AI tool reveals what attracts immune cells to tumors and what keeps them away

UT MD Anderson Research News October 13, 2026

• Researchers developed a new artificial intelligence (AI) tool that can help explain where immune cells gather in the body and what guides them there
• The AI tool identifies signals linked to attracting or repelling immune cells and could be used across cancer and other diseases
• A key finding suggests that mucins, sugar-coated proteins overproduced by many cancers, may form a physical barrier that keeps T cells away from tumors
• The tool offers researchers a new way to understand how cells navigate tissues and identify potential targets across a range of diseases

Researchers at The University of Texas MD Anderson Cancer Center and collaborating institutions in Texas developed an artificial intelligence (AI) model that helps explain how immune cells find their way to specific locations in the body and why they avoid others. The findings could help scientists better understand cancer, autoimmune diseases and treatment response.

The study, published in Nature Biomedical Engineering, was co-led by Tao Wang, Ph.D., associate professor of Bioinformatics and Computational Biology; and Linghua Wang, M.D., Ph.D., professor of Genomic Medicine, executive director and head of the Center for Cellular Language Intelligence, associate member of the James P. Allison Institute™, and focus area co-lead with the Institute for Data Science in Oncology.

“While spatial technologies can show where immune cells are located, this new tool helps us investigate why they gather in certain areas and how they reach and recognize tumor cells,” Tao Wang said. “By identifying local signals that attract immune cells as well as potential barriers that may keep them out, we may be able to identify biomarkers and therapeutic targets that could be used to improve patient outcomes.”

How does this new AI tool work?

The tool, known as Spatial Analysis of Cellular Engagement and Recruitment (SPACER), makes use of spatial transcriptomics, a molecular technique that measures gene activity within intact tissue to highlight which genes are expressed and where.

Scientists often compare cell movement to a postal system, but previously they have not fully understood the signals, or postal codes, that guide cells to the right places. The researchers developed SPACER to try and decode these signals.

Many AI models can make accurate predictions, but they often act as “black boxes” that cannot explain how they reached their conclusions. SPACER is different because it is built around how tissues are actually organized in the body. Instead of treating cells as isolated units, the tool examines groups of neighboring cells and how they work together. This makes the model’s predictions easier to understand and helps researchers uncover new biological insights, in addition to making predictions.

The team applied SPACER across 37 datasets representing several cancer types. In benchmarking tasks, the model was four- to 21-times more effective than existing approaches at identifying biologically meaningful signals linked to cell recruitment.

What were the most significant findings using SPACER?

One of the most meaningful findings was that immune cells appear to respond primarily to signals in their immediate surroundings rather than signals circulating elsewhere in the body.  

SPACER revealed that tumors expressing genes involved in antigen presentation, the process by which cells display protein fragments for immune cells to inspect, were more likely to attract T cells. This suggests that local interactions between tumors and immune cells help determine whether immune cells enter a tumor.

Additionally, the researchers uncovered evidence that mucins, a family of large, sugar-coated proteins produced by many cancers, may help create physical barriers that keep T cells away from tumors. Across several melanoma and gastric cancer datasets, tumors with higher levels of mucins were associated with poorer responses to immune checkpoint inhibitors and poorer patient outcomes.  

Can SPACER work for other diseases?

Interestingly, applying SPACER to data from preclinical models of immunotherapy-related myocarditis, or heart inflammation, identified regions of the heart and molecular signals associated with T cell recruitment. The tool suggested that CD4-positive T cells may play a larger role in driving severe heart inflammation than previously recognized.

The researchers believe SPACER could potentially be used as a diagnostic tool for cancer therapies and to improve understanding of diseases and scenarios in which cell movement and positioning are important, including autoimmune disorders, tissue repair and wound healing.

“Our goal is to understand how cells communicate and how those signals shape treatment response and patient outcomes,” said Linghua Wang. “SPACER is an exciting step toward decoding that language, allowing us to connect the patterns we see in tissues to the biology that may explain them. This helps us turn these insights into new ideas we can test in the lab.”

***

This study was funded in part by the National Institutes of Health, the Cancer Prevention and Research Institute of Texas, the U.S. Department of Defense, the Adrienne Helis Malvin Medical Research Foundation, and a Baylor College of Medicine Department of Surgery Seed Grant. For a full list of collaborating authors, disclosures and funding sources, see the full paper in Nature Biomedical Engineering.