Skip to main content

NCSA Researchers Identify Biomarkers to Accelerate Liver Toxicity Testing in New Products

Microscopic photograph of cells in purple, pink, and black

To ensure new agrichemical and pharmaceutical products are safe for humans, they must meet U.S. Food and Drug Administration toxicity standards before being allowed on the market. Often, these tests require a lot of resources, time, and are costly to conduct. Even with careful and extensive testing, some consumers may encounter toxicity-related health issues years later after an FDA-approved product is already in stores. That’s why researchers at the National Center for Supercomputing Applications (NCSA) at the University of Illinois at Urbana-Champaign (UIUC) turn to genes, machine learning, and modeling to accelerate testing, reduce costs, and mitigate public health risks.

Zeynap Madak-Erdogan, an NCSA Faculty Fellow and UIUC Food Science and Human Nutrition (FSHN) Associate Professor, studies liver toxicity and leads a collaborative team from multiple organizations and various Illinois campus units. The group recently published a paper in Scientific Reports. Madak-Erdogan says, “The aim of this research was to identify the smallest set of indicators from the liver to predict toxicity and potential liver cancer.”

Using advanced digital resources, tools, services, and expertise available at NCSA, the team identified several biomarkers and gene signatures directly linked to liver toxicity. Colleen Bushell, director of healthcare innovation at NCSA and co-author of the study with Madak-Erdogan, says this research could potentially impact the future of healthcare and pharmaceuticals advancements.

In this project, the analytics team identified biological targets by coupling machine learning feature selection with predictive modeling approaches to induce biomarker models. These models were then trained on experimental data and tested on unseen pharma data, producing valuable and informative results. From designing new molecules to identifying novel biological targets, machine learning approaches are playing a key role in accelerating drug target identification and validation. These biomarker models can be used to shorten the drug design process by finding toxic compounds before clinical trials which can result in cost savings from lower drug prices and provide more treatment choices for patients.

Colleen Bushell, NCSA Healthcare Innovation Director

For more information on the group’s work, read Illinois FSHN’s press release.


The National Center for Supercomputing Applications at the University of Illinois at Urbana-Champaign provides supercomputing and advanced digital resources for the nation’s science enterprise. At NCSA, University of Illinois faculty, staff, students and collaborators from around the globe use these resources to address research challenges for the benefit of science and society. NCSA has been advancing many of the world’s industry giants for over 35 years by bringing industry, researchers and students together to solve grand challenges at rapid speed and scale.

Back to top