Display options
Cite
Ma J, Fong SH, Luo Y, et al. Few-shot learning creates predictive models of drug response that translate from high-throughput screens to individual patients. Nat Cancer. 2021;2(2):233-244doi: 10.1038/s43018-020-00169-2.
Ma, J., Fong, S. H., Luo, Y., Bakkenist, C. J., Shen, J. P., Mourragui, S., Wessels, L. F. A., Hafner, M., Sharan, R., Peng, J., & Ideker, T. (2021). Few-shot learning creates predictive models of drug response that translate from high-throughput screens to individual patients. Nature cancer, 2(2), 233-244. https://doi.org/10.1038/s43018-020-00169-2
Ma, Jianzhu, et al. "Few-shot learning creates predictive models of drug response that translate from high-throughput screens to individual patients." Nature cancer vol. 2,2 (2021): 233-244. doi: https://doi.org/10.1038/s43018-020-00169-2
Ma J, Fong SH, Luo Y, Bakkenist CJ, Shen JP, Mourragui S, Wessels LFA, Hafner M, Sharan R, Peng J, Ideker T. Few-shot learning creates predictive models of drug response that translate from high-throughput screens to individual patients. Nat Cancer. 2021 Feb;2(2):233-244. doi: 10.1038/s43018-020-00169-2. Epub 2021 Jan 25. PMID: 34223192; PMCID: PMC8248912.
Copy Download .nbib Format: NLM
Share it on

Nat Cancer. 2021 Feb;2(2):233-244. doi: 10.1038/s43018-020-00169-2. Epub 2021 Jan 25.

Few-shot learning creates predictive models of drug response that translate from high-throughput screens to individual patients.

Nature cancer

Jianzhu Ma, Samson H Fong, Yunan Luo, Christopher J Bakkenist, John Paul Shen, Soufiane Mourragui, Lodewyk F A Wessels, Marc Hafner, Roded Sharan, Jian Peng, Trey Ideker

Affiliations

  1. Department of Medicine, University of California San Diego, La Jolla, CA, USA.
  2. Department of Computer Science, Purdue University, West Lafayette, IN, USA.
  3. Department of Bioengineering, University of California San Diego, La Jolla, CA, USA.
  4. Department of Computer Science, University of Illinois at Urbana-Champaign, Urbana, IL, USA.
  5. Department of Radiation Oncology, University of Pittsburgh School of Medicine, Pittsburgh, PA, USA.
  6. Department of Gastrointestinal Medical Oncology, University of Texas MD Anderson Cancer Center, Houston, TX, USA.
  7. Division of Molecular Carcinogenesis, Oncode Institute, The Netherlands Cancer Institute, Amsterdam, the Netherlands.
  8. Faculty of Electrical Engineering, Mathematics and Computer Science, Delft University of Technology, Delft, the Netherlands.
  9. Department of Bioinformatics and Computational Biology, Genentech, Inc., South San Francisco, CA, USA.
  10. Blavatnik School of Computer Science, Tel Aviv University, Tel Aviv, Israel.

PMID: 34223192 PMCID: PMC8248912 DOI: 10.1038/s43018-020-00169-2

Abstract

Cell-line screens create expansive datasets for learning predictive markers of drug response, but these models do not readily translate to the clinic with its diverse contexts and limited data. In the present study, we apply a recently developed technique, few-shot machine learning, to train a versatile neural network model in cell lines that can be tuned to new contexts using few additional samples. The model quickly adapts when switching among different tissue types and in moving from cell-line models to clinical contexts, including patient-derived tumor cells and patient-derived xenografts. It can also be interpreted to identify the molecular features most important to a drug response, highlighting critical roles for

References

  1. Nucleic Acids Res. 2019 Jan 8;47(D1):D559-D563 - PubMed
  2. Cell. 2016 Sep 22;167(1):260-274.e22 - PubMed
  3. Nat Protoc. 2011 Nov 03;6(12):1870-86 - PubMed
  4. Cell Cycle. 2005 Jan;4(1):63-6 - PubMed
  5. Nucleic Acids Res. 2018 Jul 6;46(12):6087-6098 - PubMed
  6. Nature. 2012 Jan 26;483(7387):100-3 - PubMed
  7. J Natl Cancer Inst. 2013 Oct 2;105(19):1441-56 - PubMed
  8. Nat Med. 2015 Nov;21(11):1318-25 - PubMed
  9. Br J Cancer. 1999 Feb;79(5-6):693-700 - PubMed
  10. Nature. 2008 Jun 12;453(7197):840-2 - PubMed
  11. Nature. 1998 Jul 2;394(6688):88-92 - PubMed
  12. Eur J Cancer. 2016 Jul;62:132-7 - PubMed
  13. Nat Methods. 2018 Apr;15(4):290-298 - PubMed
  14. Nat Genet. 2017 Dec;49(12):1779-1784 - PubMed
  15. ACS Cent Sci. 2017 Apr 26;3(4):283-293 - PubMed
  16. Cell. 2016 Jul 28;166(3):740-754 - PubMed
  17. Nature. 2019 May;569(7757):503-508 - PubMed
  18. Nat Commun. 2019 Aug 8;10(1):3574 - PubMed
  19. Nucleic Acids Res. 2011 Jan;39(Database issue):D685-90 - PubMed
  20. Int J Biol Sci. 2018 Jan 12;14(2):111-123 - PubMed
  21. Bioinformatics. 2018 May 1;34(9):1538-1546 - PubMed
  22. J Biol Chem. 2012 Dec 21;287(52):43984-94 - PubMed
  23. J Clin Oncol. 2012 Apr 1;30(10):1114-21 - PubMed
  24. Nat Commun. 2019 Nov 6;10(1):5034 - PubMed
  25. Nat Methods. 2017 Jan;14(1):61-64 - PubMed
  26. Cell Biosci. 2015 Oct 13;5:58 - PubMed
  27. Proc Natl Acad Sci U S A. 2018 Nov 6;115(45):E10576-E10585 - PubMed
  28. J Cell Sci. 2012 Dec 15;125(Pt 24):6049-57 - PubMed
  29. J Cell Biol. 2010 Sep 6;190(5):731-40 - PubMed
  30. Nat Med. 2018 Nov;24(11):1752-1761 - PubMed
  31. Science. 2015 Dec 11;350(6266):1332-8 - PubMed
  32. Clin Cancer Res. 2009 May 15;15(10):3484-94 - PubMed
  33. J Cheminform. 2014 Nov 26;6(1):47 - PubMed
  34. Oncogene. 2015 Aug 13;34(33):4403-11 - PubMed
  35. Endocr Relat Cancer. 2011 Aug 30;18(5):565-77 - PubMed

Publication Types

Grant support