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

Search research articles

Related Experiment Video

Updated: Dec 22, 2025

Modeling an Enzyme Active Site using Molecular Visualization Freeware

Modeling an Enzyme Active Site using Molecular Visualization Freeware

Published on: December 25, 2021

Learning Molecular Representations for Medicinal Chemistry.

Kangway V Chuang¹, Laura M Gunsalus¹, Michael J Keiser¹

¹Department of Pharmaceutical Chemistry, Department of Bioengineering & Therapeutic Sciences, Institute for Neurodegenerative Diseases, Kavli Institute for Fundamental Neuroscience, Bakar Computational Health Sciences Institute, University of California, San Francisco, 675 Nelson Rising Lane, San Francisco, California 94143, United States.

Journal of Medicinal Chemistry

|May 6, 2020

Summary

This summary is machine-generated.

Related Concept Videos

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 Shapes

Molecular Shapes

Molecules have characteristic shapes that are crucial for their function. The arrangement of various electron groups around the central atom dictates their molecular geometry. Electron pairs in the valence shell of a central atom will adopt an arrangement that minimizes repulsions between the electron pairs by maximizing the distance between them. The valence electrons form either bonding pairs, located primarily between bonded atoms, or lone pairs.
Two regions of electron density in a diatomic...

Predicting Molecular Geometry

Predicting Molecular Geometry

VSEPR Theory for Determination of Electron Pair Geometries

Molecular Compounds: Formulas and Nomenclature

Molecular Compounds: Formulas and Nomenclature

Molecular compounds or covalent compounds result when atoms share electrons to form covalent bonds. Since there is no electron transfer, molecular compounds do not contain ions; instead, they consist of discrete, neutral molecules.

Molecular Orbital Theory I

Molecular Orbital Theory I

Overview of Molecular Orbital Theory

Newman Projections

Newman Projections

Different notations are used to represent the three-dimensional structure of molecules on two-dimensional surfaces. One of the most commonly used representations is the dash-wedge formula. The dashed wedges, solid wedges, and the plane lines indicate the groups situated behind the plane, coming out of the plane, and in the plane, respectively.
The organic molecules rotate across the single bonds leading to numerous temporary three-dimensional structures of varying energy known as...

You might also read

Related Articles

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

Sort by

Same author

Decoding sequence determinants of gene expression in diverse cellular and disease states.

Nature methods·2026

Same author

gReLU: a comprehensive framework for DNA sequence modeling and design.

Nature methods·2025

Same author

Autoparty: Machine Learning-Guided Visual Inspection of Molecular Docking Results.

Journal of chemical information and modeling·2025

Same author

MIC: A deep learning tool for assigning ions and waters in cryo-EM and crystal structures.

Nature communications·2025

Same author

An improved model for prediction of de novo designed proteins with diverse geometries.

bioRxiv : the preprint server for biology·2025

Same author

Evolutionary-scale enzymology enables exploration of a rugged catalytic landscape.

Science (New York, N.Y.)·2025

Same journal

A Melatonin-Catechol Hybrid Molecule Prolongs Lifespan via Regulating ROS and Reprogramming Mitochondrial Metabolism.

Journal of medicinal chemistry·2026

Same journal

Discovery of SD-2301 as a Highly Potent and Selective PROTAC STAT3 Degrader Capable of Achieving Complete Tumor Regression with Single Administration.

Journal of medicinal chemistry·2026

Same journal

GID4-Recruiting PROTACs for BRD4 Degradation Overcome Resistance Driven by CRBN and VHL Deficiency.

Journal of medicinal chemistry·2026

Same journal

Alpha-Particle Therapy with an Actinium-225 Labeled Bivalent Inhibitor of Prostate-Specific Membrane Antigen is Therapeutically Efficacious in a Mouse Model of Prostate Cancer.

Journal of medicinal chemistry·2026

Same journal

Development of Telmisartan Platinum(IV) Complexes for Antimetastatic Therapy: Targeting EMT and Tumor Immunity through Suppressing AT1R.

Journal of medicinal chemistry·2026

Same journal

Library Docking for Cannabinoid-2 Receptor Ligands.

Journal of medicinal chemistry·2026

See all related articles

Deep learning models can now learn molecular representations directly from data, improving predictions for drug discovery. This approach overcomes limitations of traditional methods, offering new opportunities in cheminformatics and virtual screening.

Area of Science:

Cheminformatics
Computational Chemistry
Drug Discovery

Background:

Accurate modeling of small molecule properties and bioactivities is crucial for drug discovery.
Traditional methods rely on expert-designed molecular descriptors and fingerprints.
Limitations exist in current descriptors and fingerprints for predictive modeling.

Purpose of the Study:

To review advances in deep learning for molecular representation learning.
To discuss how learned representations address limitations of traditional descriptors.
To highlight new opportunities in cheminformatics and virtual screening.

Main Methods:

Overview of molecular representations in cheminformatics.
Explanation of key deep learning concepts relevant to molecular data.

More Related Videos

Pharmacophore Modeling for Targets with Extensive Ligand Libraries: A Case Study on SARS-CoV-2 Mpro

Pharmacophore Modeling for Targets with Extensive Ligand Libraries: A Case Study on SARS-CoV-2 Mpro

Published on: September 26, 2025

Author Spotlight: Exploring Cellular Processes by Modeling Ligands in Cryo-EM Maps

Author Spotlight: Exploring Cellular Processes by Modeling Ligands in Cryo-EM Maps

Published on: July 19, 2024

Related Experiment Videos

Last Updated: Dec 22, 2025

Modeling an Enzyme Active Site using Molecular Visualization Freeware

Modeling an Enzyme Active Site using Molecular Visualization Freeware

Published on: December 25, 2021

Pharmacophore Modeling for Targets with Extensive Ligand Libraries: A Case Study on SARS-CoV-2 Mpro

Pharmacophore Modeling for Targets with Extensive Ligand Libraries: A Case Study on SARS-CoV-2 Mpro

Published on: September 26, 2025

Author Spotlight: Exploring Cellular Processes by Modeling Ligands in Cryo-EM Maps

Author Spotlight: Exploring Cellular Processes by Modeling Ligands in Cryo-EM Maps

Published on: July 19, 2024

Discussion of active research in molecular deep learning.

Main Results:

Deep learning enables efficient and compact learning of molecular representations from data.
Learned representations can overcome limitations of expert-designed descriptors.
Potential for improved predictive modeling of small molecule properties and bioactivities.

Conclusions:

Learning molecular representations offers a promising way forward in cheminformatics.
Deep learning enhances the predictive power for small molecule properties and bioactivities.
This approach opens new avenues for virtual screening and drug discovery.