Novel AI tool not only identifies genetic mutations but also predicts the type of disease

Scientists at the Icahn School of Medicine at Mount Sinai have developed a novel artificial intelligence tool that not only identifies disease-causing genetic mutations but also predicts the type of disease those mutations may trigger.

The method, called V2P (Variant to Phenotype), is designed to accelerate genetic diagnostics and aid in the discovery of new treatments for complex and rare diseases. The findings were reported in the December 15 online issue of Nature Communications [DOI: 10.1038/s41467-025-66607-w].

Current genetic analysis tools can estimate whether a mutation is harmful, but they cannot determine the type of disease it might cause. V2P fills that gap by using advanced machine learning to link genetic variants with their likely phenotypic outcomes-that is, the diseases or traits a mutation might cause-effectively predicting how a patient's DNA could influence their health.

"Our approach allows us to pinpoint the genetic changes that are most relevant to a patient's condition, rather than sifting through thousands of possible variants," says first author David Stein, PhD, who recently completed his doctoral training in the labs of Yuval Itan, PhD, and Avner Schlessinger, PhD. "By determining not only whether a variant is pathogenic but also the type of disease it is likely to cause, we can improve both the speed and accuracy of genetic interpretation and diagnostics."

The tool was trained on a large database of both harmful and benign genetic variants, incorporating disease information to improve prediction accuracy. In tests using real, de-identified patient data, V2P often ranked the true disease-causing variant among the top 10 candidates, highlighting its potential to streamline genetic diagnostics.

Beyond diagnostics, V2P could help researchers and drug developers identify the genes and pathways most closely linked to specific diseases. This can guide the development of therapies that are genetically tailored to the mechanisms of disease, particularly in rare and complex conditions."

Dr. Avner Schlessinger, co-senior and co-corresponding author, Professor of Pharmacological Sciences, and Director of the AI Small Molecule Drug Discovery Center, Icahn School of Medicine at Mount Sinai

While V2P currently classifies mutations into broad categories such as nervous system disorders or cancers, the researchers aim to refine the tool to predict more specific disease outcomes and integrate it with additional data sources to support drug discovery.

This innovation represents a step toward precision medicine, in which treatments can be matched to a patient's genetic profile. By connecting genetic variants to their likely disease effects, V2P may help clinicians diagnose more efficiently and help scientists identify new therapeutic targets, say the investigators.

"V2P gives us a clearer window into how genetic changes translate into disease, which has important implications for both research and patient care," says Dr. Itan, co-senior and co-corresponding author, Associate Professor of Artificial Intelligence and Human Health, and Genetics and Genomic Sciences, a core member of The Charles Bronfman Institute for Personalized Medicine, and a member of The Mindich Child Health and Development Institute at the Icahn School of Medicine at Mount Sinai. "By connecting specific variants to the types of diseases they are most likely to cause, we can better prioritize which genes and pathways warrant deeper investigation. This helps us move more efficiently from understanding the biology to identifying potential therapeutic approaches and, ultimately, tailoring interventions to an individual's specific genomic profile."

The paper is titled "Expanding the utility of variant effect predictions with phenotype-specific models." 

The study's authors, as listed in the journal, are David Stein, Meltem Ece Kars, Baptiste Milisavljevic, Matthew Mort, Peter D. Stenson, Jean-Laurent Casanova, David N. Cooper, Bertrand Boisson, Peng Zhang, Avner Schlessinger, and Yuval Itan.

This work was supported by the National Institutes of Health (NIH) grants R24AI167802 and P01AI186771, the Fondation Leducq, and the Leona M. and Harry B. Helmsley Charitable Trust grant 2209-05535. Additional financial support was provided by NIH grants R01CA277794, R01HD107528, and R01NS145483. This work was supported in part by Clinical and Translational Science Awards (CTSA) grant UL1TR004419 from the National Center for Advancing Translational Sciences. Research reported in this publication was also supported by the Office of Research Infrastructure of the NIH under award number S10OD026880 and S10OD030463.