Skip to main content

Thank you for visiting You are using a browser version with limited support for CSS. To obtain the best experience, we recommend you use a more up to date browser (or turn off compatibility mode in Internet Explorer). In the meantime, to ensure continued support, we are displaying the site without styles and JavaScript.

Automatic detection of synaptic partners in a whole-brain Drosophila electron microscopy data set


We develop an automatic method for synaptic partner identification in insect brains and use it to predict synaptic partners in a whole-brain electron microscopy dataset of the fruit fly. The predictions can be used to infer a connectivity graph with high accuracy, thus allowing fast identification of neural pathways. To facilitate circuit reconstruction using our results, we develop CIRCUITMAP, a user interface add-on for the circuit annotation tool CATMAID.

This is a preview of subscription content

Access options

Buy article

Get time limited or full article access on ReadCube.


All prices are NET prices.

Fig. 1: Overview of method for synaptic partner prediction, application to the FAFB dataset and use of CIRCUITMAP for circuit reconstruction and analysis in CATMAID.
Fig. 2: Results in whole-brain FAFB dataset.

Data availability

The datasets generated and/or analysed during the current study are available in the ‘synful_fafb’ repository20 and in ‘synful_experiments’21. The following figures and tables use this data.

Code availability

The code used to train networks and predict synaptic partners is available in the synful repository ( Code used to evaluate the results is available in the synful_fafb repository ( A python library to query circuits in the FAFB volume using the predicted synaptic partners is available in the SynfulCircuit repository ( The CATMAID widget used to interactively query circuits is available in the CircuitMap repository (


  1. Denk, W., Briggman, K. L. & Helmstaedter, M. Structural neurobiology: missing link to a mechanistic understanding of neural computation. Nat. Rev. Neurosci. 13, 351–358 (2012).

    CAS  Article  Google Scholar 

  2. Zheng, Z. et al. A complete electron microscopy volume of the brain of adult Drosophila melanogaster. Cell 174, 730–743 (2018).

    CAS  Article  Google Scholar 

  3. Li, P. H. et al. Automated reconstruction of a serial-section EM Drosophila brain with flood-filling networks and local realignment. Microsc. Microanal. 25 (Suppl. 2), 1364–1365 (2019).

    Article  Google Scholar 

  4. Dorkenwald, S. et al. Automated synaptic connectivity inference for volume electron microscopy. Nat. Methods 14, 435–442 (2017).

    Article  Google Scholar 

  5. Motta, A. et al. Dense connectomic reconstruction in layer 4 of the somatosensory cortex. Science 366, eaay3134 (2019).

  6. Heinrich, L., Funke, J., Pape, C., Nunez-Iglesias, J. & Saalfeld, S. Synaptic cleft segmentation in non-isotropic volume electron microscopy of the complete drosophila brain. In Medical Image Computing and Computer Assisted Intervention – MICCAI 2018 (Springer, 2018).

  7. Huang, G. B., Scheffer, L. K. & Plaza, S. M. Fully-automatic synapse prediction and validation on a large data set. Front. Neural Circuits 12, 87 (2018).

  8. Kreshuk, A., Funke, J., Cardona, A. & Hamprecht, F. A. Who is talking to whom: synaptic partner detection in anisotropic volumes of insect brain. In Int. Conf. Medical Image Computing and Computer-Assisted Intervention, 661–668 (Springer, 2015).

  9. Turner, N. L. et al. Synaptic partner assignment using attentional voxel association networks. In 2020 IEEE International Symposium on Biomedical Imaging, 1209–1213 (IEEE Computer Society, 2020).

  10. Parag, T. et al. Detecting synapse location and connectivity by signed proximity estimation and pruning with deep nets. In Proc. European Conference on Computer Vision (ECCV) Workshops (Springer, 2018).

  11. Buhmann, J. et al. Synaptic partner prediction from point annotations in insect brains. In International Conference on Medical Image Computing and Computer-Assisted Intervention, 309–316 (Springer, 2018).

  12. Xu, C. S. et al. A connectome of the adult Drosophila central brain. eLife 9, e57443 (2020).

    Article  Google Scholar 

  13. Ronneberger, O., Fischer, P. & Brox, T. U-net: convolutional networks for biomedical image segmentation. In Int. Conf. Medical Image Computing and Computer-Assisted Intervention, 234–241 (Springer, 2015).

  14. Buhmann, J. & Funke, J. funkelab/synfulcircuit v1.0 (2021);

  15. Kazimiers, T., Gerhard, S. & Funke, J. catmaid/circuitmap (2021);

  16. Schneider-Mizell, C. M. et al. Quantitative neuroanatomy for connectomics in drosophila. eLife 5, e12059 (2016).

    Article  Google Scholar 

  17. Falk, T. et al. U-net: deep learning for cell counting, detection, and morphometry. Nat. Methods 16, 67 (2019).

    CAS  Article  Google Scholar 

  18. Funke, J. et al. Large scale image segmentation with structured loss based deep learning for connectome reconstruction. IEEE Trans. Pattern Anal. Mach. Intell. 41, 1669–1680 (2018).

