Ligand unbinding pathway and mechanism analysis assisted by machine learning and graph methods

TL;DR

This paper introduces two machine learning and graph-based methods to analyze protein-ligand unbinding pathways from biased simulations, improving path identification and clustering accuracy.

Contribution

It presents novel clustering approaches combining contact PCA with machine learning and graph algorithms to better understand unbinding mechanisms.

Findings

Contact PCA combined with machine learning effectively clusters unbinding trajectories.

Neighbor-net algorithm outperforms dendrograms in biased data clustering.

Reaction coordinate detection remains challenging in complex unbinding cases.

Abstract

We present two methods to reveal protein-ligand unbinding mechanisms in biased unbinding simulations by clustering trajectories into ensembles representing unbinding paths. The first approach is based on a contact principal component analysis for reducing the dimensionality of the input data, followed by identification of unbinding paths and training a machine learning model for trajectory clustering. The second approach clusters trajectories according to their pairwise mean Euclidean distance employing the neighbor-net algorithm, which takes into account input data bias in the distances set and is superior to dendrogram construction. Finally, we describe a more complex case where the reaction coordinate relevant for path identification is a single intra-ligand hydrogen bond, highlighting the challenges involved in unbinding path reaction coordinate detection.