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.

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

A carboxylate switch point controls long-range energy transduction in respiratory Complex I.

Nature communications·2026

Same author

Enzyme-Free Phosphorylation with Kinetic Gating in a De Novo Coiled-Coil System.

Journal of the American Chemical Society·2026

Same author

Molecular Principles of Gating Proton Transport in the Antiporter Modules of Respiratory Complex I.

Journal of the American Chemical Society·2026

Same author

Low-barrier hydrogen bond powers long-range radical transfer in the metal-free ribonucleotide reductase.

Proceedings of the National Academy of Sciences of the United States of America·2026

Same author

Quinones operate as proton-collecting antennas in energy-transducing membranes.

Proceedings of the National Academy of Sciences of the United States of America·2026

Same author

The <i>Mycobacterium smegmatis bd</i>-II terminal oxidase employs a carboxylate shift mechanism.

Proceedings of the National Academy of Sciences of the United States of America·2026

Same journal

Improving PCM in Protic Media: Markov State Models for TD-DFT Calculations.

Journal of chemical theory and computation·2026

Same journal

Efficient Coupled-Cluster Python Frameworks for Next-Generation GPUs: A Comparative Study of CuPy and PyTorch on the Hopper and Grace Hopper Architecture.

Journal of chemical theory and computation·2026

Same journal

Extending the MARTINI 3 Coarse-Grained Force Field to Polypeptoids.

Journal of chemical theory and computation·2026

Same journal

Statistical Mechanics of Density- and Temperature-Dependent Potentials: Application to Condensed Phases within GenDPDE.

Journal of chemical theory and computation·2026

Same journal

BFEE-Docking: A User-Friendly and Customizable End-to-End Tool from High-Throughput Virtual Screening to Binding Free-Energy Calculations.

Journal of chemical theory and computation·2026

Same journal

On-the-Fly Trajectory Simulation of Two-Pulse, Three-Pulse, and Higher-Order Pump-Probe Signals.

Journal of chemical theory and computation·2026

See all related articles

Search research articles

Related Experiment Video

Updated: Aug 5, 2025

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

Effective Molecular Dynamics from Neural Network-Based Structure Prediction Models.

Alexander Jussupow¹, Ville R I Kaila¹

¹Department of Biochemistry and Biophysics, Stockholm University, 10691 Stockholm, Sweden.

Journal of Chemical Theory and Computation

|March 24, 2023

Summary

This summary is machine-generated.

Recent advances in neural networks like AlphaFold2 improve protein structure prediction. Their confidence scores correlate with protein dynamics, enabling accurate molecular dynamics simulations using the new AF-ENM method.

More Related Videos

3D Modeling of Dendritic Spines with Synaptic Plasticity

3D Modeling of Dendritic Spines with Synaptic Plasticity

Published on: May 18, 2020

Incorporating Target Protein Structure Flexibility and Dynamics in Computational Drug Discovery Using Ensemble-Based Docking Analysis

Incorporating Target Protein Structure Flexibility and Dynamics in Computational Drug Discovery Using Ensemble-Based Docking Analysis

Published on: June 20, 2025

Related Experiment Videos

Last Updated: Aug 5, 2025

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

3D Modeling of Dendritic Spines with Synaptic Plasticity

3D Modeling of Dendritic Spines with Synaptic Plasticity

Published on: May 18, 2020

Incorporating Target Protein Structure Flexibility and Dynamics in Computational Drug Discovery Using Ensemble-Based Docking Analysis

Incorporating Target Protein Structure Flexibility and Dynamics in Computational Drug Discovery Using Ensemble-Based Docking Analysis

Published on: June 20, 2025

Area of Science:

Computational biology
Structural bioinformatics
Biophysics

Background:

Neural network models like AlphaFold2 and RoseTTAFold have advanced computational protein structure prediction.
These models offer confidence scores to estimate prediction uncertainties.
The relationship between these scores and intrinsic protein dynamics is not well understood.

Purpose of the Study:

To investigate the correlation between AlphaFold2 prediction scores and protein conformational dynamics.
To develop and validate a new method for deriving protein dynamics from neural network predictions.

Main Methods:

Comparison of AlphaFold2 prediction scores with large-scale molecular dynamics simulations for 28 proteins.
Development of an elastic network model (AF-ENM) based on AlphaFold2 scores.
Benchmarking AF-ENM with coarse-grained molecular dynamics simulations.

Main Results:

A strong correlation was observed between AlphaFold2 statistical scores and protein motion from molecular dynamics simulations.
The developed AF-ENM method accurately reproduced global protein dynamics.
AF-ENM combined with coarse-grained simulations provided improved accuracy.

Conclusions:

AlphaFold2 confidence scores reflect intrinsic protein dynamics.
The AF-ENM method offers a powerful approach to derive effective molecular dynamics from neural network structure predictions.
This integration enhances the utility of AI in predicting protein behavior.