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

Sequence Networks of Rotating Machines

Sequence Networks of Rotating Machines

A Y-connected synchronous generator, grounded through a neutral impedance, is designed to produce balanced internal phase voltages with only positive-sequence components. The generator's sequence networks include a source voltage that is exclusively in the positive-sequence network. The sequence components of line-to-ground voltages at the generator terminals illustrate this configuration.
Zero-sequence current induces a voltage drop across the generator's neutral impedance and other...

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

Solution-processed aqueous-insensitive transparent conductors for bio-optoelectronics.

Nature communications·2026

Same author

Structurally engineered ultrasoft PEDOT:PSS fiber microelectrodes with enhanced electrochemical performance for neural interfaces.

Science advances·2026

Same author

Chitosan and its derivatives in 3D printing: Printability, properties, and applications.

Carbohydrate polymers·2026

Same author

Disorder-mediated non-equilibrium photocurrent redistribution enables homeostatic synaptic conditioning in AgBiS<sub>2</sub> heterostructure.

Nature communications·2026

Same author

Enabling Synthetically Feasible Molecular Editing in Drug Discovery via Reaction-Regulated Graph-Based Genetic Algorithms.

JACS Au·2026

Same author

Isolated Proximal Femoral Valgus Osteotomy for Hinge Abduction Improves Femoroacetabular Relationship in Patients With Perthes Disease.

Clinical orthopaedics and related research·2026

Same journal

Investigating the stabilizing influences of organic sidechains in epoxides by rotational spectroscopy and computational chemistry: 1,2-epoxyhexane <i>versus</i> 1,2-epoxy-5-hexene.

Physical chemistry chemical physics : PCCP·2026

Same journal

Structure and dynamics of water confined in graphene oxide.

Physical chemistry chemical physics : PCCP·2026

Same journal

Comprehensive first-principles study of group IIIA-VIA A<sub>2</sub>B<sub>3</sub> two-dimensional ferroelectrics.

Physical chemistry chemical physics : PCCP·2026

Same journal

Low-resistance ohmic contacts for NbGeN<sub>3</sub> enabled by cold metals.

Physical chemistry chemical physics : PCCP·2026

Same journal

Integrated first-principles, SCAPS-1D, and a ML framework for numerical modelling and performance optimization of BaXS<sub>3</sub> (X = Zr, Hf)-based perovskite solar cells.

Physical chemistry chemical physics : PCCP·2026

Same journal

Generalized Suzuki-Chin factorization in bosonic path integral molecular dynamics.

Physical chemistry chemical physics : PCCP·2026

See all related articles

Search research articles

Related Experiment Video

Updated: Dec 12, 2025

Modeling an Enzyme Active Site using Molecular Visualization Freeware

Modeling an Enzyme Active Site using Molecular Visualization Freeware

Published on: December 25, 2021

Machine-guided representation for accurate graph-based molecular machine learning.

Gyoung S Na¹, Hyunju Chang, Hyun Woo Kim

¹Korea Research Institute of Chemical Technology (KRICT), 141, Gajeong-ro, Yuseong-gu, Daejeon, South Korea. ngs0@krict.re.kr ahwk@krict.re.kr.

Physical Chemistry Chemical Physics : PCCP

|August 12, 2020

Summary

This summary is machine-generated.

This study introduces deep metric learning (DML) for robust molecular representation in graph neural networks (GNNs). The novel approach improves machine learning accuracy, even with limited data, addressing a key challenge in cheminformatics.

More Related Videos

Analyzing Mitochondrial Morphology Through Simulation Supervised Learning

Analyzing Mitochondrial Morphology Through Simulation Supervised Learning

Published on: March 3, 2023

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

Related Experiment Videos

Last Updated: Dec 12, 2025

Modeling an Enzyme Active Site using Molecular Visualization Freeware

Modeling an Enzyme Active Site using Molecular Visualization Freeware

Published on: December 25, 2021

Analyzing Mitochondrial Morphology Through Simulation Supervised Learning

Analyzing Mitochondrial Morphology Through Simulation Supervised Learning

Published on: March 3, 2023

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

Area of Science:

Computational Chemistry
Machine Learning
Cheminformatics

Background:

Graph-based machine learning is valuable in chemistry, representing molecules as graphs.
Molecular properties' sensitivity to structural changes creates distribution challenges for molecular machine learning.
This difficulty in molecular machine learning due to property distributions is under-explored.

Purpose of the Study:

To propose a robust, machine-guided molecular representation method.
To address the challenge of mixed molecular property distributions in machine learning.
To develop an optimal representation generation for molecular datasets.

Main Methods:

Integrated deep metric learning (DML) with graph neural networks (GNNs).
Devised a novel objective function specifically for representation learning in this context.
Employed DML to automatically generate optimal molecular representations tailored to datasets.

Main Results:

Machine learning algorithms using the proposed DML-GNN method demonstrated superior prediction accuracy compared to existing state-of-the-art GNNs.
The method proved effective even on very small, limited datasets.
Achieved significant improvements in accuracy for molecular property prediction.

Conclusions:

The proposed deep metric learning approach offers a robust solution for molecular representation learning.
This method enhances the performance of graph neural networks in cheminformatics tasks.
The effectiveness on small datasets is particularly impactful for real-world applications with data scarcity.