Leveraging high-throughput screening data, deep neural networks, and conditional generative adversarial networks to advance predictive toxicology.

Item request has been placed! ×
Item request cannot be made. ×
loading   Processing Request
Read Online Read More Add to Saved list
  • Additional Information
    • Source:
      Publisher: Public Library of Science Country of Publication: United States NLM ID: 101238922 Publication Model: eCollection Cited Medium: Internet ISSN: 1553-7358 (Electronic) Linking ISSN: 1553734X NLM ISO Abbreviation: PLoS Comput Biol Subsets: MEDLINE
    • Publication Information:
      Original Publication: San Francisco, CA : Public Library of Science, [2005]-
    • Subject Terms:
      Computational Biology* ; High-Throughput Screening Assays* ; Neural Networks, Computer* ; Toxicology*; Animals ; Embryo, Nonmammalian/drug effects ; Models, Chemical ; Toxicity Tests ; Zebrafish
    • Abstract:
      There are currently 85,000 chemicals registered with the Environmental Protection Agency (EPA) under the Toxic Substances Control Act, but only a small fraction have measured toxicological data. To address this gap, high-throughput screening (HTS) and computational methods are vital. As part of one such HTS effort, embryonic zebrafish were used to examine a suite of morphological and mortality endpoints at six concentrations from over 1,000 unique chemicals found in the ToxCast library (phase 1 and 2). We hypothesized that by using a conditional generative adversarial network (cGAN) or deep neural networks (DNN), and leveraging this large set of toxicity data we could efficiently predict toxic outcomes of untested chemicals. Utilizing a novel method in this space, we converted the 3D structural information into a weighted set of points while retaining all information about the structure. In vivo toxicity and chemical data were used to train two neural network generators. The first was a DNN (Go-ZT) while the second utilized cGAN architecture (GAN-ZT) to train generators to produce toxicity data. Our results showed that Go-ZT significantly outperformed the cGAN, support vector machine, random forest and multilayer perceptron models in cross-validation, and when tested against an external test dataset. By combining both Go-ZT and GAN-ZT, our consensus model improved the SE, SP, PPV, and Kappa, to 71.4%, 95.9%, 71.4% and 0.673, respectively, resulting in an area under the receiver operating characteristic (AUROC) of 0.837. Considering their potential use as prescreening tools, these models could provide in vivo toxicity predictions and insight into the hundreds of thousands of untested chemicals to prioritize compounds for HT testing.
      Competing Interests: The authors have declared that no competing interests exist.
    • References:
      J Chem Inf Model. 2018 Jun 25;58(6):1194-1204. (PMID: 29762023)
      J Chem Inf Model. 2015 Mar 23;55(3):510-28. (PMID: 25647539)
      Regul Toxicol Pharmacol. 2020 Jun;113:104620. (PMID: 32092371)
      Toxicol Sci. 2014 Jan;137(1):212-33. (PMID: 24136191)
      J Cheminform. 2017 Nov 28;9(1):61. (PMID: 29185060)
      Front Bioeng Biotechnol. 2020 Jan 22;7:485. (PMID: 32039185)
      J Environ Sci Health C Environ Carcinog Ecotoxicol Rev. 2018;36(4):169-191. (PMID: 30628866)
      Methods Mol Biol. 2018;1800:119-139. (PMID: 29934890)
      Environ Health Perspect. 2010 Apr;118(4):485-92. (PMID: 20368123)
      J Cheminform. 2011 Oct 07;3:33. (PMID: 21982300)
      Mol Pharm. 2017 Sep 5;14(9):3098-3104. (PMID: 28703000)
      J Toxicol Environ Health B Crit Rev. 2010 Feb;13(2-4):51-138. (PMID: 20574894)
      Indian J Ophthalmol. 2008 Jan-Feb;56(1):45-50. (PMID: 18158403)
      Toxicol Sci. 2015 May;145(1):177-95. (PMID: 25711236)
      Wiley Interdiscip Rev Comput Mol Sci. 2014 Sep 1;4(5):468-481. (PMID: 25285160)
      Toxicol Sci. 2007 Jan;95(1):5-12. (PMID: 16963515)
      Chem Res Toxicol. 2016 Aug 15;29(8):1225-51. (PMID: 27367298)
      Nat Mater. 2019 May;18(5):435-441. (PMID: 31000803)
      Front Pharmacol. 2019 Jun 11;10:561. (PMID: 31244651)
      Chem Sci. 2018 Jun 6;9(24):5441-5451. (PMID: 30155234)
      Front Physiol. 2019 Aug 13;10:1044. (PMID: 31456700)
      Reprod Toxicol. 2016 Jul;62:92-9. (PMID: 27132190)
      Molecules. 2019 Sep 17;24(18):. (PMID: 31533341)
      J Comput Chem. 2017 Jun 15;38(16):1291-1307. (PMID: 28272810)
      J Cheminform. 2020 Oct 27;12(1):66. (PMID: 33372637)
      J Comput Aided Mol Des. 2020 Jul;34(7):731-746. (PMID: 32297073)
      Front Pharmacol. 2019 Feb 05;10:42. (PMID: 30804783)
      Methods Mol Biol. 2016;1425:361-81. (PMID: 27311474)
      BMC Bioinformatics. 2018 Dec 31;19(Suppl 19):526. (PMID: 30598075)
      Reprod Toxicol. 2017 Aug;71:8-15. (PMID: 28428071)
      BMC Pharmacol Toxicol. 2019 Jan 08;20(1):2. (PMID: 30621790)
      Front Genet. 2018 Nov 27;9:585. (PMID: 30538725)
      J Pharmacol Toxicol Methods. 2014 Mar-Apr;69(2):115-40. (PMID: 24361690)
      J Med Chem. 2014 Jun 26;57(12):4977-5010. (PMID: 24351051)
    • Grant Information:
      P30 ES025128 United States ES NIEHS NIH HHS; P30 ES030287 United States ES NIEHS NIH HHS; R01 CA161608 United States CA NCI NIH HHS; R56 ES030007 United States ES NIEHS NIH HHS
    • Publication Date:
      Date Created: 20210702 Date Completed: 20211101 Latest Revision: 20240402
    • Publication Date:
      20240402
    • Accession Number:
      PMC8301607
    • Accession Number:
      10.1371/journal.pcbi.1009135
    • Accession Number:
      34214078