Workstation z840

Processing, data analysis, 3D rendering and video generation for the rest of the data were done on an HP workstation Z840, with 8 core Xeon processor, 196 GB RAM, and Nvidia Quadro k5000 graphics card and HP workstation Z840 dual Xeon 256 GB DDR4 RAM, nVidia Quadro M5000 8GB graphic card. We used Imaris, Amira, and Fiji (ImageJ2) for 3D and 2D image visualization. Tile scans were stitched by Fiji’s stitching plugin49. Stitched images were saved in tiff format and optionally compressed in LZW format to enable fast processing. We removed tiles with acquisition errors using Fiji’s TrakEM2 plugin and Imglib2library. In case of tiling errors in z dimension, we used TeraStitcher (Version, 1.10, https://abria.github.io/TeraStitcher/) with its default settings to globally optimize the tiled volumes and reconstruct the entire dataset. To increase the quality of the images we used the following functions in Fiji: to enhance the contrast of microglia cells (Fig. 1n and Supplementary Fig. 2a-f) we used “Enhance Local Contrast (CLAHE)”, to equalize the images (Fig. 4a,b and Supplementary Fig. 2a-f) we used “Pseudo Flat-Field Correction”, to enhance the contrast over the background of the axonal terminals in Fig 4c,d (yellow and green boxes) we used the custom-made macro for Fiji that we utilized to generate the pre-processed data for NeuroGPS-Tree (see next paragraph: Neuron tracing)