Neuro-symbolic representation learning on biological knowledge graphs

Abstract

Motivation: Biological data and knowledge bases increasingly rely on Semantic Web technologies and the use of knowledge graphs for data integration, retrieval and federated queries. In the past years, feature learning methods that are applicable to graph-structured data are becoming available, but have not yet widely been applied and evaluated on structured biological knowledge. Results: We develop a novel method for feature learning on biological knowledge graphs. Our method combines symbolic methods, in particular knowledge representation using symbolic logic and automated reasoning, with neural networks to generate embeddings of nodes that encode for related information within knowledge graphs. Through the use of symbolic logic, these embeddings contain both explicit and implicit information. We apply these embeddings to the prediction of edges in the knowledge graph representing problems of function prediction, finding candidate genes of diseases, protein-protein interactions, or drug target relations, and demonstrate performance that matches and sometimes outperforms traditional approaches based on manually crafted features. Our method can be applied to any biological knowledge graph, and will thereby open up the increasing amount of Semantic Web based knowledge bases in biology to use in machine learning and data analytics. Availability and Implementation: https://github.com/bio-ontology-research-group/walking-rdf-and-owl Contact: [email protected]

References in corpus (3)

• Scikit-learn: Machine Learning in Python
• DeepWalk: Online Learning of Social Representations
• Analysis of the human diseasome reveals phenotype modules across common, genetic, and infectious diseases

Cited by in corpus (19)

• DeepGO: Predicting protein functions from sequence and interactions using a deep ontology-aware classifier
• Graph Embedding on Biomedical Networks: Methods, Applications, and Evaluations
• Onto2Vec: joint vector-based representation of biological entities and their ontology-based annotations
• OpenBioLink: A benchmarking framework for large-scale biomedical link prediction
• Knowledge-based Biomedical Data Science 2019
• Neurosymbolic AI for Reasoning over Knowledge Graphs: A Survey
• Ontology Embedding: A Survey of Methods, Applications and Resources
• Knowledge Graph Embedding for Ecotoxicological Effect Prediction
• Bio-JOIE: Joint Representation Learning of Biological Knowledge Bases
• Biological Systems as Heterogeneous Information Networks: A Mini-review and Perspectives
• Predicting Gene-Disease Associations with Knowledge Graph Embeddings over Multiple Ontologies
• Benchmarking neural embeddings for link prediction in knowledge graphs under semantic and structural changes
• Global and local evaluation of link prediction tasks with neural embeddings
• Benchmark datasets for biomedical knowledge graphs with negative statements
• Prediction of Adverse Biological Effects of Chemicals Using Knowledge Graph Embeddings
• Fast and scalable learning of neuro-symbolic representations of biomedical knowledge
• Scalable and interpretable rule-based link prediction for large heterogeneous knowledge graphs
• Common Cell type Nomenclature for the mammalian brain: A systematic, extensible convention
• Development of a Knowledge Graph Embeddings Model for Pain