Multi-Objective Evolutionary Design of Molecules with Enhanced Nonlinear Optical Properties

TL;DR

This paper compares various evolutionary algorithms for designing molecules with enhanced nonlinear optical properties, balancing multiple objectives and exploring diverse chemical structures.

Contribution

It systematically evaluates multiple algorithms, including quality diversity methods, for multi-objective molecular design, highlighting their strengths and weaknesses.

Findings

NSGA-II achieves high scores in all objectives.

MOME explores a wider chemical space with higher diversity.

Multiple promising molecules were identified by different methods.

Abstract

Nonlinear optical (NLO) materials are essential for many photonic, telecommunication, and laser technologies, yet discovering better NLO molecules is computationally challenging due to the vast chemical space and competing objectives. We compare evolutionary algorithms for molecular design, targeting four objectives: maximizing the ratio of first-to-second hyperpolarizability $(\beta/\gamma)$, optimizing HOMO-LUMO gap and linear polarizability to target ranges, and minimizing energy per atom. We encode molecules as SMILES strings and evaluate their properties using quantum-chemical calculations. We compare NSGA-II, MAP-Elites, MOME, a single-objective $(\mu+\lambda)$ evolutionary algorithm, and simulated annealing. Quality diversity methods maintain archives across a measure space defined by atom and bond count, enabling the discovery of structurally diverse molecules. Our results demonstrate that NSGA-II consistently earns high scores in every objective, leading to high-quality molecules, but MOME does a better job exploring a wide range of possibilities, resulting in higher global hypervolume and MOQD scores. However, each method has strengths and weaknesses, and produced many promising molecules.