Integrating AI-powered text mining from PubTator into the manual curation workflow at the Comparative Toxicogenomics Database
Database · 2025-02-21 · 2025
DOI: 10.1093/database/baaf013 ↗At a glance
Journal article in Database, published online on 2025-02-20. Written by Thomas C Wiegers and 9 co-authors. Institution: Department of Biological Sciences, North Carolina State University, Toxicology Building, 850 Main Campus Drive, Raleigh, NC 27695, USA. Major MEDLINE topics: Toxicogenetics, Data Mining, Data Curation, Databases, Factual. Cited 44 times so far (Crossref); 37 references. The full text is freely available (open access, CC BY 4.0). Funded by: NIEHS NIH HHS, National Institute of Environmental Health Sciences.
Abstract (original language)
The Comparative Toxicogenomics Database (CTD) is a manually curated knowledge- and discovery-base that seeks to advance understanding about the relationship between environmental exposures and human health. CTD’s manual curation process extracts from the biomedical literature molecular relationships between chemicals/drugs, genes/proteins, phenotypes, diseases, anatomical terms, and species. These relationships are organized in a highly systematic way in order to make them not only informative but also scientifically computational, enabling inferential hypotheses to be formed to address gaps in understanding. Integral to CTD’s functionality is the use of structured, hierarchical ontologies and controlled vocabularies to describe these molecular relationships. Normalizing text (i.e. translating raw text from the literature into these controlled vocabularies) can be a time-consuming process for biocurators. To facilitate the normalization process and improve the efficiency with which our scientists curate the literature, CTD evaluated and integrated into the curation process PubTator 3.0, a state-of-the-art, AI-powered resource which extracts and normalizes from the literature many of the key biomedical concepts CTD curates. Here, we describe CTD’s long-standing history with Natural Language Processing (NLP), how this history helped form our objectives for NLP integration, the evaluation of PubTator against our objectives, and the integration of PubTator into CTD’s curation workflow. Database URL: https://ctdbase.org
Subjects
MeSH terms (MEDLINE)
Authors and institutions
- Department of Biological Sciences, North Carolina State University, Toxicology Building, 850 Main Campus Drive, Raleigh, NC 27695, USA.
- Center for Human Health and the Environment, North Carolina State University, Toxicology Building, 850 Main Campus Drive, Raleigh, NC 27695, USA.
ORCID profiles: Allan Peter Davis
Funding
- NIEHS NIH HHS
- National Institute of Environmental Health Sciences
Cite
APA
Wiegers, T. C., Davis, A. P., Wiegers, J., Sciaky, D., Barkalow, F., Wyatt, B., Strong, M., McMorran, R., Abrar, S., & Mattingly, C. J. (2025). Integrating AI-powered text mining from PubTator into the manual curation workflow at the Comparative Toxicogenomics Database. Database, 2025. https://doi.org/10.1093/database/baaf013
Vancouver
Wiegers TC, Davis AP, Wiegers J, Sciaky D, Barkalow F, Wyatt B, et al. Integrating AI-powered text mining from PubTator into the manual curation workflow at the Comparative Toxicogenomics Database. Database. 2025;2025. doi:10.1093/database/baaf013
BibTeX
@article{Wiegers2025,
author = {Wiegers, Thomas C and Davis, Allan Peter and Wiegers, Jolene and Sciaky, Daniela and Barkalow, Fern and Wyatt, Brent and Strong, Melissa and McMorran, Roy and Abrar, Sakib and Mattingly, Carolyn J},
title = {Integrating AI-powered text mining from PubTator into the manual curation workflow at the Comparative Toxicogenomics Database},
journal = {Database},
year = {2025},
volume = {2025},
doi = {10.1093/database/baaf013}
}
EUVIMED