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

Associative Learning01:27

Associative Learning

Associative learning is a fundamental concept in behavioral psychology, wherein a connection is established between two stimuli or events, leading to a learned response. This process is critical in understanding how behaviors are acquired and modified. Conditioning, the mechanism through which associations are formed, can be divided into two main types: classical conditioning and operant conditioning, each elucidating different aspects of associative learning.
Classical conditioning, also known...

You might also read

Related Articles

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

Sort by
Same author

Identification and characterization of lncRNA-stemness-immune regulatory patterns.

Briefings in bioinformatics·2026
Same author

Hypoxia-Associated Alternative Polyadenylation of CARM1 and Tumor Microenvironment Alterations in Non-Small Cell Lung Cancer.

Genes·2026
Same author

DECODE: deep learning-based common deconvolution framework for various omics data.

Nature methods·2026
Same author

DL-GapFilling: a novel deep learning framework for improved plant genome gap filling.

Briefings in bioinformatics·2026
Same author

IMAGO: An Improved Model Based on Attention Mechanism for Enhanced Protein Function Prediction.

Biomolecules·2025
Same author

Reference-Guided Chromosome-by-Chromosome de novo Assembly at Scale Using Low-Coverage High-Fidelity Long-Reads with HiFiCCL.

Advanced science (Weinheim, Baden-Wurttemberg, Germany)·2025

Related Experiment Video

Updated: Jul 1, 2026

A Knowledge Graph Approach to Elucidate the Role of Organellar Pathways in Disease via Biomedical Reports
07:35

A Knowledge Graph Approach to Elucidate the Role of Organellar Pathways in Disease via Biomedical Reports

Published on: October 13, 2023

GHF-ACL: A novel contrastive learning framework with multi-order graph structures for herb-disease association

Yunmeng Zhang1, Xiuhong Wu2, Qiutong Wang1

  • 1College of Computer Science and Artificial Intelligence, Northeast Forestry University, Harbin, Heilongjiang, China.

Plos Computational Biology
|June 29, 2026
PubMed
Summary

Predicting herb-disease associations (HDA) is crucial for Traditional Chinese Medicine (TCM). A new framework, GHF-ACL, effectively integrates diverse data, improving prediction accuracy for herbal medicines and diseases.

More Related Videos

Evidence-based Knowledge Synthesis and Hypothesis Validation: Navigating Biomedical Knowledge Bases via Explainable AI and Agentic Systems
05:47

Evidence-based Knowledge Synthesis and Hypothesis Validation: Navigating Biomedical Knowledge Bases via Explainable AI and Agentic Systems

Published on: June 13, 2025

Related Experiment Videos

Last Updated: Jul 1, 2026

A Knowledge Graph Approach to Elucidate the Role of Organellar Pathways in Disease via Biomedical Reports
07:35

A Knowledge Graph Approach to Elucidate the Role of Organellar Pathways in Disease via Biomedical Reports

Published on: October 13, 2023

Evidence-based Knowledge Synthesis and Hypothesis Validation: Navigating Biomedical Knowledge Bases via Explainable AI and Agentic Systems
05:47

Evidence-based Knowledge Synthesis and Hypothesis Validation: Navigating Biomedical Knowledge Bases via Explainable AI and Agentic Systems

Published on: June 13, 2025

Area of Science:

  • Computational biology
  • Pharmacology
  • Traditional Chinese Medicine (TCM)

Background:

  • Predicting herb-disease associations (HDA) is vital for modernizing TCM but faces challenges due to data heterogeneity and complex herbal mechanisms.
  • Existing models struggle with high-order structural patterns and semantic inconsistencies in herbal data.
  • A standardized dataset and advanced computational models are needed to improve HDA prediction accuracy.

Purpose of the Study:

  • To introduce HData, a standardized benchmark dataset for HDA prediction, integrating herbal properties, chemical compositions, and disease associations.
  • To propose GHF-ACL, a novel multi-order graph contrastive learning framework for enhanced HDA prediction.
  • To address data heterogeneity and capture complex interactions in herbal medicine for improved drug discovery.

Main Methods:

  • Developed HData, a comprehensive dataset combining herb properties, chemical constituents, and disease associations.
  • Proposed GHF-ACL, a framework utilizing herb-disease similarity graphs and herb-chemical hypergraphs for multi-order modeling.
  • Implemented an adaptive gating-guided structural interaction module and hierarchical contrastive learning for representation alignment and consistency.

Main Results:

  • GHF-ACL demonstrated superior or competitive performance against six state-of-the-art models across multiple metrics on five datasets.
  • Significant improvements were observed in AUPR (+4.8% on LRSSL, +3.81% on Cdata), F1 score, and Recall compared to the best baseline.
  • The model excels at identifying true positive associations, particularly within imbalanced biomedical datasets.

Conclusions:

  • The proposed GHF-ACL framework effectively addresses HDA prediction challenges by synergizing multi-view graph modeling, semantic fusion, and contrastive regularization.
  • GHF-ACL provides a unified approach for HDA prediction, offering valuable insights for computational TCM and data-driven drug discovery.
  • This work establishes a robust method for understanding complex herb-disease relationships, advancing personalized medicine and pharmaceutical research.