Metadata-Version: 2.1
Name: Flow2Spatial
Version: 0.1.12
Summary: Reconstructing spatial proteomics through omics transfer learning
Home-page: http://pypi.python.org/pypi/Flow2Spatial/
Author: Ruiqiao He
Author-email: ruiqiaohe@gmail.com
License: GPL
Classifier: Development Status :: 3 - Alpha
Classifier: License :: OSI Approved :: GNU General Public License v3 (GPLv3)
Classifier: Programming Language :: Python :: 3.7
Classifier: Programming Language :: Python :: 3.8
Classifier: Topic :: Scientific/Engineering :: Bio-Informatics
Requires-Python: >=3.7.9
Description-Content-Type: text/markdown
License-File: LICENSE
Requires-Dist: shapely >=1.8.2
Requires-Dist: cvxpy >=1.1.17
Requires-Dist: anndata
Requires-Dist: scipy
Requires-Dist: numpy
Requires-Dist: pandas

## Flow2Spatial reconstructs spatial proteomics through transfer learning 

Flow2Spatial is the computational part of PLATO (parallel flow projection and transfer learning across omics data). 

It aims to reconstruct spatial proteomics from the values of parallel-flow projections in PLATO. Leveraging transfer learning, Flow2Spatial can restore fine structure of protein spatial distribution in different tissue types. 


<p align="center">
  <img src='./docs/Flow2Spatial.png'>
</p>
<p align="center">
  Overview of Flow2Spatial.
</p>

### Prerequisites 
    "torch", "shapely", "cvxpy", "anndata",
     "scipy", "numpy", "pandas"

Further tutorials please refer to  https://Flow2Spatial.readthedocs.io/. 

### Citation 

Beiyu Hu, Ruiqiao He, Kun Pang, Guibin Wang, et al. High-resolution spatially resolved proteomics of complex tissues based on microfluidics and transfer learning. Cell 188, 1-15 (2025). 
