Metadata-Version: 2.1
Name: ccsf
Version: 1.0.0
Summary: Leveraging cell-cell similarity from gene expression data for high-performance spatial and temporal cellular mappings.
Home-page: https://github.com/xinglab-ai/ccsf
Author: Md Tauhidul Islam
Author-email: tauhid@stanford.edu
Classifier: Programming Language :: Python :: 3
Classifier: Operating System :: OS Independent
Requires-Python: >=3.8
Description-Content-Type: text/markdown
License-File: LICENSE
Requires-Dist: numpy
Requires-Dist: pandas
Requires-Dist: phate
Requires-Dist: umap-learn
Requires-Dist: scanpy
Requires-Dist: scikit-learn
Requires-Dist: scipy

# ccsf
Leveraging cell-cell similarity for high-performance spatial and temporal cellular mappings from gene expression data (Cell Patterns, 2023)

## CCSF is a replacement of PCA for gene expression and other tabular data analysis
CCSF is a cell-cell similarity-driven framework of genomic data analysis for high-fidelity dimensionality reduction, clustering, visualization, and spatial and temporal cellular mappings. 
The approach exploits the similarity features of the cells for the discovery of discriminative patterns in the data. 
For a wide variety of datasets, the proposed approach drastically improves the accuracies of visualization and spatial and temporal mapping analyses as compared to PCA and state-of-the-art techniques. 
Computationally, the method is about 15 times faster than the existing ones and thus provides an urgently needed technique  for reliable and efficient analysis of genomic data.




