Molecules and Cells

Korean Society for Molecular and Cellular Biology (한국분자세포생물학회)
권호 표지
DOI QR코드

DOI QR Code

Deep Learning Approach Based on Transcriptome Profile for Data Driven Drug Discovery

  • Eun-Ji Kwon (College of Pharmacy, Seoul National University) ;
  • Hyuk-Jin Cha (College of Pharmacy, Seoul National University)
  • Received : 2022.11.02
  • Accepted : 2022.11.22
  • Published : 2023.01.31
Download PDF
⟨ Previous Next ⟩

Abstract

SMILES (simplified molecular-input line-entry system) information of small molecules parsed by one-hot array is passed to a convolutional neural network called black box. Outputs data representing a gene signature is then matched to the genetic signature of a disease to predict the appropriate small molecule. Efficacy of the predicted small molecules is examined by in vivo animal models. GSEA, gene set enrichment analysis.

Keywords

Acknowledgement

This work was supported by the Seoul National University Research Grant in 2022.

References

  1. Casamassimi, A., Federico, A., Rienzo, M., Esposito, S., and Ciccodicola, A. (2017). Transcriptome profiling in human diseases: new advances and perspectives. Int. J. Mol. Sci. 18, 1652.
  2. Chiu, Y.C., Zheng, S., Wang, L.J., Iskra, B.S., Rao, M.K., Houghton, P.J., Huang, Y., and Chen, Y. (2021). Predicting and characterizing a cancer dependency map of tumors with deep learning. Sci. Adv. 7, eabh1275.
  3. Kwon, O.S., Kim, W., Cha, H.J., and Lee, H. (2019). In silico drug repositioning: from large-scale transcriptome data to therapeutics. Arch. Pharm. Res. 42, 879-889. https://doi.org/10.1007/s12272-019-01176-3
  4. Kwon, O.S., Lee, H., Kong, H.J., Kwon, E.J., Park, J.E., Lee, W., Kang, S., Kim, M., Kim, W., and Cha, H.J. (2020). Connectivity map-based drug repositioning of bortezomib to reverse the metastatic effect of GALNT14 in lung cancer. Oncogene 39, 4567-4580. https://doi.org/10.1038/s41388-020-1316-2
  5. Muzio, G., O'Bray, L., and Borgwardt, K. (2021). Biological network analysis with deep learning. Brief. Bioinform. 22, 1515-1530. https://doi.org/10.1093/bib/bbaa257
  6. Park, J.C., Kim, J., Jang, H.K., Lee, S.Y., Kim, K.T., Kwon, E.J., Park, S., Lee, H.S., Choi, H., Park, S.Y., et al. (2022). Multiple isogenic GNE-myopathy modeling with mutation specific phenotypes from human pluripotent stem cells by base editors. Biomaterials 282, 121419.
  7. Schenone, M., Dancik, V., Wagner, B.K., and Clemons, P.A. (2013). Target identification and mechanism of action in chemical biology and drug discovery. Nat. Chem. Biol. 9, 232-240. https://doi.org/10.1038/nchembio.1199
  8. Subramanian, A., Narayan, R., Corsello, S.M., Peck, D.D., Natoli, T.E., Lu, X., Gould, J., Davis, J.F., Tubelli, A.A., Asiedu, J.K., et al. (2017). A next generation Connectivity Map: L1000 platform and the first 1,000,000 profiles. Cell 171, 1437-1452.e17. https://doi.org/10.1016/j.cell.2017.10.049
  9. Zhao, K. and So, H.C. (2019). Using drug expression profiles and machine learning approach for drug repurposing. Methods Mol. Biol. 1903, 219-237. https://doi.org/10.1007/978-1-4939-8955-3_13
  10. Zhu, J., Wang, J., Wang, X., Gao, M., Guo, B., Gao, M., Liu, J., Yu, Y., Wang, L., Kong, W., et al. (2021). Prediction of drug efficacy from transcriptional profiles with deep learning. Nat. Biotechnol. 39, 1444-1452. https://doi.org/10.1038/s41587-021-00946-z