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

Molecular Models02:00

Molecular Models

43.8K
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.
43.8K
Molecular Orbital Theory II03:51

Molecular Orbital Theory II

27.6K
Molecular Orbital Energy Diagrams
27.6K
Molecular Orbital Theory I02:35

Molecular Orbital Theory I

47.7K
Overview of Molecular Orbital Theory
47.7K
Predicting Molecular Geometry02:27

Predicting Molecular Geometry

46.0K
VSEPR Theory for Determination of Electron Pair Geometries
46.0K
Molecular and Ionic Solids02:54

Molecular and Ionic Solids

20.2K
Crystalline solids are divided into four types: molecular, ionic, metallic, and covalent network based on the type of constituent units and their interparticle interactions.
Molecular Solids
Molecular crystalline solids, such as ice, sucrose (table sugar), and iodine, are solids that are composed of neutral molecules as their constituent units. These molecules are held together by weak intermolecular forces such as London dispersion forces, dipole-dipole interactions, or hydrogen bonds, which...
20.2K
Kinetic Molecular Theory: Molecular Velocities, Temperature, and Kinetic Energy03:07

Kinetic Molecular Theory: Molecular Velocities, Temperature, and Kinetic Energy

29.9K
The kinetic molecular theory qualitatively explains the behaviors described by the various gas laws. The postulates of this theory may be applied in a more quantitative fashion to derive these individual laws.
29.9K

You might also read

Related Articles

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

Sort by
Same author

Dual Dopaminergic and Limbic-Cognitive Contributions to Gait Parameters in De Novo Parkinson Disease.

Neurology·2026
Same author

Evaluation of AI developed for rib fracture detection in identifying vertebral fractures on abdominal CT.

BMC musculoskeletal disorders·2026
Same author

Super-resolution deep learning reconstruction for brain fluid-attenuated inversion recovery: image quality and white matter hyperintensity volume analysis.

Neuroradiology·2026
Same author

Clinical validation of the Rapid Cough Questionnaire across diverse lung diseases.

BMJ open respiratory research·2026
Same author

Exploring cough hypersensitivity patterns across respiratory diseases.

Respiratory medicine·2026
Same author

Predicting unfavorable tuberculosis outcomes using machine learning: a prospective cohort.

Tropical medicine and health·2026

Related Experiment Video

Updated: Feb 7, 2026

Molecular Evolution of the Tre Recombinase
12:02

Molecular Evolution of the Tre Recombinase

Published on: May 29, 2008

10.1K

Molecular generative model based on conditional variational autoencoder for de novo molecular design.

Jaechang Lim1, Seongok Ryu1, Jin Woo Kim1

  • 1Department of Chemistry, KAIST, 291 Daehak-ro, Daejeon, 34141, Republic of Korea.

Journal of Cheminformatics
|July 12, 2018
PubMed
Summary

We developed a new AI model for designing novel molecules with desired properties. This conditional variational autoencoder allows simultaneous control over multiple molecular characteristics, aiding drug discovery.

Keywords:
Conditional variational autoencoderDeep learningMolecular design

More Related Videos

Interactive Molecular Model Assembly with 3D Printing
06:15

Interactive Molecular Model Assembly with 3D Printing

Published on: August 13, 2020

11.0K
A Concoction Pipeline for Generating Molecular Operational Taxonomic Units (MOTUs) Among Riparian and Aquatic Beetles
10:23

A Concoction Pipeline for Generating Molecular Operational Taxonomic Units (MOTUs) Among Riparian and Aquatic Beetles

Published on: July 11, 2025

689

Related Experiment Videos

Last Updated: Feb 7, 2026

Molecular Evolution of the Tre Recombinase
12:02

Molecular Evolution of the Tre Recombinase

Published on: May 29, 2008

10.1K
Interactive Molecular Model Assembly with 3D Printing
06:15

Interactive Molecular Model Assembly with 3D Printing

Published on: August 13, 2020

11.0K
A Concoction Pipeline for Generating Molecular Operational Taxonomic Units (MOTUs) Among Riparian and Aquatic Beetles
10:23

A Concoction Pipeline for Generating Molecular Operational Taxonomic Units (MOTUs) Among Riparian and Aquatic Beetles

Published on: July 11, 2025

689

Area of Science:

  • Artificial Intelligence
  • Computational Chemistry
  • Drug Discovery

Background:

  • De novo molecular design is crucial for identifying novel drug candidates.
  • Controlling multiple molecular properties simultaneously presents a significant challenge in computational chemistry.

Purpose of the Study:

  • To introduce a novel molecular generative model for de novo molecular design.
  • To enable simultaneous control over multiple molecular properties during molecule generation.

Main Methods:

  • Utilized a conditional variational autoencoder (CVAE) framework.
  • Integrated property control by imposing constraints on the model's latent space.
  • Demonstrated proof-of-concept for generating molecules with five target properties.

Main Results:

  • Successfully generated drug-like molecules with five predefined properties.
  • Showcased the ability to adjust individual molecular properties without affecting others.
  • Demonstrated manipulation of properties beyond the original dataset's range.

Conclusions:

  • The proposed CVAE model offers a powerful tool for targeted de novo molecular design.
  • This approach facilitates the generation of molecules with tailored property profiles for drug development.
  • The model's flexibility allows for property optimization beyond existing data distributions.