vima
Variational inference-based microniche analysis is a method for conducting case-control analysis on multi-sample spatial molecular datasets. vima can be applied to any spatially resolved molecular technology, is well powered even at the modest sample sizes typical of research cohorts, and avoids traditional, parameter-intensive preprocessing steps such as cell segmentation or clustering of cells into discrete cell types. It works by treating each spatial sample as an image and using a variational autoencoder to extract numerical "fingerprints" from small tissue patches that capture their biological content. It uses these fingerprints to define a large number of "microniches" – small, potentially overlapping groups of tissue patches with highly similar biology that span multiple samples. It then uses rigorous permutation testing to identify microniches whose abundance correlates significantly with case-control status after accounting for multiple testing.
installation
vima can be installed via pip as follows:
pip install vima-spatial
Note that vima requires pytorch and harmonypy. These should install automatically through pip, but if you have trouble, try installing them first, verifying that they work, and then installing vima.
demo
To get started with an example analysis on a toy spatial transcriptomics dataset, take a look at our brief demo. You can see a completed read-only version or run an interactive version yourself on a Google Colab GPU (though this requires Colab Pro due to insufficient memory provided on the free tier.)
To see how to apply vima to a stain-based modality like CODEX, immunohistochemistry, or immunofluorescence, look at our immunofluorescence demo.
citation
If you use vima, please cite:
1 maintainer
Metadata
1 maintainer
Release files for vima-spatial 0.2.10
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | |
|---|---|---|---|
| vima_spatial-0.2.10.tar.gz | 75.4 kB | Details |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Reset |
|---|---|---|---|---|
| vima_spatial-0.2.10-py3-none-any.whl | Python 3 | none | any | Details |
Total release size: 154.1 kB
Release files / vima_spatial-0.2.10.tar.gz
| Download URL | vima_spatial-0.2.10.tar.gz |
|---|---|
| Size | 75.4 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
485f2f3900e948b78f93233c7519717e69150180f1c7d670c868d834f3f8028e
|
|
BLAKE2b-256 checksum How to use checksums |
e9dee82501034d6c5150f8782af44d39639e68a5843b9df1927b445e18d99068
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.2.0 CPython/3.14.4
|
Release files / vima_spatial-0.2.10-py3-none-any.whl
| Download URL | vima_spatial-0.2.10-py3-none-any.whl |
|---|---|
| Size | 78.7 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
1283fb5b9563233162f6c0114d763b7402620db72f7faf64789c3604e8f5254e
|
|
BLAKE2b-256 checksum How to use checksums |
f63945a9a85aa15ca9818cc85bb6d251dc8b97bd1ac9326ce829d79c74cb870f
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.2.0 CPython/3.14.4
|
