Tuesday, April 21, 2026<\/p>\n
Study links specific cell populations to patient risk in melanoma and liver cancer.<\/p>\n
In a National\u00a0Institutes of\u00a0Health (NIH)-funded study, researchers developed a cancer assessment tool that can\u00a0identify\u00a0high-risk patients and the tumor cells linked to that risk. The model, called\u00a0scSurvival, uses a machine learning framework designed to analyze large-scale data at single-cell resolution.\u00a0<\/p>\n
With NIH support, Oregon Health & Science University\u00a0(OHSU)\u00a0tested the model on clinical data from more than 150 cancer patients. The tool predicted survival outcomes and linked specific cell populations to higher risk.\u00a0<\/p>\n
\u201cA risk assessment tool that not only tells you who may be at higher risk, but also provides clues as to why, could really help in these difficult cancers\u201d said\u202fAnthony\u202fLetai, M.D., Ph.D.,\u202fdirector of NIH\u2019s National Cancer Institute (NCI).\u202f\u202f\u00a0<\/p>\n
Every tumor\u00a0contains\u00a0a unique\u00a0mosaic\u00a0of cells\u00a0presenting\u00a0biological patterns\u00a0that could\u00a0indicate\u00a0how a\u00a0tumor\u00a0will progress or\u00a0respond\u00a0to treatment.\u00a0While researchers have managed to collect\u00a0single-cell gene expression data from\u00a0thousands to millions of\u00a0tumor\u00a0cells, analyzing\u00a0it\u00a0has been\u00a0another story\u00a0entirely.\u00a0\u00a0<\/p>\n
Until now, researchers have applied methods that put the big picture in a blender, averaging cell data across entire tumors or cell type, both of which erase potentially critical nuances. The authors of the new study\u00a0sought\u00a0to devise an approach that better\u00a0utilizes\u00a0the rich\u00a0datasets that are available,\u00a0preserving\u00a0their\u00a0finer details.\u00a0\u00a0<\/p>\n
\u201cBy\u00a0taking a fine-tooth comb to single-cell data,\u00a0scSurvival\u00a0is able to consider the varying influence that individual cells have on disease progression and survival outcomes,\u201d said corresponding author Zheng Xia, Ph.D., an associate\u00a0professor of biomedical engineering at OHSU.\u00a0\u00a0<\/p>\n
To\u00a0accomplish\u00a0this,\u00a0scSurvival\u00a0assigns each cell a weight\u00a0based on the degree that the cell is related to\u00a0survival, filtering out information from less important cells.\u00a0The model then\u00a0averages\u00a0the\u00a0data\u00a0from\u00a0weighted cells\u00a0together, forming its basis for survival predictions.\u00a0\u00a0<\/p>\n
Researchers trained their model on single-cell datasets paired with survival data from hundreds of patients. They then tested it on clinical data from patients with melanoma or liver cancer and found it predicted outcomes more accurately than traditional methods.\u00a0<\/p>\n
The team also traced the model\u2019s predictions back to specific cell groups,\u00a0identifying\u00a0immune and tumor cells linked to better or worse survival. In melanoma, they\u00a0identified\u00a0cell populations associated with responses to immunotherapy.\u00a0<\/p>\n
The findings show that differences in cell populations shape how tumors behave and respond to treatment. Tools like\u00a0scSurvival\u00a0may help\u00a0identify\u00a0these patterns.\u00a0<\/p>\n
This research was supported in part by NCI through grants\u00a0R01CA283171,\u00a0U01CA253472, U01CA281902, and U24CA264128.\u00a0\u00a0<\/p>\n
About the National Cancer Institute (NCI):\u202fNCI\u202fleads the National Cancer Program and NIH\u2019s efforts to dramatically reduce the prevalence of cancer and improve the lives of cancer patients and their families, through research into prevention and cancer biology, the development of new interventions, and the training and mentoring of new researchers.\u00a0<\/p>\n
About the National Institutes of Health (NIH): NIH, the nation’s medical research agency, includes 27 Institutes and Centers and is a component of the U.S. Department of Health and Human Services. NIH is the primary federal agency conducting and supporting basic, clinical, and translational medical research, and is investigating the causes, treatments, and cures for both common and rare diseases. For more information about NIH and its programs, visit www.nih.gov<\/a>.<\/p>\n NIH\u2026Turning Discovery Into Health\u00ae<\/p>\n Reference<\/p>\n