AMARO: All Heavy-Atom Transferable Neural Network Potentials of Protein Thermodynamics

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Mirarchi, Antonio, Pelaez, Raul P., Simeon, Guillem, De Fabritiis, Gianni
Formato: Preprint
Publicado: 2024
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866913575838154752
author Mirarchi, Antonio
Pelaez, Raul P.
Simeon, Guillem
De Fabritiis, Gianni
author_facet Mirarchi, Antonio
Pelaez, Raul P.
Simeon, Guillem
De Fabritiis, Gianni
contents All-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.
format Preprint
id arxiv_https___arxiv_org_abs_2409_17852
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle AMARO: All Heavy-Atom Transferable Neural Network Potentials of Protein Thermodynamics
Mirarchi, Antonio
Pelaez, Raul P.
Simeon, Guillem
De Fabritiis, Gianni
Biomolecules
Machine Learning
Biological Physics
Computational Physics
All-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.
title AMARO: All Heavy-Atom Transferable Neural Network Potentials of Protein Thermodynamics
topic Biomolecules
Machine Learning
Biological Physics
Computational Physics
url https://arxiv.org/abs/2409.17852