Add spatiomic

[maltekuehl]

Checklist for adding packages

Mandatory

Name of the tool: spatiomic

Short description: spatiomic is a computational library for the analysis of spatial proteomics, mainly via pixel-based clustering, differential cluster abundance analysis and spatial statistics. It differs from existing implementations mostly by focussing on unsupervised subcellular analyses with GPU acceleration. For more information, please refer to our paper: https://www.nature.com/articles/s41586-025-09225-2 or the documentation at https://spatiomic.org

How does the package use scverse data structures (please describe in a few sentences): Currently, most common functions accept and write to AnnData objects and the library contains additional utility functions to easily convert between PySAL spatial weights and the format used for scverse packages. Adopting xarray internally for improved SpatialData support is on our roadmap, though not yet publicly available. Examples and a list of functions with AnnData support as well as interoperability examples are shown here: https://spatiomic.org/latest/tutorials/scverse.html

• The code is publicly available under an OSI-approved license
• The package provides versioned releases
• The package can be installed from a standard registry (e.g. PyPI, conda-forge, bioconda)
• Automated tests cover essential functions of the package and a reasonable range of inputs and conditions
• Continuous integration (CI) automatically executes these tests on each push or pull request
• The package provides API documentation via a website or README
• The package uses scverse datastructures where appropriate (i.e. AnnData, MuData or SpatialData and their modality-specific extensions)
• I am an author or maintainer of the tool and agree on listing the package on the scverse website

Recommended

• Please announce this package on scverse communication channels (zulip, discourse, twitter)

• Please tag the author(s) these announcements. Handles (e.g. @scverse_team) to include are:

  • Zulip: Malte Kuehl
  • Bluesky: @maltekuehl.com

• The package provides tutorials (or "vignettes") that help getting users started quickly

• The package uses the scverse cookiecutter template.

[mikkelnrasmussen]

Hi @maltekuehl,

Thanks for submitting spatiomic — it looks super cool! Overall, the test coverage seems solid, and the tutorials are really well done.

I had a couple of comments regarding the submission checklist:

The package provides API documentation via a website or README[^3]

I took a look at the documentation site (https://spatiomic.org/latest/), but I couldn’t find any API documentation. What we’re looking for here is a complete reference of all public functions and their parameters, like this example from scirpy.

Also, I think adding SpatialData support would be a great enhancement — and it’s great to hear that you’re already planning to include it!

Best regards,
Mikkel

[maltekuehl]

Hi @mikkelnrasmussen, thanks for taking the time to review it. The AutoAPI documentation missing was a bug that only appeared on readthedocs, not when building locally or on GitHub Pages. We recently moved the documentation to RTD and an updated indirect dependency broke it on RTD only, quite the hard bug to find 😄 But fixed now, thanks for raising this issue: https://spatiomic.org/latest/autoapi/spatiomic/index.html

[maltekuehl]

Hi @mikkelnrasmussen, any update on whether this can be merged? Thanks!

[mikkelnrasmussen]

Hi @maltekuehl,

Glad to hear you found and fixed the bug - the API documentation looks great now! 😄
Everything looks good to me now.

Best,
Mikkel