Convolutional Networks on Graphs for Learning Molecular Fingerprints

Abstract

We introduce a convolutional neural network that operates directly on graphs. These networks allow end-to-end learning of prediction pipelines whose inputs are graphs of arbitrary size and shape. The architecture we present generalizes standard molecular feature extraction methods based on circular fingerprints. We show that these data-driven features are more interpretable, and have better predictive performance on a variety of tasks.

9 pages, 5 figures. To appear in Neural Information Processing Systems (NIPS)

References in corpus (7)

• Adam: A Method for Stochastic Optimization
• Spectral Networks and Locally Connected Networks on Graphs
• A Convolutional Neural Network for Modelling Sentences
• Massively Multitask Networks for Drug Discovery
• Deep Unfolding: Model-Based Inspiration of Novel Deep Architectures
• Multi-task Neural Networks for QSAR Predictions
• Toxicity Prediction using Deep Learning

Cited by in corpus (111)

• Graph Embedding Techniques, Applications, and Performance: A Survey
• Session-based Recommendation with Graph Neural Networks
• Quantum-Chemical Insights from Deep Tensor Neural Networks
• Knowledge Graph Convolutional Networks for Recommender Systems
• Molecular Contrastive Learning of Representations via Graph Neural Networks
• ChemRL-GEM: Geometry Enhanced Molecular Representation Learning for Property Prediction
• Geometric Deep Learning: Grids, Groups, Graphs, Geodesics, and Gauges
• Deep neural networks for the evaluation and design of photonic devices
• Dynamic Graph Convolutional Networks
• Gated Graph Sequence Neural Networks
• Predicting materials properties without crystal structure: Deep representation learning from stoichiometry
• A Survey on Graph Kernels
• How Powerful are Graph Neural Networks?
• A Gentle Introduction to Deep Learning for Graphs
• Graph Representation Learning in Biomedicine
• Applying machine learning techniques to predict the properties of energetic materials
• Conditional molecular design with deep generative models
• Rapid Prediction of Electron-Ionization Mass Spectrometry using Neural Networks
• Combinatorial Optimization with Physics-Inspired Graph Neural Networks
• Unifying the design space and optimizing linear and nonlinear truss metamaterials by generative modeling
• TransPolymer: a Transformer-based language model for polymer property predictions
• Improving Chemical Autoencoder Latent Space and Molecular De novo Generation Diversity with Heteroencoders
• Coarse Graining Molecular Dynamics with Graph Neural Networks
• SIGN: Scalable Inception Graph Neural Networks
• DeepSphere: Efficient spherical Convolutional Neural Network with HEALPix sampling for cosmological applications
• Bayesian semi-supervised learning for uncertainty-calibrated prediction of molecular properties and active learning
• Robust Spatial Filtering with Graph Convolutional Neural Networks
• Graph Dynamical Networks for Unsupervised Learning of Atomic Scale Dynamics in Materials
• Relational Graph Attention Networks
• General framework for E(3)-equivariant neural network representation of density functional theory Hamiltonian
• MR-GNN: Multi-Resolution and Dual Graph Neural Network for Predicting Structured Entity Interactions
• Message-passing neural networks for high-throughput polymer screening
• Quantum chemistry-augmented neural networks for reactivity prediction: Performance, generalizability and interpretability
• Graph Kernels: A Survey
• Relation Modeling with Graph Convolutional Networks for Facial Action Unit Detection
• Deeply learning molecular structure-property relationships using attention- and gate-augmented graph convolutional network
• Application of generative autoencoder in de novo molecular design
• Three-Dimensionally Embedded Graph Convolutional Network (3DGCN) for Molecule Interpretation
• Hierarchical Visualization of Materials Space with Graph Convolutional Neural Networks
• Graph Neural Networks Accelerated Molecular Dynamics
• SMILES2Vec: An Interpretable General-Purpose Deep Neural Network for Predicting Chemical Properties
• GraphVAMPNet, using graph neural networks and variational approach to markov processes for dynamical modeling of biomolecules
• MoleculeNet: A Benchmark for Molecular Machine Learning
• GRAINS: Generative Recursive Autoencoders for INdoor Scenes
• Graph Convolutional Neural Networks with Node Transition Probability-based Message Passing and DropNode Regularization
• Difficulty in chirality recognition for Transformer architectures learning chemical structures from string
• Hashing-Accelerated Graph Neural Networks for Link Prediction
• Learning Graph Neural Networks with Positive and Unlabeled Nodes
• Joint embedding of structure and features via graph convolutional networks
• Multi-View Self-Attention for Interpretable Drug-Target Interaction Prediction
• On the design space between molecular mechanics and machine learning force fields
• A Multiple Filter Based Neural Network Approach to the Extrapolation of Adsorption Energies on Metal Surfaces for Catalysis Applications
