DeepMetal: A Hierarchical Coarse-to-Fine Framework for Metal-Binding Site Prediction via Protein Language Models and SE(3)-Equivariant Graph Neural Networks
TL;DR
DeepMetal, a hierarchical coarse-to-fine framework that combines ESM-2 residue screening, biophysics-constrained Dynamic Center-Iterative Clustering (DCIC), and a site-level SE(3)-equivariant graph neural network for candidate-site validation and metal typing, is presented.
Abstract
Metal ions serve as essential cofactors in approximately 30%–40% of proteins, and accurate recognition of their binding sites is central to function annotation, drug discovery, and metalloenzyme design. Existing predictors often operate at residue level, generate many false positives, or depend strongly on high-quality bound structures. We present DeepMetal, a hierarchical coarse-to-fine framework that combines ESM-2 residue screening, biophysics-constrained Dynamic Center-Iterative Clustering (DCIC), and a site-level SE(3)-equivariant graph neural network for candidate-site validation and metal typing. On a non-redundant BioLiP2-derived benchmark, DeepMetal achieves an AUROC of 0.775 and an F2 score of 0.533 for transition-metal site localization, outperforming representative baselines MetalNet2 and PinMyMetal under the same intersectional evaluation setting. These results show that sequence-driven screening, geometry-aware assembly, and equivariant validation can jointly improve practical metal-binding site prediction from predicted protein structures.