@article{davis_wiegers_wiegers_wyatt_johnson_sciaky_barkalow_strong_planchart_mattingly_2023, title={CTD tetramers: a new online tool that computationally links curated chemicals, genes, phenotypes, and diseases to inform molecular mechanisms for environmental health}, volume={195}, ISSN={["1096-0929"]}, DOI={10.1093/toxsci/kfad069}, abstractNote={Abstract}, number={2}, journal={TOXICOLOGICAL SCIENCES}, author={Davis, Allan Peter and Wiegers, Thomas C. and Wiegers, Jolene and Wyatt, Brent and Johnson, Robin J. and Sciaky, Daniela and Barkalow, Fern and Strong, Melissa and Planchart, Antonio and Mattingly, Carolyn J.}, year={2023}, month={Sep}, pages={155–168} }
 @article{davis_wiegers_johnson_sciaky_wiegers_mattingly_2022, title={Comparative Toxicogenomics Database (CTD): update 2023}, volume={9}, ISSN={["1362-4962"]}, DOI={10.1093/nar/gkac833}, abstractNote={Abstract}, journal={NUCLEIC ACIDS RESEARCH}, author={Davis, Allan Peter and Wiegers, Thomas C. and Johnson, Robin J. and Sciaky, Daniela and Wiegers, Jolene and Mattingly, Carolyn J.}, year={2022}, month={Sep} }
 @article{davis_wiegers_wiegers_grondin_johnson_sciaky_mattingly_2021, title={CTD anatomy: Analyzing chemical-induced phenotypes and exposures from an anatomical perspective, with implications for environmental health studies}, volume={2}, ISSN={["2666-027X"]}, DOI={10.1016/j.crtox.2021.03.001}, abstractNote={The Comparative Toxicogenomics Database (CTD) is a freely available public resource that curates and interrelates chemical, gene/protein, phenotype, disease, organism, and exposure data. CTD can be used to address toxicological mechanisms for environmental chemicals and facilitate the generation of testable hypotheses about how exposures affect human health. At CTD, manually curated interactions for chemical-induced phenotypes are enhanced with anatomy terms (tissues, fluids, and cell types) to describe the physiological system of the reported event. These same anatomy terms are used to annotate the human media (e.g., urine, hair, nail, blood, etc.) in which an environmental chemical was assayed for exposure. Currently, CTD uses more than 880 unique anatomy terms to contextualize over 255,000 chemical-phenotype interactions and 167,000 exposure statements. These annotations allow chemical-phenotype interactions and exposure data to be explored from a novel, anatomical perspective. Here, we describe CTD’s anatomy curation process (including the construction of a controlled, interoperable vocabulary) and new anatomy webpages (that coalesce and organize the curated chemical-phenotype and exposure data sets). We also provide examples that demonstrate how this feature can be used to identify system- and cell-specific chemical-induced toxicities, help inform exposure data, prioritize phenotypes for environmental diseases, survey tissue and pregnancy exposomes, and facilitate data connections with external resources. Anatomy annotations advance understanding of environmental health by providing new ways to explore and survey chemical-induced events and exposure studies in the CTD framework.}, journal={CURRENT RESEARCH IN TOXICOLOGY}, author={Davis, Allan Peter and Wiegers, Thomas C. and Wiegers, Jolene and Grondin, Cynthia J. and Johnson, Robin J. and Sciaky, Daniela and Mattingly, Carolyn J.}, year={2021}, pages={128–139} }
 @article{davis_grondin_johnson_sciaky_wiegers_wiegers_mattingly_2021, title={Comparative Toxicogenomics Database (CTD): update 2021}, volume={49}, ISSN={["1362-4962"]}, DOI={10.1093/nar/gkaa891}, abstractNote={Abstract}, number={D1}, journal={NUCLEIC ACIDS RESEARCH}, author={Davis, Allan Peter and Grondin, Cynthia J. and Johnson, Robin J. and Sciaky, Daniela and Wiegers, Jolene and Wiegers, Thomas C. and Mattingly, Carolyn J.}, year={2021}, month={Jan}, pages={D1138–D1143} }
