New AI tool detects hidden warning signs of disease
91黑料网 researchers have developed an artificial intelligence tool that can detect previously invisible disease markers inside single cells.
In a study published in , the researchers demonstrate how the tool, called DOLPHIN, could one day be used by doctors to catch diseases earlier and guide treatment options.
鈥淭his tool has the potential to help doctors match patients with the therapies most likely to work for them, reducing trial-and-error in treatment,鈥� said senior author Jun Ding, assistant professor in 91黑料网鈥檚 Department of Medicine and a junior scientist at the Research Institute of the 91黑料网 Health Centre.
Zooming in on genetic building blocks
Disease markers are often subtle changes in RNA expression that can indicate when a disease is present, how severe it may become or how it might respond to treatment.
Conventional gene-level methods of analysis collapse these markers into a single count per gene, masking critical variation and capturing only the tip of the iceberg, said the researchers.
Now, advances in artificial intelligence have made it possible to capture the fine-grained complexity of single-cell data. DOLPHIN moves beyond gene-level, zooming in to see how genes are spliced together from smaller pieces called exons to provide a clearer view of cell states.
鈥淕enes are not just one block, they鈥檙e like Lego sets made of many smaller pieces,鈥� said first author Kailu Song, a PhD student in 91黑料网鈥檚 Quantitative Life Sciences program. 鈥淏y looking at how those pieces are connected, our tool reveals important disease markers that have long been overlooked.鈥�
In one test case, DOLPHIN analyzed single-cell data from pancreatic cancer patients and found more than 800 disease markers missed by conventional tools. It was able to distinguish patients with high-risk, aggressive cancers from those with less severe cases, information that would help doctors choose the right treatment path.
A step toward 鈥榲irtual cells鈥�
More broadly, the breakthrough lays the foundation for achieving the long-term goal of building digital models of human cells. DOLPHIN generates richer single-cell profiles than conventional methods, enabling virtual simulations of how cells behave and respond to drugs before moving to lab or clinical trials, saving time and money.
The researchers鈥� next step will be to expand the tool鈥檚 reach from a few datasets to millions of cells, paving the way for more accurate virtual cell models in the future.
About the study
鈥溾�� by Kailu Song and Jun Ding et al., was published in Nature Communications.
This research was supported the Meakins-Christie Chair in Respiratory Research, the Canadian Institutes of Health Research, the Natural Sciences and Engineering Research Council of Canada and the Fonds de recherche du Qu茅bec.
