Deeply learning molecular structure-property relationships using attention- and gate-augmented graph convolutional network

Abstract

Molecular structure-property relationships are key to molecular engineering for materials and drug discovery. The rise of deep learning offers a new viable solution to elucidate the structure-property relationships directly from chemical data. Here we show that the performance of graph convolutional networks (GCNs) for the prediction of molecular properties can be improved by incorporating attention and gate mechanisms. The attention mechanism enables a GCN to identify atoms in different environments. The gated skip-connection further improves the GCN by updating feature maps at an appropriate rate. We demonstrate that the resulting attention- and gate-augmented GCN could extract better structural features related to a target molecular property such as solubility, polarity, synthetic accessibility and photovoltaic efficiency compared to the vanilla GCN. More interestingly, it identified two distinct parts of molecules as essential structural features for high photovoltaic efficiency, and each of them coincided with the areas of donor and acceptor orbitals for charge-transfer excitations, respectively. As a result, the new model could accurately predict molecular properties and place molecules with similar properties close to each other in a well-trained latent space, which is critical for successful molecular engineering.

References in corpus (27)

• Efficient Estimation of Word Representations in Vector Space
• Semi-Supervised Classification with Graph Convolutional Networks
• Neural Message Passing for Quantum Chemistry
• Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation
• Fast and Accurate Modeling of Molecular Atomization Energies with Machine Learning
• Learning to Plan Chemical Syntheses
• DeepDTA: Deep Drug-Target Binding Affinity Prediction
• Molecular Graph Convolutions: Moving Beyond Fingerprints
• Convolutional Neural Networks on Graphs with Fast Localized Spectral Filtering
• Quantum-Chemical Insights from Deep Tensor Neural Networks
• Convolutional Neural Networks for Sentence Classification
• Convolutional Networks on Graphs for Learning Molecular Fingerprints
• Junction Tree Variational Autoencoder for Molecular Graph Generation
• Effective Approaches to Attention-based Neural Machine Translation
• Machine learning prediction errors better than DFT accuracy
• Objective-Reinforced Generative Adversarial Networks (ORGAN) for Sequence Generation Models
• GraphRNN: Generating Realistic Graphs with Deep Auto-regressive Models
• MolGAN: An implicit generative model for small molecular graphs
• Learning Deep Generative Models of Graphs
• Gated Graph Sequence Neural Networks
• Graph Convolutional Policy Network for Goal-Directed Molecular Graph Generation
• Conditional molecular design with deep generative models
• Grammar Variational Autoencoder
• Atomic Convolutional Networks for Predicting Protein-Ligand Binding Affinity
• Edge Attention-based Multi-Relational Graph Convolutional Networks
• Multi-Objective De Novo Drug Design with Conditional Graph Generative Model
• Sequence Tutor: Conservative Fine-Tuning of Sequence Generation Models with KL-control

Cited by in corpus (16)

• Self-Supervised Graph Transformer on Large-Scale Molecular Data
• A Comprehensive Survey on Deep Graph Representation Learning
• A Deep Generative Model for Molecule Optimization via One Fragment Modification
• Generative Models for Automatic Chemical Design
• Machine learning-assisted design of material properties
• Constrained Bayesian Optimization for Automatic Chemical Design
• All SMILES Variational Autoencoder
• Multi-View Graph Neural Networks for Molecular Property Prediction
• Improving Graph Attention Networks with Large Margin-based Constraints
• HAHE: Hierarchical Attentive Heterogeneous Information Network Embedding
• BatmanNet: Bi-branch Masked Graph Transformer Autoencoder for Molecular Representation
• Uncertainty quantification of molecular property prediction with Bayesian neural networks
• MLSolv-A: A Novel Machine Learning-Based Prediction of Solvation Free Energies from Pairwise Atomistic Interactions
• Uncertainty quantification of molecular property prediction using Bayesian neural network models
• Graph-convolution neural network-based flexible docking utilizing coarse-grained distance matrix
• Counterfactual Explanation with Multi-Agent Reinforcement Learning for Drug Target Prediction