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

Viral Structure

Viral Structure

Viruses are extraordinarily diverse in shape and size, but they all have several structural features in common. All viruses have a core that contains a DNA- or RNA-based genome. The core is surrounded by a protective coat of proteins called the capsid. The capsid is composed of subunits called capsomeres. The capsid and genome-containing core are together known as the nucleocapsid.

You might also read

Related Articles

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

Sort by

Same author

Rescuing the Function of Missense-Mutated Tumor Suppressor <i>VHL</i> using Stabilizing Small Molecules.

bioRxiv : the preprint server for biology·2026

Same author

Variation at the R181 residue of p53 confers loss of p53 DNA binding cooperativity with the retention of mitochondrial-associated apoptosis.

Molecular cancer research : MCR·2026

Same author

PPIscreenML is a method for structure-based screening of protein-protein interactions using AlphaFold.

eLife·2026

Same author

Life in the fast lane: Functional consequences of male-female dynamic differences in the renal auto-regulation of flow.

bioRxiv : the preprint server for biology·2025

Same author

DeepAtlas: a tool for effective manifold learning.

ArXiv·2025

Same author

DeepAtlas: a tool for effective manifold learning.

bioRxiv : the preprint server for biology·2025

Same journal

Chemotactic self-organization captures the dynamics of mammalian hair follicle patterning.

Proceedings of the National Academy of Sciences of the United States of America·2026

Same journal

Tomographic imaging of superconducting order using particle-hole interference.

Proceedings of the National Academy of Sciences of the United States of America·2026

Same journal

Inhibitory potential of autologous neutralizing antibodies sets quantitative limits on the rebound-competent HIV-1 reservoir.

Proceedings of the National Academy of Sciences of the United States of America·2026

Same journal

Inferring epidemiological parameters under an infectious phylogeography model with visitor dynamics.

Proceedings of the National Academy of Sciences of the United States of America·2026

Same journal

Analytical modeling for suction cup designs for skin-interfaced wearable devices.

Proceedings of the National Academy of Sciences of the United States of America·2026

Same journal

Improving cell-free metabolism through direct integration of artificial respiratory chains.

Proceedings of the National Academy of Sciences of the United States of America·2026

See all related articles

Search research articles

Related Experiment Video

Updated: Dec 14, 2025

A Virtual Machine Platform for Non-Computer Professionals for Using Deep Learning to Classify Biological Sequences of Metagenomic Data

A Virtual Machine Platform for Non-Computer Professionals for Using Deep Learning to Classify Biological Sequences of Metagenomic Data

Published on: September 25, 2021

Machine learning classification can reduce false positives in structure-based virtual screening.

Yusuf O Adeshina^1,2, Eric J Deeds^2,3, John Karanicolas⁴

¹Program in Molecular Therapeutics, Fox Chase Cancer Center, Philadelphia, PA 19111.

Proceedings of the National Academy of Sciences of the United States of America

|July 17, 2020

Summary

This summary is machine-generated.

This study introduces a new strategy for training virtual screening models, improving drug discovery accuracy. The developed vScreenML classifier demonstrates high performance in identifying active compounds for drug development.

Keywords:

machine learning classifier protein–ligand complex structure-based drug design virtual screening

More Related Videos

Identification and Classification of Position-specific GABAA Receptor Subunit Missense Variants for Their Role In Hippocampal Pyramidal Neurons

Identification and Classification of Position-specific GABA_A Receptor Subunit Missense Variants for Their Role In Hippocampal Pyramidal Neurons

Published on: June 6, 2025

A Protocol for Computer-Based Protein Structure and Function Prediction

A Protocol for Computer-Based Protein Structure and Function Prediction

Published on: November 3, 2011

Related Experiment Videos

Last Updated: Dec 14, 2025

A Virtual Machine Platform for Non-Computer Professionals for Using Deep Learning to Classify Biological Sequences of Metagenomic Data

A Virtual Machine Platform for Non-Computer Professionals for Using Deep Learning to Classify Biological Sequences of Metagenomic Data

Published on: September 25, 2021

Identification and Classification of Position-specific GABAA Receptor Subunit Missense Variants for Their Role In Hippocampal Pyramidal Neurons

Identification and Classification of Position-specific GABA_A Receptor Subunit Missense Variants for Their Role In Hippocampal Pyramidal Neurons

Published on: June 6, 2025

A Protocol for Computer-Based Protein Structure and Function Prediction

A Protocol for Computer-Based Protein Structure and Function Prediction

Published on: November 3, 2011

Area of Science:

Computational chemistry
Drug discovery
Machine learning

Background:

Virtual screening plays a crucial role in early drug discovery but often suffers from low hit rates (around 12%) due to simplistic models and inadequate training datasets.
Existing scoring functions are often trained and tested on datasets lacking thoughtful consideration, leading to oversimplification and overtraining, further exacerbated by a lack of prospective validation in published studies.

Purpose of the Study:

To develop a robust strategy for building high-quality training datasets for virtual screening.
To create and validate a general-purpose virtual screening classifier (vScreenML) using an improved training dataset approach.

Main Methods:

Developed the D-COID (Dataset of Compelling Optimized Inhibitor Decoys) strategy to generate highly matched decoy complexes for training.
Utilized the XGBoost machine learning framework to build the vScreenML classifier based on the D-COID dataset.
Performed retrospective benchmarking against existing scoring functions and prospective validation in a real-world screening campaign.

Main Results:

The vScreenML classifier, trained on D-COID, demonstrated outstanding performance in retrospective benchmarks compared to other scoring functions.
In a prospective screen against acetylcholinesterase, nearly all candidate inhibitors showed detectable activity, with 10 of 23 compounds exhibiting IC50 values better than 50 μM.
The most potent hit achieved an IC50 of 280 nM (Ki of 173 nM) without any medicinal chemistry optimization.

Conclusions:

The D-COID dataset generation strategy is effective for training accurate virtual screening classifiers.
vScreenML shows significant promise for improving the efficiency and success rate of virtual screening campaigns in drug discovery.
The D-COID strategy and vScreenML are made freely available to advance computational biology and drug discovery efforts.