Dynamic stability-driven machine learning improves binding pose identification on human serum albumin.

Clinical Snapshot

Key Findings

• P Value: < 0.001 (Holm-corrected)

• Effect Size: Not specified in abstract

• Primary Outcome: Significant improvement in binding pose identification accuracy

• Nnt Or Sensitivity: RMSD ≤ 2.5 Å for pose-level and ≤ 5.0 Å for site-level accuracy

• Confidence Interval: Not reported

Clinical Application

High - requires standard computational resources and 5 ns MD simulations Relevant for TGA drug evaluation processes and PBS pharmacokinetic assessments; applicable to Australian pharmaceutical research institutions Drug development researchers and clinical pharmacologists studying HSA binding

Abstract

Accurate identification of ligand binding modes on human serum albumin (HSA) is important for understanding drug-protein interactions that influence pharmacokinetics, including site-specific competition and protein-binding displacement. However, because HSA is a large, multisite binding protein that permits diverse binding configurations, conventional molecular docking often struggles to distinguish crystal-like poses from nonspecific surface-binding poses using static scoring functions alone. Here, we developed a machine-learning framework for HSA binding-pose identification that incorporates dynamic stability information derived from short molecular dynamics (MD) simulations. Time-dependent interaction patterns observed during MD trajectories, including contact persistence, distance fluctuations, and interaction energy-related descriptors, were quantified as interpretable features and integrated with docking scores. Using Leave-One-PDB-Out cross-validation on 31 HSA-ligand crystal structures, models incorporating MD-derived features significantly outperformed the docking score-only model under both pose-level (root-mean-square deviation [RMSD] ≤ 2.5 Å) and site-level (RMSD ≤ 5.0 Å) criteria (Holm-corrected p < 0.001). External validation using a temporally independent nateglinide-HSA complex further supported the utility of the framework for discriminating plausible binding modes within the HSA setting. Notably, informative dynamic features were obtained from 5 ns MD simulations, indicating that early-stage dynamic behavior is sufficient to improve pose discrimination. These findings show that short MD simulations can provide practically useful and interpretable features for machine-learning-based binding-pose identification on HSA. While broader validation will be required to establish applicability beyond HSA, the proposed framework offers a practical strategy for improving binding-mode analysis in pharmacokinetically relevant HSA studies.

References

1. 1.Kourogi, Y., Ogata, K., Tokunaga, J., & Takamura, N. (2026). Dynamic stability-driven machine learning improves binding pose identification on human serum albumin. Journal of Computer-Aided Molecular Design. https://doi.org/10.33011/livecoms.1.1.5067