Exploring Chemical Compound Space with Quantum-Based Machine Learning

TL;DR

This paper discusses how combining quantum mechanical calculations with machine learning enables efficient exploration of chemical compound space, advancing the design of molecules with desired properties.

Contribution

It provides a perspective on recent advances in QM-based ML methods for exploring chemical space and outlines future challenges in the field.

Findings

Integration of QM and ML accelerates compound property prediction.

Systematic approaches improve exploration of chemical space.

Combining physical theories with ML enhances understanding of molecular properties.

Abstract

Rational design of compounds with specific properties requires conceptual understanding and fast evaluation of molecular properties throughout chemical compound space (CCS) -- the huge set of all potentially stable molecules. Recent advances in combining quantum mechanical (QM) calculations with machine learning (ML) provide powerful tools for exploring wide swaths of CCS. We present our perspective on this exciting and quickly developing field by discussing key advances in the development and applications of QM-based ML methods to diverse compounds and properties and outlining the challenges ahead. We argue that significant progress in the exploration and understanding of CCS can be made through a systematic combination of rigorous physical theories, comprehensive synthetic datasets of microscopic and macroscopic properties, and modern ML methods that account for physical and chemical knowledge.