Machine Learning of Molecular Electronic Properties in Chemical Compound Space

TL;DR

This paper introduces a deep multi-task neural network trained on ab initio data to accurately predict multiple electronic properties of organic molecules, enabling rapid virtual screening with quantum-chemical level precision.

Contribution

The work presents a novel multi-task deep learning model that predicts various electronic properties simultaneously, leveraging correlations between them for improved accuracy and efficiency.

Findings

Model achieves accuracy comparable or superior to quantum-chemical methods.

Predictions are obtained at negligible computational cost.

Applicable to high-throughput screening of organic molecules.

Abstract

The combination of modern scientific computing with electronic structure theory can lead to an unprecedented amount of data amenable to intelligent data analysis for the identification of meaningful, novel, and predictive structure-property relationships. Such relationships enable high-throughput screening for relevant properties in an exponentially growing pool of virtual compounds that are synthetically accessible. Here, we present a machine learning (ML) model, trained on a data base of \textit{ab initio} calculation results for thousands of organic molecules, that simultaneously predicts multiple electronic ground- and excited-state properties. The properties include atomization energy, polarizability, frontier orbital eigenvalues, ionization potential, electron affinity, and excitation energies. The ML model is based on a deep multi-task artificial neural network, exploiting underlying correlations between various molecular properties. The input is identical to \emph{ab initio} methods, \emph{i.e.} nuclear charges and Cartesian coordinates of all atoms. For small organic molecules the accuracy of such a "Quantum Machine" is similar, and sometimes superior, to modern quantum-chemical methods---at negligible computational cost.