README.md 5.84 KB
Newer Older
1
<img align="right" width="300" src="./docs/_static/logo_SyConn.png"><br/>
Philipp Schubert's avatar
Philipp Schubert committed
2
[![Documentation Status](https://readthedocs.org/projects/syconn/badge/?version=latest)](https://syconn.readthedocs.io/en/latest/?badge=latest)
Philipp Schubert's avatar
Philipp Schubert committed
3
4
[![pipeline status](https://gitlab.mpcdf.mpg.de/pschuber/SyConn/badges/master/pipeline.svg)](https://gitlab.mpcdf.mpg.de/pschuber/SyConn/commits/master)
[![coverage report](https://gitlab.mpcdf.mpg.de/pschuber/SyConn/badges/master/coverage.svg)](https://gitlab.mpcdf.mpg.de/pschuber/SyConn/commits/master)
Philipp Schubert's avatar
Philipp Schubert committed
5
[![pylint status](https://gitlab.mpcdf.mpg.de/pschuber/SyConn/-/jobs/artifacts/master/raw/pylint/pylint.svg?job=pylint)](https://gitlab.mpcdf.mpg.de/pschuber/SyConn/-/jobs/artifacts/master/raw/pylint/pylint.log?job=pylint)
Philipp Schubert's avatar
Philipp Schubert committed
6

Philipp Schubert's avatar
Philipp Schubert committed
7
8
SyConn
------
Philipp Schubert's avatar
Philipp Schubert committed
9
10
Refactored version of SyConn for automated synaptic connectivity inference based on dense EM segmentation data. For the first version
 see below or checkout the branch [dorkenwald2017nm](https://github.com/StructuralNeurobiologyLab/SyConn/tree/dorkenwald2017nm).
11

Philipp Schubert's avatar
Philipp Schubert committed
12
Current features:
13
14
- introduction of classes for handling of supervoxels (e.g. cell fragments, predicted cellular
organelles like mitochondria, vesicle clouds etc.) and agglomerated supervoxels
15
16
- prediction of sub-cellular structures, supervoxel extraction and mesh
  generation
17
- (sub-) cellular compartment (spines, bouton and axon/dendrite/soma) and cell type classification with multiview- [\[2\]](https://www.nature.com/articles/s41467-019-10836-3) and with skeleton-based approaches [\[1\]](https://www.nature.com/articles/nmeth.4206)
18
- glia identification and separation [\[2\]](https://www.nature.com/articles/s41467-019-10836-3)
19
20
- connectivity matrix export
- KNOSSOS plugin for interactive exploration (work in progress)
Philipp Schubert's avatar
Philipp Schubert committed
21

22
If you use parts of this code base in your academic projects, please cite the corresponding publication(s).
23

Philipp Schubert's avatar
Philipp Schubert committed
24

25
26
Documentation
-------------
27
The documentation for the refactored version is still work-in-progress and can be found [here](docs/doc.md). Alternatively and for API docs please refer to the latest [readthedocs build](https://syconn.readthedocs.io/en/latest/).
Philipp Schubert's avatar
Philipp Schubert committed
28

29
For SyConn v1, please refer to the old [documentation](https://structuralneurobiologylab.github.io/SyConn/documentation/). We also present more general information about SyConn on our [Website](https://structuralneurobiologylab.github.io/SyConn/).
30

Philipp Schubert's avatar
Philipp Schubert committed
31

32
33
The Team
--------
34
The Synaptic connectivity inference toolkit is currently developed at the Max-Planck-Institute of Neurobiology in Martinsried by
Philipp Schubert's avatar
Philipp Schubert committed
35
 Philipp Schubert, Jonathan Klimesch, Alexandra Rother and Joergen Kornfeld.
36
37


38
39
Acknowledgements
----------------
Philipp Schubert's avatar
Philipp Schubert committed
40
41
42
43
44
45
We are especially grateful for the support by Winfried Denk who enabled
this work in his department. We also want to thank Christian
Guggenberger and his group at the MPCDF for cluster support and deepmind
for providing egl extension code to handle multi-gpu rendering on the
same machine. The original code snippet (under the Apache License 2.0)
used for our project can be found
46
[here](https://github.com/deepmind/dm_control/blob/30069ac11b60ee71acbd9159547d0bc334d63281/dm_control/_render/pyopengl/egl_ext.py).
Philipp Schubert's avatar
Philipp Schubert committed
47
48
Thanks to Julia Kuhl (see http://somedonkey.com/ for more beautiful
work) for designing and creating the logo and to Rangoli Saxena, Mariana
Philipp Schubert's avatar
Philipp Schubert committed
49
50
Shumliakivska, Josef Mark, Maria Kawula, Atul Mohite, Carl Constantin v. Wedemeyer,
Gaurav Kumar and Martin Drawitsch for code contributions.
51
52


53
54
Publications
------------
55
\[1\] [Automated synaptic connectivity inference for volume electron microscopy](https://www.nature.com/articles/nmeth.4206)
56
```
Philipp Schubert's avatar
Philipp Schubert committed
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
 @ARTICLE{SyConn2017,
   title     = "Automated synaptic connectivity inference for volume electron
                microscopy",
   author    = "Dorkenwald, Sven and Schubert, Philipp J and Killinger, Marius F
                and Urban, Gregor and Mikula, Shawn and Svara, Fabian and
                Kornfeld, Joergen",
   abstract  = "SyConn is a computational framework that infers the synaptic
                wiring of neurons in volume electron microscopy data sets with
                machine learning. It has been applied to zebra finch, mouse and
                zebrafish neuronal tissue samples.",
   journal   = "Nat. Methods",
   publisher = "Nature Publishing Group, a division of Macmillan Publishers Limited. All Rights Reserved.",
   year      = 2017,
   month     = Feb,
   day       = 27,
   url       = http://dx.doi.org/10.1038/nmeth.4206
 }
  ```
Philipp Schubert's avatar
Philipp Schubert committed
75

76
\[2\] [Learning cellular morphology with neural networks](https://doi.org/10.1038/s41467-019-10836-3)
77
78
79
80
81
82
83
84
85
86
87
88
89
  ```
  @Article{Schubert2019,
author={Schubert, Philipp J.
and Dorkenwald, Sven
and Januszewski, Michal
and Jain, Viren
and Kornfeld, Joergen},
title={Learning cellular morphology with neural networks},
journal={Nature Communications},
year={2019},
volume={10},
number={1},
pages={2736},
90
91
92
93
94
95
96
97
98
abstract={Reconstruction and annotation of volume electron microscopy data sets of brain tissue is challenging but
can reveal invaluable information about neuronal circuits. Significant progress has recently been made in automated
neuron reconstruction as well as automated detection of synapses. However, methods for automating the morphological
analysis of nanometer-resolution reconstructions are less established, despite the diversity of possible applications.
Here, we introduce cellular morphology neural networks (CMNs), based on multi-view projections sampled from automatically
reconstructed cellular fragments of arbitrary size and shape. Using unsupervised training, we infer morphology embeddings
(Neuron2vec) of neuron reconstructions and train CMNs to identify glia cells in a supervised classification paradigm,
which are then used to resolve neuron reconstruction errors. Finally, we demonstrate that CMNs can be used to identify
subcellular compartments and the cell types of neuron reconstructions.},
99
100
101
102
issn={2041-1723},
doi={10.1038/s41467-019-10836-3},
url={https://doi.org/10.1038/s41467-019-10836-3}
}
Philipp Schubert's avatar
Philipp Schubert committed
103
  ```