Drugs like dextromethorphan, used to treat coughs caused by colds and flu, could potentially be repurposed to help people quit smoking, according to a study by researchers at Penn State College of Medicine and the University of Minnesota. They developed a novel machine learning method, where computer programs analyze data sets for patterns and trends, to identify drugs and some of them are already being tested in clinical trials.
Cigarette smoking is a risk factor for heart disease, cancer and respiratory diseases and accounts for nearly half a million deaths in the United States each year. While smoking behaviors can be learned and unlearned, genetics also play a role in a person’s vulnerability to engaging in those behaviors. Researchers have found in previous studies that people with certain genes are more likely to become addicted to tobacco.
Using genetic data from more than 1.3 million people, the study was co-led by Dajiang Liu, PhD, professor of public health sciences and organic chemistry and molecular biology, and Bibo Jiang, PhD, assistant professor of public health sciences. A large multi-institution study that used machine learning to study these large data sets — including specific data about individuals’ genetics and their self-reported smoking behavior.
Researchers identified more than 400 genes associated with smoking behavior. Since a person can have thousands of genes, they had to determine why some of them were linked to smoking behavior. Genes that carry instructions for the production of nicotine receptors or are involved in the signaling of dopamine, the hormone that makes people feel relaxed and happy, had easy-to-understand connections. For the rest of the genes, the research team looked at which drugs were already approved to determine the role each played in biological pathways and used that information to modify those existing pathways.
Most of the genetic data in the study came from people with European ancestry, so the machine learning model had to not only study that data, but also a smaller data set of about 150,000 people with Asian, African, or American ancestry.
Liu and Jiang worked with more than 70 scientists on the project. They identified at least eight drugs that could potentially be repurposed for smoking cessation, 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 was published in 2015 Nature genetics Today, January 26.
“Repurposing drugs using big biomedical data and machine learning methods can save money, time and resources,” said Liu, a researcher at Penn State Cancer Institute and Penn State Hawk Institute of Life Sciences. “Some of the drugs we identified are already being tested in clinical trials for their ability to aid smoking cessation, but there are still other potential candidates that could be explored in future research.”
While machine learning methods have been able to incorporate smaller sets of data from different ancestries, Jiang said it is still important for researchers to build genetic databases from individuals with different ancestries.
“This will only improve the accuracy with which machine learning models can identify individuals at risk for drug abuse and determine potential biological pathways that could be targeted for useful treatments.”
Other College of Medicine authors on the project include Fang Chen, Xingyan Wang, Dylan Weissenkampen, Chacharit, Khunsrirakskull, Lina Yang, Renan Souteraud, Olivia Marks, and Karin Musa. They declare no conflict of interest.
This research was supported by the National Institutes of Health (grants r01hg008983, R56hg01035, R56hg013838 and R03D038383, R21g038385 and R03d0323837 and R01g0323837 and P01gg03838 and P01g038385). The views of the authors do not necessarily represent those of the funders.