Predicting Neoantigen Immunogenicity from In Vivo Immune Editing
- 1UC San Diego
Abstract
Neoantigen immunogenicity prediction is fundamental to personalized cancer vaccines, tumor-infiltrating lymphocyte (TIL) therapy, and TCR-T cell engineering. Existing computational predictors rely primarily on in-vitro correlates of peptide presentation or models trained against assay-based reactivity, and they are typically validated within a single therapeutic setting. We reasoned that the most direct evidence of neoantigen immunogenicity is longitudinal in-vivo elimination: under immune checkpoint blockade (ICB), subclones bearing recognized neoantigens are selectively depleted over time. Here, we present the Neoantigen Elimination Model (NEMo), a two-compartment (CD8 and CD4) machine learning classifier trained on the in-vivo editing (IVE) of neoantigens across serially sequenced, ICB-treated tumors. By using mechanistically inspired NeoPrecis features designed to capture determinants of immunogenicity beyond MHC binding affinity, NEMo recovered assay-confirmed immunogenic neoantigens across four independent, unseen clinical settings -- pre-existing immunogenicity screening, personalized cancer vaccines, TIL therapy, and a radiotherapy +/- ICB ctDNA cohort -- and stratified progression-free survival more strongly than ELISPOT-confirmed reactivity. The editing signal further revealed an immune-evasion architecture in which oncogenic drivers and neoantigens restricted to lost or silenced HLA alleles are systematically spared from editing.
Related
- Characterization of circulating neoantigen-specific T cell responses and public T cell receptors shaping immune memory in Lynch syndrome carriers
- In Vivo Base Editing of PCSK9 with VERVE-102 for Hypercholesterolemia
- Nanoparticle-Enabled Immune-Dose Shaping in Breast Cancer Radiotherapy: Reconciling Tumor Immunogenicity with Systemic Immune Preservation
- A novel HPV mRNA vaccine candidate: immunogenicity and definition of immune correlates of protection
- The immunogenicity control axis: a multi-omics framework for integrating epigenetic, DNA damage response, and immune states in cancer.
BibTeX
@misc{sears2026predicting,
title = {{Predicting Neoantigen Immunogenicity from In Vivo Immune Editing}},
author = {T. J. Sears and K.-h. Lee and M. Munoz Perez and R. Rasmussen and M. S. Pagadala and K. Tanaka and A. Subramanian and E. J. Moding and M. Zanetti and H. Carter},
howpublished = {bioRxiv},
year = {2026},
month = sep,
doi = {10.64898/2026.09.17.752425},
url = {https://www.biorxiv.org/content/10.64898/2026.09.17.752425v1},
note = {CC BY-NC},
}
RIS
TY - UNPB
TI - Predicting Neoantigen Immunogenicity from In Vivo Immune Editing
AU - T. J. Sears
AU - K.-h. Lee
AU - M. Munoz Perez
AU - R. Rasmussen
AU - M. S. Pagadala
AU - K. Tanaka
AU - A. Subramanian
AU - E. J. Moding
AU - M. Zanetti
AU - H. Carter
PY - 2026
DA - 2026/09/17
PB - bioRxiv
DO - 10.64898/2026.09.17.752425
UR - https://www.biorxiv.org/content/10.64898/2026.09.17.752425v1
AB - Neoantigen immunogenicity prediction is fundamental to personalized cancer vaccines, tumor-infiltrating lymphocyte (TIL) therapy, and TCR-T cell engineering. Existing computational predictors rely primarily on in-vitro correlates of peptide presentation or models trained against assay-based reactivity, and they are typically validated within a single therapeutic setting. We reasoned that the most direct evidence of neoantigen immunogenicity is longitudinal in-vivo elimination: under immune checkpoint blockade (ICB), subclones bearing recognized neoantigens are selectively depleted over time. Here, we present the Neoantigen Elimination Model (NEMo), a two-compartment (CD8 and CD4) machine learning classifier trained on the in-vivo editing (IVE) of neoantigens across serially sequenced, ICB-treated tumors. By using mechanistically inspired NeoPrecis features designed to capture determinants of immunogenicity beyond MHC binding affinity, NEMo recovered assay-confirmed immunogenic neoantigens across four independent, unseen clinical settings -- pre-existing immunogenicity screening, personalized cancer vaccines, TIL therapy, and a radiotherapy +/- ICB ctDNA cohort -- and stratified progression-free survival more strongly than ELISPOT-confirmed reactivity. The editing signal further revealed an immune-evasion architecture in which oncogenic drivers and neoantigens restricted to lost or silenced HLA alleles are systematically spared from editing.
ER -