    Article  Google Scholar 

  19. Wang, K., Dou, J., Kemao, Q., Di, J. & Zhao, J. Y-net: a one-to-two deep learning framework for digital holographic reconstruction. Opt. Lett. 44, 4765–4768 (2019).

    Article  Google Scholar 

  20. Buhmann, J. & Funke, J. funkelab/synful_fafb v1.0 (2021);

  21. Funke, J., Buhmann, J., Sheridan, A., Nguyen, T. M. & Malin-Mayor, C. synful_experiments (2021);

  22. Buhmann, J., Funke, J. & Nguyen, T. M. funkelab/synful v1.0 (2021);

Download references


We thank S. Lauritzen (HHMI, Janelia Research Campus) for helping with data acquisition; M. Nichols (HHMI, Janelia Research Campus) for importing CATMAID annotations; W. Patton (HHMI, Janelia Research Campus) for code contributions; N. Eckstein (HHMI, Janelia Research Campus) for helpful discussions; J. Maitin-Shepard (Google) for adding synapse visualization features to neuroglancer; V. Jayaraman (HHMI, Janelia Research Campus) for providing evaluation data; and the HHMI Janelia Connectome Annotation Team (R. Parekh, A. Suleiman, T. Paterson) for evaluation data. We also thank Z. Zheng, F. Li, C. Fisher, N. Sharifi and S. Calle-Schuler (HHMI, Janelia) for access to prepublication data used for evaluation. This work was supported by the HHMI and the Swiss National Science Foundation (grant 205321L 160133).

Author information

Authors and Affiliations



S.C.T. and J.F. conceived the work. W.-C.A.L., R.W., M.C. and J.F. acquired funding. J.B., A.S., C.M.-M., S.G., R.K., T.M.N., L.H., P.S., S.S. and J.F. developed software. J.B., C.M.-M. and J.F. carried out validation and evaluation. P.S., G.S.X.E.J. and D.D.B. generated evaluation data. J.B., T.K., S.G. and J.F. disseminated data. M.C. and J.K. supervised the work. J.B., A.S., C.M.-M., P.S. and J.F. produced visualizations. J.B., P.S. and J.F. drafted the manuscript. All authors reviewed and edited the manuscript.

Corresponding author

Correspondence to Jan Funke.

Ethics declarations

Competing interests

S.G. is the founder and CEO of UniDesign Solutions GmbH, which provides IT services.

Additional information

Peer review informationNature Methods thanks Chung-Chuan Lo, Stephan Sigrist and the other, anonymous, reviewer(s) for their contribution to the peer review of this work.

Publisher’s note Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Extended data

Extended Data Fig. 1 Brain-wide prediction accuracy.

Precision and recall over 10 densely annotated cubes in different brain regions (dataset DenseCubes). Highlights show best f-score over the detection threshold. Top row: Black triangle marks show the inter-human variance between two annotations, with one annotation treated as ground-truth evaluated against the other one. Bottom right: Visualization of the cube locations within the FAFB dataset.

Source data

Extended Data Fig. 2 Polarity of olfactory projection neurons (PN).

a, Outline of axon-dendrite splitting procedure. b, Exemplary well segregated (left) and unsegregated (right) PN. Boxplot shows segregation index (SI) for all PNs separated into uni- and multiglomerular PNs. c, Impact of completeness of neuronal reconstruction on recovery of synapses.

Source data

Supplementary information

Supplementary Information

Supplementary Figs. 1–3, Notes 1–3 and Discussion

Reporting Summary

Supplementary Data 1

Per-neuron prediction accuracy

Supplementary Video 1

CircuitMap instruction video

Supplementary Data 2

Source data for Supplementary Fig. 2.

Source data

Source Data Fig. 2

Source data for Fig. 2

Source Data Extended Data Fig. 1

Source data for Extended Data Fig. 1

Source Data Extended Data Fig. 2

Source data for Extended Data Fig. 2

Rights and permissions

Reprints and Permissions

About this article

Verify currency and authenticity via CrossMark

Cite this article

Buhmann, J., Sheridan, A., Malin-Mayor, C. et al. Automatic detection of synaptic partners in a whole-brain Drosophila electron microscopy data set. Nat Methods 18, 771–774 (2021).

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI:

Further reading


Quick links

Nature Briefing

Sign up for the Nature Briefing newsletter — what matters in science, free to your inbox daily.

Get the most important science stories of the day, free in your inbox. Sign up for Nature Briefing