Skip to main content
. Author manuscript; available in PMC: 2025 Oct 29.
Published in final edited form as: J Chem Theory Comput. 2025 Oct 6;21(19):9710–9725. doi: 10.1021/acs.jctc.5c01193

Table 3.

Performance Comparison of PB Free Energy Prediction with and without Geometric Representations, Evaluated Using R2, MAE (kcal/mol), and MAPE (%) Metricsa

method # parameters R2 (↑) MAE (↓) MAPE (↓)
AMBER PBSA
ConvNet 2.0M 0.931 481.947 10.268
PBGNN 0.5M 0.995 151.54 3.822
PBSMALL
ConvNet 2.0M 0.915 1.204 22.187
PBGNN 0.5M 0.968 0.475 8.503
a

Results are reported for two benchmark datasets, AMBER PBSA and PBSMALL. PBGNN, which encodes explicit geometric inputs, consistently achieves superior performance across all metrics and datasets compared to the non-geometry-based ConvNet baseline.