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

InstaNovo-P: a de novo peptide sequencing model for phosphoproteomics.

Nature communications·2026
Same author

Chemically synthesized, non-capped and non-polyadenylated peptide-coding RNA efficiently induces antigen-specific CD8<sup>+</sup> T cells.

Nature biomedical engineering·2026
Same author

Preclinical immunogenicity of the LP.8.1-adapted BNT162b2 COVID-19 vaccine.

NPJ vaccines·2026
Same author

A multifunctional g-C<sub>3</sub>N<sub>4</sub>@WO<sub>3</sub> hybrid nanocomposite for integrated SPE-UPLC-DAD determination and photocatalytic degradation of tetracycline hydrochloride.

RSC advances·2026
Same author

Tumor-naïve ctDNA detection with deep learning-enhanced error suppression for sensitive mutation calling.

Genome medicine·2026
Same author

Preclinical assessment of broadly neutralizing HIV-1 antibody BNT351 with optimized pharmacokinetics and potent antiviral activity.

iScience·2026

Related Experiment Video

Updated: Jan 10, 2026

Measuring TCR-pMHC Binding In Situ using a FRET-based Microscopy Assay
19:05

Measuring TCR-pMHC Binding In Situ using a FRET-based Microscopy Assay

Published on: October 30, 2015

12.8K

Assessing data size requirements for training generalizable sequence-based TCR specificity models via pan-allelic

Antoine Delaunay1, Miles McGibbon2, Bachir Djermani3

  • 1InstaDeep Ltd, 5 Merchant Sq, London, UK. a.delaunay@instadeep.com.

Scientific Reports
|November 27, 2025
PubMed
Summary

Developing personalized T cell receptor (TCR) therapies requires predicting TCR-neoepitope binding. Current machine learning models need millions of data points to generalize, far exceeding available data for effective oncology treatments.

Keywords:
OncologyPersonalized T cell therapySample size estimationTCR specificity prediction

More Related Videos

Use of Single Chain MHC Technology to Investigate Co-agonism in Human CD8+ T Cell Activation
12:09

Use of Single Chain MHC Technology to Investigate Co-agonism in Human CD8+ T Cell Activation

Published on: February 28, 2019

10.2K
Stability and Structure of Bat Major Histocompatibility Complex Class I with Heterologous &#946;2-Microglobulin
11:17

Stability and Structure of Bat Major Histocompatibility Complex Class I with Heterologous β2-Microglobulin

Published on: March 10, 2021

6.8K

Related Experiment Videos

Last Updated: Jan 10, 2026

Measuring TCR-pMHC Binding In Situ using a FRET-based Microscopy Assay
19:05

Measuring TCR-pMHC Binding In Situ using a FRET-based Microscopy Assay

Published on: October 30, 2015

12.8K
Use of Single Chain MHC Technology to Investigate Co-agonism in Human CD8+ T Cell Activation
12:09

Use of Single Chain MHC Technology to Investigate Co-agonism in Human CD8+ T Cell Activation

Published on: February 28, 2019

10.2K
Stability and Structure of Bat Major Histocompatibility Complex Class I with Heterologous &#946;2-Microglobulin
11:17

Stability and Structure of Bat Major Histocompatibility Complex Class I with Heterologous β2-Microglobulin

Published on: March 10, 2021

6.8K

Area of Science:

  • Immunology
  • Computational Biology
  • Oncology

Background:

  • Personalized T cell receptor (TCR) therapies for cancer rely on identifying TCRs that bind patient-specific neoepitopes.
  • The vast diversity of TCR and neoepitope repertoires presents a significant challenge for developing generalizable predictive models.

Purpose of the Study:

  • To estimate the required training data size for a machine learning model predicting TCR-pMHC specificity.
  • To assess the generalizability of existing models to unseen TCRs and epitopes.

Main Methods:

  • Validated existing models' limited generalizability to single-residue epitope dissimilarities.
  • Imputed the point-mutation ligandome across 34 human MHC alleles, representing it as a graph.
  • Determined the dominating set of the graph to estimate data requirements.

Main Results:

  • Published TCR specificity models fail to generalize beyond minimal epitope sequence variations.
  • An estimated 1 to 100 million unique epitopes are needed for a generalizable sequence-based TCR specificity prediction model.
  • This requirement is approximately 1000 times larger than current publicly available data.

Conclusions:

  • Current datasets are insufficient for training robust, generalizable TCR specificity prediction models for personalized cancer therapy.
  • Significant expansion of training data is necessary to advance the field of TCR-based oncology treatments.