mmg-sc 0.1.0__tar.gz

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
mmg_sc-0.1.0/PKG-INFO ADDED
@@ -0,0 +1,41 @@
1
+ Metadata-Version: 2.4
2
+ Name: mmg-sc
3
+ Version: 0.1.0
4
+ Summary: Meta Marker Generator (MMG) for multimodal and cross-species single-cell data integration
5
+ Project-URL: Homepage, https://github.com/sunyk740/MMG
6
+ Project-URL: Bug Reports, https://github.com/sunyk740/MMG/issues
7
+ Project-URL: Repository, https://github.com/sunyk740/MMG.git
8
+ Author-email: Yongkang Sun <sunyk2023@ion.ac.cn>
9
+ License: MIT
10
+ Classifier: Intended Audience :: Science/Research
11
+ Classifier: License :: OSI Approved :: MIT License
12
+ Classifier: Operating System :: OS Independent
13
+ Classifier: Programming Language :: Python :: 3
14
+ Classifier: Programming Language :: Python :: 3.8
15
+ Classifier: Programming Language :: Python :: 3.9
16
+ Classifier: Programming Language :: Python :: 3.10
17
+ Classifier: Programming Language :: Python :: 3.11
18
+ Classifier: Topic :: Scientific/Engineering :: Bio-Informatics
19
+ Requires-Python: <3.12,>=3.8
20
+ Requires-Dist: matplotlib==3.7.5
21
+ Requires-Dist: numpy==1.22.4
22
+ Requires-Dist: pandas==2.0.3
23
+ Requires-Dist: pot==0.9.4
24
+ Requires-Dist: scanpy==1.9.3
25
+ Requires-Dist: scikit-learn==1.3.2
26
+ Requires-Dist: scipy==1.10.1
27
+ Requires-Dist: seaborn==0.13.2
28
+ Requires-Dist: torch==2.0.1
29
+ Description-Content-Type: text/markdown
30
+
31
+ # MMG
32
+ **MMG (Meta Marker Generator)** is an interpretable linear framework for cross-modal and cross-species single-cell data integration.
33
+
34
+ ## 📖 Overview
35
+
36
+ MMG learns concise, linearly weighted gene combinations called **"meta-markers"** through a denoising autoencoder with adversarial domain adaptation. Unlike black-box deep learning approaches, MMG produces interpretable gene weight vectors that capture essential cellular identity information while remaining robust to technical artifacts.
37
+
38
+ ## 📦 Installation
39
+
40
+ ```bash
41
+ pip install mmg-sc
mmg_sc-0.1.0/README.md ADDED
@@ -0,0 +1,11 @@
1
+ # MMG
2
+ **MMG (Meta Marker Generator)** is an interpretable linear framework for cross-modal and cross-species single-cell data integration.
3
+
4
+ ## 📖 Overview
5
+
6
+ MMG learns concise, linearly weighted gene combinations called **"meta-markers"** through a denoising autoencoder with adversarial domain adaptation. Unlike black-box deep learning approaches, MMG produces interpretable gene weight vectors that capture essential cellular identity information while remaining robust to technical artifacts.
7
+
8
+ ## 📦 Installation
9
+
10
+ ```bash
11
+ pip install mmg-sc