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

Behavior of Gas Molecules: Molecular Diffusion, Mean Free Path, and Effusion

Behavior of Gas Molecules: Molecular Diffusion, Mean Free Path, and Effusion

Although gaseous molecules travel at tremendous speeds (hundreds of meters per second), they collide with other gaseous molecules and travel in many different directions before reaching the desired target. At room temperature, a gaseous molecule will experience billions of collisions per second. The mean free path is the average distance a molecule travels between collisions. The mean free path increases with decreasing pressure; in general, the mean free path for a gaseous molecule will be...

Predicting Molecular Geometry

Predicting Molecular Geometry

VSEPR Theory for Determination of Electron Pair Geometries

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.

Molecular Geometry and Dipole Moments

Molecular Geometry and Dipole Moments

The VSEPR theory can be used to determine the electron pair geometries and molecular structures as follows:

Diffusion

Diffusion

Diffusion is the passive movement of substances down their concentration gradients—requiring no expenditure of cellular energy. Substances, such as molecules or ions, diffuse from an area of high concentration to an area of low concentration in the cytosol or across membranes. Eventually, the concentration will even out, with the substance moving randomly but causing no net change in concentration. Such a state is called dynamic equilibrium, which is essential for maintaining overall...

Diffusion

Diffusion

Diffusion is a type of passive transport. In passive transport, a substance tends to move from an area of high concentration to an area of low concentration until the concentration is equal across the space. For example, take the diffusion of substances through the air. When someone opens a perfume bottle in a room filled with people, the perfume is at its highest concentration in the bottle and is at its lowest at the edges of the room. The perfume vapor will diffuse, or spread away, from the...

You might also read

Related Articles

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

Sort by

Same author

Network Clustering Approach Reveals Key Proteins and Biological Functions in the Response of Whiteleg Shrimp (Penaeus vannamei) to Acute Hepatopancreatic Necrosis Disease.

Marine biotechnology (New York, N.Y.)·2026

Same author

Self-supervised domain adaptation of protein language model based solely on positive enzyme-reaction pairs.

Computational and structural biotechnology journal·2025

Same author

Relationship between Antiviral Activity against Influenza A Virus Induced by Compound Combinations and Changes in the Physical Properties of Lipid Bilayers.

ACS pharmacology & translational science·2025

Same author

Long short-term memory-based forecasting of influenza epidemics using surveillance and meteorological data in Tokyo, Japan.

Frontiers in public health·2025

Same author

Implementation of a Conditional Latent Diffusion-Based Generative Model to Synthetically Create Unlabeled Histopathological Images.

Bioengineering (Basel, Switzerland)·2025

Same author

Field dynamics of the root endosphere microbiome assembly in paddy rice cultivated under no fertilizer input.

Plant & cell physiology·2025

Search research articles

Related Experiment Video

Updated: Mar 18, 2026

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

Graph latent diffusion-based molecular representation learning for enhanced generalization in molecular property

Daiki Koge¹, Naoaki Ono², Takashi Abe³

¹Department of Electrical and Information Engineering, Graduate School of Science and Technology, Niigata University, Ikarashi, Niigata, 950-2181, Japan. daiki-ko@ie.niigata-u.ac.jp.

Journal of Cheminformatics

|March 17, 2026

Summary

This summary is machine-generated.

Latent diffusion models enhance molecular representation learning for better property prediction. Graph LDA, a novel model, shows improved generalization due to smooth and multimodal latent representations.

Keywords:

Denoising diffusion probabilistic model Generalization performance Latent diffusion model Molecular representation Transformer

More Related Videos

Synthesis of Cyclic Polymers and Characterization of Their Diffusive Motion in the Melt State at the Single Molecule Level

Synthesis of Cyclic Polymers and Characterization of Their Diffusive Motion in the Melt State at the Single Molecule Level

Published on: September 26, 2016

Related Experiment Videos

Last Updated: Mar 18, 2026

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

Synthesis of Cyclic Polymers and Characterization of Their Diffusive Motion in the Melt State at the Single Molecule Level

Synthesis of Cyclic Polymers and Characterization of Their Diffusive Motion in the Melt State at the Single Molecule Level

Published on: September 26, 2016

Area of Science:

Computational Chemistry
Machine Learning
Drug Discovery

Background:

Molecular representation learning is crucial for predicting chemical properties.
Traditional methods often struggle with generalization.
Deep generative models offer potential for improved representations.

Purpose of the Study:

To evaluate the impact of latent diffusion models on molecular representation learning.
To assess generalization performance in molecular property prediction.
To analyze the factors contributing to improved generalization.

Main Methods:

Formulated a deep generative model using a latent diffusion prior.
Introduced evaluation metrics: Widely Applicable Information Criterion (WAIC) and Widely Applicable Bayesian Information Criterion (WBIC).
Developed an analysis framework based on smoothness and multi-modality.
Constructed the Graph Latent Diffusion Autoencoder (Graph LDA).

Main Results:

Graph LDA demonstrated superior generalization performance compared to other models.
Latent diffusion-based priors consistently improved generalization.
Analysis confirmed that smoothness and multi-modality of latent representations drive superior performance.
Distinct generalization behaviors were observed across different models.

Conclusions:

Latent diffusion models significantly enhance molecular representation learning for property prediction.
Graph LDA's architecture, leveraging latent diffusion priors, yields robust and generalizable molecular representations.
The findings provide a principled understanding and guidelines for developing high-generalization molecular representation learning models.