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: Jul 2, 2026

Generating the Transcriptional Regulation View of Transcriptomic Features for Prediction Task and Dark Biomarker Detection on Small Datasets

Generating the Transcriptional Regulation View of Transcriptomic Features for Prediction Task and Dark Biomarker Detection on Small Datasets

Published on: March 1, 2024

A Multitask Prediction Framework for CircRNAs, Drugs, and Diseases Based on Multi-View Information Integration and

Shudong Wang¹, Bo Yue¹, Tiyao Liu¹

¹College of Computer Science and Technology, Qingdao Institute of Software, China University of Petroleum (East China), Qingdao 266580, China.

ACS Synthetic Biology

|July 1, 2026

Summary

Related Concept Videos

You might also read

Related Articles

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

Sort by

Same author

CDK4-selective inhibitor AU2-94 for the treatment of advanced and therapy-resistant prostate cancer.

Journal of experimental & clinical cancer research : CR·2026

Same author

DriveGen: Shared Video-Condition Encoding for Autonomous Multi-View Video Generation.

IEEE transactions on visualization and computer graphics·2026

Same author

Point-of-care testing reduces antibiotic prescribing for adults with community-acquired pneumonia: a systematic review and meta-analysis.

Frontiers in pharmacology·2026

Same author

TSGNAS: A Topology- and Semantic-Guided Graph Neural Network Architecture Searcher.

IEEE transactions on neural networks and learning systems·2026

Same author

The Impact of Sex on the Median Effective Dose of Dexmedetomidine for Preoperative Sedation in Adults Undergoing Upper Limb Surgery: An Up-and-Down Sequential Allocation Study.

Drug design, development and therapy·2026

Same author

Tuning the Lattice Thermal Conductivity of Monolayer GaGeTe under Biaxial Tensile Strain: The Critical Role of Four-Phonon Scattering.

ACS applied materials & interfaces·2026

This summary is machine-generated.

This study introduces MVII-GCL, a computational framework for predicting circRNA-drug sensitivity associations (CRAs) and drug-disease associations (RDAs). It effectively integrates multiple data views and uses graph contrastive learning to improve prediction accuracy.

Area of Science:

Bioinformatics
Computational Biology
Drug Discovery

Background:

Computational methods accelerate drug discovery by predicting circRNA-drug sensitivity associations (CRAs) and drug-disease associations (RDAs).
Existing methods often analyze these associations in isolation, missing crucial interdependencies between circRNAs, drugs, and diseases.

Purpose of the Study:

To develop a novel multitask prediction framework, MVII-GCL, that integrates multiview information and graph contrastive learning.
To overcome the limitations of isolated prediction methods by exploiting the interplay between biological entities.

Main Methods:

Constructed a multiview network integrating attribute, topology, and association data.
Employed a multiview attention encoder with domain-specific encoders and Top-k sparse attention.

Keywords:

biomedical network prediction circRNA-drug sensitivity association drug-disease association graph contrastive learning multitask learning multiview information integration

Related Experiment Videos

Last Updated: Jul 2, 2026

Generating the Transcriptional Regulation View of Transcriptomic Features for Prediction Task and Dark Biomarker Detection on Small Datasets

Generating the Transcriptional Regulation View of Transcriptomic Features for Prediction Task and Dark Biomarker Detection on Small Datasets

Published on: March 1, 2024

Integrated symmetric graph contrastive learning as a regularization term within a multitask learning paradigm.

Main Results:

Achieved high performance in 5-fold cross-validation for drug-disease association prediction (AUC: 0.9764, AUPR: 0.9750, F1: 0.9234).
Demonstrated strong results in circRNA-drug sensitivity prediction (AUC: 0.9301, AUPR: 0.9339, F1: 0.8609).
Case studies validated the model's capability in discovering potential associations.

Conclusions:

MVII-GCL offers a robust and effective computational approach for predicting CRAs and RDAs.
The framework's ability to integrate diverse data perspectives and leverage graph contrastive learning enhances prediction accuracy.
This work provides a valuable tool for advancing drug discovery and understanding disease mechanisms.