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

You might also read

Related Articles

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

Sort by
Same author

Cultural comparison of positive development: network analyses of adolescents' ecological systems in Mainland and non-Mainland China.

BMC psychology·2026
Same author

Magnetic field-assisted immersion freezing preserves starch structure and quality of fresh waxy corn puree.

Food chemistry: X·2026
Same author

Machine learning-guided risk stratification in elderly AML based on genomic, immunophenotypic and therapeutic profiles.

BMC geriatrics·2026
Same author

Zn<sup>2+</sup>/Ca<sup>2+</sup> co-overloaded nano-modulator amplifies reactive oxygen species to potentiate shikonin-induced necroptosis against triple‑negative breast cancer.

Journal of nanobiotechnology·2026
Same author

Advanced Chitin Nanocrystals/CeO<sub>2</sub> Derived Hydrogel for Efficient Solar Steam Generation and Antibacterial Performance.

Small (Weinheim an der Bergstrasse, Germany)·2026
Same author

In Situ Biosynthesis of Pd Nanocrystals in Bifidobacterium Bioreactor as Dual Immune Stimulators for Immuno-Chemodynamic Therapy of Cold Tumor.

Small (Weinheim an der Bergstrasse, Germany)·2026

Related Experiment Video

Updated: Jul 27, 2025

Characterizing Mutational Load and Clonal Composition of Human Blood
07:58

Characterizing Mutational Load and Clonal Composition of Human Blood

Published on: July 11, 2019

7.4K

Graph-ETMB: A graph neural network-based model for tumour mutation burden estimation.

Wanting Yang1, Yan Qiang1, Wei Wu2

  • 1College of Information and Computer, Taiyuan University of Technology, Taiyuan, Shanxi 030000, China.

Computational Biology and Chemistry
|June 7, 2023
PubMed
Summary
This summary is machine-generated.

Tumor mutational burden (TMB) predicts immunotherapy response but whole exome sequencing is costly. A new graph neural network approach developed a small, 20-gene panel for accurate TMB estimation and cost-effective immunotherapy prediction.

Keywords:
Data representationGraph neural networkImmunotherapy efficacyPrognosisTumor mutational burden

More Related Videos

Detecting Somatic Genetic Alterations in Tumor Specimens by Exon Capture and Massively Parallel Sequencing
11:02

Detecting Somatic Genetic Alterations in Tumor Specimens by Exon Capture and Massively Parallel Sequencing

Published on: October 18, 2013

19.5K
Demonstrating a Multi-drug Resistant Mycobacterium tuberculosis Amplification Microarray
07:35

Demonstrating a Multi-drug Resistant Mycobacterium tuberculosis Amplification Microarray

Published on: April 25, 2014

12.8K

Related Experiment Videos

Last Updated: Jul 27, 2025

Characterizing Mutational Load and Clonal Composition of Human Blood
07:58

Characterizing Mutational Load and Clonal Composition of Human Blood

Published on: July 11, 2019

7.4K
Detecting Somatic Genetic Alterations in Tumor Specimens by Exon Capture and Massively Parallel Sequencing
11:02

Detecting Somatic Genetic Alterations in Tumor Specimens by Exon Capture and Massively Parallel Sequencing

Published on: October 18, 2013

19.5K
Demonstrating a Multi-drug Resistant Mycobacterium tuberculosis Amplification Microarray
07:35

Demonstrating a Multi-drug Resistant Mycobacterium tuberculosis Amplification Microarray

Published on: April 25, 2014

12.8K

Area of Science:

  • Oncology
  • Genomics
  • Bioinformatics

Background:

  • Tumor mutational burden (TMB) is a key biomarker for predicting immunotherapy response.
  • Whole exome sequencing (WES) for TMB assessment is limited by high costs, tissue requirements, and long turnaround times.
  • Cancer-specific mutation landscapes necessitate tailored approaches for accurate TMB estimation.

Purpose of the Study:

  • To develop a cost-effective, cancer-specific gene panel for accurate TMB estimation.
  • To utilize a graph neural network framework to address TMB cancer specificity.
  • To predict immunotherapy response using the developed TMB panel.

Main Methods:

  • A graph neural network (GNN) framework, Graph-ETMB, was employed to model correlations between mutated genes.
  • Message-passing and aggregation algorithms were used within the GNN.
  • The GNN was trained on lung adenocarcinoma data using a semi-supervised approach to identify a minimal gene set for TMB estimation.

Main Results:

  • A novel, cancer-specific mutation panel comprising 20 genes (0.16 Mb) was developed.
  • This panel is significantly smaller than most current clinical panels.
  • The panel demonstrated efficacy in predicting immunotherapy response on an independent validation dataset.

Conclusions:

  • The developed Graph-ETMB approach provides a cost-effective and accurate method for TMB estimation.
  • The 20-gene panel facilitates precise clinical decision-making for immunotherapy.
  • This strategy overcomes limitations of WES and improves TMB assessment for cancer treatment.