MLPA: A Multi-scale Digital Twin Framework for Personalized Cancer Simulation and Treatment Optimization

Abstract

We introduce the Multi-level Parameterized Automata (MLPA), an innovative digital twin model that revolutionizes personalized cancer growth simulation and treatment optimization. MLPA integrates macroscopic electronic health records and microscopic genomic data, employing stochastic cellular automata to model tumor progression and treatment efficacy dynamically. This multi-scale approach enables MLPA to simulate complex cancer behaviors, including metastasis and pharmacological responses, with remarkable precision. Our validation using bioluminescent imaging from mice demonstrates MLPA's exceptional predictive power, achieving an improvement in accuracy over baseline models for tumor growth prediction. The model accurately captures tumors' characteristic S-shaped growth curve and shows high fidelity in simulating various scenarios, from natural progression to aggressive growth and drug treatment responses. MLPA's ability to simulate drug effects through gene pathway perturbation, validated through equivalence testing, underscores its potential as a powerful tool for precision oncology. The framework offers a robust platform for exploring personalized treatment strategies, potentially transforming patient outcomes by optimizing therapy based on individual biological profiles. We present the theoretical foundation, implementation, and validation of MLPA, highlighting its capacity to advance the field of computational oncology and foster more effective, tailored cancer treatment solutions. As we progress towards precision medicine, MLPA stands at the forefront, offering new possibilities in cancer modeling and treatment optimization. The code and imaging dataset used is available at https://github.com/alphamind-club/MLPA.