Efficient Chemical Space Exploration Using Active Learning Based on Marginalized Graph Kernel: an Application for Predicting the Thermodynamic Properties of Alkanes with Molecular Simulation
This work addresses the challenge of high computational cost in molecular simulation for chemists and materials scientists, offering an incremental improvement by integrating active learning with existing methods.
The researchers tackled the problem of efficiently exploring chemical space for predicting thermodynamic properties of alkanes by developing an active learning algorithm based on Gaussian process regression and marginalized graph kernel, achieving accurate predictions with only 313 molecules (0.124% of the total) for computational test sets (R² > 0.99) and experimental test sets (R² > 0.94).
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.