zERExtractor: An Automated Platform for Enzyme-Catalyzed Reaction Data Extraction from Scientific Literature

Clinical Snapshot

Key Findings

• P Value: Not reported

• Effect Size: 89.9% accuracy in table recognition, >98% in molecular image recognition

• Primary Outcome: Automated extraction accuracy of enzyme reaction data from scientific literature

• Nnt Or Sensitivity: >2% improvement over strongest baseline, >95% accuracy on realistic benchmarks

• Confidence Interval: Not reported

Clinical Application

High feasibility with publicly accessible online platform, though requires technical expertise for implementation Relevant for Australian research institutions and biotechnology companies engaged in enzyme research, particularly those developing therapeutic enzymes or industrial biocatalysts Researchers in enzymology, biotechnology, and computational biology requiring systematic literature data extraction

Abstract

The rapid expansion of enzyme reaction literature has created a major bottleneck in database curation, leaving vast amounts of enzyme-substrate-condition relationships unstructured and inaccessible for DL-driven modeling. How to fully utilize the enzymatic reaction data has been an important task for future accurate enzyme activity prediction models. Current deep learning (DL)-based data extraction models heavily rely on large language models (LLMs) without a fidelity check and the ability to continuously evolve. To address these issues, we developed zERExtractor (Zelixir's Enzyme Reaction Data Extractor), an accuracy-oriented and extensible platform for extracting enzyme-catalyzed reaction data from scientific publications. This system offers a unified multimodal information extraction framework (covering molecular reaction diagrams, tables, and texts) to integrate enzymatic reaction descriptors into structured storage. We employ fine-tuned large LLMs together with DL in a human-in-the-loop pipeline that evolves through data fidelity validation by experts and active learning. Also, zERExtractor achieves 89.9% accuracy in table recognition and over 98% accuracy in molecular image recognition on synthetic data sets, outperforming the strongest baseline by more than 2% and consistently maintaining above 95% on realistic benchmarks. zERExtractor bridges the data gap in enzyme reaction data with a scalable framework for accurate multimodal extraction, advancing DL-driven enzyme modeling and enabling future applications in computational enzymology and biotechnology. The platform is publicly accessible online at https://zpaper.zelixir.com/.