Machine Learning, Quantum Mechanics, and Chemical Compound Space

TL;DR

This paper reviews recent advances in machine learning models that predict molecular and solid properties based on quantum chemistry data, focusing on applications in chemical space exploration.

Contribution

It provides a comprehensive overview of machine learning approaches applied to quantum chemistry for molecules and materials, highlighting recent developments.

Findings

Machine learning models can accurately predict molecular properties.

Quantum chemistry data effectively train ML models for chemical space.

The review emphasizes the potential of ML in materials discovery.

Abstract

We review recent studies dealing with the generation of machine learning models of molecular and solid properties. The models are trained and validated using standard quantum chemistry results obtained for organic molecules and materials selected from chemical space at random.