Modeling polypharmacy side effects with graph convolutional networks

Abstract

The use of drug combinations, termed polypharmacy, is common to treat patients with complex diseases and co-existing conditions. However, a major consequence of polypharmacy is a much higher risk of adverse side effects for the patient. Polypharmacy side effects emerge because of drug-drug interactions, in which activity of one drug may change if taken with another drug. The knowledge of drug interactions is limited because these complex relationships are rare, and are usually not observed in relatively small clinical testing. Discovering polypharmacy side effects thus remains an important challenge with significant implications for patient mortality. Here, we present Decagon, an approach for modeling polypharmacy side effects. The approach constructs a multimodal graph of protein-protein interactions, drug-protein target interactions, and the polypharmacy side effects, which are represented as drug-drug interactions, where each side effect is an edge of a different type. Decagon is developed specifically to handle such multimodal graphs with a large number of edge types. Our approach develops a new graph convolutional neural network for multirelational link prediction in multimodal networks. Decagon predicts the exact side effect, if any, through which a given drug combination manifests clinically. Decagon accurately predicts polypharmacy side effects, outperforming baselines by up to 69%. We find that it automatically learns representations of side effects indicative of co-occurrence of polypharmacy in patients. Furthermore, Decagon models particularly well side effects with a strong molecular basis, while on predominantly non-molecular side effects, it achieves good performance because of effective sharing of model parameters across edge types. Decagon creates opportunities to use large pharmacogenomic and patient data to flag and prioritize side effects for follow-up analysis.

Presented at ISMB 2018

References in corpus (5)

• Adam: A Method for Stochastic Optimization
• DeepWalk: Online Learning of Social Representations
• Neural Message Passing for Quantum Chemistry
• Complex Embeddings for Simple Link Prediction
• Data Fusion by Matrix Factorization

Cited by in corpus (127)

