More Sophisticated Is Not Always Better: A Comparison of Similarity Measures for Unsupervised Learning of Pathways in Biomolecular Simulations
Open Access
- 8 October 2025
- journal article
- Published by American Chemical Society (ACS) in The Journal of Physical Chemistry B
- Vol. 129 (42) , 10956-10966
Abstract
Finding process pathways in molecular simulations such as the unbinding paths of small molecule ligands from their binding sites at protein targets in a set of trajectories via unsupervised learning approaches requires the definition of a suitable similarity measure between trajectories. Here, we evaluate the performance of four such measures with varying degree of sophistication, i.e., Euclidean and Wasserstein distances, Procrustes analysis, and dynamic time warping, when analyzing trajectory data from two different biased simulation driving protocols in the form of constant velocity constraint targeted MD and steered MD. In a streptavidin-biotin benchmark system with known ground truth clusters, Wasserstein distances yielded the best clustering performance, closely followed by Euclidean distances, both being the most computationally efficient similarity measures. In a more complex A2a receptor-inhibitor system, however, the simplest measure, i.e., Euclidean distances, was sufficient to reveal meaningful and interpretable clusters.Keywords
All Related Versions
Funding Information
- Deutsche Forschungsgemeinschaft (FOR 5099 - 431 945 604, INST 37/935-1 FUGG, WO 2410/2-1)
- Ministerium f??r Wissenschaft, Forschung und Kunst Baden-W??rttemberg
This publication has 63 references indexed in Scilit:
- Residence time in drug discovery: current insights and future perspectivesPharmacological Reports, 2025
- WASCO: A Wasserstein-based Statistical Tool to Compare Conformational Ensembles of Intrinsically Disordered ProteinsJournal of Molecular Biology, 2023
- New approaches for computing ligand–receptor binding kineticsCurrent Opinion in Structural Biology, 2018
- Kinetics for Drug Discovery: an industry-driven effort to target drug residence timeDrug Discovery Today, 2017
- A review of moving object trajectory clustering algorithmsArtificial Intelligence Review, 2016
- Generalizing DTW to the multi-dimensional case requires an adaptive approachData Mining and Knowledge Discovery, 2016
- Optimal Transport2009
- Steered Molecular Dynamics1999
- Targeted molecular dynamics: A new approach for searching pathways of conformational transitionsJournal of Molecular Graphics, 1994
- Generalized Procrustes AnalysisPsychometrika, 1975