Graph Representation Learning in Biomedicine

Abstract

Biomedical networks (or graphs) are universal descriptors for systems of interacting elements, from molecular interactions and disease co-morbidity to healthcare systems and scientific knowledge. Advances in artificial intelligence, specifically deep learning, have enabled us to model, analyze, and learn with such networked data. In this review, we put forward an observation that long-standing principles of systems biology and medicine -- while often unspoken in machine learning research -- provide the conceptual grounding for representation learning on graphs, explain its current successes and limitations, and even inform future advancements. We synthesize a spectrum of algorithmic approaches that, at their core, leverage graph topology to embed networks into compact vector spaces. We also capture the breadth of ways in which representation learning has dramatically improved the state-of-the-art in biomedical machine learning. Exemplary domains covered include identifying variants underlying complex traits, disentangling behaviors of single cells and their effects on health, assisting in diagnosis and treatment of patients, and developing safe and effective medicines.

References in corpus (11)

• LINE: Large-scale Information Network Embedding
• Deep learning for molecular design - a review of the state of the art
• SchNet: A continuous-filter convolutional neural network for modeling quantum interactions
• MixHop: Higher-Order Graph Convolutional Architectures via Sparsified Neighborhood Mixing
• An infectious disease model on empirical networks of human contact: bridging the gap between dynamic network data and contact matrices
• A Survey on Graph-Based Deep Learning for Computational Histopathology
• Deep Learning of High-Order Interactions for Protein Interface Prediction
• DeepGS: Deep Representation Learning of Graphs and Sequences for Drug-Target Binding Affinity Prediction
• Towards Explainable Graph Representations in Digital Pathology
• MARS: Markov Molecular Sampling for Multi-objective Drug Discovery
• Representation Learning of EHR Data via Graph-Based Medical Entity Embedding

Cited by in corpus (16)

• AI-driven multi-omics integration for multi-scale predictive modeling of causal genotype-environment-phenotype relationships
• Multimodal Data Integration for Oncology in the Era of Deep Neural Networks: A Review
• Current and future directions in network biology
• HMSG: Heterogeneous Graph Neural Network based on Metapath Subgraph Learning
• RNA-KG: An ontology-based knowledge graph for representing interactions involving RNA molecules
• Multimodal Learning for Multi-Omics: A Survey
• Self-explainable Graph Neural Network for Alzheimer's Disease And Related Dementias Risk Prediction
• Unveiling the frontiers of deep learning: innovations shaping diverse domains
• Advancing Biomedicine with Graph Representation Learning: Recent Progress, Challenges, and Future Directions
• Zoo Guide to Network Embedding
• Beyond Euclid: An Illustrated Guide to Modern Machine Learning with Geometric, Topological, and Algebraic Structures
• DRExplainer: Quantifiable Interpretability in Drug Response Prediction with Directed Graph Convolutional Network
• Community detection for directed networks revisited using bimodularity
• Computational strategies for cross-species knowledge transfer
• Efficient and Robust Continual Graph Learning for Graph Classification in Biology
• Statistical physics analysis of graph neural networks: Approaching optimality in the contextual stochastic block model