Discovery of structure-property relations for molecules via hypothesis-driven active learning over the chemical space

TL;DR

This paper introduces a hypothesis-driven active learning framework using Gaussian processes to efficiently explore chemical space and discover structure-property relationships, improving robustness over traditional methods.

Contribution

The authors develop a novel active learning approach combining hypothesis learning with Gaussian processes, inspired by symbolic regression, for better exploration of chemical space.

Findings

Effective in approximating physical laws in chemical datasets

Demonstrated on QM9 dataset with promising results

Framework applicable to molecular and solid-state materials

Abstract

Discovery of the molecular candidates for applications in drug targets, biomolecular systems, catalysts, photovoltaics, organic electronics, and batteries, necessitates development of machine learning algorithms capable of rapid exploration of the chemical spaces targeting the desired functionalities. Here we introduce a novel approach for the active learning over the chemical spaces based on hypothesis learning. We construct the hypotheses on the possible relationships between structures and functionalities of interest based on a small subset of data and introduce them as (probabilistic) mean functions for the Gaussian process. This approach combines the elements from the symbolic regression methods such as SISSO and active learning into a single framework. The primary focus of constructing this framework is to approximate physical laws in an active learning regime toward a more robust predictive performance, as traditional evaluation on hold-out sets in machine learning doesn't account for out-of-distribution effects and may lead to a complete failure on unseen chemical space. Here, we demonstrate it for the QM9 dataset, but it can be applied more broadly to datasets from both domains of molecular and solid-state materials sciences.