Machine Learning‐Engineered Nanozyme System for Synergistic Anti‐Tumor Ferroptosis/Apoptosis Therapy
Tianliang Li, Bin Cao, Tianhao Su, Lixing Lin, Dong Wang, Xinting Liu, Haoyu Wan, Haiwei Ji, Zixuan He, Yingying Chen, Lingyan Feng, Tong‐Yi Zhang
Abstract
Nanozymes with multienzyme-like activity have sparked significant interest in anti-tumor therapy via responding to the tumor microenvironment (TME). However, the consequent induction of protective autophagy substantially compromises the therapeutic efficacy. Here, a targeted nanozyme system (Fe-Arg-CDs@ZIF-8/HAD, FZH) is shown, which enhances synergistic anti-tumor ferroptosis/apoptosis therapy by leveraging machine learning (ML). A novel ML model, termed the sequential backward Tree-Classifier for Gaussian Process Regression (TCGPR), is proposed to improve data pattern recognition following the divide-and-conquer principle. Based on this, a Bayesian optimization algorithm is employed to select candidates from the extensive search space. Leveraging this fresh material discovery framework, a novel strategy for enhancing nanozyme-based tumor therapy, has been developed. The results reveal that FZH effectively exerts anti-tumor effects by sequentially responding to the TME, having a cascade reaction to induce ferroptosis. Moreover, the endogenous elevation of high concentration nitric oxide (NO) serves as a direct mechanism for killing tumor cells while concurrently suppressing the protective autophagy induced by oxidative stress (OS), enhancing synergistic ferroptosis/apoptosis therapy. Overall, a novel strategy for improving nanozyme-based tumor therapy has been proposed, underlying the integration of ML, experiments, and biological applications.