Oncolytic viral therapy (OVT) is an emerging precision therapy for aggressive and recurrent cancers. However, its clinical efficacy is hindered by the complexity of tumor-virus-immune interactions and the lack of predictive models for personalized treatment. This pilot study develops a data-driven, and AI-powered computational model combining time-delayed Generalized Lotka–Volterra (GLV) equations with advanced optimization algorithms, including Genetic Algorithms (GA), Differential Evolution (DE), and Reinforcement Learning (RL) to optimize OVT oscillations’ growth and damping. We hypothesize that the model can provide accurate, real-time predictions of OVT responses while identifying key biomarkers to enhance therapeutic efficacy. We demonstrate the model’s strong predictive accuracy (MSE 0.82) and its capacity to identify experimentally validated biomarkers such as TNF, NF-kB, CD81, TRAF2, IL18, and BID, among other inflammatory cytokines and extracellular matrix reconstruction factors, despite being causally agnostic and unaware of specific experimental conditions or therapeutic combinations. Gene set enrichment analysis computationally identified pathway-level similarities between combined OVT and immune checkpoint blockade and photodynamic therapy, suggesting predictive convergence in immune signaling programs . To our knowledge, this is the first in silico integration of time-delay GLV predator–prey modeling with explainable AI for OVT predictions, recovering experimentally validated biomarkers in an unbiased, data-agnostic forecast. This hybrid model represents a significant step toward precision oncology and computational medicine, enabling longitudinal, adaptive treatment regimens, and the development of targeted immunotherapies based on molecular signatures, potentially improving patient outcomes in predictive medicine.
Uthamacumaran et al. (Sun,) studied this question.