METHODS article
Front. Immunol.
Sec. Vaccines and Molecular Therapeutics
This article is part of the Research TopicData-Driven Vaccine Design for Microbial-Associated DiseasesView all 10 articles
A Computational Framework for Optimizing mRNA Vaccine Delivery via AI-Guided Nanoparticle Design and In Silico Gene Expression Profiling
Provisionally accepted
- Department of Health and Drug Sciences, University of Catania, Catania, Italy
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
Recent concerns about off-target immune activation following non-targeted mRNA vaccine delivery have prompted the need for rational design strategies that optimize nanoparticle formulations. Building upon our previous in silico work using the Universal Immune System Simulator to characterize immune responses to mRNA vaccines, we present a computational framework that integrates synthetic transcriptomics with artificial intelligence-driven optimization to guide the development of safer and more targeted lipid nanoparticles. We generated biologically informed, synthetic RNA-seq datasets to emulate gene expression profiles in immune-related tissues post-vaccination. Differential gene expression analysis identified compartment-specific transcriptional responses, which were then used to construct a risk index based on predicted immune activation and the number of upregulated immune markers. Parallelly, we trained a Random Forest regression model on simulated lipid nanoparticles formulations to predict immune activation values and embedded this model into a genetic algorithm to identify optimal lipid nanoparticles design parameters (size, charge, polyethylene glycol content, and targeting). The proposed framework enables early-stage, fully in silico screening of mRNA vaccine delivery strategies. Our results highlight the potential of combining mechanistic immune modeling, synthetic transcriptomic validation, and Artificial Intelligence-based design to accelerate the development of safer and more effective mRNA-based therapies. By enabling rapid, data-driven optimization of delivery systems prior to experimental validation, this approach can significantly shorten vaccine development timelines, reduce costs, and support the creation of more personalized and adaptable immunization strategies. In the long term, this paradigm shift toward computationally guided vaccine development could redefine the future of immunization, paving the way for next-generation vaccines that are safer, more targeted, and rapidly adaptable to emerging infectious threats and individual patient needs.
Keywords: mRNA vaccines, Lipid nanoparticles, synthetic transcriptomics, AI-driven optimization, immune modeling, synthetic omics data, optimization algorithms, Vaccine delivery
Received: 14 May 2025; Accepted: 18 Nov 2025.
Copyright: © 2025 Di Salvatore, Russo and Pappalardo. 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: Valentina Di Salvatore, valentinadisalvatore@unict.it
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.