Existing medications that may help people quit smoking identified through machine learning

Medicines such as dextromethorphan, used to treat coughs caused by cold and flu, could be repurposed to help people quit smoking cigarettes, according to a study by Medical College of Pennsylvania and researchers from the University of Minnesota. They’ve developed a new machine learning method, in which computer programs analyze data sets for patterns and trends, to identify drugs, and they said some are already being tested in clinical trials.

Cigarette smoking is a risk factor for cardiovascular disease, cancer, and respiratory disease and accounts for nearly half a million deaths in the United States each year. While smoking behaviors can be learned and not learned, genes also play a role in a person’s risk of engaging in these behaviors. The researchers found a precedent study People with certain genes are more likely to become addicted to tobacco.

Using genetic data from more than 1.3 million people, Dajiang Liu, Ph.D.Professor of Public Health Sciences, Biochemistry, and Molecular Biology Bibo Jiang, Ph.D.assistant professor of public health sciences, co-led a large, multi-institutional study that used machine learning to study these large datasets — which include specific data about a person’s genetics and self-reported smoking behaviors.

Want more breaking news?

participation in technology networksThe Daily Newsletter, which delivers breaking science news straight to your inbox every day.

Sign up for free

Researchers have identified more than 400 genes associated with smoking behaviors. Since a person can have thousands of genes, they had to determine why some of these genes are associated with smoking behaviors. Genes that carry instructions for producing nicotine receptors or are involved in signaling for the hormone dopamine, which makes people feel relaxed and happy, have links that are easy to understand. For the remaining genes, the research team had to determine the role each one plays in biological pathways and, using that information, discover which drugs are already approved to modify those existing pathways.

Most of the genetic data in the study was from people of European ancestry, so a machine learning model had to be designed to study not only that data, but also a smaller data set of about 150,000 people of Asian, African, or American ancestry.

Liu and Jiang worked with more than 70 scientists on the project. They identified at least eight re-usable smoking cessation medications, such as dextromethorphan, which is commonly used to treat coughs caused by colds and flu, and galantamine, which is used to treat Alzheimer’s disease. the study Published in Nature Genetics today, January 26.

“Recycling drugs using biomedical big data and machine learning methods can save money, time and resources,” Liu said. Penn State Cancer Institute And Penn State Hack Institutes of Life Sciences researcher. “Some of the drugs we’ve identified are already being tested in clinical trials for their ability to help smokers quit, but there are still other potential candidates that could be explored in future research.”

While the machine learning method was able to integrate a small set of data from diverse ancestors, Jiang said it is still important for researchers to build genetic databases from individuals of diverse ancestry.

“This will only improve the accuracy with which machine learning models can identify individuals at risk for drug misuse and identify potential biological pathways that can be targeted for beneficial therapies.”

Reference: Chen F, Wang X, Jang SK, et al. Multilineage transcriptome-level association analyzes provide insights into the biology of tobacco use and drug reuse. Nat Genet. 2023: 1-10. doi: 10.1038 / s41588-022-01282-x

This article has been republished from the following Materials. Note: Article may have been edited for length and content. For more information, please contact the mentioned resource.

Leave a Comment