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

Predicting Molecular Geometry02:27

Predicting Molecular Geometry

36.1K
VSEPR Theory for Determination of Electron Pair Geometries
36.1K
Gene Families01:57

Gene Families

9.1K
Gene families consist of groups of genes proposed to have originated from a common ancestor. Typically these arise through events in which a gene or genes are mistakenly duplicated during cell division. Unlike their parent genes (which are subject to selection pressure to maintain function), these gene copies do not need to preserve their sequences and may evolve at a relatively faster rate.
Occasionally these regions can be adapted to take on new roles within the organism, becoming novel genes...
9.1K
Molecular Models02:00

Molecular Models

40.5K
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.
40.5K
Conserved Binding Sites01:49

Conserved Binding Sites

4.4K
Many proteins’ biological role depends on their interactions with their ligands, small molecules that bind to specific locations on the protein known as ligand-binding sites. Ligand-binding sites are often conserved among homologous proteins as these sites are critical for protein function.
Binding sites are often located in large pockets, and if their location on a protein’s surface is unknown, it can be predicted using various approaches. The energetic method computationally...
4.4K
Ligand Binding Sites02:40

Ligand Binding Sites

13.2K
Proteins are dynamic macromolecules that carry out a wide variety of essential processes; however, the activities of most proteins depend on their interactions with other molecules or ions, known as ligands.
Protein-ligand interactions are quite specific; even though numerous potential ligands surround a cellular protein at any given time, only a particular ligand can bind to that protein. Moreover, a ligand binds only to a dedicated area on the surface of the protein, known as the...
13.2K
Predicting Products: Substitution vs. Elimination02:52

Predicting Products: Substitution vs. Elimination

12.3K
When a nucleophile and an alkyl halide react, nucleophilic substitution and β-elimination reactions compete to generate products.
The following factors can influence the mechanisms competing against each other:
12.3K

You might also read

Related Articles

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

Sort by
Same author

Application of acute myocardial infarction-related key genes in noninvasive diagnosis: a comprehensive analysis based on transcriptome and single-cell transcriptome.

Frontiers in genetics·2026
Same author

Causal relationship and pathogenic mechanism analysis of breast cancer and coronary heart disease based on mendelian randomization and transcriptome data analysis.

Immunogenetics·2026
Same author

Isolated right ventricular apical hypoplasia with atrial fibrillation in a young female at her third trimester: a case report.

Gynecology and pelvic medicine·2026
Same author

Ambient temperature variations and antimicrobial resistance: a multicountry analysis of non-linear relationships and temperature thresholds.

BMJ global health·2026
Same author

NbVQ1 physically turns off the NbWRKY45-NbCAT2 module to te ROS burst and disease resistance in plants under high-potassium regime.

Plant physiology·2026
Same author

Can family health alleviate income-related health disparity in China? A population-based study.

Archives of public health = Archives belges de sante publique·2026

Related Experiment Video

Updated: Sep 14, 2025

A Protocol for Computer-Based Protein Structure and Function Prediction
16:41

A Protocol for Computer-Based Protein Structure and Function Prediction

Published on: November 3, 2011

68.9K

Expert-Guided Substructure Information Bottleneck for Molecular Property Prediction.

Tianyi Jiang1,2, Qiang Yao1,2, Zeyu Wang1,2

  • 1Institute of Cyberspace Security, Zhejiang University of Technology, Hangzhou 310023, China.

Journal of Chemical Information and Modeling
|July 24, 2025
PubMed
Summary

This study introduces a new framework, Expert-Guided Substructure Information Bottleneck (ESIB-Mol), to improve molecular property prediction. ESIB-Mol enhances accuracy by focusing on key molecular features and filtering noise, outperforming existing methods.

More Related Videos

Curation of Computational Chemical Libraries Demonstrated with Alpha-Amino Acids
08:21

Curation of Computational Chemical Libraries Demonstrated with Alpha-Amino Acids

Published on: April 13, 2022

2.7K
Identification and Classification of Position-specific GABAA Receptor Subunit Missense Variants for Their Role In Hippocampal Pyramidal Neurons
08:04

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

Published on: June 6, 2025

514

Related Experiment Videos

Last Updated: Sep 14, 2025

A Protocol for Computer-Based Protein Structure and Function Prediction
16:41

A Protocol for Computer-Based Protein Structure and Function Prediction

Published on: November 3, 2011

68.9K
Curation of Computational Chemical Libraries Demonstrated with Alpha-Amino Acids
08:21

Curation of Computational Chemical Libraries Demonstrated with Alpha-Amino Acids

Published on: April 13, 2022

2.7K
Identification and Classification of Position-specific GABAA Receptor Subunit Missense Variants for Their Role In Hippocampal Pyramidal Neurons
08:04

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

Published on: June 6, 2025

514

Area of Science:

  • Cheminformatics and computational chemistry.
  • Machine learning applications in drug discovery and materials science.

Background:

  • Molecular property prediction is vital but hindered by data limitations and structural complexity.
  • Current Mixture of Experts (MoE) models often overlook crucial functional group information and struggle with noisy data.

Purpose of the Study:

  • To develop an advanced framework, ESIB-Mol, for optimizing molecular representation learning.
  • To enhance the accuracy and interpretability of molecular property predictions by integrating MoE with the Information Bottleneck (IB) principle.

Main Methods:

  • Proposed the Expert-Guided Substructure Information Bottleneck (ESIB-Mol) framework.
  • Utilized substructure-specific experts to capture key molecular scaffolds and functional groups.
  • Applied the Information Bottleneck (IB) principle to filter redundant information and improve representation learning.
  • Implemented a dynamic gating mechanism for adaptive expert assignment and computational efficiency.

Main Results:

  • ESIB-Mol demonstrated superior performance in molecular property prediction tasks.
  • The framework effectively integrated substructure information and noise filtering.
  • Experiments on benchmark datasets confirmed the model's enhanced accuracy and generalization capabilities.

Conclusions:

  • ESIB-Mol offers a significant advancement in molecular property prediction by effectively leveraging substructure information and the IB principle.
  • The proposed method addresses limitations of existing MoE models, paving the way for more accurate and interpretable cheminformatics predictions.