Grappa -- A Machine Learned Molecular Mechanics Force Field
- URL: http://arxiv.org/abs/2404.00050v2
- Date: Thu, 1 Aug 2024 16:14:27 GMT
- Title: Grappa -- A Machine Learned Molecular Mechanics Force Field
- Authors: Leif Seute, Eric Hartmann, Jan Stühmer, Frauke Gräter,
- Abstract summary: Grappa is a machine learning framework to predict molecular parameters from the molecular graph.
It predicts energies and forces of small molecules, peptides, RNA and radicals at state-of-the-art molecular mechanics accuracy.
Our force field sets the stage for biomolecular simulations closer to chemical accuracy, but with the same computational cost as established protein force fields.
- Score: 1.3499500088995464
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: Simulating large molecular systems over long timescales requires force fields that are both accurate and efficient. In recent years, E(3) equivariant neural networks have lifted the tension between computational efficiency and accuracy of force fields, but they are still several orders of magnitude more expensive than established molecular mechanics (MM) force fields. Here, we propose Grappa, a machine learning framework to predict MM parameters from the molecular graph, employing a graph attentional neural network and a transformer with symmetry-preserving positional encoding. The resulting Grappa force field outperformstabulated and machine-learned MM force fields in terms of accuracy at the same computational efficiency and can be used in existing Molecular Dynamics (MD) engines like GROMACS and OpenMM. It predicts energies and forces of small molecules, peptides, RNA and - showcasing its extensibility to uncharted regions of chemical space - radicals at state-of-the-art MM accuracy. We demonstrate Grappa's transferability to macromolecules in MD simulations from a small fast folding protein up to a whole virus particle. Our force field sets the stage for biomolecular simulations closer to chemical accuracy, but with the same computational cost as established protein force fields.
Related papers
- On the design space between molecular mechanics and machine learning force fields [25.315758265685293]
Machine learning force fields (MLFFs) represent a meaningful endeavor towards this direction.
We argue that the utility of the MLFF models is no longer bottlenecked by accuracy but primarily by their speed.
We discuss the desired properties and challenges now faced by the force field development community.
arXiv Detail & Related papers (2024-09-03T14:21:46Z) - Machine-learned molecular mechanics force field for the simulation of
protein-ligand systems and beyond [33.54862439531144]
Development of reliable and molecular mechanics (MM) force fields is indispensable for biomolecular simulation and computer-aided drug design.
We introduce a generalized and machine-learned MM force field, ttexttespaloma-0.3, and an end-to-end differentiable framework using graph neural networks.
The force field reproduces quantum chemical energetic properties of chemical domains highly relevant to drug discovery, including small molecules, peptides, and nucleic acids.
arXiv Detail & Related papers (2023-07-13T23:00:22Z) - QH9: A Quantum Hamiltonian Prediction Benchmark for QM9 Molecules [69.25826391912368]
We generate a new Quantum Hamiltonian dataset, named as QH9, to provide precise Hamiltonian matrices for 999 or 2998 molecular dynamics trajectories.
We show that current machine learning models have the capacity to predict Hamiltonian matrices for arbitrary molecules.
arXiv Detail & Related papers (2023-06-15T23:39:07Z) - Towards Predicting Equilibrium Distributions for Molecular Systems with
Deep Learning [60.02391969049972]
We introduce a novel deep learning framework, called Distributional Graphormer (DiG), in an attempt to predict the equilibrium distribution of molecular systems.
DiG employs deep neural networks to transform a simple distribution towards the equilibrium distribution, conditioned on a descriptor of a molecular system.
arXiv Detail & Related papers (2023-06-08T17:12:08Z) - Statistically Optimal Force Aggregation for Coarse-Graining Molecular
Dynamics [55.41644538483948]
coarse-grained (CG) models have the potential to simulate large molecular complexes beyond what is possible with atomistic molecular dynamics.
A widely used methodology for learning CG force-fields maps forces from all-atom molecular dynamics to the CG representation and matches them with a CG force-field on average.
We show that there is flexibility in how to map all-atom forces to the CG representation, and that the most commonly used mapping methods are statistically inefficient and potentially even incorrect in the presence of constraints in the all-atom simulation.
arXiv Detail & Related papers (2023-02-14T14:35:39Z) - Molecular Geometry-aware Transformer for accurate 3D Atomic System
modeling [51.83761266429285]
We propose a novel Transformer architecture that takes nodes (atoms) and edges (bonds and nonbonding atom pairs) as inputs and models the interactions among them.
Moleformer achieves state-of-the-art on the initial state to relaxed energy prediction of OC20 and is very competitive in QM9 on predicting quantum chemical properties.
arXiv Detail & Related papers (2023-02-02T03:49:57Z) - Accurate Machine Learned Quantum-Mechanical Force Fields for
Biomolecular Simulations [51.68332623405432]
Molecular dynamics (MD) simulations allow atomistic insights into chemical and biological processes.
Recently, machine learned force fields (MLFFs) emerged as an alternative means to execute MD simulations.
This work proposes a general approach to constructing accurate MLFFs for large-scale molecular simulations.
arXiv Detail & Related papers (2022-05-17T13:08:28Z) - Chemical-Reaction-Aware Molecule Representation Learning [88.79052749877334]
We propose using chemical reactions to assist learning molecule representation.
Our approach is proven effective to 1) keep the embedding space well-organized and 2) improve the generalization ability of molecule embeddings.
Experimental results demonstrate that our method achieves state-of-the-art performance in a variety of downstream tasks.
arXiv Detail & Related papers (2021-09-21T00:08:43Z) - Symmetry-adapted graph neural networks for constructing molecular
dynamics force fields [10.820190246285122]
We develop a symmetry-adapted graph neural networks framework to construct force fields automatically for molecular dynamics simulations.
We show that MDGNN accurately reproduces the results of both classical and first-principles molecular dynamics.
arXiv Detail & Related papers (2021-01-08T09:32:24Z) - End-to-End Differentiable Molecular Mechanics Force Field Construction [0.5269923665485903]
We propose an alternative approach that uses graph neural networks to perceive chemical environments.
The entire process is modular and end-to-end differentiable with respect to model parameters.
We show that this approach is not only sufficiently to reproduce legacy atom types, but that it can learn to accurately reproduce and extend existing molecular mechanics force fields.
arXiv Detail & Related papers (2020-10-02T20:59:46Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.