OpenBioLink: A benchmarking framework for large-scale biomedical link prediction
This provides a standardized tool for researchers in biomedical informatics to evaluate machine-learning algorithms for link prediction, though it is incremental as it focuses on benchmarking rather than new methods.
The authors tackled the lack of dedicated benchmarks for biomedical link prediction by introducing OpenBioLink, a large-scale, high-quality, and challenging framework, and provided preliminary baseline evaluation results.
SUMMARY: Recently, novel machine-learning algorithms have shown potential for predicting undiscovered links in biomedical knowledge networks. However, dedicated benchmarks for measuring algorithmic progress have not yet emerged. With OpenBioLink, we introduce a large-scale, high-quality and highly challenging biomedical link prediction benchmark to transparently and reproducibly evaluate such algorithms. Furthermore, we present preliminary baseline evaluation results. AVAILABILITY AND IMPLEMENTATION: Source code, data and supplementary files are openly available at https://github.com/OpenBioLink/OpenBioLink CONTACT: matthias.samwald ((at)) meduniwien.ac.at