Efficient Chemical Space Exploration Using Active Learning Based on Marginalized Graph Kernel: an Application for Predicting the Thermodynamic Properties of Alkanes with Molecular Simulation

TL;DR

This paper presents an active learning framework combining Gaussian process regression and marginalized graph kernels to efficiently explore chemical space and accurately predict thermodynamic properties of alkanes with minimal data.

Contribution

The study introduces a novel active learning algorithm that effectively reduces data requirements for molecular property prediction using high-throughput simulations and graph neural networks.

Findings

Only 313 molecules needed for high-accuracy GNN models

Achieved R^2 > 0.99 on computational test sets

Demonstrated reliable uncertainty quantification

Abstract

We introduce an explorative active learning (AL) algorithm based on Gaussian process regression and marginalized graph kernel (GPR-MGK) to explore chemical space with minimum cost. Using high-throughput molecular dynamics simulation to generate data and graph neural network (GNN) to predict, we constructed an active learning molecular simulation framework for thermodynamic property prediction. In specific, targeting 251,728 alkane molecules consisting of 4 to 19 carbon atoms and their liquid physical properties: densities, heat capacities, and vaporization enthalpies, we use the AL algorithm to select the most informative molecules to represent the chemical space. Validation of computational and experimental test sets shows that only 313 (0.124\% of the total) molecules were sufficient to train an accurate GNN model with $\rm R^2 > 0.99$ for computational test sets and $\rm R^2 > 0.94$ for experimental test sets. We highlight two advantages of the presented AL algorithm: compatibility with high-throughput data generation and reliable uncertainty quantification.