Beyond Static Brain Atlases: AI-Powered Open Databasing and Dynamic Mining of Brain-Wide Neuron Morphometry
Listed in
This article is not in any list yet, why not save it to one of your lists.Abstract
We introduce NeuroXiv (neuroxiv.org), a large-scale, AI-powered database that provides detailed 3D morphologies of individual neurons, designed to support a wide array of neuroscience applications. NeuroXiv offers a comprehensive collection of 175,149 atlas-oriented reconstructed morphologies of individual neurons derived from more than 518 mouse brains, classified into 292 distinct types and mapped into the Common Coordinate Framework Version 3 (CCFv3). The platform also allows uploading and databasing custom neuron morphologies, which are systematically mapped to brain atlases for objective comparisons. Powered by a cutting-edge AI engine (AIPOM), NeuroXiv enables interactive, user-specific analysis and data mining. We specifically optimized a mixture-of-experts algorithm to harness the capabilities of multiple large language models, deploying it on a client program to achieve more than 10 times better performance compared to a typical server-side setup. We demonstrate NeuroXiv's scalability, efficiency, flexibility, openness, and robustness through various applications.
