High-throughput property-driven generative design of functional organic molecules

Abstract

The design of molecules and materials with tailored properties is challenging, as candidate molecules must satisfy multiple competing requirements that are often difficult to measure or compute. While molecular structures, produced through generative deep learning, will satisfy those patterns, they often only possess specific target properties by chance and not by design, which makes molecular discovery via this route inefficient. In this work, we predict molecules with (pareto)-optimal properties by combining a generative deep learning model that predicts three dimensional conformations of molecules with a supervised deep learning model that takes these as inputs and predicts their electronic structure. Optimization of (multiple) molecular properties is achieved by screening newly generated molecules for desirable electronic properties and reusing hit molecules to retrain the generative model with a bias. The approach is demonstrated to find optimal molecules for organic electronics applications. Our method is generally applicable and eliminates the need for quantum chemical calculations during predictions, making it suitable for high-throughput screening in materials and catalyst design.

arXiv comment26 pages, 15 figures

References in corpus (13)

• On representing chemical environments
• SchNet - a deep learning architecture for molecules and materials
• Big Data meets Quantum Chemistry Approximations: The $\Delta$-Machine Learning Approach
• GuacaMol: Benchmarking Models for De Novo Molecular Design
• Resolution-of-identity approach to Hartree-Fock, hybrid density functionals, RPA, MP2, and \textit{GW} with numeric atom-centered orbital basis functions
• Deep learning for molecular design - a review of the state of the art
• SchNetPack: A Deep Learning Toolbox For Atomistic Systems
• The GW compendium: A practical guide to theoretical photoemission spectroscopy
• Combining SchNet and SHARC: The SchNarc machine learning approach for excited-state dynamics
• Inverse design of 3d molecular structures with conditional generative neural networks
• Learning to design drug-like molecules in three-dimensional space using deep generative models
• Physically inspired deep learning of molecular excitations and photoemission spectra
• GeoMol: Torsional Geometric Generation of Molecular 3D Conformer Ensembles

Cited by in corpus (7)

• Generative diffusion model for surface structure discovery
• Reinforcement learning for traversing chemical structure space: Optimizing transition states and minimum energy paths of molecules
• Variational quantum algorithm for ergotropy estimation in quantum many-body batteries
• Improved decision making with similarity based machine learning: Applications in chemistry
• Machine learning for accelerated bandgap prediction in strain-engineered quaternary III-V semiconductors
• Improving Electrolyte Performance for Target Cathode Loading Using Interpretable Data-Driven Approach
• MolMiner: Toward Controllable, 3D-Aware, Fragment-Based Molecular Design