Implicit solvent approach based on generalized Born and transferable graph neural networks for molecular dynamics simulations

Katzberger, Paul; Riniker, Sereina

doi:10.1063/5.0147027

Cited by 6 publications

(20 citation statements)

References 41 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Consequently, there is a compelling need to develop more accurate and systematically improvable representations of the solvation free energy. GNNs have recently emerged as alternatives to traditional implicit solvent functional forms. , …”

Section: Resultsmentioning

confidence: 99%

“…It is worth noting that, due to the unavailability of the exact solvation free energy for each solute configuration, employing RMSE as a loss function is unfeasible. Additionally, while force matching has been used to train GNNs as implicit solvent models, pre-existing data can only be used if it is possible to extract the forces exerted on the solute atoms by the solvent. , Without forces or exact solvation free energies available to fit, the training process transitions into an unsupervised learning problem; hence, our adoption of potential contrasting.…”

Section: Resultsmentioning

confidence: 99%

See 1 more Smart Citation

Transferable Implicit Solvation via Contrastive Learning of Graph Neural Networks

Airas,

Ding,

Zhang

2023

ACS Cent. Sci.

View full text Add to dashboard Cite

Implicit solvent models are essential for molecular dynamics simulations of biomolecules, striking a balance between computational efficiency and biological realism. Efforts are underway to develop accurate and transferable implicit solvent models and coarse-grained (CG) force fields in general, guided by a bottom-up approach that matches the CG energy function with the potential of mean force (PMF) defined by the finer system. However, practical challenges arise due to the lack of analytical expressions for the PMF and algorithmic limitations in parameterizing CG force fields. To address these challenges, a machine learning-based approach is proposed, utilizing graph neural networks (GNNs) to represent the solvation free energy and potential contrasting for parameter optimization. We demonstrate the effectiveness of the approach by deriving a transferable GNN implicit solvent model using 600,000 atomistic configurations of six proteins obtained from explicit solvent simulations. The GNN model provides solvation free energy estimations much more accurately than state-of-the-art implicit solvent models, reproducing configurational distributions of explicit solvent simulations. We also demonstrate the reasonable transferability of the GNN model outside of the training data. Our study offers valuable insights for deriving systematically improvable implicit solvent models and CG force fields from a bottom-up perspective.

show abstract

Section: Resultsmentioning

confidence: 99%

Section: Resultsmentioning

confidence: 99%

Transferable Implicit Solvation via Contrastive Learning of Graph Neural Networks

Airas,

Ding,

Zhang

2023

ACS Cent. Sci.

View full text Add to dashboard Cite

show abstract

“…Graphs can be used to represent molecules as nodes and bonds. These graph neural networks (GNNs) − can learn complex relationships between atoms in molecules, which can be used to predict molecular properties. , DL architectures such as AlphaFold have been used successfully to predict three-dimensional properties of proteins. DL accelerates quantum chemistry by predicting electronic properties.…”

Section: Machine Learning Techniquesmentioning

confidence: 99%

Molecular Simulation Meets Machine Learning

Sadus

2023

J. Chem. Eng. Data

View full text Add to dashboard Cite

Molecular simulation that encompasses both Monte Carlo and molecular dynamics methods, coupled with ever-increasing computing power, has provided very valuable insights linking the nature of intermolecular interactions directly to the macroscopic properties of materials. In contrast, machine learning can be used to predict molecular properties by finding patterns in data rather than directly evaluating molecular interactions. Suitable machine learning approaches for molecules include supervised, unsupervised, reinforcement, and deep learning, with the latter commonly using neural net algorithms. There is considerable overlap in the scope of application of the two approaches, which can be combined for maximum benefit. Careful integration of machine learning with molecular simulation also means that the hypothesis-centered approach of the latter can be both maintained and enhanced. Using machine learning with molecular simulation offers gains in computational efficiency, predictive capabilities, and generalizability. However, the black-box nature of machine learning provides challenges of interpretability and transparency. Data quality, generalizability, and peer review are also issues that require attention. Nonetheless, the combination of the two approaches offers the possibility of greatly expanded predictive capabilities.

show abstract

“…While many of them are indeed much faster than their explicit counterpart, the major drawback of these methods is that they do not describe the local solvation effects correctly. Based on recent successes of applying machine learning (ML) in the field of chemistry [8], ML-based approaches have been developed to learn the effects of a given environment (solvent) on a solute [9][10][11][12][13]. These models are either too slow and/or not sufficiently transferable between different molecules to be practically usable in MD simulations, leaving explicit solvent simulations as the only reliable solution for generating accurate conformational ensembles in solution.…”

Section: Introductionmentioning

confidence: 99%

General Graph Neural Network Based Implicit Solvation Model for Organic Molecules in Water

Katzberger,

Riniker

2024

Preprint

View full text Add to dashboard Cite

The dynamical behavior of small molecules in their environment can be studied with molecular dynamics (MD) simulations to gain deeper insight on an atomic level and thus complement and rationalize the interpretation of experimental findings. Such approaches are of great value in various areas of research, e.g., in the development of new therapeutics. The accurate description of solvation effects in such simulations is thereby key and has in consequence been an active field of research since the introduction of MD. Until today the most accurate approaches involve computationally expensive explicit solvent simulations, while widely applied models using an implicit solvent description suffer from reduced accuracy. Recently, machine learning (ML) approaches that provide a probabilistic representation of solvation effects have been proposed as potential alternatives. However, the associated computational costs and minimal or lacking transferability used to render them unusable in practice. Here, we report the first example of a transferable ML-based implicit solvent model trained on a diverse set of 3’000’000 molecular structures that can be applied to organic small molecules for simulations in water. Extensive testing against reference calculations demonstrated that the model delivers on par accuracy with explicit solvent simulations while providing up to 18-fold increase in sampling rate.

show abstract

Implicit solvent approach based on generalized Born and transferable graph neural networks for molecular dynamics simulations

Cited by 6 publications

References 41 publications

Transferable Implicit Solvation via Contrastive Learning of Graph Neural Networks

Transferable Implicit Solvation via Contrastive Learning of Graph Neural Networks

Molecular Simulation Meets Machine Learning

General Graph Neural Network Based Implicit Solvation Model for Organic Molecules in Water

Contact Info

Product

Resources

About