We've updated our Privacy Policy to make it clearer how we use your personal data. We use cookies to provide you with a better experience. You can read our Cookie Policy here.


Identifying Metabolism-Disrupting Chemicals With Machine Learning

Identifying Metabolism-Disrupting Chemicals With Machine Learning content piece image
Credit: JESHOOTS.COM on Unsplash.
Listen with
Register for free to listen to this article
Thank you. Listen to this article using the player above.

Want to listen to this article for FREE?

Complete the form below to unlock access to ALL audio articles.

Read time: 1 minute

Chemicals in your furniture, plastic housewares and pesticides used in your yard may be making you fat, according to Boston University Schools of Medicine (BUSM) and Public Health (BUSPH)  researchers.

A growing number of environmental pollutants (organotins in pesticides, phthalates in plastics, flame retardants in furniture) activate fat-forming pathways and enhance weight gain through white-fat accumulation.

In a new study, researchers developed a novel experimental and computational framework for the identification of so-called metabolism-disrupting chemicals (MDCs), also known as obesogens, which are environmental chemicals that increase the risk of metabolic diseases (such as obesity, diabetes and cardiovascular disease) in subjects exposed to them.

“Our study developed machine learning methods to accurately identify and characterize new metabolism-disrupting chemicals and applied these methods to the classification of a set of as-yet uncharacterized chemicals suspected to be obesogens,” explained corresponding author Stefano Monti, PhD, associate professor of medicine at BUSM.

Using a high-throughput chemical screening approach combined with a machine learning approach, the researchers “profiled” a set of more than 60 chemicals with known effects (known to be either obesogens or non-obesogens) and used them to “train” a computer model to predict their metabolism-disrupting potential. These RNA-sequencing profiles, together with the known chemical labels, were fed to a computer model that was trained to distinguish between the two classes, and then applied to the classification of unlabeled chemicals.

According to the researchers, the rapid increases in obesity and metabolic diseases over the last few decades correlate with substantial increases in environmental chemical production and exposures. “The prevalence of obesity has reached epidemic proportions, and changes in diet and the modern lifestyle cannot fully account for it. Thus, the accurate prediction of the adverse effects of chemical exposure is an urgent goal,” said co-corresponding author Jennifer J. Schlezinger, PhD, associate professor of environmental health at BUSPH.

The researchers believe this study goes beyond simply predicting whether a chemical may or may not adversely affect a person’s metabolism, as it also points to the possible biological mechanisms through which it may exercise that effect. “In our panel of profiled chemicals, we also included known drugs used in the treatment of metabolic diseases, such as type 2 diabetes, which allowed us to compare and contrast the positive and negative effects of chemicals targeting our metabolism. This understanding will in turn be instrumental to the design of more effective and targeted drugs with minimal side-effects,” said Monti.

“By improving our ability to identify potentially harmful chemicals, we would be able to limit their use, or adopt safer procedures for their use, and thus prevent their adverse effects on human health,” said Schlezinger.

Reference: Kim Stephanie, Reed Eric, Monti Stefano, Schlezinger Jennifer J. A data-driven transcriptional taxonomy of adipogenic chemicals to identify white and brite adipogens. Environ. Health Perspect. 129(7):077006. doi: 10.1289/EHP6886.

This article has been republished from the following materials. Note: material may have been edited for length and content. For further information, please contact the cited source.