 @article{grondin_davis_wiegers_wiegers_sciaky_johnson_mattingly_2021, title={Predicting molecular mechanisms, pathways, and health outcomes induced by Juul e-cigarette aerosol chemicals using the Comparative Toxicogenomics Database}, volume={2}, ISSN={["2666-027X"]}, DOI={10.1016/j.crtox.2021.08.001}, abstractNote={There is a critical need to understand the health risks associated with vaping e-cigarettes, which has reached epidemic levels among teens. Juul is currently the most popular type of e-cigarette on the market. Using the Comparative Toxicogenomics Database (CTD; http://ctdbase.org), a public resource that integrates chemical, gene, phenotype and disease data, we aimed to analyze the potential molecular mechanisms of eight chemicals detected in the aerosols generated by heating Juul e-cigarette pods: nicotine, acetaldehyde, formaldehyde, free radicals, crotonaldehyde, acetone, pyruvaldehyde, and particulate matter. Curated content in CTD, including chemical-gene, chemical-phenotype, and chemical-disease interactions, as well as associated phenotypes and pathway enrichment, were analyzed to help identify potential molecular mechanisms and diseases associated with vaping. Nicotine shows the most direct disease associations of these chemicals, followed by particulate matter and formaldehyde. Together, these chemicals show a direct marker or mechanistic relationship with 400 unique diseases in CTD, particularly in the categories of cardiovascular diseases, nervous system diseases, respiratory tract diseases, cancers, and mental disorders. We chose three respiratory tract diseases to investigate further, and found that in addition to cellular processes of apoptosis and cell proliferation, prioritized phenotypes underlying Juul-associated respiratory tract disease outcomes include response to oxidative stress, inflammatory response, and several cell signaling pathways (p38MAPK, NIK/NFkappaB, calcium-mediated).}, journal={CURRENT RESEARCH IN TOXICOLOGY}, author={Grondin, Cynthia J. and Davis, Allan Peter and Wiegers, Jolene A. and Wiegers, Thomas C. and Sciaky, Daniela and Johnson, Robin J. and Mattingly, Carolyn J.}, year={2021}, pages={272–281} }
 @article{davis_wiegers_grondin_johnson_sciaky_wiegers_mattingly_2020, title={Leveraging the Comparative Toxicogenomics Database to Fill in Knowledge Gaps for Environmental Health: A Test Case for Air Pollution-induced Cardiovascular Disease}, volume={177}, ISSN={["1096-0929"]}, DOI={10.1093/toxsci/kfaa113}, abstractNote={Abstract}, number={2}, journal={TOXICOLOGICAL SCIENCES}, author={Davis, Allan Peter and Wiegers, Thomas C. and Grondin, Cynthia J. and Johnson, Robin J. and Sciaky, Daniela and Wiegers, Jolene and Mattingly, Carolyn J.}, year={2020}, month={Oct}, pages={392–404} }
 @article{davis_grondin_johnson_sciaky_mcmorran_wiegers_wiegers_mattingly_2019, title={The Comparative Toxicogenomics Database: update 2019}, volume={47}, ISSN={["1362-4962"]}, DOI={10.1093/nar/gky868}, abstractNote={Abstract The Comparative Toxicogenomics Database (CTD; http://ctdbase.org/) is a premier public resource for literature-based, manually curated associations between chemicals, gene products, phenotypes, diseases, and environmental exposures. In this biennial update, we present our new chemical–phenotype module that codes chemical-induced effects on phenotypes, curated using controlled vocabularies for chemicals, phenotypes, taxa, and anatomical descriptors; this module provides unique opportunities to explore cellular and system-level phenotypes of the pre-disease state and allows users to construct predictive adverse outcome pathways (linking chemical–gene molecular initiating events with phenotypic key events, diseases, and population-level health outcomes). We also report a 46% increase in CTD manually curated content, which when integrated with other datasets yields more than 38 million toxicogenomic relationships. We describe new querying and display features for our enhanced chemical–exposure science module, providing greater scope of content and utility. As well, we discuss an updated MEDIC disease vocabulary with over 1700 new terms and accession identifiers. To accommodate these increases in data content and functionality, CTD has upgraded its computational infrastructure. These updates continue to improve CTD and help inform new testable hypotheses about the etiology and mechanisms underlying environmentally influenced diseases.}, number={D1}, journal={NUCLEIC ACIDS RESEARCH}, author={Davis, Allan Peter and Grondin, Cynthia J. and Johnson, Robin J. and Sciaky, Daniela and McMorran, Roy and Wiegers, Jolene and Wiegers, Thomas C. and Mattingly, Carolyn J.}, year={2019}, month={Jan}, pages={D948–D954} }
