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 Videos

DANE-MDA: Predicting microRNA-disease associations via deep attributed network embedding.

Bo-Ya Ji1,2,3, Zhu-Hong You1,2,3, Yi Wang1,3

  • 1Xinjiang Technical Institutes of Physics and Chemistry, Chinese Academy of Sciences, Urumqi 830011, China.

Iscience
|May 27, 2021
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

Incorporating graph representation and mutual attention mechanism for MiRNA-MRNA interaction prediction.

Frontiers in genetics·2025
Same author

A multi-source molecular network representation model for protein-protein interactions prediction.

Scientific reports·2024
Same author

Identification of gene biomarkers for brain diseases via multi-network topological semantics extraction and graph convolutional network.

BMC genomics·2024
Same author

MAGCDA: A Multi-Hop Attention Graph Neural Networks Method for CircRNA-Disease Association Prediction.

IEEE journal of biomedical and health informatics·2023
Same author

GSLCDA: An Unsupervised Deep Graph Structure Learning Method for Predicting CircRNA-Disease Association.

IEEE journal of biomedical and health informatics·2023
Same author

RDRGSE: A Framework for Noncoding RNA-Drug Resistance Discovery by Incorporating Graph Skeleton Extraction and Attentional Feature Fusion.

ACS omega·2023

This study introduces DANE-MDA, a machine learning method for predicting microRNA-disease associations. It enhances accuracy in identifying potential links between microRNAs and diseases.

Area of Science:

  • Bioinformatics
  • Computational Biology
  • Machine Learning

Background:

  • Traditional experimental methods for identifying microRNA-disease associations are time-consuming and expensive.
  • Computational approaches offer a more efficient alternative for predicting these crucial biological relationships.

Purpose of the Study:

  • To develop and validate a novel computational method, DANE-MDA, for predicting microRNA-disease associations.
  • To leverage deep attributed network embedding to integrate structural and attribute features for improved prediction accuracy.

Main Methods:

  • The DANE-MDA method employs deep stacked auto-encoders to extract integrated features from diverse matrix orders.
  • Random forest classifiers are utilized to train the model on these extracted features.
Keywords:
CancerComputational bioinformaticsSystems biology

Related Experiment Videos

  • The method was evaluated using 5-fold cross-validation on the HMDD v2.0 and v3.0 datasets.

    • Main Results:

    • DANE-MDA achieved high performance metrics, including average accuracy (85.59% on v3.0, 83.21% on v2.0), sensitivity (84.23% on v3.0, 80.39% on v2.0), and AUC (0.9264 on v3.0, 0.9113 on v2.0).
    • Case studies demonstrated successful prediction and retrieval of top microRNAs for breast, colon, and lung neoplasms, with 47, 47, and 46 out of the top 50 identified, respectively.

    Conclusions:

    • DANE-MDA effectively predicts microRNA-disease associations by integrating structural and attribute information through deep attributed network embedding.
    • The method shows significant potential for advancing research in microRNA-related diseases and identifying novel diagnostic or therapeutic targets.