Published April 25, 2024 | Version v1
Dataset Open

EnzChemRED, a rich enzyme chemistry relation extraction dataset

Creators

  • 1. ROR icon National Center for Biotechnology Information
  • 2. ROR icon SIB Swiss Institute of Bioinformatics
  • 3. ROR icon Dalian University of Technology

Description

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 UniProtKB and ChEBI identifiers. We show that fine-tuning language models with EnzChemRED significantly boosts their ability to identify proteins and chemicals in text (86.30% F1 score) and to extract the chemical conversions in which they participate (86.66% F1 score), and the enzymes that catalyze those conversions (83.79% F1 score). We apply our methods 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.

Corresponding authors: Alan Bridge (alan.bridge@sib.swiss) and Zhiyong Lu (zhiyong.lu@nih.gov)

Content

This repository contains data to support the development of natural language processing (NLP) methods to mine biochemical reactions from text for Rhea and UniProt.

Files

README.txt

Files (62.5 MB)

Name Size Download all
md5:e6e7ab9d612527059d8c2d89c2658f62
56.4 MB Download
md5:36fda2aa2bf1da5486c7e37f2c414ae8
4.4 MB Download
md5:d05097c7cc566d1a4d043862a608e38a
1.7 MB Download
md5:6ebe65cb0fab187909281694796f19c7
3.0 kB Preview Download

Additional details

Identifiers

DOI
10.1038/s41597-024-03835-7

Dates

Created
2024-04-25

Software

Repository URL
https://github.com/ncbi-nlp/EnzChemRED
Programming language
Python