 @article{davis_wiegers_wiegers_johnson_sciaky_grondin_mattingly_2018, title={Chemical-Induced Phenotypes at CTD Help Inform the Predisease State and Construct Adverse Outcome Pathways}, volume={165}, ISSN={["1096-0929"]}, DOI={10.1093/toxsci/kfy131}, abstractNote={The Comparative Toxicogenomics Database (CTD; http://ctdbase.org) is a public resource that manually curates the scientific literature to provide content that illuminates the molecular mechanisms by which environmental exposures affect human health. We introduce our new chemical-phenotype module that describes how chemicals can affect molecular, cellular, and physiological phenotypes. At CTD, we operationally distinguish between phenotypes and diseases, wherein a phenotype refers to a nondisease biological event: eg, decreased cell cycle arrest (phenotype) versus liver cancer (disease), increased fat cell proliferation (phenotype) versus morbid obesity (disease), etc. Chemical-phenotype interactions are expressed in a formal structured notation using controlled terms for chemicals, phenotypes, taxon, and anatomical descriptors. Combining this information with CTD's chemical-disease module allows inferences to be made between phenotypes and diseases, yielding potential insight into the predisease state. Integration of all 4 CTD modules furnishes unique opportunities for toxicologists to generate computationally predictive adverse outcome pathways, linking chemical-gene molecular initiating events with phenotypic key events, adverse diseases, and population-level health outcomes. As examples, we present 3 diverse case studies discerning the effect of vehicle emissions on altered leukocyte migration, the role of cadmium in influencing phenotypes preceding Alzheimer disease, and the connection of arsenic-induced glucose metabolic phenotypes with diabetes. To date, CTD contains over 165 000 interactions that connect more than 6400 chemicals to 3900 phenotypes for 760 anatomical terms in 215 species, from over 19 000 scientific articles. To our knowledge, this is the first comprehensive set of manually curated, literature-based, contextualized, chemical-induced, nondisease phenotype data provided to the public.}, number={1}, journal={TOXICOLOGICAL SCIENCES}, author={Davis, Allan Peter and Wiegers, Thomas C. and Wiegers, Jolene and Johnson, Robin J. and Sciaky, Daniela and Grondin, Cynthia J. and Mattingly, Carolyn J.}, year={2018}, month={Sep}, pages={145–156} }
 @article{davis_grondin_johnson_sciaky_king_mcmorran_wiegers_wiegers_mattingly_2017, title={The Comparative Toxicogenomics Database: update 2017}, volume={45}, ISSN={["1362-4962"]}, DOI={10.1093/nar/gkw838}, abstractNote={The Comparative Toxicogenomics Database (CTD; http://ctdbase.org/) provides information about interactions between chemicals and gene products, and their relationships to diseases. Core CTD content (chemical-gene, chemical-disease and gene-disease interactions manually curated from the literature) are integrated with each other as well as with select external datasets to generate expanded networks and predict novel associations. Today, core CTD includes more than 30.5 million toxicogenomic connections relating chemicals/drugs, genes/proteins, diseases, taxa, Gene Ontology (GO) annotations, pathways, and gene interaction modules. In this update, we report a 33% increase in our core data content since 2015, describe our new exposure module (that harmonizes exposure science information with core toxicogenomic data) and introduce a novel dataset of GO-disease inferences (that identify common molecular underpinnings for seemingly unrelated pathologies). These advancements centralize and contextualize real-world chemical exposures with molecular pathways to help scientists generate testable hypotheses in an effort to understand the etiology and mechanisms underlying environmentally influenced diseases.}, number={D1}, journal={NUCLEIC ACIDS RESEARCH}, author={Davis, Allan Peter and Grondin, Cynthia J. and Johnson, Robin J. and Sciaky, Daniela and King, Benjamin L. and McMorran, Roy and Wiegers, Jolene and Wiegers, Thomas C. and Mattingly, Carolyn J.}, year={2017}, month={Jan}, pages={D972–D978} }
