AI tools and datasets point to tailored treatments for kidney disease patients

Doctors treating kidney disease have long depended on trial-and-error to find the best therapies for individual patients. Now, new artificial intelligence (AI) tools developed by researchers in the Perelman School of Medicine and the Wharton School at the University of Pennsylvania can analyze kidney disease at the cellular level to match the most effective treatments and speed up solutions. This breakthrough, published this week in Nature Genetics, could impact millions who have kidney disease.

“We are moving from guesswork to precision,” said Katalin Susztak, MD, Ph.D., a professor of Nephrology, Genetics and director of the Penn/CHOP Kidney Innovation Center. “Kidney diseases are not all the same, but the use of AI helped us identify and catalog 70 distinct kinds of kidney cells that appear across human and animal samples. This improves the reliability of research and can lead to potential treatments.”

AI tools transform kidney disease care

The Penn team tackled a major challenge in single-cell RNA sequencing, a cutting-edge technique that examines the genetic activity of individual cells. Until now, this method has been difficult to apply to individual patients due to inconsistent cell type definition and uncertainty about which lab models (like mice or rats) best match human diseases.

The team’s solution includes SISKA 1.0 Atlas: A massive dataset built from over 1 million cells across 140 human, mouse, and rat kidney samples. In combination with a new statistical method that examines gene programs—sets of co-regulated genes representing biological pathways—rather than individual genes, it was easier to spot disease-related problems in a person’s cells. The new, open-source tool, called CellSpectra, was created right at Penn.

“We built CellSpectra to do what current methods cannot: analyze one patient’s sample at a time, and interpret it in the context of species, disease, and therapy,” said Nancy Zhang, Ph.D., the Ge Li and Ning Zhao professor of statistics and data science at the Wharton School.

“Both of these tools will be free for anyone to use. Now researchers, scientists, and clinicians will all have access to these tools that allow personalized treatments with greater precision,” Susztak added.

Beyond RNA: A new protein catalog and disease trait map

In a separate study, the Susztak team has also created the first comprehensive catalog of kidney proteins, offering a new lens on how protein abundance, not just gene expression, contributes to disease. This work, published in Nature Medicine, found that protein levels in kidney cells often don’t match gene activity (a mismatch called discordance), showing that studying genes alone isn’t enough to understand how diseases develop.

“This is a significant step forward in understanding the biology of kidney disease—not just at the RNA level, but also at the functional protein level,” said Susztak. “Linking protein profiles with traits like blood pressure, lipid levels, and kidney function opens new doors for therapies that target the right molecules in the right patients.”