• Graph Neural Networks: A Review of Methods and Applications
• Deep Graph Library: A Graph-Centric, Highly-Performant Package for Graph Neural Networks
• Machine Learning for Integrating Data in Biology and Medicine: Principles, Practice, and Opportunities
• GNNExplainer: Generating Explanations for Graph Neural Networks
• MolTrans: Molecular Interaction Transformer for Drug Target Interaction Prediction
• Graph Embedding on Biomedical Networks: Methods, Applications, and Evaluations
• A Gentle Introduction to Deep Learning for Graphs
• Everything is Connected: Graph Neural Networks
• Graph Representation Learning in Biomedicine
• Higher-Order Explanations of Graph Neural Networks via Relevant Walks
• Artificial Intelligence for Drug Discovery: Are We There Yet?
• DGL-LifeSci: An Open-Source Toolkit for Deep Learning on Graphs in Life Science
• Drug Repurposing for COVID-19 via Knowledge Graph Completion
• SumGNN: Multi-typed Drug Interaction Prediction via Efficient Knowledge Graph Summarization
• SIGN: Scalable Inception Graph Neural Networks
• Multi-view Graph Contrastive Representation Learning for Drug-Drug Interaction Prediction
• Interpretable and Efficient Heterogeneous Graph Convolutional Network
• Deep Learning on Graphs: A Survey
• Graph Neural Networks: Taxonomy, Advances and Trends
• Multimodal Data Integration for Oncology in the Era of Deep Neural Networks: A Review
• A Survey on Hyperdimensional Computing aka Vector Symbolic Architectures, Part II: Applications, Cognitive Models, and Challenges
• A Review of Biomedical Datasets Relating to Drug Discovery: A Knowledge Graph Perspective
• Differentiable Graph Module (DGM) for Graph Convolutional Networks
• GNNGuard: Defending Graph Neural Networks against Adversarial Attacks
• MR-GNN: Multi-Resolution and Dual Graph Neural Network for Predicting Structured Entity Interactions
• Network Medicine Framework for Identifying Drug Repurposing Opportunities for COVID-19
• Current and future directions in network biology
• Comprehensive evaluation of deep and graph learning on drug-drug interactions prediction
• GoGNN: Graph of Graphs Neural Network for Predicting Structured Entity Interactions
• Temporal Graph Networks for Deep Learning on Dynamic Graphs
• Deep learning of contagion dynamics on complex networks
• Graph Neural Networks for Molecules
• Drug-Drug Adverse Effect Prediction with Graph Co-Attention
• MedGCN: Medication recommendation and lab test imputation via graph convolutional networks
• Predicting the hosts of prokaryotic viruses using GCN-based semi-supervised learning
• Is Homophily a Necessity for Graph Neural Networks?
• Foundations of Population-Based SHM, Part IV: The Geometry of Spaces of Structures and their Feature Spaces
• Neurosymbolic AI for Reasoning over Knowledge Graphs: A Survey
• Automating Botnet Detection with Graph Neural Networks
• Comparison of biomedical relationship extraction methods and models for knowledge graph creation
• Subgraph Neural Networks
• PGM-Explainer: Probabilistic Graphical Model Explanations for Graph Neural Networks
• Predicting Biomedical Interactions with Higher-Order Graph Convolutional Networks
• Dual-Primal Graph Convolutional Networks
• Interpretable Graph Convolutional Neural Networks for Inference on Noisy Knowledge Graphs
• Directed Acyclic Graph Neural Networks
• Joint embedding of structure and features via graph convolutional networks
• Deep learning for dynamic graphs: models and benchmarks
• Learning to Extrapolate Knowledge: Transductive Few-shot Out-of-Graph Link Prediction
• DeepGS: Deep Representation Learning of Graphs and Sequences for Drug-Target Binding Affinity Prediction
• Feature Overcorrelation in Deep Graph Neural Networks: A New Perspective
• Prot2Text: Multimodal Protein's Function Generation with GNNs and Transformers
• Learning to Denoise Biomedical Knowledge Graph for Robust Molecular Interaction Prediction
• TCL: Transformer-based Dynamic Graph Modelling via Contrastive Learning
• Generative Causal Explanations for Graph Neural Networks
• Towards a Unified Framework for Fair and Stable Graph Representation Learning
• GripNet: Graph Information Propagation on Supergraph for Heterogeneous Graphs
• GAMENet: Graph Augmented MEmory Networks for Recommending Medication Combination
• View-based Explanations for Graph Neural Networks
• SimGNN: A Neural Network Approach to Fast Graph Similarity Computation
• Bio-JOIE: Joint Representation Learning of Biological Knowledge Bases
• SWAG: Item Recommendations using Convolutions on Weighted Graphs
• Interpreting the Mechanism of Synergism for Drug Combinations Using Attention-Based Hierarchical Graph Pooling
• CASTER: Predicting Drug Interactions with Chemical Substructure Representation
• Learning to Describe for Predicting Zero-shot Drug-Drug Interactions
