Scientists develop a new gene biomarker identification method for toxicity testing

Companies like agrochemicals and pharmaceuticals must check extensively for possible toxicity when they develop new products before they can obtain regulatory approval. In general, toxicity testing involves time-consuming and costly animal studies.

From left: University of Illinois researchers Zeynep Madak-Erdogan, Rohit Bhargava, and Colleen Bushell collaborated on a project to detect potential liver toxicity through genetic biomarker identification. Image Credit: University of Illinois.

Scientists from the University of Illinois have created a new method for identifying gene biomarkers that reduces the testing process to a few days while ensuring a high level of precision.

The aim of this research was to identify the smallest set of indicators from the liver to predict toxicity and potential liver cancer. The agrochemical industry has a pipeline where they test new compounds in terms of toxicity-related endpoints. Liver toxicity is one of the most important endpoints, because the liver is the organ that receives the blood supply and cleans it, making it one of the biggest targets in terms of environmental toxic action.”

Zeynep Madak-Erdogan, Study Lead Author and Associate Professor, Department of Food Science and Human Nutrition, University of Illinois

She further adds that companies usually do this through long-term animal experiments. The animals are tracked for up to one year to verify whether they develop liver cancer after exposure to such compounds.

Such studies demand thousands of mice or rats, and a lot of person-hours to take care of the animals, to gather the samples, and for data analysis.

Published in Scientific Reports, the study determines a biomarker gene signature that signifies possible liver toxicity just 24 hours after exposure.

Madak-Erdogan and her team assessed the information from a huge database from the National Institute of Environmental Health Sciences. A collaborative study involving researchers from the U of I National Center for Supercomputing Applications (NCSA) used machine learning methods to distinguish gene biomarkers in messenger RNA to predict future toxicity.

From designing new molecules to identifying novel biological targets, machine learning approaches are playing a key role in accelerating drug target identification and validation.”

Colleen Bushell, Director, Healthcare Innovation Program Office, National Center for Supercomputing Applications, University of Illinois

This study is not the first one to use such approaches, but it is the most extensive one, according to Madak-Erdogan. The team used a significant amount of data and several machine learning methods to find the techniques that offer the quickest and most accurate results.

“We are assessing the best prediction techniques and finding the best indicators for liver toxicity. Instead of going for months or years, now we can just treat a few mice for 24 hours, collect livers, look at the biomarkers we identified, and predict whether the animal will potentially develop liver cancer or not,” explained Bushell.

The results from the study can be widely applied by toxicologists and other scientists. It can also be useful for the agrochemical and pharmaceutical industry to optimize their testing abilities.

Our findings show machine learning approaches are definitely very valuable in analyzing the vast amount of biological data that we create in our research activities. Collaboration between life sciences and computer sciences is very important for this work.”

Zeynep Madak-Erdogan, Study Lead Author and Associate Professor, Department of Food Science and Human Nutrition, University of Illinois