Researchers at the University of California San Diego have developed a new artificial intelligence (AI) method that can predict how cells are organized in disease microenvironments. The method, called sc-ATAC-seq, can identify rare cell types and their interactions within complex tissues. This information could help researchers better understand how diseases develop and spread, and potentially lead to new treatments.

"By understanding how cells are organized in disease microenvironments, we can gain insights into disease mechanisms and develop targeted therapies," said Dr. Bing Ren, professor of cellular and molecular medicine at UC San Diego and senior author of the study.

Currently, scientists usually use single-cell RNA sequencing (scRNA-seq) to study gene expression in individual cells. While scRNA-seq provides valuable information about the genes that are active in a cell, it cannot provide information about the cell's interactions with other cells in the tissue.

sc-ATAC-seq addresses this limitation by using a technique called assay for transposase-accessible chromatin sequencing (ATAC-seq). ATAC-seq measures the accessibility of DNA to transposases, which are enzymes that can insert DNA into the genome. Open chromatin regions are usually associated with active genes, while closed chromatin regions are associated with inactive genes. sc-ATAC-seq combines ATAC-seq with scRNA-seq to provide information on both gene expression and chromatin accessibility in individual cells.

"We found that sc-ATAC-seq can identify rare cell populations that are often missed by scRNA-seq alone," said Dr. Xinyu Zhao, the first author of the study and a postdoctoral researcher at UC San Diego. "For example, we were able to identify a population of cancer stem cells that are responsible for tumor growth and metastasis."

The researchers further developed a set of computational tools to analyze sc-ATAC-seq data and predict the organization of cells in tissue microenvironments. These tools allow researchers to generate spatial maps of cells and identify rare cell-cell interactions that may be important for disease development.

"We believe that sc-ATAC-seq will be a valuable tool for studying a wide range of diseases, including cancer, neurodegenerative diseases, and autoimmune diseases," said Ren. "It could also be used to develop new therapies that target specific cell-cell interactions within disease microenvironments."

The study was published in the journal Nature Biotechnology.