Metadata-Version: 2.4
Name: mmspao
Version: 1.0.0
Summary: Multi-modal spatial omics integration with views and combinations.
Home-page: https://github.com/linjing-lab/mmspao
Download-URL: https://github.com/linjing-lab/mmspao/tags
Author: 林景
Author-email: linjing010729@163.com
License: MIT
Project-URL: Source, https://github.com/linjing-lab/mmspao/tree/main/mmspao/
Project-URL: Tracker, https://github.com/linjing-lab/mmspao/issues
Classifier: Development Status :: 5 - Production/Stable
Classifier: Intended Audience :: Healthcare Industry
Classifier: Intended Audience :: Information Technology
Classifier: Intended Audience :: Science/Research
Classifier: Programming Language :: Python :: 3.10
Classifier: Programming Language :: Python :: 3.11
Classifier: Programming Language :: Python :: 3.12
Classifier: License :: OSI Approved :: MIT License
Classifier: Topic :: Scientific/Engineering
Classifier: Topic :: Scientific/Engineering :: Bio-Informatics
Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
Classifier: Topic :: Software Development
Classifier: Topic :: Software Development :: Libraries
Classifier: Topic :: Software Development :: Libraries :: Python Modules
Description-Content-Type: text/markdown
Requires-Dist: numpy>=1.26.4
Requires-Dist: scanpy>=1.10.4
Requires-Dist: scikit-learn>=1.7.1
Requires-Dist: scipy>=1.15.3
Requires-Dist: tqdm>=4.67.1
Dynamic: author
Dynamic: author-email
Dynamic: classifier
Dynamic: description
Dynamic: description-content-type
Dynamic: download-url
Dynamic: home-page
Dynamic: license
Dynamic: project-url
Dynamic: requires-dist
Dynamic: summary

# mmspao

Multi-modal spatial omics integration with views and combinations.

Experiments were executed on NVIDIA A40 of 46068MiB memory in linux with torch==2.1.0+cu121

## Overview

mmspao is an innovative algorithm for multimodal spatial omics analysis, its core advantage is that it can seamlessly integrate transcriptome, proteome, epigenetics, metabolome and other data types. Through the unique modal interactive feature extraction and adaptive fusion mechanism, it can significantly improve the accuracy and biological interpretability of spatial domain recognition. The algorithm uses Kolmogorov-Arnold Network (KAN) to generate mode specific embedding, and constructs interactive features by calculating the outer product between modes. Finally, combined with Leiden clustering, it realizes the collaborative analysis of multimodal data.

## install mmspao

```python
pip install torch==2.1.0 --index-url https://download.pytorch.org/whl/cu121
pip install mmspao
# pip install numpy==1.26.4
```
