If you have an ACS member number, please enter it here so we can link this account to your membership. (optional)

ACS values your privacy. By submitting your information, you are gaining access to C&EN and subscribing to our weekly newsletter. We use the information you provide to make your reading experience better, and we will never sell your data to third party members.



Forecasting toxicity before the damage is done

Using toxicity data for thousands of chemicals, researchers developed 
computational program that predicts whether drug candidate is likely to cause liver damage

by Erika Gebel Berg, special to C&EN
March 28, 2016 | A version of this story appeared in Volume 94, Issue 13

The liver takes the brunt of the job clearing drugs from the body. Now, researchers have developed a computational model that predicts which drug candidates will prove toxic to the organ (Chem. Res. Toxicol. 2016, DOI: 10.1021/acs.chemrestox.5b00465). Denis Mulliner of Sanofi and his team developed a model that incorporated human and animal toxicity data from 3,712 compounds—three or more times the number used in most earlier models—organizing the data based on each chemical’s molecular properties and mechanism of liver toxicity. The model looks for common chemical and structural properties that lead to a particular type of toxicity. The team then tested its model with 269 proprietary compounds not included in the database. The liver toxicity of these compounds had been tested in animals, and the new model correctly identified 72% of the hepatotoxic compounds. The researchers are sharing this database, along with the model’s source code, with the scientific community “to advance the field of predictive toxicology,” Mulliner says.


This article has been sent to the following recipient:

Chemistry matters. Join us to get the news you need.