NeuroXiv: AI-powered open databasing and dynamic mining of brain-wide neuron morphometry

作者：Shengdian Jiang, Lijun Wang, Zhixi Yun, Hanbo Chen, Lijuan Liu, Jianhua Yao, Hanchuan Peng · 发表于：Nature Methods · 年份：2025 · DOI：10.1038/s41592-025-02687-2 · 被引用次数：6 · 研究领域：Cell Image Analysis Techniques、Advanced Electron Microscopy Techniques and Applications、Advanced Fluorescence Microscopy Techniques

Neuron morphology has been extensively reconstructed at the whole-brain scale by various projects in recent years. Here, to facilitate interactive exploration in a standardized and scalable manner, we introduce NeuroXiv (neuroxiv.org), a large-scale database containing 175,149 reconstructed neuron morphologies mapped to the Common Coordinate Framework Version 3 (CCFv3). In addition, NeuroXiv incorporates an AI-powered mining engine (AIPOM) for dynamic, user-specific data mining, delivering enhanced performance via a custom client program. The NeuroXiv platform enables AI-powered open mining of a database of reconstructions of more than 175,000 mouse neurons, registered to the Common Coordinate Framework. The platform supports queries about connectivity, projection patterns and other morphological features.