 @article{li_sun_johnson_sciaky_wei_leaman_davis_mattingly_wiegers_lu_et al._2016, title={BioCreative V CDR task corpus: a resource for chemical disease relation extraction}, ISSN={["1758-0463"]}, DOI={10.1093/database/baw068}, abstractNote={Community-run, formal evaluations and manually annotated text corpora are critically important for advancing biomedical text-mining research. Recently in BioCreative V, a new challenge was organized for the tasks of disease named entity recognition (DNER) and chemical-induced disease (CID) relation extraction. Given the nature of both tasks, a test collection is required to contain both disease/chemical annotations and relation annotations in the same set of articles. Despite previous efforts in biomedical corpus construction, none was found to be sufficient for the task. Thus, we developed our own corpus called BC5CDR during the challenge by inviting a team of Medical Subject Headings (MeSH) indexers for disease/chemical entity annotation and Comparative Toxicogenomics Database (CTD) curators for CID relation annotation. To ensure high annotation quality and productivity, detailed annotation guidelines and automatic annotation tools were provided. The resulting BC5CDR corpus consists of 1500 PubMed articles with 4409 annotated chemicals, 5818 diseases and 3116 chemical-disease interactions. Each entity annotation includes both the mention text spans and normalized concept identifiers, using MeSH as the controlled vocabulary. To ensure accuracy, the entities were first captured independently by two annotators followed by a consensus annotation: The average inter-annotator agreement (IAA) scores were 87.49% and 96.05% for the disease and chemicals, respectively, in the test set according to the Jaccard similarity coefficient. Our corpus was successfully used for the BioCreative V challenge tasks and should serve as a valuable resource for the text-mining research community. Database URL: http://www.biocreative.org/tasks/biocreative-v/track-3-cdr/}, journal={DATABASE-THE JOURNAL OF BIOLOGICAL DATABASES AND CURATION}, author={Li, J. and Sun, Y. P. and Johnson, R. J. and Sciaky, D. and Wei, C. H. and Leaman, R. and Davis, A. P. and Mattingly, Carolyn and Wiegers, T. C. and Lu, Z. Y. and et al.}, year={2016}, month={May} }
 @article{davis_wiegers_king_wiegers_grondin_sciaky_johnson_mattingly_2016, title={Generating Gene Ontology-Disease Inferences to Explore Mechanisms of Human Disease at the Comparative Toxicogenomics Database}, volume={11}, ISSN={["1932-6203"]}, DOI={10.1371/journal.pone.0155530}, abstractNote={Strategies for discovering common molecular events among disparate diseases hold promise for improving understanding of disease etiology and expanding treatment options. One technique is to leverage curated datasets found in the public domain. The Comparative Toxicogenomics Database (CTD; http://ctdbase.org/) manually curates chemical-gene, chemical-disease, and gene-disease interactions from the scientific literature. The use of official gene symbols in CTD interactions enables this information to be combined with the Gene Ontology (GO) file from NCBI Gene. By integrating these GO-gene annotations with CTD’s gene-disease dataset, we produce 753,000 inferences between 15,700 GO terms and 4,200 diseases, providing opportunities to explore presumptive molecular underpinnings of diseases and identify biological similarities. Through a variety of applications, we demonstrate the utility of this novel resource. As a proof-of-concept, we first analyze known repositioned drugs (e.g., raloxifene and sildenafil) and see that their target diseases have a greater