Why Predicting Which Peptides Will Trigger Anti-Cancer Immune Responses Is Still Hard

Computer prediction of tumor peptide antigens is useful but unreliable — nearly one-third of validated cancer antigens would be missed by standard binding cutoffs.

Lee, Maxwell Y et al.·Journal for immunotherapy of cancer·2020·n/a (review)Review
RPEP-04935Reviewn/a (review)2020RETHINKTHC RESEARCH DATABASErethinkthc.com/research

Quick Facts

Study Type
Review
Evidence
n/a (review)
Sample
N=N/A (review)
Participants
N/A (review of validated T cell cancer antigens)

What This Study Found

Nearly one-third of experimentally validated T cell tumor antigens have MHC binding affinities (IC50 > 500 nM) below standard prediction cutoffs, highlighting the limitations of in silico approaches.

Key Numbers

~33% of validated antigens had IC50 >500 nM; multi-step processing pathway; patient-specific validation recommended

How They Did This

Literature review of antigen processing, presentation, epitope discovery, and computational prediction methods. Validated tumor antigens assessed against predicted MHC class I binding scores.

Why This Research Matters

Personalized cancer vaccines depend on accurately predicting which tumor peptides the immune system will recognize. If algorithms miss one-third of real antigens, patients may receive suboptimal vaccines.

The Bigger Picture

Personalized cancer vaccines (neoantigen vaccines) are a rapidly growing immunotherapy approach. Improving antigen prediction accuracy is critical to making these vaccines effective for more patients.

What This Study Doesn't Tell Us

Review article — no new experimental data generated; computational prediction tools have continued to improve since publication.

Questions This Raises

  • ?Can machine learning approaches trained on validated antigens improve prediction accuracy beyond traditional binding affinity cutoffs?
  • ?Should clinical neoantigen vaccine pipelines use lower IC50 thresholds to avoid missing valid antigens?
  • ?How much does antigen processing (not just MHC binding) contribute to prediction failures?

Trust & Context

Key Stat:
~33% missed Nearly one-third of validated tumor antigens have MHC binding below the standard 500 nM cutoff
Evidence Grade:
N/A — narrative review synthesizing existing literature on antigen processing and prediction accuracy.
Study Age:
Published in 2020; AI-based antigen prediction tools have advanced significantly since then.
Original Title:
Antigen processing and presentation in cancer immunotherapy.
Published In:
Journal for immunotherapy of cancer, 8(2) (2020)
Database ID:
RPEP-04935

Evidence Hierarchy

Meta-Analysis / Systematic Review
Randomized Controlled Trial
Cohort / Case-Control
Cross-Sectional / ObservationalSnapshot without intervening
This study
Case Report / Animal Study

Summarizes existing research on a topic.

What do these levels mean? →

Frequently Asked Questions

What are tumor antigens?

Peptide fragments from mutated or abnormal proteins in cancer cells that the immune system can recognize and attack.

Why can't computers just predict the right vaccine targets?

Antigen processing involves many steps beyond just binding to MHC molecules, and current algorithms oversimplify this complexity, missing about a third of real targets.

Read More on RethinkPeptides

Cite This Study

RPEP-04935·https://rethinkpeptides.com/research/RPEP-04935

APA

Lee, Maxwell Y; Jeon, Jun W; Sievers, Cem; Allen, Clint T. (2020). Antigen processing and presentation in cancer immunotherapy.. Journal for immunotherapy of cancer, 8(2). https://doi.org/10.1136/jitc-2020-001111

MLA

Lee, Maxwell Y, et al. "Antigen processing and presentation in cancer immunotherapy.." Journal for immunotherapy of cancer, 2020. https://doi.org/10.1136/jitc-2020-001111

RethinkPeptides

RethinkPeptides Research Database. "Antigen processing and presentation in cancer immunotherapy." RPEP-04935. Retrieved from https://rethinkpeptides.com/research/lee-2020-antigen-processing-and-presentation

Access the Original Study

Study data sourced from PubMed, a service of the U.S. National Library of Medicine, National Institutes of Health.

This study breakdown was produced by the RethinkPeptides research team. We analyze and report published research findings without making health recommendations. All interpretations are based solely on the published abstract and study data.