Geometric Graph Learning

A multiscale geometric graph-learning scoring function that uses extended atom-type features to model protein–ligand interactions and predict binding affinities with high accuracy.

Geometric Graph Learning for Protein–Protein Interactions (GGL-PPI) integrates geometric graph representation and machine learning to forecast mutation-induced binding free energy changes.

Introduces sybylGGL-Score and ecifGGL-Score, graph-based learning models integrating extensive atom types for state-of-the-art protein-ligand binding affinity prediction.