Related Experiment Video
Updated: Jul 7, 2026

Leveraging CyVerse Resources for De Novo Comparative Transcriptomics of Underserved Non-model Organisms
Published on: May 9, 2017
Integrating AI-powered text mining from PubTator into the manual curation workflow at the Comparative Toxicogenomics
Thomas C Wiegers1, Allan Peter Davis1, Jolene Wiegers1
1Department of Biological Sciences, North Carolina State University, Toxicology Building, 850 Main Campus Drive, Raleigh, NC 27695, USA.
The Comparative Toxicogenomics Database (CTD) now uses PubTator 3.0, an AI tool, to speed up the curation of scientific literature on environmental exposures and human health. This integration enhances the efficiency of linking chemicals, genes, diseases, and phenotypes.
Area of Science:
- Toxicogenomics
- Bioinformatics
- Computational Biology
Background:
- The Comparative Toxicogenomics Database (CTD) manually curates literature to understand environmental exposures and human health.
- CTD organizes molecular relationships between chemicals, genes, phenotypes, diseases, and species using ontologies and controlled vocabularies.
- Manual text normalization for curation is time-consuming.
Purpose of the Study:
- To improve the efficiency of CTD's literature curation process.
- To evaluate and integrate PubTator 3.0, an AI-powered resource, into CTD's workflow.
- To leverage Natural Language Processing (NLP) for faster data extraction and normalization.
Main Methods:
- CTD evaluated PubTator 3.0's capabilities against its specific curation objectives.
- PubTator 3.0 was integrated into CTD's existing curation workflow.
- The study describes CTD's history with NLP and its strategy for NLP integration.
Main Results:
- PubTator 3.0 successfully extracts and normalizes key biomedical concepts relevant to CTD's curation needs.
- The integration of PubTator 3.0 is expected to significantly improve the efficiency of CTD's biocurators.
- This AI-powered approach facilitates faster hypothesis generation regarding environmental health impacts.
Conclusions:
- Integrating AI tools like PubTator 3.0 enhances the efficiency of large-scale biological databases.
- Streamlined curation processes accelerate scientific discovery in toxicogenomics.
- CTD's adoption of NLP demonstrates a commitment to advancing human health research through efficient data management.
Related Concept Videos
Drug Discovery: Overview
Toxic Reactions: Overview
Toxicity falls into two primary categories: local and systemic.
Local toxicity appears at the exposure site, such as protein denaturation caused by caustic substances.
In contrast, systemic toxicity requires the toxic agent's absorption and distribution,...
Teratogenicity
Mutagenicity and Carcinogenicity
Drug Biotransformation: Overview
Tandem Mass Spectrometry

