Message-passing neural networks for high-throughput polymer screening

Abstract

Machine learning methods have shown promise in predicting molecular properties, and given sufficient training data machine learning approaches can enable rapid high-throughput virtual screening of large libraries of compounds. Graph-based neural network architectures have emerged in recent years as the most successful approach for predictions based on molecular structure, and have consistently achieved the best performance on benchmark quantum chemical datasets. However, these models have typically required optimized 3D structural information for the molecule to achieve the highest accuracy. These 3D geometries are costly to compute for high levels of theory, limiting the applicability and practicality of machine learning methods in high-throughput screening applications. In this study, we present a new database of candidate molecules for organic photovoltaic applications, comprising approximately 91,000 unique chemical structures.Compared to existing datasets, this dataset contains substantially larger molecules (up to 200 atoms) as well as extrapolated properties for long polymer chains. We show that message-passing neural networks trained with and without 3D structural information for these molecules achieve similar accuracy, comparable to state-of-the-art methods on existing benchmark datasets. These results therefore emphasize that for larger molecules with practical applications, near-optimal prediction results can be obtained without using optimized 3D geometry as an input. We further show that learned molecular representations can be leveraged to reduce the training data required to transfer predictions to a new DFT functional.

7 pages, 3 figures

References in corpus (13)

• Adam: A Method for Stochastic Optimization
• Neural Message Passing for Quantum Chemistry
• How transferable are features in deep neural networks?
• SchNet - a deep learning architecture for molecules and materials
• ANI-1: An extensible neural network potential with DFT accuracy at force field computational cost
• Graph Networks as a Universal Machine Learning Framework for Molecules and Crystals
• Quantum-Chemical Insights from Deep Tensor Neural Networks
• Convolutional Networks on Graphs for Learning Molecular Fingerprints
• Machine learning prediction errors better than DFT accuracy
• SchNet: A continuous-filter convolutional neural network for modeling quantum interactions
• Gated Graph Sequence Neural Networks
• Predicting Electronic Structure Properties of Transition Metal Complexes with Neural Networks
• Neural Message Passing with Edge Updates for Predicting Properties of Molecules and Materials

Cited by in corpus (10)

• TransPolymer: a Transformer-based language model for polymer property predictions
• Perspective on integrating machine learning into computational chemistry and materials science
• Keeping it Simple: Language Models can learn Complex Molecular Distributions
• A graph representation of molecular ensembles for polymer property prediction
• Polymer informatics at-scale with multitask graph neural networks
• ASGN: An Active Semi-supervised Graph Neural Network for Molecular Property Prediction
• Accelerating amorphous polymer electrolyte screening by learning to reduce errors in molecular dynamics simulated properties
• Machine Learned Interatomic Potential for Dispersion Strengthened Plasma Facing Components
• Multiresolution Graph Transformers and Wavelet Positional Encoding for Learning Hierarchical Structures
• SMILES-X: autonomous molecular compounds characterization for small datasets without descriptors