GO-HKP: A Gene Ontology hierarchy-driven framework for enzyme <mml:math xmlns:mml="http://www.w3.org/1998/Math/MathML" display="inline" id="d1e186" altimg="si25.svg"> <mml:msub> <mml:mrow> <mml:mi mathvariant="italic">k</mml:mi> </mml:mrow> <mml:mrow

GO-HKP is a Gene Ontology hierarchy-driven framework for predicting enzyme turnover numbers ( k cat ) with improved coverage, generalizability, and interpretability. It integrates curated UniProt data, ontology-based k cat propagation, and sequence-driven GO annotation (DeepGO-SE) to infer k cat for both annotated and novel enzymes. Benchmarking across four genome-scale metabolic models demonstrated substantial improvements in reaction coverage—by 56.67%, 25.1%, 16.0%, and 14.5%—compared with existing methods, highlighting its strong gap-filling capability. GO-HKP offers a biologically grounded, scalable, and transparent approach, supporting applications in metabolic engineering, drug discovery, and systems biology. The framework and Python package are available via GitHub for broad usability and reproducibility. • Ontology-driven framework integrates GO hierarchy for enzyme k cat prediction. • Curated UniProt-GO dataset enables robust and scalable kinetic annotation. • Dual strategy mapping combines empirical GO annotation and DeepGO-SE inference. • Superior coverage achieved across four diverse genome-scale metabolic models (GEMs).