Unveiling Cell Identity: A Machine Learning Method Improves Understanding of Gene Expression Patterns

Cell identity can be improved by machine learning

Genes are expressed and activated in a way that creates patterns of cells with similar types and functions across organs and tissues. These patterns help us better understand cells, which can lead to a better understanding of disease mechanisms.

Researchers can now observe gene expression across tissue samples in their spatial context thanks to spatial transcriptomics. New computational methods are required to help make sense of these data and identify and understand gene expression patterns.

To fill this gap, a research team led Jian Ma, Ray and Stephanie Lane professor of Computational Biology at Carnegie Mellon University’s School of Computer Science has developed a machine-learning tool. The paper on this method, SPICEMIX appeared as the cover article in the latest issue of Nature Genetics.