Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Concept Videos

The Equilibrium Binding Constant and Binding Strength02:18

The Equilibrium Binding Constant and Binding Strength

13.4K
The equilibrium binding constant (Kb) quantifies the strength of a protein-ligand interaction. Kb can be calculated as follows when the reaction is at equilibrium:
13.4K
Conserved Binding Sites01:49

Conserved Binding Sites

4.3K
Many proteins’ biological role depends on their interactions with their ligands, small molecules that bind to specific locations on the protein known as ligand-binding sites. Ligand-binding sites are often conserved among homologous proteins as these sites are critical for protein function.
Binding sites are often located in large pockets, and if their location on a protein’s surface is unknown, it can be predicted using various approaches. The energetic method computationally...
4.3K
Multimachine Stability01:25

Multimachine Stability

227
Multimachine stability analysis is crucial for understanding the dynamics and stability of power systems with multiple synchronous machines. The objective is to solve the swing equations for a network of M machines connected to an N-bus power system.
In analyzing the system, the nodal equations represent the relationship between bus voltages, machine voltages, and machine currents. The nodal equation is given by:
227
Molecular Models02:00

Molecular Models

40.4K
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.
40.4K
Mechanistic Models: Compartment Models in Algorithms for Numerical Problem Solving01:29

Mechanistic Models: Compartment Models in Algorithms for Numerical Problem Solving

100
Mechanistic models play a crucial role in algorithms for numerical problem-solving, particularly in nonlinear mixed effects modeling (NMEM). These models aim to minimize specific objective functions by evaluating various parameter estimates, leading to the development of systematic algorithms. In some cases, linearization techniques approximate the model using linear equations.
In individual population analyses, different algorithms are employed, such as Cauchy's method, which uses a...
100

You might also read

Related Articles

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

Sort by
Same author

Boltz-ABFE: Free Energy Perturbation without Crystal Structures.

Journal of chemical theory and computation·2026
Same author

AQuaRef: machine learning accelerated quantum refinement of protein structures.

Nature communications·2025
Same author

Optimizing Absolute Binding Free Energy Calculations for Production Usage.

Journal of chemical theory and computation·2025
Same author

Evaluation of Machine Learning/Molecular Mechanics End-State Corrections with Mechanical Embedding to Calculate Relative Protein-Ligand Binding Free Energies.

Journal of chemical theory and computation·2025
Same author

Understanding the Catalytic Efficiency of Two Polyester Degrading Enzymes: An Experimental and Theoretical Investigation.

ACS omega·2024
Same author

AQuaRef: Machine learning accelerated quantum refinement of protein structures.

bioRxiv : the preprint server for biology·2024

Related Experiment Video

Updated: Sep 10, 2025

Incorporating Target Protein Structure Flexibility and Dynamics in Computational Drug Discovery Using Ensemble-Based Docking Analysis
08:49

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

Published on: June 20, 2025

521

Basic Stability Tests of Machine Learning Potentials for Molecular Simulations in Computational Drug Discovery.

Kavindri Ranasinghe1,2, Adam L Baskerville2, Geoffrey P F Wood1,2

  • 1Recursion, Schrödinger Building, Oxford Science Park, Oxford OX4 4GE, U.K.

Journal of Chemical Information and Modeling
|August 27, 2025
PubMed
Summary

Neural network potentials offer fast molecular simulations but require careful testing. This study evaluates various models, finding significant differences in stability and accuracy, highlighting the need for rigorous selection in applications.

More Related Videos

Author Spotlight: Streamlining Protein Target Prediction and Validation via Molecular Docking and CETSA
10:21

Author Spotlight: Streamlining Protein Target Prediction and Validation via Molecular Docking and CETSA

Published on: February 23, 2024

2.9K
Quantitative Structure-Activity Relationship, Activity Prediction, and Molecular Dynamics of Non-nucleotide Reverse Transcriptase Inhibitors
10:29

Quantitative Structure-Activity Relationship, Activity Prediction, and Molecular Dynamics of Non-nucleotide Reverse Transcriptase Inhibitors

Published on: May 9, 2025

1.5K

Related Experiment Videos

Last Updated: Sep 10, 2025

Incorporating Target Protein Structure Flexibility and Dynamics in Computational Drug Discovery Using Ensemble-Based Docking Analysis
08:49

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

Published on: June 20, 2025

521
Author Spotlight: Streamlining Protein Target Prediction and Validation via Molecular Docking and CETSA
10:21

Author Spotlight: Streamlining Protein Target Prediction and Validation via Molecular Docking and CETSA

Published on: February 23, 2024

2.9K
Quantitative Structure-Activity Relationship, Activity Prediction, and Molecular Dynamics of Non-nucleotide Reverse Transcriptase Inhibitors
10:29

Quantitative Structure-Activity Relationship, Activity Prediction, and Molecular Dynamics of Non-nucleotide Reverse Transcriptase Inhibitors

Published on: May 9, 2025

1.5K

Area of Science:

  • Computational chemistry
  • Materials science
  • Machine learning

Background:

  • Neural network potentials (NNPs) trained on quantum-mechanical data provide efficient molecular interaction calculations.
  • However, NNPs can exhibit instabilities, nonphysical behavior, or insufficient accuracy, limiting their use in molecular simulations.

Purpose of the Study:

  • To systematically assess the reliability and performance of various neural network potentials (NNPs) for molecular simulations.
  • To evaluate the impact of model architecture on NNP performance using a consistent testing framework.

Main Methods:

  • Conducted gas and condensed phase stability tests on eight in-house NNPs (ANI-2x and MACE architectures) and four public NNPs (ANI-2x, ANI-1ccx, MACE-OFF23, AIMNet2).
  • Performed normal-mode analysis on benchmark molecules and molecular dynamics simulations to identify instabilities and nonphysical behavior.
  • Evaluated protein-ligand interaction energies and compared results with experimental binding affinities and other computational methods.

Main Results:

  • Significant variations in model performance were observed; some MACE models showed instabilities during simulations and steric clashes.
  • Published ANI-2x and one in-house MACE model failed to accurately represent liquid water, forming solid phases.
  • ANI-1ccx exhibited nonphysical energy minima in condensed water, leading to phase transitions.
  • One in-house NNP demonstrated superior agreement with experimental water structure compared to standard models.
  • Most NNPs showed better correlation with experimental binding affinities than docking scores, with ANI-2x approaching DFT accuracy.

Conclusions:

  • No single NNP is universally suitable; model architecture and training data significantly influence performance.
  • Rigorous testing across different phases and conditions is crucial for selecting reliable NNPs.
  • Careful consideration during NNP training and selection is essential for successful real-world applications.