Unraveling the Power of NAP-CNB’s Machine Learning-Enhanced Tumor Neoantigen Prediction

Aug 5, 2026

Upload by Sage

Proof-of-concept classical vaccination experiments validate the in silico identification of tumor neoantigens using the machine learning-based NAP-CNB platform. Unlike other TNA predictors, NAP-CNB leverages RNA-seq data to incorporate the relative expression of neoantigens in tumors. In mice, predicted TNAs elicit potent antitumor responses after classical vaccination. Optimal activity occurs when targeting the more highly expressed antigen, not necessarily the most immunogenic. Multi-neoantigen vaccination markedly improves responses compared with individual neoantigens, supporting NAP-CNB for personalized immunotherapy development.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages10

Reading Time25 min

AccessFree to download

Introduction

Tumor neoantigens and immunotherapy challenges

Neoantigen prediction and need for validation

NAP-CNB platform overview

Short report / Abstract

Proof-of-concept vaccination validation with NAP-CNB

Key findings: expression-driven targeting and multiantigen synergy

SHORT REPORT Unraveling the power of NAP-CNB’s machine learning-enhanced tumor neoantigen prediction Almudena Mendez-Perez1, Andres M Acosta-Moreno1, Carlos Wert-Carvajal1,2, Pilar Ballesteros-Cuartero1, Ruben Sánchez-García1,3, Jose R Macias1, Rebeca Sanz-Pamplona4,5, Ramon Alemany6, Carlos Oscar Sorzano1, Arrate Munoz-Barrutia2, Esteban Veiga1* 1Centro Nacional de Biotecnología, Consejo Superior de Investigaciones Científicas, Madrid, Spain; 2 Departamento de Bioingenieria, Universidad Carlos III de Madrid, Leganés, Madrid, Spain; 3 University of Oxford, Department of Statistics & XChem, Oxford, United Kingdom; 4Catalan Institute of Oncology (ICO), Oncobell Program, Bellvitge Biomedical Research Institute (IDIBELL), L'Hospitalet de Llobregat, Barcelona, Spain; 5 University Hospital Lozano Blesa, Aragon Health Research Institute (IISA), ARAID Foundation, Aragon Government, Zaragoza, Spain; 6 Procure Program, Institut Català d'Oncologia-Oncobell Program, Catalan Institute of Oncology (ICO), Oncobell Program, Bellvitge Biomedical Research Institute (IDIBELL), L'Hospitalet de Llobregat, Barcelona, Spain *For correspondence: [eveiga@cnb.csic.es](eveiga@cnb.csic.es) Competing interest: The authors declare that no competing interests exist. Funding: See page 8 Preprint posted 22 November 2023 Sent for Review 07 January 2024 Reviewed preprint posted 05 June 2024 Reviewed preprint revised 12 February 2025 Version of Record published 11 March 2025 Reviewing Editor: Neeha Zaidi, Johns Hopkins University, United States Copyright Mendez-Perez et al. This article is distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use and redistribution provided that the original author and source are credited. | eLife Assessment
Veiga et al demonstrate the importance of incorporating RNAseq and machine learning approaches for neoantigen prediction. The evidence is convincing, and these findings contribute important information towards the selection of neoantigens for personalized antitumor vaccination. | | --- | | Abstract In this study, we present a proof-of-concept classical vaccination experiment that validates the in silico identification of tumor neoantigens (TNAs) using a machine learning-based platform called NAP-CNB. Unlike other TNA predictors, NAP-CNB leverages RNA-seq data to consider the relative expression of neoantigens in tumors. Our experiments show the efficacy of NAP-CNB. Predicted TNAs elicited potent antitumor responses in mice following classical vaccination protocols. Notably, optimal antitumor activity was observed when targeting the antigen with higher expression in the tumor, which was not the most immunogenic. Additionally, the vaccination combining different neoantigens resulted in vastly improved responses compared to each one individually, showing the worth of multiantigen-based approaches. These findings validate NAP-CNB asan innovative TNA identification platform and make a substantial contribution to advancing the next generation of personalized immunotherapies. | Introduction A new window of hope to treat previously intractable tumors is emerging through immunotherapies (Chen and Mellman, 2013) . However, the response rates of these therapies remain low and relapses are common (Kalbasi and Ribas, 2020; Novello et al., 2023) . Moreover, the severe undesired side Mendez-Perez et al. eLife 2024;13:RP95010. DOI: [https://doi.org/10.7554/eLife.95010](https://doi.org/10.7554/eLife.95010) 1 of 10 Short report Cancer Biology | Immunology and Inflammation effects induce many patients to abandon the treatments (Kalbasi and Ribas, 2020), highlighting the urgent need for more specific novel therapies. In this regard, the main challenges for most anticancer immunotherapies are the identification of tumor-specific antigens (neoantigens) (Schumacher and Schreiber, 2015) to avoid undesired side effects and the development of mult

FAQs

What is NAP-CNB and what problem does it address?

NAP-CNB uses RNA-seq data to consider the relative expression of neoantigens in tumors, rather than relying on RNA-seq expression less directly than alternative predictors.

Which neoantigen targeting strategy produced optimal antitumor activity in mice?

Optimal antitumor activity was observed when targeting the antigen with higher expression in the tumor, even when it was not the most immunogenic.

Why are multiantigen vaccination approaches beneficial in the study?

Combining different neoantigens produced vastly improved antitumor responses compared with each neoantigen used individually, supporting multiantigen-based strategies.

Aug 5, 2026

Upload by Sage