Predicting molecular docking of per- and polyfluoroalkyl substances to blood protein using generative artificial intelligence algorithm DiffDock

• Published in: BioTechniques Vol. 76; no. 1; pp. 14 - 26
• Main Authors: B Fortela, Dhan Lord, Mikolajczyk, Ashley P, Carnes, Miranda R, Sharp, Wayne, Revellame, Emmanuel, Hernandez, Rafael, Holmes, William E, Zappi, Mark E
• Format: Journal Article
• Language: English
• Published: England Future Science Ltd 01.01.2024; Taylor & Francis Group
• Subjects: Algorithms; Artificial Intelligence; Blood Proteins; Fluorocarbons; generative artificial intelligence; human health; Humans; molecular docking; Molecular Docking Simulation; per- and polyfluoroalkyl substances; target-based screening; molecular docking; per- and polyfluoroalkyl substances; blood proteins; generative artificial intelligence; human health; target-based screening
• ISSN: 0736-6205; 1940-9818; 1940-9818
• DOI: 10.2144/btn-2023-0070

This study computationally evaluates the molecular docking affinity of various perfluoroalkyl and polyfluoroalkyl substances (PFAs) towards blood proteins using a generative machine-learning algorithm, DiffDock, specialized in protein–ligand blind-docking learning and prediction. Concerns about the chemical pathways and accumulation of PFAs in the environment and eventually in the human body has been rising due to empirical findings that levels of PFAs in human blood has been rising. DiffDock may offer a fast approach in determining the fate and potential molecular pathways of PFAs in human body. This study demonstrates the capability of generative AI algorithm DiffDock to accelerate protein PFA molecular docking computations that can lead to efficient studies of PFA fate in the human body.