Deep learning of tautomer stability from crystallographic proton positions

Tautomerism plays a central role in molecular recognition, physicochemical properties, and chemical reactivity, yet rapid identification of stable tautomeric states remains a persistent challenge in molecular design and structure-based drug discovery. Quantum-mechanical approaches are often too computationally demanding for library-scale application, while rule-based and 3D-dependent machine-learning methods remain limited in either transferability or throughput. Here, we show that experimentally resolved hydrogen positions in the Cambridge Structural Database (CSD) provide a powerful large-scale source of supervision for learning tautomer stability. Using more than 1.1 million tautomeric states derived from proton-resolved crystal structures, we trained a 2D graph neural network that predicts stable tautomeric states directly from molecular topology, without conformer generation or quantum calculations. The model achieved a recall of 0.97 and a precision of 0.88 on a comprehensive test set spanning crystal structures, aqueous-solution benchmarks, and drug-like molecules, demonstrating encouraging performance across crystalline and aqueous environments. Applied to 5075 PDBbind ligands with multiple tautomeric states, the model identified 126 cases in which the assigned tautomeric state is likely incorrect; in each case, the reassigned stable tautomer exhibited improved hydrogen-bonding patterns together with fewer unsatisfied polar atoms. We further developed an open-source workflow, Tautomer-Predictor, capable of processing the 4.6-million-compound Enamine collection in about 3.2 h on a single GPU-enabled node. Together, these results establish crystallographic proton placement as a rich and underexploited source of chemical knowledge for learning tautomer stability, and provide a practical route to large-scale tautomer assignment for molecular discovery.