A kernel-based approach to molecular conformation analysis

TL;DR

This paper introduces a kernel-based machine learning framework that unifies and extends existing methods for analyzing biomolecular conformation dynamics, demonstrated on molecular simulation data.

Contribution

It presents a novel approach combining kernel methods with transfer operator theory, unifying existing techniques and enabling new efficient algorithms for molecular conformation analysis.

Findings

Unified framework encompasses Markov State Models, EDMD, TICA

New algorithms outperform traditional methods in examples

Effective analysis demonstrated on alanine dipeptide and NTL9

Abstract

We present a novel machine learning approach to understanding conformation dynamics of biomolecules. The approach combines kernel-based techniques that are popular in the machine learning community with transfer operator theory for analyzing dynamical systems in order to identify conformation dynamics based on molecular dynamics simulation data. We show that many of the prominent methods like Markov State Models, EDMD, and TICA can be regarded as special cases of this approach and that new efficient algorithms can be constructed based on this derivation. The results of these new powerful methods will be illustrated with several examples, in particular the alanine dipeptide and the protein NTL9.