A CTD–Pfizer collaboration: manual curation of 88 000 scientific articles text mined for drug–disease and drug–phenotype interactions

By Allan Peter Davis, Thomas C. Wiegers, Phoebe M. Roberts, B. King, Jean M. Lay, Kelley Lennon-Hopkins, Daniela Sciaky, Robin J. Johnson, Heather Keating, Heather Keating and 5 more. 2013

103 citations recorded by the source corpus.

Improving the prediction of chemical toxicity is a goal common to both environmental health research and pharmaceutical drug development. To improve safety detection assays, it is critical to have a reference set of molecules with well-defined toxicity annotations for training and validation purposes. Here, we describe a collaboration between safety researchers at Pfizer and the research team at the Comparative Toxicogenomics Database (CTD) to text mine and manually review a collection of 88 629 articles relating over 1 200 pharmaceutical drugs to their potential involvement in cardiovascular, neurological, renal and hepatic toxicity. In 1 year, CTD biocurators curated 2 54 173 toxicogenomic interactions (1 52 173 chemical–disease, 58 572 chemical–gene, 5 345 gene–disease and 38 083 phenotype interactions). All chemical–gene–disease interactions are fully integrated with public CTD, and phenotype interactions can be downloaded. We describe Pfizer’s text-mining process to collate the articles, and CTD’s curation strategy, performance metrics, enhanced data content and new module to curate phenotype information. As well, we show how data integration can connect phenotypes to diseases. This curation can be leveraged for information about toxic endpoints important to drug safety and help develop testable hypotheses for drug–disease events. The availability of these detailed, contextualized, high-quality annotations curated from seven decades’ worth of the scientific literature should help facilitate new mechanistic screening assays for pharmaceutical compound survival. This unique partnership demonstrates the importance of resource sharing and collaboration between public and private entities and underscores the complementary needs of the environmental health science and pharmaceutical communities. Database URL: http://ctdbase.org/

Subfields: Computational Theory and Mathematics, Molecular Biology

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computational Theory and Mathematics

In Molecular Biology

Citations in the corpus

The Comparative Toxicogenomics Database: update 2017 (2016, methodology): “We previously released an initial deposit of this dataset using MeSH terms as our phenotype descriptions (26); however, since then, we have mapped those terms to the more versatile GOBP controlled vocabulary to reflect greater granularity and broader coverage of biological concepts.”
Snorkel: rapid training data creation with weak supervision (2019, background): “Some big companies are able to absorb this cost, hiring large teams to label training data [12,16,31].”
Comparative Toxicogenomics Database (CTD): update 2021 (2020, methodology): “go), and we use a variety of strategies to prioritize and efficiently curate articles, including text mining (7,8,12), targeted journal curation to maintain data currency (16), and chemical-centric queries to improve data completeness (3).”
The Comparative Toxicogenomics Database's 10th year anniversary: update 2015 (2014, methodology): “to manually curate 88,000 articles describing the toxic actions of pharmaceuticals on cardiovascular, neurological, hepatic and renal systems (20).”
The Comparative Toxicogenomics Database: update 2019 (2018, methodology): “We use novel biocuration paradigms (6) to curate disparate data for toxicogenomics (7–10), phenotypes (11–12), diseases (11,13–16), environmental exposures (17–20), and pharmaceuticals (11,21).”
Assessing the state of the art in biomedical relation extraction: overview of the BioCreative V chemical-disease relation (CDR) task (2016, background): “Of all 1500 articles, most (1400) were selected from an existing CTD-Pfizer collaboration-related dataset (see details below).”