AMARO: All heavy-atom transferable neural network potentials of protein thermodynamics

Mirarchi, AntonioPeláez, Raúl P.Simeon, GuillemDe Fabritiis, Gianni2025-01-142025-01-142024Mirarchi A, Peláez RP, Simeon G, De Fabritiis G. AMARO: All heavy-atom transferable neural network potentials of protein thermodynamics. J Chem Theory Comput. 2024 Nov 26;20(22):9871-8. DOI: 10.1021/acs.jctc.4c012391549-9618http://hdl.handle.net/10230/69120All-atom molecular simulations offer detailed insights into macromolecular phenomena, but their substantial computational cost hinders the exploration of complex biological processes. We introduce Advanced Machine-learning Atomic Representation Omni-force-field (AMARO), a new neural network potential (NNP) that combines an O(3)-equivariant message-passing neural network architecture, TensorNet, with a coarse-graining map that excludes hydrogen atoms. AMARO demonstrates the feasibility of training coarser NNP, without prior energy terms, to run stable protein dynamics with scalability and generalization capabilities.application/pdfengCopyright © 2024 American Chemical Society. This publication is licensed under CC-BY 4.0 (https://creativecommons.org/licenses/by/4.0/).AMARO: All heavy-atom transferable neural network potentials of protein thermodynamicsinfo:eu-repo/semantics/articlehttp://dx.doi.org/10.1021/acs.jctc.4c01239ConformationEnergyFree energyHydrogenMolecular dynamics simulationsinfo:eu-repo/semantics/openAccess