MSGID: 1:317/3 63d8995c   
   PID: hpt/lnx 1.9.0-cur 2019-01-08   
   TID: hpt/lnx 1.9.0-cur 2019-01-08   
    Machine learning identifies drugs that could potentially help smokers   
   quit    
      
     Date:   
         January 30, 2023   
     Source:   
         Penn State   
     Summary:   
         Medications like dextromethorphan, used to treat coughs caused by   
         cold and flu, could potentially be repurposed to help people quit   
         smoking cigarettes, according to a new study. Researchers developed   
         a novel machine learning method, where computer programs analyze   
         data sets for patterns and trends, to identify the drugs and said   
         that some of them are already being tested in clinical trials.   
      
      
         Facebook Twitter Pinterest LinkedIN Email   
   FULL STORY   
   ==========================================================================   
   Medications like dextromethorphan, used to treat coughs caused by cold   
   and flu, could potentially be repurposed to help people quit smoking   
   cigarettes, according to a study by Penn State College of Medicine and   
   University of Minnesota researchers. They developed a novel machine   
   learning method, where computer programs analyze data sets for patterns   
   and trends, to identify the drugs and said that some of them are already   
   being tested in clinical trials.   
      
      
   ==========================================================================   
   Cigarette smoking is risk factor for cardiovascular 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 plays a role in a person's risk for engaging   
   in those behaviors.   
      
   The researchers found in a prior study that 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, and of biochemistry and   
   molecular biology and Bibo Jiang, Ph.D., assistant professor of public   
   health sciences, co-led a large multi-institution study that used machine   
   learning to study these large data sets -- which include specific data   
   about a person's genetics and their self-reported smoking behaviors.   
      
   The researchers identified more than 400 genes that were related to   
   smoking behaviors. Since a person can have thousands of genes, they   
   had to determine why some of those genes were connected to smoking   
   behaviors. Genes that carry instructions for the production of nicotine   
   receptors or are involved in signaling for the hormone dopamine,   
   which make people feel relaxed and happy, had easy-to-understand   
   connections. For the remaining genes, the research team had to determine   
   the role each plays in biological pathways and using that information,   
   figured out what medications are already approved for modifying those   
   existing pathways.   
      
   Most of the genetic data in the study is from people with European   
   ancestries, so the machine learning model had to be tailored to not only   
   study that data, but also a smaller data set of around 150,000 people   
   with Asian, African or American ancestries.   
      
   Liu and Jiang worked with more than 70 scientists on the project. They   
   identified at least eight medications that could potentially be   
   repurposed for smoking cessation, such as dextromethorphan, which is   
   commonly used to treat coughs caused by cold and flu, and galantamine,   
   which is used to treat Alzheimer's disease. The study was published in   
   Nature Geneticstoday, Jan. 26.   
      
   "Re-purposing drugs using big biomedical data and machine learning   
   methods can 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 tested   
   in clinical trials for their ability to help smokers quit, but there   
   are still other possible candidates that could be explored in future   
   research."  While the machine learning method was able to incorporate a   
   small set of data from diverse ancestries, Jiang said it's still important   
   for researchers to build out genetic databases from individuals with   
   diverse ancestries.   
      
   "This will only improve the accuracy with which machine learning models   
   can identify individuals at risk for drug misuse and determine potential   
   biological pathways that can be targeted for helpful treatments."   
   Other 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 declare no conflicts   
   of interest.   
      
   This research was supported by The National Institutes of Health (grants   
   R01HG008983, R56HG011035, R01HG011035, R56HG012358, R01GM126479,   
   R21AI160138 and R03OD032630) and Penn State College of Medicine's   
   Biomedical Informatics and Artificial Intelligence Program in the   
   Strategic Plan. The views of the authors do not necessarily represent   
   the views of the funders.   
      
