Thomas Papikinos, Marios Krokidis, Aris Vrahatis, Panagiotis Vlamos, Themis P Exarchos
{"title":"Drug repurposing for obsessive-compulsive disorder using deep learning-based binding affinity prediction models.","authors":"Thomas Papikinos, Marios Krokidis, Aris Vrahatis, Panagiotis Vlamos, Themis P Exarchos","doi":"10.3934/Neuroscience.2024013","DOIUrl":null,"url":null,"abstract":"<p><p>Obsessive-compulsive disorder (OCD) is a chronic psychiatric disease in which patients suffer from obsessions compelling them to engage in specific rituals as a temporary measure to alleviate stress. In this study, deep learning-based methods were used to build three models which predict the likelihood of a molecule interacting with three biological targets relevant to OCD, SERT, D2, and NMDA. Then, an ensemble model based on those models was created which underwent external validation on a large drug database using random sampling. Finally, case studies of molecules exhibiting high scores underwent bibliographic validation showcasing that good performance in the ensemble model can indicate connection with OCD pathophysiology, suggesting that it can be used to screen molecule databases for drug-repurposing purposes.</p>","PeriodicalId":7732,"journal":{"name":"AIMS Neuroscience","volume":null,"pages":null},"PeriodicalIF":3.1000,"publicationDate":"2024-06-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11230860/pdf/","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"AIMS Neuroscience","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.3934/Neuroscience.2024013","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"2024/1/1 0:00:00","PubModel":"eCollection","JCR":"Q2","JCRName":"NEUROSCIENCES","Score":null,"Total":0}
引用次数: 0
Abstract
Obsessive-compulsive disorder (OCD) is a chronic psychiatric disease in which patients suffer from obsessions compelling them to engage in specific rituals as a temporary measure to alleviate stress. In this study, deep learning-based methods were used to build three models which predict the likelihood of a molecule interacting with three biological targets relevant to OCD, SERT, D2, and NMDA. Then, an ensemble model based on those models was created which underwent external validation on a large drug database using random sampling. Finally, case studies of molecules exhibiting high scores underwent bibliographic validation showcasing that good performance in the ensemble model can indicate connection with OCD pathophysiology, suggesting that it can be used to screen molecule databases for drug-repurposing purposes.
期刊介绍:
AIMS Neuroscience is an international Open Access journal devoted to publishing peer-reviewed, high quality, original papers from all areas in the field of neuroscience. The primary focus is to provide a forum in which to expedite the speed with which theoretical neuroscience progresses toward generating testable hypotheses. In the presence of current and developing technology that offers unprecedented access to functions of the nervous system at all levels, the journal is designed to serve the role of providing the widest variety of the best theoretical views leading to suggested studies. Single blind peer review is provided for all articles and commentaries.