KG-Hub -- Building and Exchanging Biological Knowledge Graphs
Abstract
Knowledge graphs (KGs) are a powerful approach for integrating heterogeneous data and making inferences in biology and many other domains, but a coherent solution for constructing, exchanging, and facilitating the downstream use of knowledge graphs is lacking. Here we present KG-Hub, a platform that enables standardized construction, exchange, and reuse of knowledge graphs. Features include a simple, modular extract-transform-load (ETL) pattern for producing graphs compliant with Biolink Model (a high-level data model for standardizing biological data), easy integration of any OBO (Open Biological and Biomedical Ontologies) ontology, cached downloads of upstream data sources, versioned and automatically updated builds with stable URLs, web-browsable storage of KG artifacts on cloud infrastructure, and easy reuse of transformed subgraphs across projects. Current KG-Hub projects span use cases including COVID-19 research, drug repurposing, microbial-environmental interactions, and rare disease research. KG-Hub is equipped with tooling to easily analyze and manipulate knowledge graphs. KG-Hub is also tightly integrated with graph machine learning (ML) tools which allow automated graph machine learning, including node embeddings and training of models for link prediction and node classification.
Cite
@article{arxiv.2302.10800,
title = {KG-Hub -- Building and Exchanging Biological Knowledge Graphs},
author = {J Harry Caufield and Tim Putman and Kevin Schaper and Deepak R Unni and Harshad Hegde and Tiffany J Callahan and Luca Cappelletti and Sierra AT Moxon and Vida Ravanmehr and Seth Carbon and Lauren E Chan and Katherina Cortes and Kent A Shefchek and Glass Elsarboukh and James P Balhoff and Tommaso Fontana and Nicolas Matentzoglu and Richard M Bruskiewich and Anne E Thessen and Nomi L Harris and Monica C Munoz-Torres and Melissa A Haendel and Peter N Robinson and Marcin P Joachimiak and Christopher J Mungall and Justin T Reese},
journal= {arXiv preprint arXiv:2302.10800},
year = {2023}
}