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

Conserved Binding Sites01:49

Conserved Binding Sites

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 analyses the...

You might also read

Related Articles

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

Sort by
Same author

Ischemic Postconditioning in Patients With Acute Stroke With Successful Recanalization After Endovascular Therapy: A Pilot Randomized Controlled Trial.

Stroke·2026
Same author

The Association Between Childhood Maltreatment and Adult Intestinal Disorders: A Three-Level Meta-Analysis.

Trauma, violence & abuse·2026
Same author

Digital heart initiative: an ecosystem for digital discovery and precision medicine in cardiology.

National science review·2026
Same author

Mechanistic study on hyaluronic acid polysiloxane gel promoting wound repair guided by wet healing theory.

Biomedical materials (Bristol, England)·2026
Same author

IHGCN-PLA: An interpretable heterogeneous graph convolutional network for protein-ligand binding affinity prediction with multimodal interaction fusion.

Journal of biomedical informatics·2026
Same author

Comparative profiles of pediatric Mendeliome: A Single-Centre 572-Whole-Exome Sequencing Study in Xinjiang.

Human heredity·2026

Related Experiment Video

Updated: Jun 20, 2026

Incorporating Target Protein Structure Flexibility and Dynamics in Computational Drug Discovery Using Ensemble-Based Docking Analysis
08:49

Incorporating Target Protein Structure Flexibility and Dynamics in Computational Drug Discovery Using Ensemble-Based Docking Analysis

Published on: June 20, 2025

Multimodal Drug-Target Affinity Prediction Via FastKAN-Based Hierarchical Fusion of Sequence, Structure, and Tabular

Guishen Wang, Yuxiang Kong, Yuyouqiang Fu

    IEEE Journal of Biomedical and Health Informatics
    |June 18, 2026
    PubMed
    Summary

    This study introduces TabKAN-DTA, a novel framework for drug-target binding affinity (DTBA) prediction. It enhances AI-aided drug discovery by dynamically integrating multimodal data for improved accuracy and interpretability.

    More Related Videos

    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

    Related Experiment Videos

    Last Updated: Jun 20, 2026

    Incorporating Target Protein Structure Flexibility and Dynamics in Computational Drug Discovery Using Ensemble-Based Docking Analysis
    08:49

    Incorporating Target Protein Structure Flexibility and Dynamics in Computational Drug Discovery Using Ensemble-Based Docking Analysis

    Published on: June 20, 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

    Area of Science:

    • Computational chemistry
    • Bioinformatics
    • Artificial intelligence in drug discovery

    Background:

    • Drug-target binding affinity (DTBA) prediction is crucial for AI-aided drug discovery.
    • Current methods struggle with fusing multimodal data (chemical structure, biological sequences) due to limitations in capturing non-linear synergies and dynamic inter-modal importance.
    • This hinders model interpretability and generalization.

    Purpose of the Study:

    • To develop an advanced framework, TabKAN-DTA, for accurate and interpretable multimodal DTBA prediction.
    • To address the limitations of existing methods in handling heterogeneous data fusion and quantifying inter-modal importance.
    • To improve the generalization and interpretability of DTBA prediction models.

    Main Methods:

    • Proposed TabKAN-DTA framework utilizing a FastKAN-based adaptive gating mechanism for input-adaptive nonlinear transformations.
    • Implemented learnable activation functions to dynamically quantify inter-modal importance.
    • Introduced a TabPFN-based tabular encoder to incorporate physicochemical properties and molecular descriptors.

    Main Results:

    • Achieved state-of-the-art performance on standard DTBA prediction benchmarks.
    • Ablation studies confirmed the significant contribution of the tabular modality to performance gains.
    • Demonstrated improved predictive accuracy and interpretability on a non-small cell lung cancer drug repurposing dataset.

    Conclusions:

    • TabKAN-DTA establishes a new paradigm for interpretable multimodal DTBA prediction.
    • The framework effectively captures complex non-linear synergies between chemical and biological data.
    • Dynamic inter-modal importance quantification enhances model interpretability and generalization capabilities in drug discovery.