# More Sophisticated Is Not Always Better: A Comparison of Similarity Measures for Unsupervised Learning of Pathways in Biomolecular Simulations

## TL;DR

This paper compares different similarity measures for analyzing molecular simulation data and finds that simpler methods can be as effective as more complex ones.

## Contribution

The study evaluates and compares the effectiveness of four similarity measures in clustering biomolecular simulation trajectories.

## Key findings

- Wasserstein distances provided the best clustering performance in a streptavidin–biotin system.
- Euclidean distances were sufficient for meaningful clustering in a more complex A2a receptor-inhibitor system.
- More sophisticated similarity measures did not consistently outperform simpler ones.

## 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.