Transferring Chemical and Energetic Knowledge Between Molecular Systems with Machine Learning

TL;DR

This paper introduces a machine learning method that transfers knowledge from simple to complex molecular systems using hypergraph representations, achieving high accuracy in classifying free-energy states and clustering structures.

Contribution

It presents a novel hypergraph-based transfer learning approach with new message passing layers for molecular property prediction, demonstrating effectiveness on complex biomolecular systems.

Findings

Achieved AUC of 0.92 in transfer learning from tri-alanine to deca-alanine.

Successfully clustered secondary structures with similar free-energy values.

Proved the feasibility of reliable transfer learning models for molecular systems.

Abstract

Predicting structural and energetic properties of a molecular system is one of the fundamental tasks in molecular simulations, and it has use cases in chemistry, biology, and medicine. In the past decade, the advent of machine learning algorithms has impacted on molecular simulations for various tasks, including property prediction of atomistic systems. In this paper, we propose a novel methodology for transferring knowledge obtained from simple molecular systems to a more complex one, possessing a significantly larger number of atoms and degrees of freedom. In particular, we focus on the classification of high and low free-energy states. Our approach relies on utilizing (i) a novel hypergraph representation of molecules, encoding all relevant information for characterizing the potential energy of a conformation, and (ii) novel message passing and pooling layers for processing and making predictions on such hypergraph-structured data. Despite the complexity of the problem, our results show a remarkable AUC of 0.92 for transfer learning from tri-alanine to the deca-alanine system. Moreover, we show that the very same transfer learning approach can be used to group, in an unsupervised way, various secondary structures of deca-alanine in clusters having similar free-energy values. Our study represents a proof of concept that reliable transfer learning models for molecular systems can be designed paving the way to unexplored routes in prediction of structural and energetic properties of biologically relevant systems.