P. Maini

Learning to Adapt - Deep Reinforcement Learning in Treatment-Resistant Prostate Cancer

This paper applies deep reinforcement learning to adaptive drug scheduling in prostate cancer, showing it can extend time to progression by up to a quarter and outperform current protocols.

Adaptive therapy for ovarian cancer: An integrated approach to PARP inhibitor scheduling

This study develops an adaptive therapy protocol for PARP inhibitors by combining mathematical modeling and experiments to optimize treatment scheduling and mitigate resistance.

Turnover modulates the need for a cost of resistance in adaptive therapy

This study investigates whether a cost of resistance is necessary for adaptive therapy to delay cancer progression, finding that cell turnover modulates this requirement depending on tumor growth conditions.

The Goldilocks Window of Personalized Chemotherapy: An Immune Perspective

This study uses mathematical modeling to show that optimal chemotherapy scheduling must balance tumor reduction and immune preservation to maximize treatment efficacy.

Dissecting targeted therapy resistance: Integrating models to quantify environment mediated drug resistance

This paper quantifies environmental contributions to drug resistance in melanoma, revealing heterogeneity that impacts treatment dynamics and suggests strategies to target both tumor and stroma.