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 25, 2026

Evaluation of Biomarkers in Glioma by Immunohistochemistry on Paraffin-Embedded 3D Glioma Neurosphere Cultures
06:32

Evaluation of Biomarkers in Glioma by Immunohistochemistry on Paraffin-Embedded 3D Glioma Neurosphere Cultures

Published on: January 9, 2019

Graph informed biomarker discovery framework using transcriptomic machine learning for glioblastoma prognosis.

Osama Mahmoud1, Mahmoud Mounir2, Walaa Gad2

  • 1Information Systems Department, Faculty of Computer and Information Sciences, Ain Shams University, Cairo, Egypt. osama.mahmoud@cis.asu.edu.eg.

Scientific Reports
|June 23, 2026
PubMed
Summary
This summary is machine-generated.

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

Robust transcriptomic signatures of Alzheimer's disease progression: validated explainable AI approach.

Scientific reports·2026
Same author

Comparative analysis of supervised and ensemble models with unsupervised exploration for alzheimer's disease prediction.

Scientific reports·2026
Same author

Knowledge-based question answering using graph neural networks and contextual language representations.

Scientific reports·2026
Same author

Personalized Smart Home Automation Using Machine Learning: Predicting User Activities.

Sensors (Basel, Switzerland)·2025
Same author

A hybrid Stacking-SMOTE model for optimizing the prediction of autistic genes.

BMC bioinformatics·2023
Same author

A diagnostic model for COVID-19 based on proteomics analysis.

Computers in biology and medicine·2023

Graph-Informed Biomarker Discovery (GIBD) integrates gene expression and protein networks to identify glioblastoma prognostic signals. This transcriptomics-only framework shows promise for predicting patient risk and guiding future research.

Area of Science:

  • Bioinformatics
  • Computational Biology
  • Genomics

Background:

  • Identifying reproducible prognostic biomarkers from high-dimensional transcriptomics is difficult due to ignored network context.
  • Gene-level models often fail to capture complex biological interactions crucial for accurate prognosis.

Purpose of the Study:

  • To develop and validate a novel framework, Graph-Informed Biomarker Discovery (GIBD), for identifying prognostic signals in primary glioblastoma.
  • To integrate RNA-sequencing data with protein-protein interaction networks for robust biomarker discovery.

Main Methods:

  • GIBD framework construction using weighted protein-protein interaction (WPPI) features from STRING and RNA-seq data.
  • Model development, feature selection, and threshold setting were performed exclusively on The Cancer Genome Atlas (TCGA) cohort.
Keywords:
External validationGlioblastomaGraph-informed machine learningPrognostic modelingTranscriptomicsWeighted protein–protein interaction

More Related Videos

Generating the Transcriptional Regulation View of Transcriptomic Features for Prediction Task and Dark Biomarker Detection on Small Datasets
03:37

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

Published on: March 1, 2024

Related Experiment Videos

Last Updated: Jun 25, 2026

Evaluation of Biomarkers in Glioma by Immunohistochemistry on Paraffin-Embedded 3D Glioma Neurosphere Cultures
06:32

Evaluation of Biomarkers in Glioma by Immunohistochemistry on Paraffin-Embedded 3D Glioma Neurosphere Cultures

Published on: January 9, 2019

Generating the Transcriptional Regulation View of Transcriptomic Features for Prediction Task and Dark Biomarker Detection on Small Datasets
03:37

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

Published on: March 1, 2024

  • External validation of the locked GIBD-XGBoost K100 model was conducted using the Chinese Glioma Genome Atlas (CGGA) cohort.

    • Main Results:

    • The locked GIBD-XGBoost K100 model, using 100 features, achieved an out-of-fold AUC of 0.617 in TCGA and an AUC of 0.609 in the CGGA cohort.
    • External validation in CGGA demonstrated a sensitivity of 73.9%, specificity of 50.6%, and balanced accuracy of 62.3%.
    • SHAP analysis identified TSPAN13 as a key contributor, and Gene Set Enrichment Analysis (GSEA) revealed significant enrichment of inflammatory, hypoxic, and angiogenic pathways in high-risk groups.

    Conclusions:

    • GIBD successfully developed a locked, transcriptomics-only prognostic model for glioblastoma, demonstrating external validation potential.
    • The framework identified key biological pathways associated with high-risk glioblastoma, including inflammation and angiogenesis.
    • The GIBD model provides a promising transcriptomic risk-prioritization signal that warrants further prospective recalibration and multimodal validation for clinical translation.