Spectral Decomposition of Chemical Semantics for Activity Cliffs-Aware Molecular Property Prediction

Accurately predicting physicochemical and biological properties of molecules is vital for modern drug discovery, yet existing deep learning models struggle to replicate the multi-level reasoning of chemists. Relying on single molecular graphs, they fail to capture the interplay among global scaffolds, functional groups, and pharmacophoric patterns, and often miss subtle perturbations causing "activity cliffs". PrismNet is proposed as a spectral graph network that mimics chemical intuition through a computational prism analogy. It applies a dual-decomposition strategy: refracting molecules into three chemical perspectives-scaffolds, functional groups, and pharmacophores-and resolving each into spectral frequencies. A dynamic learning strategy further enhances its ability to handle heterogeneous data. PrismNet achieves state-of-the-art performance across 64 benchmark datasets, including 30 activity cliff datasets. Importantly, its predictions are chemically interpretable, autonomously identifying key substructures aligned with known structure-activity relationships. This framework unifies multi-scale semantics and spectral decomposition, enabling reliable and trustworthy in silico screening for drug discovery.