EnzChemRED, a rich enzyme chemistry relation extraction dataset

TL;DR

EnzChemRED is a new annotated dataset of enzyme-related literature that improves NLP models' ability to extract enzyme functions and reactions, aiding biological knowledge curation.

Contribution

The paper introduces EnzChemRED, a curated dataset for enzyme relation extraction, and demonstrates its effectiveness in enhancing NLP models for enzyme curation tasks.

Findings

Fine-tuning models with EnzChemRED improves NER and RE performance.

Achieved average F1 scores above 83% for enzyme and chemical relation extraction.

Developed an end-to-end pipeline for enzyme knowledge extraction from PubMed abstracts.

Abstract

Expert curation is essential to capture knowledge of enzyme functions from the scientific literature in FAIR open knowledgebases but cannot keep pace with the rate of new discoveries and new publications. In this work we present EnzChemRED, for Enzyme Chemistry Relation Extraction Dataset, a new training and benchmarking dataset to support the development of Natural Language Processing (NLP) methods such as (large) language models that can assist enzyme curation. EnzChemRED consists of 1,210 expert curated PubMed abstracts in which enzymes and the chemical reactions they catalyze are annotated using identifiers from the UniProt Knowledgebase (UniProtKB) and the ontology of Chemical Entities of Biological Interest (ChEBI). We show that fine-tuning pre-trained language models with EnzChemRED can significantly boost their ability to identify mentions of proteins and chemicals in text (Named Entity Recognition, or NER) and to extract the chemical conversions in which they participate (Relation Extraction, or RE), with average F1 score of 86.30% for NER, 86.66% for RE for chemical conversion pairs, and 83.79% for RE for chemical conversion pairs and linked enzymes. We combine the best performing methods after fine-tuning using EnzChemRED to create an end-to-end pipeline for knowledge extraction from text and apply this to abstracts at PubMed scale to create a draft map of enzyme functions in literature to guide curation efforts in UniProtKB and the reaction knowledgebase Rhea. The EnzChemRED corpus is freely available at https://ftp.expasy.org/databases/rhea/nlp/.