Novel Tool Identifies Cell Types in Human Tissue Samples

Scientists at Oregon Health & Science University’s Knight Cancer Institute have developed a machine learning tool called OmicsTweezer to better understand the mix of cell types within human tissue. This tool focuses on estimating cell composition in tumors and nearby tissue by analyzing data from tissue samples, a task central to cancer research. Their findings were published in Cell Genomics.

OmicsTweezer compares known patterns from single-cell data—where researchers can study one cell at a time — with the more complex, mixed data from bulk samples. It does this by aligning both types of data in a shared digital space, making it easier to match patterns and reduce errors caused by differences in how the data was collected, leading to more reliable results.

“It’s still very expensive to profile a large clinical sample size using single-cell technology,” explained lead researcher Zheng Xia. “But there is an abundance of bulk data—and by integrating single-cell and bulk data together, we can build a much clearer picture.” 

The team tested OmicsTweezer on simulated data and tissue from prostate and colon cancer patients. The tool identified subtle differences in cell subtypes and detected population changes that could point to treatment targets. “With this tool, we can now estimate the fractions of those populations defined by single-cell data in bulk data from patient groups,” Xia added. “That could help us understand which cell populations are changing during disease progression and guide treatment decisions.”