Search research articles

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

A foundation model for atomistic materials chemistry.

The Journal of chemical physics·2025

Same author

Dataset exploring the atomic scale structure and ionic dynamics of polyanion sodium cathode materials.

Scientific data·2025

Same author

First-Principles Molecular Dynamics with Potential and Charge Fluctuations Applied to Au(111) in Alkaline Solutions.

Journal of chemical theory and computation·2025

Same author

Setting the standard for machine learning in phase field prediction: a benchmark dataset and baseline metrics.

Scientific data·2024

Same author

CALiSol-23: Experimental electrolyte conductivity data for various Li-salts and solvent combinations.

Scientific data·2024

Same author

Transcriptomics analysis reveals molecular alterations underpinning spaceflight dermatology.

Communications medicine·2024

Same journal

QSAR in the Browser: An Interactive Cheminformatics Web Application.

Journal of chemical information and modeling·2026

Same journal

FoldDoF: Utilizing the Primary Degrees of Freedom of Protein Backbone for Geometric Modeling and Generation.

Journal of chemical information and modeling·2026

Same journal

Derisking Affinity Optimization for Macrocycles and Cyclic Peptides: High-Precision Free Energy Simulations across Five Diverse Targets.

Journal of chemical information and modeling·2026

Same journal

An End-User Audit of Reproducibility, Data Leakage, and Overfitting of the Top-Ranked ADMET Prediction Models in TDC Leaderboards.

Journal of chemical information and modeling·2026

Same journal

PFASGroups: An Open-Source Framework for Automated Identification, Structural Classification, and Prioritization of Per- and Polyfluoroalkyl Substances.

Journal of chemical information and modeling·2026

Same journal

DeepKbhb: Context-Aware Prediction of Human Lysine β-Hydroxybutyrylation Sites.

Journal of chemical information and modeling·2026

See all related 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

Search research articles

Related Experiment Video

Updated: Jul 27, 2025

A Workflow for Lipid Nanoparticle LNP Formulation Optimization using Designed Mixture-Process Experiments and Self-Validated Ensemble Models SVEM

A Workflow for Lipid Nanoparticle LNP Formulation Optimization using Designed Mixture-Process Experiments and Self-Validated Ensemble Models SVEM

Published on: August 18, 2023

Equivariant Graph-Representation-Based Actor-Critic Reinforcement Learning for Nanoparticle Design.

Jonas Elsborg¹, Arghya Bhowmik¹

¹Department of Energy Conversion and Storage, Technical University of Denmark, 2800 Kongens Lyngby, Denmark.

Journal of Chemical Information and Modeling

|June 5, 2023

Summary

This summary is machine-generated.

We developed a reinforcement learning (RL) method for discovering low-energy nanoparticle structures, showing promise but also limitations in generalization for molecular design.

More Related Videos

A System to Create Stable Nanoparticle Aerosols from Nanopowders

A System to Create Stable Nanoparticle Aerosols from Nanopowders

Published on: July 26, 2016

A Continuous-flow Photocatalytic Reactor for the Precisely Controlled Deposition of Metallic Nanoparticles

A Continuous-flow Photocatalytic Reactor for the Precisely Controlled Deposition of Metallic Nanoparticles

Published on: April 10, 2019

Related Experiment Videos

Last Updated: Jul 27, 2025

A Workflow for Lipid Nanoparticle LNP Formulation Optimization using Designed Mixture-Process Experiments and Self-Validated Ensemble Models SVEM

A Workflow for Lipid Nanoparticle LNP Formulation Optimization using Designed Mixture-Process Experiments and Self-Validated Ensemble Models SVEM

Published on: August 18, 2023

A System to Create Stable Nanoparticle Aerosols from Nanopowders

A System to Create Stable Nanoparticle Aerosols from Nanopowders

Published on: July 26, 2016

A Continuous-flow Photocatalytic Reactor for the Precisely Controlled Deposition of Metallic Nanoparticles

A Continuous-flow Photocatalytic Reactor for the Precisely Controlled Deposition of Metallic Nanoparticles

Published on: April 10, 2019

Area of Science:

Computational Materials Science
Artificial Intelligence in Chemistry
Nanotechnology and Nanomaterials

Background:

Discovering stable, low-energy nanoparticle structures is crucial for materials science applications.
Traditional methods like basin-hopping can be computationally intensive and may not scale effectively.
Reinforcement learning (RL) offers a novel approach to explore complex chemical spaces for structure prediction.

Purpose of the Study:

To develop and evaluate an actor-critic reinforcement learning method for identifying stable nanoparticle structures.
To compare the performance of the RL agent against classical basin-hopping methods.
To investigate the agent's ability to construct stable mono- and bimetallic clusters.

Main Methods:

Developed a policy-based reinforcement learning (RL) method using an actor-critic architecture.
Employed a molecule-building approach, treating nanoparticles as flexible metallic molecules.
Utilized an equivariant molecular graph representation and a physics-informed reward function for policy learning.

Main Results:

The RL agent successfully identified known stable configurations for small mono- and bimetallic clusters.
Demonstrated effectiveness in constructing stable clusters in both single and multi-component experiments.
Observed limitations in generalization, indicating a tendency for overfitting in certain scenarios.

Conclusions:

The actor-critic RL approach shows potential for discovering low-energy nanoparticle structures.
Generalization challenges highlight current limitations of actor-critic methods in molecular design.
Further research is needed to enhance learning properties for achieving universal applicability in nanoparticle design.