Prescription drugs: Machine Learning Discover Drugs that could help smokers quit
Prescription drugs:
Prescription drugs & Dextromethorphan and other medications, which are used to treat coughs brought on by flu and cold, could be used to aid people in quitting smoking cigarettes, according to research conducted by Penn State College of Medicine and the University of Minnesota researchers. They came up with a unique machine learning approach, which lets computer programs examine data sets to find patterns and patterns to determine the drug. They also said that sure of them are being evaluated as a clinical trials.
Cause of cancer
Smoking cigarettes can be a leading cause of cancer, cardiovascular disease, and respiratory illnesses and accounts for close to one million premature deaths across the United States each year. Smoking habits are learned or unlearned. The genetic component impacts a person’s susceptibility to engaging in these habits. Researchers found in their previous study that those with specific genes have a higher chance of becoming addicted to smoking tobacco.
Biochemistry
Utilizing genetic information of more than 1.3 million individuals, Dajiang Liu, Ph.D. is a professor of the public health sciences as well as of biochemistry and molecular biology, as well as Bibo Jiang, Ph.D. as an assistant professor of health science, led an extensive multi-institutional study that utilized machine learning to analyze the vast data sets including specific information regarding a person’s genetics as well as their self-reported smoking habits.
Researchers identified over 400 genes linked to smoking habits. Because a person could have hundreds of genes, they needed to figure out why sure of them were related to smoking-related behaviors. Genes that control the creation of nicotine receptors or are involved in signaling to the dopamine hormone, which makes people feel relaxed and content, have easy-to-understand connections. For the other genes, researchers had to discover the function each one plays in the biochemical pathways. They could determine the medications approved to alter those pathways based on that knowledge.
Most of the genetic information used in the study comes from people of European origins, so the model needed to be adapted to analyze the data and to study a smaller collection of about 150,000 people who have Asian, African, or American family ancestry.
Dextromethorphan & Prescription drugs
Liu and Jiang collaborated with over 70 scientists in the research. They found at least eight drugs that could aid in smoking cessation, like dextromethorphan, widely used to treat coughs caused due to influenza, and colds galantamine, used to treat Alzheimer’s disease. This study is published by Nature Genetics today, Jan. 26.
“Re-purposing drugs by using huge biomedical data and machine-learning techniques can help save time, money and money,” stated Liu, an Penn State Cancer Institute and Penn State Huck Institutes of the Life Sciences researcher. “Some of the medications we identified are being evaluated in clinical trials to determine their potential to aid smokers quit smoking, but there are many other possibilities to be investigated in the future.”
Although the machine-learning method could integrate only a few pieces of information from different ancestries, Jiang declared that it’s vital for researchers to construct genetic databases for people with various ancestral bloodlines.
Also Read: Binance hack: The Biggest Crypto currency Hacks of All Time
“Prescription drugs is only going to improve the precision with which machines learning models can recognize people at risk of drug misuse as well as identify possible biological pathways that could be targeted to provide effective treatments.”
Additional College of Medicine authors on the project include Fang Chen, Xingyan Wang, Dylan Weissenkampen, Chachrit, Khunsriraksakul, Lina Yang, Renan Sauteraud, Olivia Marx, and Karine Moussa. They have not disclosed any conflicts of interest. A complete list of the authors involved in the project is included in the text.
Conclusion
Additionally, Prescription drugs research was aided by funding from The National Institutes of Health (grants R01HG008983 and R56HG011035 and the R01HG011035 grant, R56HG012358, the R01 (R21AI160138, R03OD032630)) in conjunction with Penn State College Of Medicine’s Biomedical Informatics and Artificial Intelligence Program in the Strategic Plan. The views expressed by the authors may not reflect the opinions of the researchers or the funders.
