PT  - JOURNAL ARTICLE
AU  - Julia Buhmann
AU  - Arlo Sheridan
AU  - Stephan Gerhard
AU  - Renate Krause
AU  - Tri Nguyen
AU  - Larissa Heinrich
AU  - Philipp Schlegel
AU  - Wei-Chung Allen Lee
AU  - Rachel Wilson
AU  - Stephan Saalfeld
AU  - Gregory Jefferis
AU  - Davi Bock
AU  - Srinivas Turaga
AU  - Matthew Cook
AU  - Jan Funke
TI  - Automatic Detection of Synaptic Partners in a Whole-Brain <em>Drosophila</em> EM Dataset
AID  - 10.1101/2019.12.12.874172
DP  - 2020 Jan 01
TA  - bioRxiv
PG  - 2019.12.12.874172
4099  - http://biorxiv.org/content/early/2020/03/19/2019.12.12.874172.short
4100  - http://biorxiv.org/content/early/2020/03/19/2019.12.12.874172.full
AB  - The study of neural circuits requires the reconstruction of neurons and the identification of synaptic connections between them. To scale the reconstruction to the size of whole-brain datasets, semi-automatic methods are needed to solve those tasks. Here, we present an automatic method for synaptic partner identification in insect brains, which uses convolutional neural networks to identify post-synaptic sites and their pre-synaptic partners. The networks can be trained from human generated point annotations alone and require only simple post-processing to obtain final predictions. We used our method to extract 244 million putative synaptic partners in the fifty-teravoxel full adult fly brain (FAFB) electron microscopy (EM) dataset and evaluated its accuracy on 146,643 synapses from 702 neurons with a total cable length of 312 mm in four different brain regions. The predicted synaptic connections can be used together with a neuron segmentation to infer a connectivity graph with high accuracy: between 92% and 96% of edges linking connected neurons are correctly classified as weakly connected (less than five synapses) and strongly connected (at least five synapses). Our synaptic partner predictions for the FAFB dataset are publicly available, together with a query library allowing automatic retrieval of up- and downstream neurons.