English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Neural embedding-based machine learning models have shown promise forpredicting novel links in biomedical knowledge graphs. Unfortunately, theirpractical utility is diminished by their lack of interpretability. Recently,the fully interpretable, rule-based algorithm AnyBURL yielded highlycompetitive results on many general-purpose link prediction benchmarks.However, its applicability to large-scale prediction tasks on complexbiomedical knowledge bases is limited by long inference times and difficultieswith aggregating predictions made by multiple rules. We improve upon AnyBURL byintroducing the SAFRAN rule application framework which aggregates rulesthrough a scalable clustering algorithm. SAFRAN yields new state-of-the-artresults for fully interpretable link prediction on the establishedgeneral-purpose benchmark FB15K-237 and the large-scale biomedical benchmarkOpenBioLink. Furthermore, it exceeds the results of multiple establishedembedding-based algorithms on FB15K-237 and narrows the gap between rule-basedand embedding-based algorithms on OpenBioLink. We also show that SAFRANincreases inference speeds by up to two orders of magnitude.

Scalable and interpretable rule-based link prediction for large heterogeneous knowledge graphs