REVIEW article
Front. Oncol.
Sec. Molecular and Cellular Oncology
This article is part of the Research TopicDecoding Cancer Complexity with Artificial Intelligence and Molecular Level Studies: Informatics-Driven Approaches for Therapeutic InnovationView all articles
AI-Powered Mapping of Tumor Immunity for Optimized mRNA Vaccine Engineering
Provisionally accepted
- Indian Institute of Technology Bombay, Mumbai, India
Select one of your emails
You have multiple emails registered with Frontiers:
Notify me on publication
Please enter your email address:
If you already have an account, please login
You don't have a Frontiers account ? You can register here
Messenger RNA (mRNA) vaccines represent a versatile and scalable platform for cancer immunotherapy; however, their clinical efficacy depends critically on precise vaccine design capable of eliciting robust, selective, and durable antitumor immune responses. Recent advances in bioinformatics and artificial intelligence (AI) have substantially improved the rational design, evaluation, and optimization of mRNA-based cancer vaccines. In particular, personalized vaccine strategies targeting patient-specific tumor neoantigens have demonstrated significant promise, although challenges remain in accurately identifying immunogenic targets within highly heterogeneous tumors and overcoming immune evasion mechanisms. Machine learning and deep learning approaches enhance neoantigen prediction by integrating peptide–major histocompatibility complex (MHC) binding, antigen processing, and T cell receptor recognition, thereby improving immunogenicity assessment beyond conventional pipelines. AI-driven mRNA sequence optimization including codon usage refinement and untranslated region (UTR) engineering further enhances protein expression, translation efficiency, and mRNA stability. In parallel, AI-guided modeling of mRNA secondary structures and lipid nanoparticle (LNP) formulations supports efficient intracellular delivery, improved stability, and controlled immune activation. This review provides a structured overview of AI-enabled computational frameworks for mRNA cancer vaccine development and offers practical guidance for integrating in silico predictions with experimental validation. By addressing tumor heterogeneity, antigen processing constraints, and patient-specific immune landscapes, bioinformatics-driven strategies enable more rational and translatable mRNA vaccine design. Collectively, these advances establish a robust foundation for the development of personalized mRNA-based cancer immunotherapies with improved immunogenicity and therapeutic efficacy.
Keywords: 5′ UTR, codon optimization, deep learning, Immunotherapy, mRNA design, Neoantigen prediction, personalized cancer vaccines
Received: 12 Dec 2025; Accepted: 29 Jan 2026.
Copyright: © 2026 Srivastava. This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) or licensor are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms.
* Correspondence: Ruby Srivastava
Disclaimer: All claims expressed in this article are solely those of the authors and do not necessarily represent those of their affiliated organizations, or those of the publisher, the editors and the reviewers. Any product that may be evaluated in this article or claim that may be made by its manufacturer is not guaranteed or endorsed by the publisher.