EUVIMEDEUVIMED entdecken
Open Access

ToxCompl completion of the DrugMatrix toxicogenomics database: an integrated resource for hypothesis generation

Laura J Word iD, Guojing Cong iD, Robert M Patton iD, Frank Chao iD, Daniel L Svoboda iD, Warren M Casey iD, Charles P Schmitt iD, Jeremy N Erickson iD, Parker Combs iD, Scott S Auerbach iD

Toxicological Sciences · 2026

DOI: 10.1093/toxsci/kfag113 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Toxicological Sciences, 2026. Verfasst von Laura J Word und 9 weiteren Autor:innen. Beteiligte Einrichtung: Division of Translational Toxicology, National Institute of Environmental Health Sciences, Research Triangle Park, NC, United States. Hauptthemen laut MEDLINE: Toxicogenetics, Databases, Genetic, Databases, Factual. Die Arbeit nennt 120 Literaturangaben. Der Volltext ist frei in PubMed Central verfügbar. Gefördert von: Oak Ridge National Laboratory (ORNL), National Institutes of Health (NIH) and the National Institute of Environmental Health Sciences (NIEHS), U.S. Department of Energy (DOE), Office of Science.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The DrugMatrix database contains systematically generated toxicogenomics data from short-term in vivo studies for over 600 chemicals. However, most potential endpoints are missing due to a lack of experimental measurements. Therefore, we leveraged matrix factorization and machine learning methods to predict the missing values, which includes gene expression across 8 tissues on 2 expression platforms along with paired clinical chemistry, hematology, and histopathology. We propose a method, ToxCompl, that applies systematic hybrid sampling guided by Bayesian optimization in conjunction with low-rank matrix factorization to predict the missing values. In-depth validation of the ToxCompl predicted data from machine learning, biological, and toxicological perspectives shows that the predicted differential gene expression aligns well with what would be anticipated. This includes examining the connectivity pattern of predicted gene expression responses, characterizing molecular pathway-level responses from sets of differentially expressed genes, evaluating known transcriptional biomarkers of tissue toxicity, and characterizing predicted apical endpoints. For example, we identified kidney toxicants using the transcriptional biomarker Havcr1. All measured and predicted DrugMatrix data (i.e., gene expression, clinical chemistry, hematology, and histopathology) are available to the public (https://rstudio.niehs.nih.gov/toxcompl/). Notably, predicted clinical chemistry of subtle effects and histopathological prediction are 2 areas we will continue to improve. The main advantage of the ToxCompl approach is that it drastically extends the toxicogenomic landscape into many data-poor tissues in the absence of acquiring additional experimental data, thereby allowing researchers to formulate mechanistic hypotheses about effects in tissues that have been underrepresented in the literature.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

ToxicogeneticsDatabases, GeneticDatabases, FactualHumansAnimalsMachine LearningGene Expression ProfilingBayes TheoremBiocuration

Stichwörter der Autor:innen

artificial intelligencebioinformaticsbiological modelingcomputational toxicologygene expressiontoxicogenomics

Autor:innen und Institutionen

  • Division of Translational Toxicology, National Institute of Environmental Health Sciences, Research Triangle Park, NC, United States.
  • Contemporaries Inc, Columbia, MD, United States.
  • Data and AI Section, Oak Ridge National Laboratory, Oak Ridge, TN, United States.
  • Sciome LLC, Research Triangle Park, NC, United States.
  • Axle Informatics, North Bethesda, MD, United States.

ORCID-Profile: Laura J Word, Guojing Cong, Robert M Patton, Frank Chao, Daniel L Svoboda, Warren M Casey, Charles P Schmitt, Jeremy N Erickson, Parker Combs, Scott S Auerbach

Förderung

  • Oak Ridge National Laboratory (ORNL)
  • National Institutes of Health (NIH) and the National Institute of Environmental Health Sciences (NIEHS)
  • U.S. Department of Energy (DOE), Office of Science
  • Intramural NIH HHS
  • Compute and Data Environment for Science (CADES)
  • ORNL
  • Department of Health and Human Services (HHS)
  • NIEHS

Zitieren

APA

Word, L. J., Cong, G., Patton, R. M., Chao, F., Svoboda, D. L., Casey, W. M., Schmitt, C. P., Erickson, J. N., Combs, P., & Auerbach, S. S. (2026). ToxCompl completion of the DrugMatrix toxicogenomics database: an integrated resource for hypothesis generation. Toxicological Sciences. https://doi.org/10.1093/toxsci/kfag113

Vancouver

Word LJ, Cong G, Patton RM, Chao F, Svoboda DL, Casey WM, et al. ToxCompl completion of the DrugMatrix toxicogenomics database: an integrated resource for hypothesis generation. Toxicological Sciences. 2026. doi:10.1093/toxsci/kfag113

BibTeX
@article{Word2026,
  author = {Word, Laura J and Cong, Guojing and Patton, Robert M and Chao, Frank and Svoboda, Daniel L and Casey, Warren M and Schmitt, Charles P and Erickson, Jeremy N and Combs, Parker and Auerbach, Scott S},
  title = {ToxCompl completion of the DrugMatrix toxicogenomics database: an integrated resource for hypothesis generation},
  journal = {Toxicological Sciences},
  year = {2026},
  doi = {10.1093/toxsci/kfag113}
}
Kostenlos starten →