TUMOR.AI

Project Details

• Fellow: Dr. Chrysovalantis Voutouri

• Coordinator: AnaBioSi-Data Ltd

• Project Acronym: E-TUMOR.AI

• Project Title: Enhancing Tumor Microenvironment and mRNA Vaccine Synergy through In Silico Analysis and AI-Driven Predictive Analytics

• Total Funding: €64,968

• Programme: RESTART 2016–2020, Pillar III – Transformation of the RTDI System

• Duration: 12 months

Summary

Modern cancer immunotherapy faces two formidable challenges: the suppressive nature of the tumor microenvironment (TME) and the limited delivery efficiency of mRNA-based vaccines. The E-TUMOR.AI project aims to confront these issues by developing a sophisticated mathematical and computational framework that simulates the intricate dynamics between tumors, mRNA vaccines, and the immune system.

Building on extensive experience in mathematical modeling of biological systems, the project introduces a novel in silico platform that captures the effects of tumor stiffness, vessel compression, immune cell trafficking, and mRNA pharmacodynamics. The model accounts for multiscale processes, integrating tissue mechanics, vascular biology, and immune interactions to simulate how mechanical and biological barriers affect mRNA vaccine efficacy.

By integrating AI-driven analytics, E-TUMOR.AI will extract predictive biomarkers and define biological programs that govern treatment response. This dual approach—mechanistic modeling and machine learning—will personalize cancer treatment strategies, optimize therapeutic schedules, and improve outcomes across diverse tumor profiles.

Objectives

RO1 – Development of the Mathematical Framework
Develop a comprehensive computational model to simulate the Cancer-Immunity Cycle and the physical and immunological barriers within the TME, incorporating vaccine delivery dynamics and immune system activation.

RO2 – Validation and Calibration
Validate the model using preclinical data and literature-based experimental results. Calibrate model parameters through iterative simulations and comparisons to published tumor response metrics.

RO3 – Predictive Analytics for Optimization
Use AI techniques (including PCA, NMF, and machine learning) to analyze simulation outcomes. Identify key biological programs and optimal intervention points, enabling personalized therapy planning and biomarker discovery.

Innovation

This project introduces a transformative, AI-augmented in silico platform capable of simulating and optimizing mRNA cancer vaccine strategies. Innovations include:

• Mechanistic modeling of TME and its impact on vaccine dynamics

• AI-based identification of predictive biomarkers and biological programs

• Simulation-driven treatment personalization

This integrated approach aims to revolutionize cancer immunotherapy by merging systems biology with real-time predictive analytics, facilitating smarter, patient-specific treatments.