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 Experiment Video

Updated: Jun 28, 2026

Cross-Modal Multivariate Pattern Analysis
13:51

Cross-Modal Multivariate Pattern Analysis

Published on: November 9, 2011

Predicting piRNA-Disease Associations Based on Dual-View Learning and Multi-head Self-Attention Mechanism Fusion.

Manyu Zheng1, Ying Fang1, Lijie Na2

  • 1School of Computer Science and Software Engineering, University of Science and Technology Liaoning, Anshan, 114051, China.

Interdisciplinary Sciences, Computational Life Sciences
|June 22, 2026
PubMed
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

SPSGL: uncovering psychiatric network mechanisms via structural-prior guided synaptic graph learning.

Health information science and systems·2026
Same author

MicroRNAs in endometriosis: bioinformatics resources, machine learning strategies, and multi-omics perspectives.

Journal of translational medicine·2026
Same author

Cross-algorithm machine learning and consensus features for early disseminated intravascular coagulation risk prediction in sepsis-induced coagulopathy.

Journal of translational medicine·2026
Same author

Dual-Modal Fusion Based on Peptide Sequence and Molecular Graph with Bidirectional Cross-Attention for Precise Peptide Toxicity Prediction.

Journal of chemical information and modeling·2026
Same author

ADFC-ATP: Attention-Guided Dual-View Fusion and Contrastive Pretraining for Robust Aquatic Toxicity Prediction.

Journal of cellular and molecular medicine·2026
Same author

Multimodal Multi-Granularity Fusion Model with Mamba Architecture for Ames Mutagenicity Prediction.

Journal of medicinal chemistry·2026

A new deep learning framework, PiDA-DVLSA, accurately predicts PIWI-interacting RNA (piRNA) disease associations. This computational approach overcomes limitations of traditional methods for large-scale screening, aiding precision diagnostics.

Area of Science:

  • Genomics
  • Bioinformatics
  • Computational Biology

Background:

  • PIWI-interacting RNAs (piRNAs) are key epigenetic regulators involved in genomic stability and gene expression.
  • Traditional experimental methods for piRNA research are low-throughput, costly, and time-consuming.
  • There is a need for efficient computational tools to systematically screen piRNA-disease associations.

Purpose of the Study:

  • To develop an advanced predictive framework, PiDA-DVLSA, for identifying piRNA-disease associations.
  • To leverage multimodal deep learning for enhanced accuracy and efficiency in piRNA research.
  • To provide a computational basis for precision diagnostics and therapeutics.

Main Methods:

  • Developed PiDA-DVLSA, an end-to-end multimodal deep learning system.
Keywords:
AutoencoderGraph transformerHeterogeneous information networkMulti-head self-attention mechanismPiRNA-disease associations

Related Experiment Videos

Last Updated: Jun 28, 2026

Cross-Modal Multivariate Pattern Analysis
13:51

Cross-Modal Multivariate Pattern Analysis

Published on: November 9, 2011

  • Integrated autoencoder for nonlinear dimensionality reduction and denoising of piRNA and disease features.
  • Employed dual graph transformers and multi-head self-attention for modeling complex interactions and fusing multi-source information.

    • Main Results:

    • PiDA-DVLSA achieved excellent performance on a benchmark dataset, with AUC of 0.9437 and AUPR of 0.9195.
    • The framework significantly outperformed eight mainstream algorithms.
    • Successfully predicted biologically significant piRNA-disease associations in independent case studies for breast cancer, glioblastoma, and Alzheimer's disease.

    Conclusions:

    • PiDA-DVLSA demonstrates high practicality and effectiveness for real-world scientific research.
    • The model provides a robust computational foundation for advancing precision diagnostics and therapeutic strategies.
    • The framework is publicly available, facilitating further research in piRNA-disease association studies.