Researchers at Penn State College of Medicine identified eight medications that might be utilized to assist people in avoiding smoking. A team of more than 70 researchers contributed to the analysis of genetic and smoking behavior data from more than 1.3 million people.
According to a research conducted by experts at Penn State College of Medicine and the University of Minnesota, certain medications, such as dextromethorphan, which is commonly used to treat coughs caused by colds and the flu, may be used to assist individuals in quitting smoking. The researchers used a cutting-edge machine learning technique to analyze data sets to discover patterns and trends, and identify drugs that may be beneficial.
Cigarette smoking is a major contributor to cardiovascular disease, cancer, and respiratory ailments and is responsible for over half a million deaths every year in the United States. However, genetics also play a role in a person's likelihood of engaging in such behaviors.
Dajiang Liu, Ph.D., assistant professor of public health sciences, co-led a large multi-institution research that utilized machine learning to analyze these large data sets, which include detailed information about a person's genetics and self-reported smoking habits.
The researchers identified more than 400 genes associated with smoking behaviors. Many of the genes that are involved in the generation of nicotine receptors or the signaling for the hormone dopamine, which makes people feel relaxed and happy, were easy-to-understand connections.
The majority of genetic data in the study comes from people with European ancestry, thus the machine learning model had to be tailored to encompass both the study and a smaller sample of around 150,000 people with Asian, African, or American ancestry.
Liu and Jiang collaborated with more than 70 scientists to develop at least eight medications that might be used for smoking cessation, such as dextromethorphan, commonly used to treat cold and flu coughs, and galantamine, used to treat Alzheimer's disease.
'Repurposing medications with huge biomedical data and machine learning techniques may save money, time, and resources,' said Liu, a Penn State Cancer Institute and Penn State Huck Institutes of the Life Sciences researcher. "Some of the drugs we identified are already being evaluated in clinical studies for their ability to help smokers quit, but there are still other possibilities that may be investigated in future research.
Jiang said it's still important for researchers to build out genetic databases from individuals with diverse ancestries.
"This will only increase the speed at which machine learning algorithms can identify individuals at risk of drug misuse and pinpoint potential biological pathways that may be targeted for helpful treatments."
Fang Chen, Seon-Kyeong Jang, Anna H. Barnett, Diane M. Becker, James W. Coulter, I-Te Lee, Daniel Levy, Karine A. Lutz, Ani W. Manichaikul, Lisa W. Martin, Elizabeth C. Oelsner, Jerome I. Rotter, Eric O. Johnson, Robert Kaplan, I-Te Lee, Dana B. Hancock, Mark Vrieze, and Dajiang J.
In the strategic plan, the National Institutes of Health and Penn State College of Medicine funded the biomedical information and artificial intelligence program. The views of the authors do not necessarily represent the views of the funders.
