Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

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

Diverse crystal size effects in covalent organic frameworks.

Nature communications·2020

Same author

Retroreflection and diffraction of a Bose-Einstein condensate by evanescent standing wave potential.

Scientific reports·2020

Same author

MEX3A is upregulated in esophageal squamous cell carcinoma (ESCC) and promotes development and progression of ESCC through targeting CDK6.

Aging·2020

Same author

Preparation of Programmed Cell Death-Ligand 1 Antibody Nanoparticles Based on Nude Mouse Model and Its Therapeutic Effect on Lung Cancer.

Journal of nanoscience and nanotechnology·2020

Same author

Controlling and optimizing the morphology and microstructure of 3D interconnected activated carbons for high performance supercapacitors.

Nanotechnology·2020

Same author

Clinical outcomes of dialysis patients with COVID-19 in the initial phase of the COVID-19 outbreak in Wuhan, China.

International urology and nephrology·2020

Search research articles

Related Experiment Video

Updated: Jan 8, 2026

A High Throughput MHC II Binding Assay for Quantitative Analysis of Peptide Epitopes

A High Throughput MHC II Binding Assay for Quantitative Analysis of Peptide Epitopes

Published on: March 25, 2014

NeoGuider: neoepitope prediction using advanced feature engineering.

Xiaofei Zhao¹, Lei Wei², Zhen Xie¹

¹MOE Key Lab of Bioinformatics, Bioinformatics Division of BNRIST, Center for Synthetic and Systems Biology and Department of Automation, Tsinghua University, Beijing, China.

Genome Medicine

|December 24, 2025

Summary

NeoGuider, a machine-learning model, accurately predicts cancer immunotherapy neoepitopes. This bioinformatics tool enhances neoepitope discovery and prioritization from sequencing data, improving treatment design.

Keywords:

Cancer immunotherapy Class imbalance Feature engineering Neoantigen Neoepitope Next-generation sequencing Nonlinearity

More Related Videos

A Protocol for Computer-Based Protein Structure and Function Prediction

A Protocol for Computer-Based Protein Structure and Function Prediction

Published on: November 3, 2011

Peptide Scanning-assisted Identification of a Monoclonal Antibody-recognized Linear B-cell Epitope

Peptide Scanning-assisted Identification of a Monoclonal Antibody-recognized Linear B-cell Epitope

Published on: March 24, 2017

Related Experiment Videos

Last Updated: Jan 8, 2026

A High Throughput MHC II Binding Assay for Quantitative Analysis of Peptide Epitopes

A High Throughput MHC II Binding Assay for Quantitative Analysis of Peptide Epitopes

Published on: March 25, 2014

A Protocol for Computer-Based Protein Structure and Function Prediction

A Protocol for Computer-Based Protein Structure and Function Prediction

Published on: November 3, 2011

Peptide Scanning-assisted Identification of a Monoclonal Antibody-recognized Linear B-cell Epitope

Peptide Scanning-assisted Identification of a Monoclonal Antibody-recognized Linear B-cell Epitope

Published on: March 24, 2017

Area of Science:

Computational biology
Immunology
Bioinformatics

Background:

Predicting neoepitope immunogenicity is crucial for developing effective cancer immunotherapies.
Existing prediction methods struggle with nonlinearity and class imbalance in immunogenicity data.

Purpose of the Study:

To develop a machine-learning model, NeoGuider, for accurate prediction of neoepitope immunogenicity.
To create a bioinformatics pipeline for detecting and prioritizing neoepitope candidates.

Main Methods:

Developed NeoGuider, a supervised machine-learning model.
Utilized custom kernel density estimation and centered isotonic regression for supervised feature transformation.
Implemented NeoGuider as a bioinformatics pipeline integrating neoepitope detection and prioritization.

Main Results:

NeoGuider demonstrated superior performance in neoepitope prediction compared to existing methods.
Benchmarking was conducted on 7 cohorts, 113 patients, and 635 immunogenic candidates.
The model effectively addresses nonlinearity and class imbalance in immunogenicity prediction.

Conclusions:

NeoGuider offers a robust and accurate approach for predicting neoepitope immunogenicity.
The bioinformatics pipeline facilitates improved neoepitope discovery for cancer immunotherapy.
NeoGuider is an open-source tool available for broader research application.