Brief Communication | Published:

Visualization and analysis of single-cell RNA-seq data by kernel-based similarity learning

Nature Methods volume 14, pages 414416 (2017) | Download Citation

Abstract

We present single-cell interpretation via multikernel learning (SIMLR), an analytic framework and software which learns a similarity measure from single-cell RNA-seq data in order to perform dimension reduction, clustering and visualization. On seven published data sets, we benchmark SIMLR against state-of-the-art methods. We show that SIMLR is scalable and greatly enhances clustering performance while improving the visualization and interpretability of single-cell sequencing data.

Access optionsAccess options

Rent or Buy article

Get time limited or full article access on ReadCube.

from$8.99

All prices are NET prices.

References

  1. 1.

    , & Nat. Rev. Genet. 14, 618–630 (2013).

  2. 2.

    et al. Nat. Biotechnol. 32, 1053–1058 (2014).

  3. 3.

    et al. Nat. Neurosci. 18, 145–153 (2015).

  4. 4.

    et al. Cell Stem Cell 17, 471–485 (2015).

  5. 5.

    & Genome Biol. 16, 241 (2015).

  6. 6.

    et al. Cell 161, 1202–1214 (2015).

  7. 7.

    et al. Nat. Commun. 8, 14049 (2017).

  8. 8.

    , & In Proc. 21st Int. Conf. Mach. Learn (eds. Greiner, R. & Schuurmans, D.) 6 (ICML, 2004).

  9. 9.

    & J. Mach. Learn. Res. 12, 2211–2268 (2011).

  10. 10.

    et al. Nat. Methods 11, 333–337 (2014).

  11. 11.

    et al. Nat. Biotechnol. 33, 155–160 (2015).

  12. 12.

    Principal Component Analysis (Wiley Online Library, 2002).

  13. 13.

    & J. Mach. Learn. Res. 9, 2579–2605 (2008).

  14. 14.

    & Science 315, 972–976 (2007).

  15. 15.

    & In Proc. 21st Int. Conf. Mach. Learn (eds. Greiner, R. & Schuurmans, D.) 225–232 (ICML, 2004).

  16. 16.

    et al. Cell 163, 1663–1677 (2015).

  17. 17.

    Zeisel, A. et al. Title. Science 347, 1138–1142 (2015).

  18. 18.

    Stat. Comput. 17, 395–416 (2007).

  19. 19.

    et al. Adv. Neural Inf. Process. Syst. 3297–3305 (2016).

  20. 20.

    , & Interior-Point Polynomial Algorithms in Convex Programming (SIAM, 1994).

  21. 21.

    The Symmetric Eigenvalue Problem (SIAM, 1980).

  22. 22.

    & In Proc. 10th IEEE Conf. Data Min. (eds. Webb, G.I. et al.) 599–608 (IEEE, 2010).

  23. 23.

    , & Adv. Neural Inf. Process. Syst. 18, 507–514 (2005).

  24. 24.

    , , & Bioinformatics 28, 573–580 (2012).

  25. 25.

    J. Mach. Learn. Res. 15, 3221–3245 (2014).

Download references

Acknowledgements

The authors would like to thank G.X. Zheng, J. Terry and T. Mikkelsen from 10x Genomics for providing access to the PBMC data as well as suggestions for the manuscript and the in silico experiments. E.P. acknowledges support from an NDSEG Fellowship and a Hertz Fellowship. J.Z. acknowledges support from a Stanford Graduate Fellowship.

Author information

Affiliations

  1. Department of Computer Science, Stanford University, Stanford, California, USA.

    • Bo Wang
    • , Emma Pierson
    • , Daniele Ramazzotti
    •  & Serafim Batzoglou
  2. Department of Electrical Engineering, Stanford University, Stanford, California, USA.

    • Junjie Zhu
  3. Department of Pathology, Stanford University, Stanford, California, USA.

    • Daniele Ramazzotti

Authors

  1. Search for Bo Wang in:

  2. Search for Junjie Zhu in:

  3. Search for Emma Pierson in:

  4. Search for Daniele Ramazzotti in:

  5. Search for Serafim Batzoglou in:

Contributions

B.W., J.Z., and S.B. conceived the study and planned experiments. B.W. designed the algorithm and implemented the software in MATLAB. D.R. and B.W. developed the software package in R. J.Z. and E.P. performed data analysis and implemented the simulation study. J.Z. and E.P. drafted the manuscript. B.W. and S.B. contributed to the manuscript. All authors read and approved the final manuscript.

Competing interests

S.B. is currently on a leave of absence from Stanford, and he is VP of Applied and Computational Biology at Illumina.

Corresponding authors

Correspondence to Bo Wang or Serafim Batzoglou.

Supplementary information

PDF files

  1. 1.

    Supplementary Text and Figures

    Supplementary Figures 1–29, Supplementary Tables 1–10 and Supplementary Notes 1–10

Zip files

  1. 1.

    Supplementary Software 1

    Matlab and R implementations of SIMLR with four small-scale single-cell RNA-seq datasets

About this article

Publication history

Received

Accepted

Published

DOI

https://doi.org/10.1038/nmeth.4207

Further reading