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

Mouse Models of Cancer Study02:43

Mouse Models of Cancer Study

4.7K
Mice have long served as models for studying human biology and pathology because of their phylogenetic and physiological similarity with humans. They are also easy to maintain and breed in the laboratory, and hence, many inbred strains are now available for research. Studies on mice have contributed immeasurably to our understanding of cancer biology.
The development of transgenic, knockout, and knock-in mice has led to an exponential increase in their use as model organisms in research,...
4.7K
Mouse Models of Cancer Study02:43

Mouse Models of Cancer Study

2.2K
2.2K
Protein Networks02:26

Protein Networks

3.7K
An organism can have thousands of different proteins, and these proteins must cooperate to ensure the health of an organism. Proteins bind to other proteins and form complexes to carry out their functions. Many proteins interact with multiple other proteins creating a complex network of protein interactions.
These interactions can be represented through maps depicting protein-protein interaction networks, represented as nodes and edges. Nodes are circles that are representative of a protein,...
3.7K
Cancer Survival Analysis01:21

Cancer Survival Analysis

860
Cancer survival analysis focuses on quantifying and interpreting the time from a key starting point, such as diagnosis or the initiation of treatment, to a specific endpoint, such as remission or death. This analysis provides critical insights into treatment effectiveness and factors that influence patient outcomes, helping to shape clinical decisions and guide prognostic evaluations. A cornerstone of oncology research, survival analysis tackles the challenges of skewed, non-normally...
860

You might also read

Related Articles

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

Sort by
Same author

Aberrant acetylation caused by a CDYL splicing mutation contributes to thin mid-piece related asthenoteratozoospermia and male infertility.

Andrology·2025
Same author

Aging-dependent Change in Th17 and Cytokine Response in Multiple Sclerosis.

medRxiv : the preprint server for health sciences·2025
Same author

Comprehensive financial health assessment using Advanced machine learning techniques: Evidence based on private companies listed on ChiNext.

PloS one·2024
Same author

Selective-excitation-based method for measurement of NMR relaxation time.

Analytica chimica acta·2024
Same author

3D variability analysis reveals a hidden conformational change controlling ammonia transport in human asparagine synthetase.

Nature communications·2024
Same author

Investigating the interplay between depression and pregnancy loss: a cross-sectional analysis using NHANES data.

Journal of psychosomatic obstetrics and gynaecology·2024

Related Experiment Video

Updated: Apr 28, 2026

Author Spotlight: Impact of Intergenic Interactions on Disease-Identifying Dark Biomarkers
03:37

Author Spotlight: Impact of Intergenic Interactions on Disease-Identifying Dark Biomarkers

Published on: March 1, 2024

1.6K

M-GNN: A Topology-Enhanced Multi-Modal Graph Neural Network for Cancer Driver Gene Prediction.

Lu Qin1,2, Wen Zhu3, Xinyi Liao4

  • 1School of Mathematics and Statistics, Hainan Normal University, Haikou 571158, China.

Metabolites
|April 27, 2026
PubMed
Summary

M-GNN accurately identifies cancer driver genes by integrating multi-omics data and network topology. This computational tool enhances targeted therapy development by providing robust and interpretable predictions.

Keywords:
cancer driver genesgraph neural networksknowledge distillationmulti-omics integrationtopological feature enhancement

More Related Videos

Discovery of Driver Genes in Colorectal HT29-derived Cancer Stem-Like Tumorspheres
06:52

Discovery of Driver Genes in Colorectal HT29-derived Cancer Stem-Like Tumorspheres

Published on: July 22, 2020

6.0K

Related Experiment Videos

Last Updated: Apr 28, 2026

Author Spotlight: Impact of Intergenic Interactions on Disease-Identifying Dark Biomarkers
03:37

Author Spotlight: Impact of Intergenic Interactions on Disease-Identifying Dark Biomarkers

Published on: March 1, 2024

1.6K
Discovery of Driver Genes in Colorectal HT29-derived Cancer Stem-Like Tumorspheres
06:52

Discovery of Driver Genes in Colorectal HT29-derived Cancer Stem-Like Tumorspheres

Published on: July 22, 2020

6.0K

Area of Science:

  • Computational biology
  • Genomics
  • Bioinformatics

Background:

  • Accurate cancer driver gene identification is crucial for understanding tumorigenesis and developing targeted therapies.
  • Existing graph neural network (GNN) methods for multi-omics integration often fail to fully leverage biological network topology.
  • There is a need for advanced computational tools that can effectively integrate diverse omics data and network information for improved driver gene prediction.

Purpose of the Study:

  • To develop M-GNN, a novel multi-modal GNN framework for accurate cancer driver gene prediction.
  • To enhance feature representation by incorporating knowledge distillation and an attention mechanism for adaptive fusion of omics data.
  • To validate the robustness and interpretability of M-GNN in identifying cancer driver genes.

Main Methods:

  • Utilized separate Graph Convolutional Network (GCN) encoders for four omics data types (mutation, expression, methylation, CNV).
  • Implemented knowledge distillation using soft labels from a pre-trained model to improve feature representation.
  • Employed an attention mechanism for adaptive fusion of omics features and a dual-path classifier (GCN and MLP) to preserve gene properties and network topology.

Main Results:

  • M-GNN achieved the highest or second-highest AUPRC on three public PPI networks compared to five state-of-the-art methods.
  • Ablation studies confirmed the significant contribution of each module within the M-GNN framework.
  • Biological interpretability analysis, including GO enrichment and drug sensitivity analysis, validated the reliability of predicted cancer driver genes.

Conclusions:

  • M-GNN offers a robust and interpretable computational approach for systematic cancer driver gene identification.
  • The framework effectively integrates multi-omics and network data, outperforming existing methods.
  • M-GNN represents a valuable tool for advancing cancer research and the development of targeted therapies.