Oregon Health & Science University researchers have developed a first-of-its-kind method to predict cancer patient survival using advanced molecular data from individual cells.
Survival analysis is central to clinical oncology. Modern cancer studies can now measure gene activity in single cells from a patient's tumor and link this information to how long patients live. However, until now, there has not been a good way to use this detailed cell-level data to directly predict survival.
The study, published today in Cancer Discovery, describes a method called scSurvival that uses single-cell genetic data to identify which cells inside a tumor are most strongly linked to patient survival. Unlike traditional methods that average signals across an entire tumor, the new approach pinpoints harmful and helpful cell populations that can drive disease progression. The research team presented these findings today at the American Association for Cancer Research conference.
"This is the first kind of single-cell survival analysis that directly links individual tumor cells to patient outcomes," said Tao Ren, Ph.D., co-lead author of the study and postdoctoral fellow specializing in mathematics in the OHSU School of Medicine. "It allows us to see which cells are really driving disease progression instead of treating all cells the same."
Co-lead author Faming Zhao, Ph.D., said the approach helps solve a long-standing problem in cancer research.
"Tumors are very complex, and important signals can be lost when data are averaged across thousands or millions of cells," said Zhao, a postdoctoral fellow specializing in cancer biology in the OHSU School of Medicine. "By looking at survival at single-cell resolution, we can better understand why patients with the same cancer can have very different outcomes."
Expertise across fields
In tests using melanoma and liver cancer data, the tool more accurately predicted patient outcomes than standard methods. It also uncovered specific immune and tumor cell states tied to better or worse survival. For example, the researchers found certain immune cells that appear to help patients respond better to immunotherapy, while others were linked to poorer outcomes.
Senior author Zheng Xia, Ph.D., associate professor of biomedical engineering in the OHSU School of Medicine and a member of the OHSU Knight Cancer Institute , said the work reflects both technical innovation and close collaboration across disciplines.
"This study was made possible by strong collaboration at the Knight Cancer Institute between computational scientists, cancer biologists and clinicians," Xia said. "By bringing together expertise from different fields, we were able to use artificial intelligence to develop a new way to study survival using single-cell data."
Xia said the model goes beyond traditional machine learning approaches by capturing complex biological patterns that were previously difficult to study.
"This work uses artificial intelligence to develop a new way to study survival using single-cell data," Xia said. "The model is more complex than traditional machine learning approaches, and it allows us to capture information that was not accessible before."
Understanding these differences matters for patients, researchers said, because tumors are made up of many cell types that behave differently. Treatments that work for one patient may fail in another if harmful cell populations are missed.
While scSurvival is not yet used in clinical care, the researchers say it could eventually help doctors better identify high-risk patients and support the development of more precise, targeted cancer therapies.
The open-source scSurvival program and its tutorials are freely available at GitHub , Zenodo and Code Ocean .
In addition to Xia, OHSU co-authors on this study include Canping Chen, M.S., Le Zhou, Ph.D., Gordon Mills, M.D., Ph.D., Lisa Coussens, Ph.D., FAACR, FAIO.
This research was supported by the National Institute of General Medical Sciences, of the National Institutes of Health, under Award number R01GM147365, the National Cancer Institute, of the National Institutes of Health, under Award numbers R01CA283171, U01CA253472, U01CA281902 and U24CA264128, and the Office of Research Infrastructure Programs, Office of the Director, of the National Institutes of Health under Award number S10OD034224. This work was also supported by the U.S. Army Medical Research Acquisition Activity, 808 Schreider Street, Fort Detrick, MD 21702-514, in the amount of $1,525,292, through the Prostate Cancer Research Program, under Award No. HT94252410551, as well as the Silver Family Innovation Fund OHSU Faculty Excellence & Innovation Award, The Susan G. Komen Foundation, the National Foundation for Cancer Research and the Hildegard Lamfrom Endowed Chair in Basic Research. The content is solely the responsibility of the authors and does not necessarily represent the official views of the NIH, the U.S. Department of Defense or any other funders. The researchers wish to acknowledge the TCGA Research Network, the Gene Expression Omnibus and the Sequence Read Archive.
