Machine Learning-Guided Photoresponsive Behavior of Metal Nanoclusters for Biomedical Diagnosis and Therapy: Mechanisms, Applications, and Emerging Perspectives

作者：Hailin Wu · 发表于：International Journal of Applied Science · 年份：2026 · DOI：10.64440/ijas/ijas1005

Metal nanoclusters (MNCs), typically composed of several to hundreds of metal atoms with dimensions below approximately 3 nm, have emerged as a distinctive class of nanomaterials for biomedical diagnosis and therapy. Their ultrasmall dimensions, atomically precise structures, discrete electronic states, tunable surface chemistry, and favorable photophysical properties enable optical responses that differ fundamentally from those of conventional metal nanoparticles. Upon photoexcitation, MNCs may undergo radiative recombination, charge trapping, energy or electron transfer, and nonradiative relaxation, thereby generating photoluminescence, reactive oxygen species, or localized heat. These processes provide the mechanistic basis for biosensing, bioimaging, photodynamic therapy, photothermal therapy, and integrated theranostic applications. Recent advances have further demonstrated that ligand engineering, core alloying, heteroatom doping, aggregation-induced emission, supramolecular assembly, and biomolecular templating can substantially regulate the optical and biological behavior of MNCs. More recently, machine learning (ML) has emerged as an additional design variable capable of accelerating the prediction of nanocluster structures, optical properties, ligand effects, fluorescence behavior, and biological responses. ML-assisted analysis can integrate multidimensional structural, spectroscopic, and biological datasets and thereby facilitate rational rather than trial-and-erro...