Universally applicable and tunable graph-based coarse-graining for Machine learning force fields

• URL: http://arxiv.org/abs/2504.01973v1
• Date: Mon, 24 Mar 2025 16:55:53 GMT
• Title: Universally applicable and tunable graph-based coarse-graining for Machine learning force fields
• Authors: Christoph Brunken, Sebastien Boyer, Mustafa Omar, Martin Maarand, Olivier Peltre, Solal Attias, Bakary N'tji Diallo, Anastasia Markina, Olaf Othersen, Oliver Bent,
• Abstract summary: We present the first transferable DL-based CG force field approach for a wide range of biosystems.<n>Our CG algorithm does not rely on hard-coded rules and is tuned to output coarse-grained systems optimised for minimal statistical noise.<n>Our force field model is also the first CG variant that is based on the MACE architecture and is trained on a custom dataset.
• Score: 2.562432568682358
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Coarse-grained (CG) force field methods for molecular systems are a crucial tool to simulate large biological macromolecules and are therefore essential for characterisations of biomolecular systems. While state-of-the-art deep learning (DL)-based models for all-atom force fields have improved immensely over recent years, we observe and analyse significant limitations of the currently available approaches for DL-based CG simulations. In this work, we present the first transferable DL-based CG force field approach (i.e., not specific to only one narrowly defined system type) applicable to a wide range of biosystems. To achieve this, our CG algorithm does not rely on hard-coded rules and is tuned to output coarse-grained systems optimised for minimal statistical noise in the ground truth CG forces, which results in significant improvement of model training. Our force field model is also the first CG variant that is based on the MACE architecture and is trained on a custom dataset created by a new approach based on the fragmentation of large biosystems covering protein, RNA and lipid chemistry. We demonstrate that our model can be applied in molecular dynamics simulations to obtain stable and qualitatively accurate trajectories for a variety of systems, while also discussing cases for which we observe limited reliability.

Related papers

• HEroBM: a deep equivariant graph neural network for universal backmapping from coarse-grained to all-atom representations [0.0]
  coarse-grained (CG) techniques have emerged as invaluable tools to sample large-scale systems. They sacrifice atomistic details that might hold significant relevance in deciphering the investigated process. A recommended approach is to identify key CG conformations and process them using backmapping methods, which retrieve atomistic coordinates. We introduce HEroBM, a dynamic and scalable method that employs deep equivariant graph neural networks and a hierarchical approach to achieve high-resolution backmapping.
  arXiv  Detail & Related papers  (2024-04-25T13:54:31Z)
• MS-MANO: Enabling Hand Pose Tracking with Biomechanical Constraints [50.61346764110482]
  We integrate a musculoskeletal system with a learnable parametric hand model, MANO, to create MS-MANO. This model emulates the dynamics of muscles and tendons to drive the skeletal system, imposing physiologically realistic constraints on the resulting torque trajectories. We also propose a simulation-in-the-loop pose refinement framework, BioPR, that refines the initial estimated pose through a multi-layer perceptron network.
  arXiv  Detail & Related papers  (2024-04-16T02:18:18Z)
• Navigating protein landscapes with a machine-learned transferable coarse-grained model [29.252004942896875]
  coarse-grained (CG) model with similar prediction performance has been a long-standing challenge. We develop a bottom-up CG force field with chemical transferability, which can be used for extrapolative molecular dynamics on new sequences. We demonstrate that the model successfully predicts folded structures, intermediates, metastable folded and unfolded basins, and the fluctuations of intrinsically disordered proteins.
  arXiv  Detail & Related papers  (2023-10-27T17:10:23Z)
• 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)
• Invertible Coarse Graining with Physics-Informed Generative Artificial Intelligence [9.343446996260328]
  Two challenges are commonly present in multiscale molecular modeling. One is to construct coarse grained models by passing information from the fine to coarse levels; the other is to restore finer molecular details given coarse grained configurations. We present a theory connecting them, and develop a methodology called Cycle Coarse Graining (CCG) to solve both problems in a unified manner.
  arXiv  Detail & Related papers  (2023-05-02T08:05:42Z)
• 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)
• Implicit Geometry and Interaction Embeddings Improve Few-Shot Molecular Property Prediction [53.06671763877109]
  We develop molecular embeddings that encode complex molecular characteristics to improve the performance of few-shot molecular property prediction. Our approach leverages large amounts of synthetic data, namely the results of molecular docking calculations. On multiple molecular property prediction benchmarks, training from the embedding space substantially improves Multi-Task, MAML, and Prototypical Network few-shot learning performance.
  arXiv  Detail & Related papers  (2023-02-04T01:32:40Z)
• Two for One: Diffusion Models and Force Fields for Coarse-Grained Molecular Dynamics [15.660348943139711]
  We leverage connections between score-based generative models, force fields and molecular dynamics to learn a CG force field without requiring any force inputs during training. While having a vastly simplified training setup compared to previous work, we demonstrate that our approach leads to improved performance across several small- to medium-sized protein simulations.
  arXiv  Detail & Related papers  (2023-02-01T17:09:46Z)
• Reinforcement Learning for Molecular Dynamics Optimization: A Stochastic Pontryagin Maximum Principle Approach [3.0077933778535706]
  We present a novel reinforcement learning framework designed to optimize molecular dynamics. Our framework focuses on the entire trajectory rather than just the final molecular configuration. Our method makes it suitable for applications in areas such as drug discovery and molecular design.
  arXiv  Detail & Related papers  (2022-12-06T20:44:24Z)
• Retrieval-based Controllable Molecule Generation [63.44583084888342]
  We propose a new retrieval-based framework for controllable molecule generation. We use a small set of molecules to steer the pre-trained generative model towards synthesizing molecules that satisfy the given design criteria. Our approach is agnostic to the choice of generative models and requires no task-specific fine-tuning.
  arXiv  Detail & Related papers  (2022-08-23T17:01:16Z)
• 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)
• Efficient Model-Based Multi-Agent Mean-Field Reinforcement Learning [89.31889875864599]
  We propose an efficient model-based reinforcement learning algorithm for learning in multi-agent systems. Our main theoretical contributions are the first general regret bounds for model-based reinforcement learning for MFC. We provide a practical parametrization of the core optimization problem.
  arXiv  Detail & Related papers  (2021-07-08T18:01:02Z)
• Ensemble Learning of Coarse-Grained Molecular Dynamics Force Fields with a Kernel Approach [2.562811344441631]
  Gradient-domain machine learning (GDML) is an accurate and efficient approach to learn a molecular potential and associated force field. We demonstrate its application to learn an effective coarse-grained (CG) model from all-atom simulation data. Using ensemble learning and stratified sampling, we propose a data-efficient and memory-saving alternative.
  arXiv  Detail & Related papers  (2020-05-04T21:20:01Z)

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.