Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

Related Concept Videos

Molecular Models

Molecular Models

Physical models representing molecular architectures of chemical compounds play essential roles in understanding chemistry. The use of molecular models makes it easier to visualize the structures and shapes of atoms and molecules.

Neural Circuits

Neural Circuits

Neural circuits and neuronal pools are two of the main structures found in the nervous system. Neural circuits are networks of neurons that work together to carry out a specific task or process. They consist of interconnected neurons and glial cells, which provide structural and metabolic support.
Neuronal pools are collections of nerve cells with similar functions and interact through chemical and electrical signals. These pools include both interneurons (the central neural circuit nodes that...

Predicting Molecular Geometry

Predicting Molecular Geometry

VSEPR Theory for Determination of Electron Pair Geometries

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by

Same author

Molecular mechanisms and biotechnology applications of CRISPR-Cas12a.

Nature reviews. Molecular cell biology·2026

Same author

Advancing Reproducibility and Open Data in Theoretical and Computational Chemistry.

Journal of chemical theory and computation·2026

Same author

Orthosteric and allosteric effects of anti-CRISPR II-C1 inhibition on <i>Geo</i> Cas9 from integrated structural biophysics.

bioRxiv : the preprint server for biology·2026

Same author

Deep learning and cryogenic electron microscopy modeling for gene editing dynamics.

Current opinion in structural biology·2026

Same author

Computation and deep-learning-driven advances in CRISPR genome editing.

Nature structural & molecular biology·2026

Same author

Design Rules for Expanding PAM Compatibility in CRISPR-Cas9 from the VQR, VRER and EQR variants.

The journal of physical chemistry. B·2025

Same journal

Metabolic disruptions through a three-dimensional genomic lens.

Current opinion in structural biology·2026

Same journal

Collective variable design for biomolecular conformational dynamics.

Current opinion in structural biology·2026

Same journal

Polymer scaling in protein crowding: From dilute coils to semidilute meshes.

Current opinion in structural biology·2026

Same journal

Tuning the physicochemical properties of rationally designed protein-based biomolecular condensates.

Current opinion in structural biology·2026

Same journal

Editorial overview: Folding, binding and protein design.

Current opinion in structural biology·2026

Same journal

Macromolecular crowding reshapes the conformational landscapes of intrinsically disordered proteins: mechanisms, cellular contexts, and functional consequences.

Current opinion in structural biology·2026

See all related articles

Search research articles

Home
Graph Neural Networks For Molecular Dynamics Simulations.

Home
Graph Neural Networks For Molecular Dynamics Simulations.

Related Experiment Video

Structure-Based Simulation and Sampling of Transcription Factor Protein Movements along DNA from Atomic-Scale Stepping to Coarse-Grained Diffusion

Structure-Based Simulation and Sampling of Transcription Factor Protein Movements along DNA from Atomic-Scale Stepping to Coarse-Grained Diffusion

Published on: March 1, 2022

Graph neural networks for molecular dynamics simulations.

Mohd Ahsan¹, Chinmai Pindi¹, Souvik Sinha¹

¹Department of Bioengineering, University of California Riverside, 900 University Avenue, Riverside, CA 52512, United States.

Current Opinion in Structural Biology

|February 26, 2026

View abstract on PubMed

Summary

This summary is machine-generated.

Graph neural networks (GNNs) enhance molecular dynamics (MD) simulations by using data-driven approaches. These networks improve accuracy, enable faster simulations, and aid in analyzing complex biomolecular data.

More Related Videos

Author Spotlight: Streamlining Visual Dynamics to Simplify Molecular Dynamics Simulations Using Gromacs

Author Spotlight: Streamlining Visual Dynamics to Simplify Molecular Dynamics Simulations Using Gromacs

Published on: August 9, 2024

Novel 3D/VR Interactive Environment for MD Simulations, Visualization and Analysis

Novel 3D/VR Interactive Environment for MD Simulations, Visualization and Analysis

Published on: December 18, 2014

Related Experiment Videos

Structure-Based Simulation and Sampling of Transcription Factor Protein Movements along DNA from Atomic-Scale Stepping to Coarse-Grained Diffusion

Structure-Based Simulation and Sampling of Transcription Factor Protein Movements along DNA from Atomic-Scale Stepping to Coarse-Grained Diffusion

Published on: March 1, 2022

Author Spotlight: Streamlining Visual Dynamics to Simplify Molecular Dynamics Simulations Using Gromacs

Author Spotlight: Streamlining Visual Dynamics to Simplify Molecular Dynamics Simulations Using Gromacs

Published on: August 9, 2024

Novel 3D/VR Interactive Environment for MD Simulations, Visualization and Analysis

Novel 3D/VR Interactive Environment for MD Simulations, Visualization and Analysis

Published on: December 18, 2014

Area of Science:

Computational chemistry
Biophysics
Machine learning

Background:

Molecular dynamics (MD) simulations are crucial for understanding biomolecular systems.
Traditional physics-based MD methods face limitations in accuracy and timescale.
Data-driven approaches offer complementary strategies to enhance MD simulations.

Purpose of the Study:

To explore the application of Graph Neural Networks (GNNs) in advancing molecular dynamics (MD) simulations.
To highlight how GNNs can integrate chemical and structural information for improved accuracy.
To showcase GNNs' potential in accelerating biomolecular discovery.

Main Methods:

Representing atoms and their interactions as graphs for GNN input.
Training neural network force fields on quantum mechanical data.

Utilizing GNNs for predicting atomic forces and discovering collective variables.

Applying attention mechanisms and transferable embeddings for trajectory analysis.

Main Results:

GNNs enable accurate neural network force fields and efficient prediction of atomic forces.
Automated discovery of collective variables facilitates enhanced sampling in simulations.
GNNs provide interpretable insights into high-dimensional molecular trajectories.
Successful applications demonstrated in protein-DNA assembly and cryptic pocket discovery.

Conclusions:

Graph neural networks (GNNs) represent a powerful, data-driven paradigm for molecular dynamics (MD) simulations.
GNNs significantly enhance the accuracy, efficiency, and analytical capabilities of MD.
The integration of GNNs promises to accelerate mechanistic and translational discoveries in biomolecular sciences.