Organize, query, and visualize spatial omics data with a unified Python framework.
npx skills add https://github.com/Ketomihine/my_skills --skill spatialdata
Please help me install this Agent Skill. Skill: spatialdata Source: https://github.com/Ketomihine/my_skills/tree/main/spatialdata Command: npx skills add https://github.com/Ketomihine/my_skills --skill spatialdata
SpatialData provides a unified Python-based framework to manage, analyze, and visualize multi-modal spatial omics data, enabling seamless integration of images, labels, shapes, points, and tabular annotations with robust metadata about coordinate systems and transformations.
Install SpatialData using pip, then load a sample SpatialData object (e.g., from spatialdata.datasets import blobs; sdata = blobs()) to begin exploring Images, Labels, Points, Shapes, and Tables.
High-intent search queries and answers about installing and using this skill.
A unified spatial omics data framework provides a single SpatialData object to represent images, labels, shapes, points, and tabular annotations. It solves the problem of fragmented multi-modal data by embedding coordinate transformations and metadata directly alongside the spatial elements.
To load and query Visium or Xenium datasets, you use the spatialdata-io ecosystem tool to read the raw files into a SpatialData object. Once loaded, you can query regions of interest and join spatial elements with their corresponding annotation tables for downstream analysis.
Yes, the framework supports scalable storage and lazy loading through NGFF-compatible formats and the SpatialData Zarr extension. This allows you to read and write large spatial omics datasets efficiently without loading the entire dataset into memory at once.
Yes, you can apply coordinate transformations to align datasets across different scales by defining intrinsic and extrinsic coordinate spaces. The framework manages robust metadata for these transformations, enabling precise alignment of images, labels, and points.
The best way to organize spatial elements and annotation tables is by storing them together in a single SpatialData object. This unified data model ensures that images, labels, shapes, points, and tables remain synchronized with robust coordinate system metadata.
KetomihineOrchestrate spatial transcriptomics analysis with Giotto Suite workflows.
SciMate-AIAnalyze Zarr Python for scalable chunked array storage and parallel I/O.
CHENyiru3Parse and analyze spatial transcriptomics datasets in R with multi-platform support.
qinyan-aiManage biological data artifacts with provenance tracking and ontology annotation.
