Brief Communication | Published:

Convolutional neural networks for automated annotation of cellular cryo-electron tomograms

Nature Methods volume 14, pages 983985 (2017) | Download Citation

Abstract

Cellular electron cryotomography offers researchers the ability to observe macromolecules frozen in action in situ, but a primary challenge with this technique is identifying molecular components within the crowded cellular environment. We introduce a method that uses neural networks to dramatically reduce the time and human effort required for subcellular annotation and feature extraction. Subsequent subtomogram classification and averaging yield in situ structures of molecular components of interest. The method is available in the EMAN2.2 software package.

Access optionsAccess options

Rent or Buy article

Get time limited or full article access on ReadCube.

from$8.99

All prices are NET prices.

Accessions

Primary accessions

Electron Microscopy Data Bank

Referenced accessions

Electron Microscopy Data Bank

References

  1. 1.

    , & J. Cell Biol. 202, 407–419 (2013).

  2. 2.

    et al. J. Struct. Biol. 194, 383–394 (2016).

  3. 3.

    , , , & J. Struct. Biol. 182, 235–245 (2013).

  4. 4.

    et al. Science 347, 439–442 (2015).

  5. 5.

    , , & Nat. Commun. 6, 6019 (2015).

  6. 6.

    , & J. Struct. Biol. 192, 279–286 (2015).

  7. 7.

    et al. J. Struct. Biol. 177, 135–144 (2012).

  8. 8.

    , & Ultramicroscopy 155, 20–26 (2015).

  9. 9.

    et al. Proc. Natl. Acad. Sci. USA 99, 14153–14158 (2002).

  10. 10.

    , & Nature 521, 436–444 (2015).

  11. 11.

    , , & J. Struct. Biol. 162, 368–379 (2008).

  12. 12.

    et al. Microsc. Microanal. 22, 487–496 (2016).

  13. 13.

    et al. Proc. Natl. Acad. Sci. USA 112, 14266–14271 (2015).

  14. 14.

    et al. Nature 502, 707–710 (2013).

  15. 15.

    et al. Nature 494, 385–389 (2013).

  16. 16.

    et al. Cell Rep. 3, 759–768 (2013).

  17. 17.

    et al. J. Struct. Biol. 161, 459–468 (2008).

  18. 18.

    et al. J. Cell Biol. 174, 759–765 (2006).

  19. 19.

    & Science 309, 484–487 (2005).

  20. 20.

    et al. J. Struct. Biol. 157, 38–46 (2007).

  21. 21.

    & In Proc. 27th Int. Conf. Mach. Learn. (eds. Fürnkranz, J. & Joachims, T.) 807–814 (ICML, 2010).

  22. 22.

    , , & In Proc. 25th Int. Conf. Mach. Learn (eds. McCallum, A. & Roweis, S.) 1096–1103 (ICML, 2008).

  23. 23.

    , , , & Preprint at (2012).

  24. 24.

    , & Mon. Not. R. Astron. Soc. 450, 1441–1459 (2015).

  25. 25.

    & Nat. Methods 12, 931–934 (2015).

  26. 26.

    , & Preprint at (2015).

  27. 27.

    , & In Advances in Neural Information Processing Systems 25 (eds. Pereira, F., Burges, C.J.C., Bottou, L. & Weinberger, K.Q.) 1097–1105 (Curran Associates, 2012).

  28. 28.

    et al. Nat. Protoc. 9, 2630–2642 (2014).

  29. 29.

    et al. Proc. Natl. Acad. Sci. USA 100, 5950–5955 (2003).

  30. 30.

    , , & Mol. Biochem. Parasitol. 99, 89–101 (1999).

  31. 31.

    , & Acta Trop. 45, 33–43 (1988).

  32. 32.

    et al. Protocol Exchange (2017).

Download references

Acknowledgements

We gratefully acknowledge support of NIH grants (R01GM080139, P01NS092525, P41GM103832), Ovarian Cancer Research Fund and Singapore Ministry of Education. Molecular graphics and analyses performed with UCSF ChimeraX, developed by the Resource for Biocomputing, Visualization, and Informatics at the University of California, San Francisco.

Author information

Author notes

    • Wei Dai

    Present address: Department of Cell Biology and Neuroscience, Center for Integrative Proteomics Research, Rutgers University, Piscataway, New Jersey, USA.

Affiliations

  1. Graduate Program in Structural and Computational Biology and Molecular Biophysics, Baylor College of Medicine, Houston, Texas, USA.

    • Muyuan Chen
  2. Verna Marrs and McLean Department of Biochemistry and Molecular Biology, Baylor College of Medicine, Houston, Texas, USA.

    • Muyuan Chen
    • , Wei Dai
    • , Stella Y Sun
    • , Darius Jonasch
    • , Michael F Schmid
    • , Wah Chiu
    •  & Steven J Ludtke
  3. Department of Biological Science, Centre for BioImaging Sciences, National University of Singapore, Singapore.

    • Cynthia Y He

Authors

  1. Search for Muyuan Chen in:

  2. Search for Wei Dai in:

  3. Search for Stella Y Sun in:

  4. Search for Darius Jonasch in:

  5. Search for Cynthia Y He in:

  6. Search for Michael F Schmid in:

  7. Search for Wah Chiu in:

  8. Search for Steven J Ludtke in:

Contributions

M.C. designed the protocol. W.D., S.Y.S. and C.Y.H. provided the test data sets. M.C. and D.J. tested and refined the protocol. M.C., W.D., S.Y.S., M.F.S., W.C. and S.J.L. wrote the paper and provided suggestions during development.

Competing interests

The authors declare no competing financial interests.

Corresponding author

Correspondence to Steven J Ludtke.

Integrated supplementary information

Supplementary information

PDF files

  1. 1.

    Supplementary Text and Figures

    Supplementary Figures 1–6 and Supplementary Table 1.

  2. 2.

    Life Sciences Reporting Summary

  3. 3.

    Supplementary Protocol

    Supplementary Protocol.

Videos

  1. 1.

    Workflow of automated tomogram annotation

    Demonstration of tomogram annotation workflow with our software package, using a PC12 cell tomogram as an example. The process includes selection of training set, annotation of the tomogram, and subtomogram averaging results.

  2. 2.

    Annotation of the PC12 cell tomogram

    Movie showing the PC12 cell tomogram used in the figure and its annotation, including volume rendering and slice view of the input tomogram, and a 3D view of annotated features.

  3. 3.

    Annotation of the human platelet cell tomogram

    Movie showing the human platelet cell tomogram used in the figure and its annotation, including volume rendering and slice view of the input tomogram, and a 3D view of annotated features.

  4. 4.

    Annotation of the African Trypanosomes cell tomogram

    Movie showing the African Trypanosomes cell tomogram used in the figure and its annotation, including volume rendering and slice view of the input tomogram, and a 3D view of annotated features.

  5. 5.

    Annotation of the Cyanobacteria cell tomogram

    Movie showing the Cyanobacteria cell tomogram used in the figure and its annotation, including volume rendering and slice view of the input tomogram, and a 3D view of annotated features.

About this article

Publication history

Received

Accepted

Published

DOI

https://doi.org/10.1038/nmeth.4405

Further reading