An Extendible, Graph-Neural-Network-Based Approach for Accurate Force
Field Development of Large Flexible Organic Molecules
- URL: http://arxiv.org/abs/2106.00927v1
- Date: Wed, 2 Jun 2021 04:12:54 GMT
- Title: An Extendible, Graph-Neural-Network-Based Approach for Accurate Force
Field Development of Large Flexible Organic Molecules
- Authors: Xufei Wang, Yuanda Xu, Han Zheng, Kuang Yu
- Abstract summary: We develop an extendible ab initio force field for large flexible organic molecules at CW level of accuracy.
Tests on polyethylene glycol polymer chains show that our strategy is highly accurate and robust for molecules of different sizes.
- Score: 4.456834955307613
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: An accurate force field is the key to the success of all molecular mechanics
simulations on organic polymers and biomolecules. Accuracy beyond density
functional theory is often needed to describe the intermolecular interactions,
while most correlated wavefunction (CW) methods are prohibitively expensive for
large molecules. Therefore, it posts a great challenge to develop an extendible
ab initio force field for large flexible organic molecules at CW level of
accuracy. In this work, we face this challenge by combining the physics-driven
nonbonding potential with a data-driven subgraph neural network bonding model
(named sGNN). Tests on polyethylene glycol polymer chains show that our
strategy is highly accurate and robust for molecules of different sizes.
Therefore, we can develop the force field from small molecular fragments (with
sizes easily accessible to CW methods) and safely transfer it to large
polymers, thus opening a new path to the next-generation organic force fields.
Related papers
- UniIF: Unified Molecule Inverse Folding [67.60267592514381]
We propose a unified model UniIF for inverse folding of all molecules.
Our proposed method surpasses state-of-the-art methods on all tasks.
arXiv Detail & Related papers (2024-05-29T10:26:16Z) - 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) - 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) - MUDiff: Unified Diffusion for Complete Molecule Generation [104.7021929437504]
We present a new model for generating a comprehensive representation of molecules, including atom features, 2D discrete molecule structures, and 3D continuous molecule coordinates.
We propose a novel graph transformer architecture to denoise the diffusion process.
Our model is a promising approach for designing stable and diverse molecules and can be applied to a wide range of tasks in molecular modeling.
arXiv Detail & Related papers (2023-04-28T04:25:57Z) - Engineering long-range molecular potentials by external drive [0.0]
We report the engineering of molecular potentials at large interatomic distances.
The molecular states are generated by off-resonant optical coupling to a highly excited, long-range Rydberg molecular potential.
Our results open numerous possibilities to create long-range molecules between ultracold ground state atoms.
arXiv Detail & Related papers (2023-03-14T09:01:19Z) - 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) - 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) - Scalable Fragment-Based 3D Molecular Design with Reinforcement Learning [68.8204255655161]
We introduce a novel framework for scalable 3D design that uses a hierarchical agent to build molecules.
In a variety of experiments, we show that our agent, guided only by energy considerations, can efficiently learn to produce molecules with over 100 atoms.
arXiv Detail & Related papers (2022-02-01T18:54:24Z) - 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) - Coarse Graining Molecular Dynamics with Graph Neural Networks [3.0279361008741827]
We introduce a hybrid architecture for the machine learning of coarse-grained force fields that learns their own features via a subnetwork.
We demonstrate that this framework succeeds at reproducing the thermodynamics for small biomolecular systems.
arXiv Detail & Related papers (2020-07-22T13:20:08Z) - Self-Supervised Graph Transformer on Large-Scale Molecular Data [73.3448373618865]
We propose a novel framework, GROVER, for molecular representation learning.
GROVER can learn rich structural and semantic information of molecules from enormous unlabelled molecular data.
We pre-train GROVER with 100 million parameters on 10 million unlabelled molecules -- the biggest GNN and the largest training dataset in molecular representation learning.
arXiv Detail & Related papers (2020-06-18T08:37:04Z)
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.