Metadata-Version: 2.1
Name: scMINGLE
Version: 1.0.1
Summary: MINGLE: A mutual information-based interpretable framework for automatic cell type annotation in single-cell chromatin accessibility data
Author: Yifan Huang
Requires-Python: >=3.10.10
Description-Content-Type: text/markdown
License-File: LICENSE.txt
Requires-Dist: scanpy (>=1.9.1)
Requires-Dist: torch (>=2.0.1)
Requires-Dist: torch-geometric (>=2.5.2)
Requires-Dist: scikit-learn (>=1.3.2)
Requires-Dist: scipy (>=1.11.4)

MINGLE is an a mutual information-based interpretable framework that leverages similarities and topological structures among cells for accurate cell type annotation. Additionally, we introduce a convex hull-based identification strategy to effectively identify novel cell types.
