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

You might also read

Related Articles

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

Sort by
Same author

Special Topics: Developments of Theoretical and Computational Chemistry Methods in Asia.

Journal of chemical theory and computation·2026
Same author

MAHLER: Integrating Metadynamics and Inverse Folding to Predict Antibody-Antigen Kinetics.

bioRxiv : the preprint server for biology·2026
Same author

Detecting and quantifying overparametrization in RNA language models with REDIAL.

bioRxiv : the preprint server for biology·2026
Same author

Advancing Reproducibility and Open Data in Theoretical and Computational Chemistry.

Journal of chemical theory and computation·2026
Same author

Machine learning for biomolecular modeling.

The Journal of chemical physics·2026
Same author

Machine Learning Driven Advances in Molecular Dynamics of Bulk and Interfacial Aqueous Systems.

Chemical reviews·2026

Related Experiment Video

Updated: Jun 22, 2025

Author Spotlight: Advancing Alzheimer's Research – Exploring Early Detection and Multi-Omics Approaches
09:47

Author Spotlight: Advancing Alzheimer's Research – Exploring Early Detection and Multi-Omics Approaches

Published on: December 15, 2023

1.0K

Augmenting Human Expertise in Weighted Ensemble Simulations through Deep Learning based Information Bottleneck.

Dedi Wang1, Pratyush Tiwary2,3

  • 1Biophysics Program and Institute for Physical Science and Technology, University of Maryland, College Park 20742, USA.

Arxiv
|July 1, 2024
PubMed
Summary
This summary is machine-generated.

This study introduces a hybrid approach combining data-driven collective variables (CVs) with expert knowledge to improve enhanced sampling simulations. This method refines the weighted ensemble (WE) technique for more efficient and interpretable molecular dynamics simulations.

More Related Videos

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications
03:31

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Published on: December 15, 2023

515
Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness
03:14

Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness

Published on: December 6, 2024

543

Related Experiment Videos

Last Updated: Jun 22, 2025

Author Spotlight: Advancing Alzheimer's Research – Exploring Early Detection and Multi-Omics Approaches
09:47

Author Spotlight: Advancing Alzheimer's Research – Exploring Early Detection and Multi-Omics Approaches

Published on: December 15, 2023

1.0K
Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications
03:31

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Published on: December 15, 2023

515
Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness
03:14

Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness

Published on: December 6, 2024

543

Area of Science:

  • Computational Chemistry
  • Molecular Dynamics Simulations
  • Enhanced Sampling Techniques

Background:

  • The weighted ensemble (WE) method is a powerful simulation technique for studying molecular kinetics.
  • Effective WE simulations rely heavily on the choice of collective variables (CVs) and binning strategies.
  • The State Predictive Information Bottleneck (SPIB) method offers automated CV construction for enhanced sampling.

Purpose of the Study:

  • To develop a hybrid approach integrating data-driven and expert-guided CVs for WE simulations.
  • To enhance the efficiency and accuracy of enhanced sampling by combining SPIB and expert knowledge.
  • To improve the analysis and interpretation of WE simulation data.

Main Methods:

  • Incorporation of expert knowledge into the data-driven SPIB pipeline.
  • Hybrid CV construction combining SPIB-learned and expert-defined variables.
  • Benchmarking on alanine dipeptide and chignoin systems using the hybrid approach.

Main Results:

  • The hybrid approach effectively guides WE simulations towards states of interest.
  • Reduced run-to-run variances were observed with the hybrid method.
  • Enhanced identification of metastable states, pathways, and direct visualization of dynamics.

Conclusions:

  • The hybrid approach synergizes data-driven and expert knowledge for superior WE simulations.
  • This method improves sampling efficiency, reduces variance, and aids in data interpretation.
  • The integrated SPIB model facilitates a deeper understanding of molecular dynamics.