Precision in Predicting Catalytic Performance of Medium Chain Dehydrogenase: A Benchmark Data Set and Comparative Metrics
Medium-chain dehydrogenases/reductases are highly versatile oxidoreductases with broad industrial relevance but complex structure-function relationships that continue to challenge catalytic performance prediction. A Benchmark for Medium-Chain Dehydrogenases (MCDBench) is introduced as a rigorously curated benchmark dataset comprising 792 enzyme-substrate-cofactor combinations, including experimentally validated inactive cases obtained under standardized conditions. MCDBench spans 36 chemically diverse alcohol substrates, representative MDR subclasses, and multiple cofactor types, enabling systematic evaluation of model generalization. Benchmarking four representative activity-prediction models (DLKcat, UniKP, TurNuP, and CataPro) shows that correlations with experimental activities remain modest under standardized conditions, and that distinguishing active from inactive catalytic space remains a practical challenge across enzyme classes and substrate types. Analysis points to a positive-data skew inherited from widely used biochemical databases and the relative scarcity of validated negative samples as key factors shaping this behavior. By providing a standardized benchmark that integrates experimentally validated negative cases, MCDBench offers a unified experimental and computational framework to help the field measure and further improve the discrimination of active and inactive catalytic space for biocatalyst design.
Authors
- Ye Ni (ORCID: https://orcid.org/0000-0003-4887-7517)
- Xiangyuan Gu (ORCID: https://orcid.org/0009-0001-7565-5584)
- Jieyu Zhou (ORCID: https://orcid.org/0000-0003-3292-0314)
- Xiaoyi Lin
Institutions
- Jiangnan University (CN)
Publication Details
- Journal
- bioRxiv (Cold Spring Harbor Laboratory)
- Published
- 2026-11-17
- DOI
- https://doi.org/10.64898/2026.11.13.766581
- Primary Topic
- Enzyme Catalysis and Immobilization
- Type
- preprint
Funders
- National Natural Science Foundation of China
- Government of Jiangsu Province