degree of similarity when comparing GO terms vs. genes. Next, a computational analysis predicts seemingly non-intuitive diseases (e.g., stomach ulcers and atherosclerosis) as being similar to bipolar disorder, and these are validated in the literature as reported co-diseases. Additionally, we leverage other CTD content to develop testable hypotheses about thalidomide-gene networks to treat seemingly disparate diseases. Finally, we illustrate how CTD tools can rank a series of drugs as potential candidates for repositioning against B-cell chronic lymphocytic leukemia and predict cisplatin and the small molecule inhibitor JQ1 as lead compounds. The CTD dataset is freely available for users to navigate pathologies within the context of extensive biological processes, molecular functions, and cellular components conferred by GO. This inference set should aid researchers, bioinformaticists, and pharmaceutical drug makers in finding commonalities in disease mechanisms, which in turn could help identify new therapeutics, new indications for existing pharmaceuticals, potential disease comorbidities, and alerts for side effects.}, number={5}, journal={PLOS ONE}, author={Davis, Allan Peter and Wiegers, Thomas C. and King, Benjamin L. and Wiegers, Jolene and Grondin, Cynthia J. and Sciaky, Daniela and Johnson, Robin J. and Mattingly, Carolyn J.}, year={2016}, month={May} }
 @article{davis_grondin_lennon-hopkins_saraceni-richards_sciaky_king_wiegers_mattingly_2015, title={The Comparative Toxicogenomics Database's 10th year anniversary: update 2015}, volume={43}, ISSN={["1362-4962"]}, DOI={10.1093/nar/gku935}, abstractNote={Ten years ago, the Comparative Toxicogenomics Database (CTD; http://ctdbase.org/) was developed out of a need to formalize, harmonize and centralize the information on numerous genes and proteins responding to environmental toxic agents across diverse species. CTD's initial approach was to facilitate comparisons of nucleotide and protein sequences of toxicologically significant genes by curating these sequences and electronically annotating them with chemical terms from their associated references. Since then, however, CTD has vastly expanded its scope to robustly represent a triad of chemical–gene, chemical–disease and gene–disease interactions that are manually curated from the scientific literature by professional biocurators using controlled vocabularies, ontologies and structured notation. Today, CTD includes 24 million toxicogenomic connections relating chemicals/drugs, genes/proteins, diseases, taxa, phenotypes, Gene Ontology annotations, pathways and interaction modules. In this 10th year anniversary update, we outline the evolution of CTD, including our increased data content, new ‘Pathway View’ visualization tool, enhanced curation practices, pilot chemical–phenotype results and impending exposure data set. The prototype database originally described in our first report has transformed into a sophisticated resource used actively today to help scientists develop and test hypotheses about the etiologies of environmentally influenced diseases.}, number={D1}, journal={NUCLEIC ACIDS RESEARCH}, author={Davis, Allan Peter and Grondin, Cynthia J. and Lennon-Hopkins, Kelley and Saraceni-Richards, Cynthia and Sciaky, Daniela and King, Benjamin L. and Wiegers, Thomas C. and Mattingly, Carolyn J.}, year={2015}, month={Jan}, pages={D914–D920} }
 @article{davis_wiegers_roberts_king_lay_lennon-hopkins_sciaky_johnson_keating_greene_et al._2013, title={A CTD-Pfizer collaboration: manual curation of 88 000 scientific articles text mined for drug-disease and drug-phenotype interactions}, ISSN={["1758-0463"]}, DOI={10.1093/database/bat080}, abstractNote={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/}, journal={DATABASE-THE JOURNAL OF BIOLOGICAL DATABASES AND CURATION}, author={Davis, Allan Peter and Wiegers, Thomas C. and Roberts, Phoebe M. and King, Benjamin L. and Lay, Jean M. and Lennon-Hopkins, Kelley and Sciaky, Daniela and Johnson, Robin and Keating, Heather and Greene, Nigel and et al.}, year={2013}, month={Nov} }