A Classification Scheme for Inverse Design of Molecules: from Targeted Electronic Properties to Atomicity

TL;DR

This paper proposes a novel classification-based approach for inverse molecular design, predicting atomic composition from targeted electronic properties, achieving over 90% accuracy on a dataset of small organic molecules.

Contribution

It introduces a new classification scheme for inverse molecular design that directly predicts atomicity from electronic properties, a novel approach in the field.

Findings

Achieved over 90% prediction accuracy with various classification methods.

Validated the approach on the QM7b dataset of 7211 molecules.

Demonstrated the feasibility of inverse design via classification.

Abstract

In machine learning and molecular design, there exist two approaches: discriminative and generative. In the discriminative approach dubbed forward design, the goal is to map a set of features/molecules to their respective electronics properties. In the generative approach dubbed inverse design, a set of electronics properties is given and the goal is to find the features/molecules that have these properties. These tasks are very challenging because the chemical compound space is very large. In this study, we explore a new scheme for the inverse design of molecules based on a classification paradigm that takes as input the targeted electronic properties and output the atomic composition of the molecules (i.e. atomicity or atom counts of each type in a molecule). To test this new hypothesis, we analyzed the quantum mechanics QM7b dataset consisting of 7211 small organic molecules and 14 electronic properties. Results obtained using twenty three different classification approaches including a regularized Bayesian neural network show that it is possible to achieve detection/prediction accuracy > 90%.