Building connectome analysis tools with representation learning on neuronal skeleton and circuit topology

Analyzing connectome plays a significant role in the investigation of neurological diseases and brain research. However, the efficiency of utilizing anatomical, physiological, or molecular characteristics of neurons is relatively low and costly. With the advancements in volume electron microscopy(VEM) and analysis techniques for brain tissue, we are able to obtain whole-brain connectome consisting neuronal high-resolution morphology and connectivity information. Nevertheless, few tools are built based on such data for automated connectome analysis. In this paper, we introduce a connectome analysis tool based on a representation learning model termed NeuNet. NeuNet consists of three key components: Connectome Encoder, Skeleton Encoder, and Readout Layer, which together integrate information pertaining to neuronal connectivity and morphology. Furthermore, we reprocess and release a brain neuron reconstruction dataset from a Drosophila Nerve Cord VEM data. We apply the proposed tool to tasks related to connectome analysis, including neuron classification, brain circuit layout, neuron retrieval and neuron morphology description, and the experiments demonstrate the effectiveness of our tool. We will soon release our code and data on https://github.com/WHUminghui/ConnectomeAnalysisTool.