Display options
Cite
Romano JD, Hao Y, Moore JH. Improving QSAR Modeling for Predictive Toxicology using Publicly Aggregated Semantic Graph Data and Graph Neural Networks. Pac Symp Biocomput. 2022;27:187-198
Romano, J. D., Hao, Y., & Moore, J. H. (2022). Improving QSAR Modeling for Predictive Toxicology using Publicly Aggregated Semantic Graph Data and Graph Neural Networks. Pacific Symposium on Biocomputing. Pacific Symposium on Biocomputing, 27187-198.
Romano, Joseph D, et al. "Improving QSAR Modeling for Predictive Toxicology using Publicly Aggregated Semantic Graph Data and Graph Neural Networks." Pacific Symposium on Biocomputing. Pacific Symposium on Biocomputing vol. 27 (2022): 187-198.
Romano JD, Hao Y, Moore JH. Improving QSAR Modeling for Predictive Toxicology using Publicly Aggregated Semantic Graph Data and Graph Neural Networks. Pac Symp Biocomput. 2022;27:187-198. PMID: 34890148; PMCID: PMC8714189.
Copy Download .nbib Format: NLM
Share it on

Pac Symp Biocomput. 2022;27:187-198.

Improving QSAR Modeling for Predictive Toxicology using Publicly Aggregated Semantic Graph Data and Graph Neural Networks.

Pacific Symposium on Biocomputing. Pacific Symposium on Biocomputing

Joseph D Romano, Yun Hao, Jason H Moore

Affiliations

  1. Institute for Biomedical Informatics, University of Pennsylvania, Philadelphia, Pennsylvania 19104, United States.

PMID: 34890148 PMCID: PMC8714189

Abstract

Quantitative Structure-Activity Relationship (QSAR) modeling is a common computational technique for predicting chemical toxicity, but a lack of new methodological innovations has impeded QSAR performance on many tasks. We show that contemporary QSAR modeling for predictive toxicology can be substantially improved by incorporating semantic graph data aggregated from open-access public databases, and analyzing those data in the context of graph neural networks (GNNs). Furthermore, we introspect the GNNs to demonstrate how they can lead to more interpretable applications of QSAR, and use ablation analysis to explore the contribution of different data elements to the final models' performance.

References

  1. J Chem Inf Comput Sci. 2002 Nov-Dec;42(6):1273-80 - PubMed
  2. Bioinformatics. 2020 Feb 15;36(4):1241-1251 - PubMed
  3. J Cheminform. 2017 Nov 28;9(1):61 - PubMed
  4. Regul Toxicol Pharmacol. 2019 Aug;106:90-104 - PubMed
  5. Mol Inform. 2010 Jul 12;29(6-7):476-88 - PubMed
  6. Exp Ther Med. 2017 May;13(5):2529-2536 - PubMed
  7. J Chem Inf Model. 2006 Jul-Aug;46(4):1535 - PubMed
  8. J Chem Inf Comput Sci. 2003 Nov-Dec;43(6):1947-58 - PubMed
  9. Comb Chem High Throughput Screen. 2006 Mar;9(3):213-28 - PubMed
  10. Nucleic Acids Res. 2015 Jan;43(Database issue):D36-42 - PubMed
  11. Nature. 2004 Dec 16;432(7019):862-5 - PubMed
  12. Elife. 2017 Sep 22;6: - PubMed
  13. Curr Opin Pharmacol. 2013 Oct;13(5):802-6 - PubMed
  14. J Cheminform. 2021 May 26;13(1):41 - PubMed
  15. J Chem Inf Model. 2016 Dec 27;56(12):2353-2360 - PubMed
  16. J Med Chem. 2014 Jun 26;57(12):4977-5010 - PubMed
  17. Wiley Interdiscip Rev Comput Mol Sci. 2016 Mar;6(2):147-172 - PubMed
  18. Environ Health Perspect. 2013 Jul;121(7):756-65 - PubMed

Publication Types

Grant support