Scalable Enzyme Reaction Retrieval Enables Metagenomic Biocatalyst Discovery
- 1Xiamen University
Abstract
Enzyme catalyzed reactions drive metabolism and enable diverse applications in biotechnology and sustainable synthesis, but assigning catalytic functions to uncharacterized enzymes and finding enzymes for target reactions remain major challenges. Despite recent advances in machine learning, translating enzyme function prediction into systematic discovery across the vast space of uncharacterized proteins and biochemical reactions remains challenging. Here we present EzHit, a lightweight framework for bidirectional enzyme reaction retrieval. Across enzyme annotation, orphan-reaction retrieval and family-specific fine-tuning benchmarks, EzHit achieved strong top-ranked performance and outperformed representative enzyme reaction matching baselines. We further show that Mahalanobis distance based geometric confidence provides more useful reliability estimates than probability-derived uncertainty metrics or evidential learning, enabling confidence-aware prioritization of high scoring candidates. Owing to its efficiency, EzHit was applied to a nearly trillion-scale OMG_Prot50 with RHEA screen, yielding 8.20 billion retained enzyme reaction associations across 30.27 million predicted enzyme sequences. Experimental validation further confirmed the activity of EzHit prioritized metagenomic enzyme candidates for a sparsely annotated reaction. Together, these results establish EzHit as a scalable framework for enzyme annotation, reaction-guided mining and biocatalyst discovery
Related
- A scalable Zebrafish Platform for genetic validation and functional discovery of stage-specific breast cancer metastasis regulators
- A zebrafish model of NEXMIF-related encephalopathy identified drivers of hyperlocomotion and provides a scalable platform for drug discovery.
- Generative discovery of chemical reaction networks
- Omics data discovery agents: Agent-supported retrieval, reanalysis, and synthesis of published omics data
- Enhancing Carbon Conversion Efficiency and Product Yield Through Systematic Biocatalyst Design for Microbial Electrosynthesis
BibTeX
@misc{luo2026scalable,
title = {{Scalable Enzyme Reaction Retrieval Enables Metagenomic Biocatalyst Discovery}},
author = {D. Luo and M. Jiang and B. Wang},
howpublished = {bioRxiv},
year = {2026},
month = oct,
doi = {10.64898/2026.10.15.759509},
url = {https://www.biorxiv.org/content/10.64898/2026.10.15.759509v1},
note = {CC BY-NC-ND},
}
RIS
TY - UNPB
TI - Scalable Enzyme Reaction Retrieval Enables Metagenomic Biocatalyst Discovery
AU - D. Luo
AU - M. Jiang
AU - B. Wang
PY - 2026
DA - 2026/10/15
PB - bioRxiv
DO - 10.64898/2026.10.15.759509
UR - https://www.biorxiv.org/content/10.64898/2026.10.15.759509v1
AB - Enzyme catalyzed reactions drive metabolism and enable diverse applications in biotechnology and sustainable synthesis, but assigning catalytic functions to uncharacterized enzymes and finding enzymes for target reactions remain major challenges. Despite recent advances in machine learning, translating enzyme function prediction into systematic discovery across the vast space of uncharacterized proteins and biochemical reactions remains challenging. Here we present EzHit, a lightweight framework for bidirectional enzyme reaction retrieval. Across enzyme annotation, orphan-reaction retrieval and family-specific fine-tuning benchmarks, EzHit achieved strong top-ranked performance and outperformed representative enzyme reaction matching baselines. We further show that Mahalanobis distance based geometric confidence provides more useful reliability estimates than probability-derived uncertainty metrics or evidential learning, enabling confidence-aware prioritization of high scoring candidates. Owing to its efficiency, EzHit was applied to a nearly trillion-scale OMG_Prot50 with RHEA screen, yielding 8.20 billion retained enzyme reaction associations across 30.27 million predicted enzyme sequences. Experimental validation further confirmed the activity of EzHit prioritized metagenomic enzyme candidates for a sparsely annotated reaction. Together, these results establish EzHit as a scalable framework for enzyme annotation, reaction-guided mining and biocatalyst discovery
ER -