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

Molecular and Ionic Solids

Molecular and Ionic Solids

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...

Kinetic Molecular Theory and Gas Laws Explain Properties of Gas Molecules

Kinetic Molecular Theory and Gas Laws Explain Properties of Gas Molecules

The test of the kinetic molecular theory (KMT) and its postulates is its ability to explain and describe the behavior of a gas. The various gas laws (Boyle’s, Charles’s, Gay-Lussac’s, Avogadro’s, and Dalton’s laws) can be derived from the assumptions of the KMT, which have led chemists to believe that the assumptions of the theory accurately represent the properties of gas molecules.

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 Orbital Theory II

Molecular Orbital Theory II

Molecular Orbital Energy Diagrams

Molecular Orbital Theory I

Molecular Orbital Theory I

Overview of Molecular Orbital Theory

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

AOP Network Box: An Integrative Framework for Bridging Adverse Outcome Pathways and Biological Networks.

Chemical research in toxicology·2026

Same author

scMix: learning temporal dynamics of gene expression under irregular time intervals.

Bioinformatics (Oxford, England)·2026

Same author

Trends in Widefield Fundus Photography and Optical Coherence Tomography Examination in South Korea (2015-2024).

Korean journal of ophthalmology : KJO·2025

Same author

Cancer-Associated Retinopathy in a Patient with Small Cell Lung Cancer and Esophageal Cancer: A Case Report.

Korean journal of ophthalmology : KJO·2025

Same author

BIDpred: unraveling B cell Immunodominance hierarchical pattern using statistical feature discovery and deep learning prediction.

Frontiers in immunology·2025

Same author

Morphological characteristics of high myopes complicated by serous retinal detachment with dome-shaped macula or inferior staphyloma.

Graefe's archive for clinical and experimental ophthalmology = Albrecht von Graefes Archiv fur klinische und experimentelle Ophthalmologie·2025

Search research articles

Related Experiment Video

Updated: Jan 25, 2026

Molecular Evolution of the Tre Recombinase

Molecular Evolution of the Tre Recombinase

Published on: May 29, 2008

FP2VEC: a new molecular featurizer for learning molecular properties.

Woosung Jeon¹, Dongsup Kim¹

¹Department of Bio and Brain Engineering, Korea Advanced Institute of Science and Technology, Yuseong-gu, Daejeon, Republic of Korea.

Bioinformatics (Oxford, England)

|May 10, 2019

Summary

A new molecular featurizer, FP2VEC, represents chemical compounds as trainable embedding vectors. This approach, combined with convolutional neural networks (CNNs), achieves competitive quantitative structure-activity relationship (QSAR) prediction results, particularly for classification tasks.

More Related Videos

Light-driven Molecular Motors on Surfaces for Single Molecular Imaging

Light-driven Molecular Motors on Surfaces for Single Molecular Imaging

Published on: March 13, 2019

Excitonic Hamiltonians for Calculating Optical Absorption Spectra and Optoelectronic Properties of Molecular Aggregates and Solids

Excitonic Hamiltonians for Calculating Optical Absorption Spectra and Optoelectronic Properties of Molecular Aggregates and Solids

Published on: May 27, 2020

Related Experiment Videos

Last Updated: Jan 25, 2026

Molecular Evolution of the Tre Recombinase

Molecular Evolution of the Tre Recombinase

Published on: May 29, 2008

Light-driven Molecular Motors on Surfaces for Single Molecular Imaging

Light-driven Molecular Motors on Surfaces for Single Molecular Imaging

Published on: March 13, 2019

Excitonic Hamiltonians for Calculating Optical Absorption Spectra and Optoelectronic Properties of Molecular Aggregates and Solids

Excitonic Hamiltonians for Calculating Optical Absorption Spectra and Optoelectronic Properties of Molecular Aggregates and Solids

Published on: May 27, 2020

Area of Science:

Computational chemistry
Cheminformatics
Machine learning

Background:

Quantitative structure-activity relationship (QSAR) models are crucial for predicting chemical compound properties.
Deep learning has significantly enhanced QSAR prediction accuracy.
Novel molecular featurizers are needed to fully leverage deep learning in cheminformatics.

Purpose of the Study:

To develop a novel molecular featurizer, FP2VEC, inspired by natural language processing techniques.
To represent chemical compounds as sets of trainable embedding vectors.
To improve the performance of deep learning-based QSAR models.

Main Methods:

Developed FP2VEC, a new molecular featurizer representing compounds as embedding vectors.
Utilized a convolutional neural network (CNN) architecture, adapted from natural language processing.
Tested the FP2VEC-CNN model on benchmark datasets for QSAR tasks.

Main Results:

The FP2VEC-CNN model achieved competitive results across various QSAR tasks, especially in classification.
Demonstrated the effectiveness of FP2VEC for multitask learning.
Outperformed conventional extended connectivity fingerprints (ECFP) in certain applications.

Conclusions:

FP2VEC is a promising new featurizer for deep learning in QSAR.
The analogy between chemical compounds and natural language is beneficial for developing molecular representations.
FP2VEC offers a powerful tool for advancing chemical property prediction.