{"id":131431,"date":"2022-09-22T15:24:58","date_gmt":"2022-09-22T19:24:58","guid":{"rendered":"https:\/\/www.ucf.edu\/news\/?p=131431"},"modified":"2024-02-02T11:01:48","modified_gmt":"2024-02-02T16:01:48","slug":"ai-based-screening-method-could-boost-speed-of-new-drug-discovery","status":"publish","type":"post","link":"https:\/\/www.ucf.edu\/news\/ai-based-screening-method-could-boost-speed-of-new-drug-discovery\/","title":{"rendered":"AI-based Screening Method Could Boost Speed of New Drug Discovery"},"content":{"rendered":"
Developing life-saving medicines can take billions of dollars and decades of time, but University of Central Florida researchers are aiming to speed up this process with a new artificial intelligence-based drug screening process they\u2019ve developed.<\/p>\n
Using a method that models drug and target protein interactions using natural language processing techniques, the researchers achieved up to 97% accuracy in identifying promising drug candidates. The results were published recently in the journal Briefings in Bioinformatics<\/em>.<\/p>\n The technique represents drug\u2013protein interactions through words for each protein binding site and uses deep learning to extract the features that govern the complex interactions between the two.<\/p>\n \u201cWith AI becoming more available, this has become something that AI can tackle,\u201d says study co-author Ozlem Garibay, an assistant professor in UCF\u2019s Department of Industrial Engineering and Management Systems. \u201cYou can try out so many variations of proteins and drug interactions and find out which are more likely to bind or not.\u201d<\/p>\n The model they\u2019ve developed, known as AttentionSiteDTI, is the first to be interpretable using the language of protein binding sites.<\/p>\n The work is important because it will help drug designers identify critical protein binding sites along with their functional properties, which is key to determining if a drug will be effective.<\/p>\n The researchers made the achievement by devising a self-attention mechanism that makes the model learn which parts of the protein interact with the drug compounds, while achieving state-of-the-art prediction performance.<\/p>\n The mechanism\u2019s self-attention ability works by selectively focusing on the most relevant parts of the protein.<\/p>\n The researchers validated their model using in-lab experiments that measured binding interactions between compounds and proteins and then compared the results with the ones their model computationally predicted. As drugs to treat COVID are still of interest, the experiments also included testing and validating drug compounds that would bind to a spike protein of the SARS-CoV2 virus.<\/p>\n Garibay says the high agreement between the lab results and the computational predictions illustrates the potential of AttentionSiteDTI to pre-screen potentially effective drug compounds and accelerate the exploration of new medicines and the repurposing of existing ones.<\/p>\n \u201cThis high impact research was only possible due to interdisciplinary collaboration between materials engineering and AI\/machine learning and computer scientists to address COVID related discovery\u201d says Sudipta Seal, study co-author and chair of UCF\u2019s Department of Materials Science and Engineering.<\/p>\n