• Tri-graph Information Propagation for Polypharmacy Side Effect Prediction
• A Tailored Convolutional Neural Network for Nonlinear Manifold Learning of Computational Physics Data using Unstructured Spatial Discretizations
• Graph Meta Learning via Local Subgraphs
• mGNN: Generalizing the Graph Neural Networks to the Multilayer Case
• GRAF: Graph Attention-aware Fusion Networks
• Bi-Level Graph Neural Networks for Drug-Drug Interaction Prediction
• On the Unreasonable Effectiveness of Feature propagation in Learning on Graphs with Missing Node Features
• Power to the Relational Inductive Bias: Graph Neural Networks in Electrical Power Grids
• Zoo Guide to Network Embedding
• AWB-GCN: A Graph Convolutional Network Accelerator with Runtime Workload Rebalancing
• Identifying Illicit Accounts in Large Scale E-payment Networks -- A Graph Representation Learning Approach
• Relation Matters in Sampling: A Scalable Multi-Relational Graph Neural Network for Drug-Drug Interaction Prediction
• Duality between predictability and reconstructability in complex systems
• GENN: Predicting Correlated Drug-drug Interactions with Graph Energy Neural Networks
• K-Paths: Reasoning over Graph Paths for Drug Repurposing and Drug Interaction Prediction
• Graph Neural Networks with Parallel Neighborhood Aggregations for Graph Classification
• SMORE: Knowledge Graph Completion and Multi-hop Reasoning in Massive Knowledge Graphs
• Hierarchical Message-Passing Graph Neural Networks
• Heterogeneous Graph Matching Networks
• Utilising Graph Machine Learning within Drug Discovery and Development
• SkipGNN: Predicting Molecular Interactions with Skip-Graph Networks
• Graph-Aware Transformer: Is Attention All Graphs Need?
• A comparative study of similarity-based and GNN-based link prediction approaches
• Accelerating SpMM Kernel with Cache-First Edge Sampling for Graph Neural Networks
• Dr-COVID: Graph Neural Networks for SARS-CoV-2 Drug Repurposing
• Deep learning in bioinformatics: introduction, application, and perspective in big data era
• Towards Multimodal Graph Large Language Model
• On an application of graph neural networks in population based SHM
• A Knowledge Graph-based Approach for Exploring the U.S. Opioid Epidemic
• Heterogeneous network approach to predict individuals' mental health
• Improving Molecule Generation and Drug Discovery with a Knowledge-enhanced Generative Model
• Persistent homology analysis of type 2 diabetes genome-wide association studies in protein-protein interaction networks
• Graph Sequential Network for Reasoning over Sequences
• Exploiting Heterogeneous Graph Neural Networks with Latent Worker/Task Correlation Information for Label Aggregation in Crowdsourcing
• Co-attention Graph Pooling for Efficient Pairwise Graph Interaction Learning
• Drug-Drug Interaction Prediction with Wasserstein Adversarial Autoencoder-based Knowledge Graph Embeddings
• Simulating Execution Time of Tensor Programs using Graph Neural Networks
• Expanding Label Sets for Graph Convolutional Networks
• An In-depth Summary of Recent Artificial Intelligence Applications in Drug Design
• Graph Neural Networks Including Sparse Interpretability
• Hierarchical Protein Function Prediction with Tail-GNNs
• The Role of Graph Topology in the Performance of Biomedical Knowledge Graph Completion Models
• Drug Interaction Vectors Neural Network: DrIVeNN
• GINA: Neural Relational Inference From Independent Snapshots
• Fast Polypharmacy Side Effect Prediction Using Tensor Factorisation
• Personalized Hashtag Recommendation for Micro-videos
• Propagate-Selector: Detecting Supporting Sentences for Question Answering via Graph Neural Networks
• Graph Neural Networks for Node-Level Predictions
• Graph Convolutional Networks Meet with High Dimensionality Reduction
• Recent Advances in Automated Question Answering In Biomedical Domain
• Deep Dynamic Effective Connectivity Estimation from Multivariate Time Series
• Deep Learning Meets SAR
• Graph Feature Gating Networks
• Feedback-Based Quantum Control for Safe and Synergistic Drug Combination Design
• A Multi-Scale Graph Neural Process with Cross-Drug Co-Attention for Drug-Drug Interactions Prediction
• Modeling Pharmacological Effects with Multi-Relation Unsupervised Graph Embedding
• DURENDAL: Graph deep learning framework for temporal heterogeneous networks
• Towards Fast Evaluation of Unsupervised Link Prediction by Random Sampling Unobserved Links
• Deep graph embedding for prioritizing synergistic anticancer drug combinations
• Subspace Graph Physics: Real-Time Rigid Body-Driven Granular Flow Simulation
• DrugDBEmbed : Semantic Queries on Relational Database using Supervised Column Encodings
• PyKale: Knowledge-Aware Machine Learning from Multiple Sources in Python