• Graph Neural Networks: Methods, Applications, and Opportunities
• SpreadGNN: Serverless Multi-task Federated Learning for Graph Neural Networks
• Mean-field theory of graph neural networks in graph partitioning
• Automated discovery of GPCR bioactive ligands
• A Physically-informed Graph-based Order Parameter for the Universal Characterization of Atomic Structures
• A Universal Framework for Accurate and Efficient Geometric Deep Learning of Molecular Systems
• Improving black-box optimization in VAE latent space using decoder uncertainty
• ZerNet: Convolutional Neural Networks on Arbitrary Surfaces via Zernike Local Tangent Space Estimation
• Meta-Learning GNN Initializations for Low-Resource Molecular Property Prediction
• ASNets: Deep Learning for Generalised Planning
• Learning 3D Representations of Molecular Chirality with Invariance to Bond Rotations
• Named entity recognition architecture combining contextual and global features
• SimGNN: A Neural Network Approach to Fast Graph Similarity Computation
• Distance Metric Learning for Graph Structured Data
• Graph Neural Networks for the Prediction of Substrate-Specific Organic Reaction Conditions
• Graph Deconvolutional Generation
• Structural Inference of Networked Dynamical Systems with Universal Differential Equations
• Towards Heterogeneous Multi-Agent Reinforcement Learning with Graph Neural Networks
• VulSPG: Vulnerability detection based on slice property graph representation learning
• Learning Attributed Graph Representations with Communicative Message Passing Transformer
• Superpixels and Graph Convolutional Neural Networks for Efficient Detection of Nutrient Deficiency Stress from Aerial Imagery
• Data Considerations in Graph Representation Learning for Supply Chain Networks
• Graph Convolutional Networks with EigenPooling
• HD-Bind: Encoding of Molecular Structure with Low Precision, Hyperdimensional Binary Representations
• A Generative Model for Molecular Distance Geometry
• Identifying Autism Spectrum Disorder Based on Individual-Aware Down-Sampling and Multi-Modal Learning
• Grouping-matrix based Graph Pooling with Adaptive Number of Clusters
• Information Obfuscation of Graph Neural Networks
• Artificial Intelligence in Drug Discovery: Applications and Techniques
• Are Graph Neural Networks Miscalibrated?
• Face-GCN: A Graph Convolutional Network for 3D Dynamic Face Identification/Recognition
• Looking back to lower-level information in few-shot learning
• Beyond Clicks: Modeling Multi-Relational Item Graph for Session-Based Target Behavior Prediction
• An Overview on the Application of Graph Neural Networks in Wireless Networks
• Improving Molecular Graph Neural Network Explainability with Orthonormalization and Induced Sparsity
• "Found in Translation": Predicting Outcomes of Complex Organic Chemistry Reactions using Neural Sequence-to-Sequence Models
• Leveraging binding-site structure for drug discovery with point-cloud methods
• Molecular Graph Representation Learning via Structural Similarity Information
• An In-depth Summary of Recent Artificial Intelligence Applications in Drug Design
• A Genetic Algorithm with Tree-structured Mutation for Hyperparameter Optimisation of Graph Neural Networks
• CAP: Co-Adversarial Perturbation on Weights and Features for Improving Generalization of Graph Neural Networks
• Accurate Prediction of Free Solvation Energy of Organic Molecules via Graph Attention Network and Message Passing Neural Network from Pairwise Atomistic Interactions
• Graph-to-Sequence Learning using Gated Graph Neural Networks
• A Framework for Joint Unsupervised Learning of Cluster-Aware Embedding for Heterogeneous Networks
• Network topology mapping of Chemical Compounds Space
• A unifying primary framework for quantum graph neural networks from quantum graph states
• Scaffold Embeddings: Learning the Structure Spanned by Chemical Fragments, Scaffolds and Compounds
• Neural Network Potential Energy Surface for the low temperature Ring Polymer Molecular Dynamics of the H2CO + OH reaction
• GeoT: A Geometry-aware Transformer for Reliable Molecular Property Prediction and Chemically Interpretable Representation Learning
• Fast Mesh Data Augmentation via Chebyshev Polynomial of Spectral filtering
• Revisiting convolutional neural network on graphs with polynomial approximations of Laplace-Beltrami spectral filtering
• Discriminative Learning of Similarity and Group Equivariant Representations
• Deep Learning Accelerated Gold Nanocluster Synthesis
• Which Hyperparameters to Optimise? An Investigation of Evolutionary Hyperparameter Optimisation in Graph Neural Network For Molecular Property Prediction
• Efficient Deep Gaussian Process Models for Variable-Sized Input
• Fast Haar Transforms for Graph Neural Networks
• RaWaNet: Enriching Graph Neural Network Input via Random Walks on Graphs
• Learning Atomic Multipoles: Prediction of the Electrostatic Potential with Equivariant Graph Neural Networks
• SEEN: Sharpening Explanations for Graph Neural Networks using Explanations from Neighborhoods