       * RELATED_TOPICS   
             o Health_&_Medicine   
                   # Smoking # Medical_Topics # Personalized_Medicine   
                   # Public_Health_Education # Genes # Teen_Health #   
                   Diseases_and_Conditions # Healthy_Aging   
       * RELATED_TERMS   
             o Pharmaceutical_company o Tobacco_smoking o   
             Personalized_medicine o Computational_neuroscience o Neurology   
             o Clinical_trial o Avian_flu o Virus   
      
   ==========================================================================   
   Story Source: Materials provided by Penn_State. Original written by   
   Zachary Sweger. Note: Content may be edited for style and length.   
      
      
   ==========================================================================   
   Journal Reference:   
      1. Fang Chen, Xingyan Wang, Seon-Kyeong Jang, Bryan C. Quach, J. Dylan   
         Weissenkampen, Chachrit Khunsriraksakul, Lina Yang, Renan Sauteraud,   
         Christine M. Albert, Nicholette D. D. Allred, Donna K. Arnett,   
         Allison E.   
      
         Ashley-Koch, Kathleen C. Barnes, R. Graham Barr, Diane M. Becker,   
         Lawrence F. Bielak, Joshua C. Bis, John Blangero, Meher Preethi   
         Boorgula, Daniel I. Chasman, Sameer Chavan, Yii-Der I. Chen,   
         Lee-Ming Chuang, Adolfo Correa, Joanne E. Curran, Sean P. David,   
         Lisa de las Fuentes, Ranjan Deka, Ravindranath Duggirala,   
         Jessica D. Faul, Melanie E. Garrett, Sina A. Gharib, Xiuqing Guo,   
         Michael E. Hall, Nicola L. Hawley, Jiang He, Brian D. Hobbs,   
         John E. Hokanson, Chao A. Hsiung, Shih-Jen Hwang, Thomas M. Hyde,   
         Marguerite R. Irvin, Andrew E. Jaffe, Eric O. Johnson, Robert   
         Kaplan, Sharon L. R. Kardia, Joel D. Kaufman, Tanika N. Kelly,   
         Joel E.   
      
         Kleinman, Charles Kooperberg, I-Te Lee, Daniel Levy, Sharon   
         M. Lutz, Ani W. Manichaikul, Lisa W. Martin, Olivia Marx, Stephen   
         T. McGarvey, Ryan L.   
      
         Minster, Matthew Moll, Karine A. Moussa, Take Naseri, Kari E. North,   
         Elizabeth C. Oelsner, Juan M. Peralta, Patricia A. Peyser, Bruce M.   
      
         Psaty, Nicholas Rafaels, Laura M. Raffield, Muagututi'a Sefuiva   
         Reupena, Stephen S. Rich, Jerome I. Rotter, David A. Schwartz,   
         Aladdin H. Shadyab, Wayne H-H. Sheu, Mario Sims, Jennifer A. Smith,   
         Xiao Sun, Kent D. Taylor, Marilyn J. Telen, Harold Watson, Daniel   
         E. Weeks, David R. Weir, Lisa R.   
      
         Yanek, Kendra A. Young, Kristin L. Young, Wei Zhao, Dana B. Hancock,   
         Bibo Jiang, Scott Vrieze, Dajiang J. Liu. Multi-ancestry   
         transcriptome-wide association analyses yield insights into   
         tobacco use biology and drug repurposing. Nature Genetics, 2023;   
         DOI: 10.1038/s41588-022-01282-x   
   ==========================================================================   
      
   Link to news story:   
   https://www.sciencedaily.com/releases/2023/01/230130130517.htm   
      
   --- up 48 weeks, 10 hours, 50 minutes   
    * Origin: -=> Castle Rock BBS <=- Now Husky HPT Powered! (1:317/3)   
   SEEN-BY: 15/0 106/201 114/705 123/120 153/7715 226/30 227/114 229/110   
   SEEN-BY: 229/111 112 113 114 307 317 400 426 428 470 664 700 292/854   
   SEEN-BY: 298/25 305/3 317/3 320/219 396/45   
   PATH: 317/3 229/426