssey,” with families facing years of testing and uncertainty. The researchers said that, despite advances in genetic sequencing, many patients remain undiagnosed.
In clinical testing, EvORanker ranked the correct disease-causing gene as the top candidate in nearly 70% of cases and placed it among the top five in 95% of cases, outperforming existing tools, particularly when the gene involved had not previously been linked to disease. The study was led by Dr. Christina Canavati and Prof. Yuval Tabach ofthe Hebrew University’s Faculty of Medicine and builds on earlier researc conducted with Nobel laureate Gary Ruvkun.
Researchers said the system could help doctors reach diagnoses faster and, in some cases, point to existing drugs that might be repurposed for treatment.
In one case cited in the study, the tool identified a previously unrecognized gene linked to a child’s neurodevelopmental disorder after extensive testing had failed to produce a diagnosis. In another, it helped uncover the genetic basis of a severe disorder affecting multiple organs.
The team said it is also studying potential applications for cancer, including why some tumors regress unexpectedly.
Rare diseases affect up to 5% of the global population, the researchers said, adding that the rate in Israel may be as high as 8% in some communities.
EvORanker is now available to researchers and clinicians, with further studies underway.
Related Topics
