gnodevae 0.0.3__tar.gz → 0.0.4__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.
Files changed (29) hide show
  1. {gnodevae-0.0.3 → gnodevae-0.0.4}/GNODEVAE/__init__.py +1 -1
  2. {gnodevae-0.0.3/gnodevae.egg-info → gnodevae-0.0.4}/PKG-INFO +11 -11
  3. {gnodevae-0.0.3 → gnodevae-0.0.4}/README.md +10 -10
  4. {gnodevae-0.0.3 → gnodevae-0.0.4/gnodevae.egg-info}/PKG-INFO +11 -11
  5. {gnodevae-0.0.3 → gnodevae-0.0.4}/pyproject.toml +1 -1
  6. {gnodevae-0.0.3 → gnodevae-0.0.4}/GNODEVAE/CLEAR.py +0 -0
  7. {gnodevae-0.0.3 → gnodevae-0.0.4}/GNODEVAE/GODEVAE.py +0 -0
  8. {gnodevae-0.0.3 → gnodevae-0.0.4}/GNODEVAE/GODEVAE_agent.py +0 -0
  9. {gnodevae-0.0.3 → gnodevae-0.0.4}/GNODEVAE/GODEVAE_env.py +0 -0
  10. {gnodevae-0.0.3 → gnodevae-0.0.4}/GNODEVAE/GODEVAE_trainer.py +0 -0
  11. {gnodevae-0.0.3 → gnodevae-0.0.4}/GNODEVAE/SC3.py +0 -0
  12. {gnodevae-0.0.3 → gnodevae-0.0.4}/GNODEVAE/agent.py +0 -0
  13. {gnodevae-0.0.3 → gnodevae-0.0.4}/GNODEVAE/env.py +0 -0
  14. {gnodevae-0.0.3 → gnodevae-0.0.4}/GNODEVAE/mixin.py +0 -0
  15. {gnodevae-0.0.3 → gnodevae-0.0.4}/GNODEVAE/module.py +0 -0
  16. {gnodevae-0.0.3 → gnodevae-0.0.4}/GNODEVAE/module_refined.py +0 -0
  17. {gnodevae-0.0.3 → gnodevae-0.0.4}/GNODEVAE/partition_time.py +0 -0
  18. {gnodevae-0.0.3 → gnodevae-0.0.4}/GNODEVAE/scGCC.py +0 -0
  19. {gnodevae-0.0.3 → gnodevae-0.0.4}/GNODEVAE/scGNN.py +0 -0
  20. {gnodevae-0.0.3 → gnodevae-0.0.4}/GNODEVAE/trainer.py +0 -0
  21. {gnodevae-0.0.3 → gnodevae-0.0.4}/GNODEVAE/utils.py +0 -0
  22. {gnodevae-0.0.3 → gnodevae-0.0.4}/GNODEVAE/utils_ODE.py +0 -0
  23. {gnodevae-0.0.3 → gnodevae-0.0.4}/LICENSE +0 -0
  24. {gnodevae-0.0.3 → gnodevae-0.0.4}/MANIFEST.in +0 -0
  25. {gnodevae-0.0.3 → gnodevae-0.0.4}/gnodevae.egg-info/SOURCES.txt +0 -0
  26. {gnodevae-0.0.3 → gnodevae-0.0.4}/gnodevae.egg-info/dependency_links.txt +0 -0
  27. {gnodevae-0.0.3 → gnodevae-0.0.4}/gnodevae.egg-info/requires.txt +0 -0
  28. {gnodevae-0.0.3 → gnodevae-0.0.4}/gnodevae.egg-info/top_level.txt +0 -0
  29. {gnodevae-0.0.3 → gnodevae-0.0.4}/setup.cfg +0 -0
@@ -3,4 +3,4 @@ from .GODEVAE_agent import GNODEVAE_agent_r, GNODEVAE_agent_subgraph
3
3
 
4
4
  __all__ = [agent, agent_r, GNODEVAE_agent_r, GNODEVAE_agent_subgraph]
5
5
 
6
- __version__ = '0.0.3'
6
+ __version__ = '0.0.4'
@@ -1,6 +1,6 @@
1
1
  Metadata-Version: 2.4
2
2
  Name: gnodevae
3
- Version: 0.0.3
3
+ Version: 0.0.4
4
4
  Summary: A Graph-Based ODE-VAE Enhances Clustering for Single-Cell Data
5
5
  Author-email: Zeyu Fu <fuzeyu99@126.com>
6
6
  License: MIT License
@@ -61,35 +61,35 @@ Dynamic: license-file
61
61
 
62
62
  ## Introduction
63
63
 
64
- GNODEVAE is an innovative computational framework that integrates Graph Attention Networks (GAT), Neural Ordinary Differential Equations (NODE), and Variational Autoencoders (VAE). It addresses three critical challenges in single-cell RNA sequencing data analysis:
64
+ GNODEVAE is a computational framework that integrates Graph Attention Networks (GAT), Neural Ordinary Differential Equations (NODE), and Variational Autoencoders (VAE). It targets three common challenges in single-cell RNA sequencing data analysis:
65
65
 
66
66
  1. Capturing complex topological relationships between cells
67
67
  2. Modeling continuous dynamic processes of cell differentiation
68
68
  3. Handling high levels of technical noise and biological variation
69
69
 
70
- This novel integration significantly improves the accurate identification of cell subpopulations, reconstruction of developmental trajectories, and understanding of cellular heterogeneity.
70
+ The integration is intended to support identification of cell subpopulations, reconstruction of developmental trajectories, and analysis of cellular heterogeneity.
71
71
 
72
72
  ## Key Contributions
73
73
 
74
74
  ### 1. Dynamic Attention Weighting for Biological Significance
75
75
 
76
- The GAT's attention mechanism adaptively weights gene expression profiles, prioritizing meaningful biological relationships while minimizing technical noise - particularly valuable for heterogeneous cell populations.
76
+ The GAT attention mechanism adaptively weights gene expression profiles, prioritizing biological relationships while reducing technical noise in heterogeneous cell populations.
77
77
 
78
78
  ### 2. Continuous-Time Developmental Modeling via Neural ODEs
79
79
 
80
- Integration of neural ordinary differential equations transforms static representations into dynamic systems, with time variables providing natural parameterization of developmental processes and enabling predictions at any point in cellular development.
80
+ Neural ordinary differential equations transform static representations into dynamic systems, with time variables providing a continuous parameterization of developmental processes.
81
81
 
82
82
  ### 3. Biologically Consistent Latent Space Representations
83
83
 
84
- The model's latent space effectively captures biological phenomena like varying rates of cell differentiation, while attention weights align with established developmental relationships between cell types.
84
+ The model's latent space is designed to capture variation in cell differentiation rates, while attention weights can be inspected alongside known developmental relationships between cell types.
85
85
 
86
- ### 4. Comprehensive Benchmark Leadership
86
+ ### 4. Benchmarking Summary
87
87
 
88
- When compared with six advanced single-cell analysis methods (scVI, DIP-VAE, TC-VAE, β-VAE, Info-VAE, and scTour), GNODEVAE ranked first across all 13 test datasets, demonstrating exceptional versatility across diverse biological contexts.
88
+ The accompanying study compares GNODEVAE with several single-cell analysis methods, including scVI, DIP-VAE, TC-VAE, beta-VAE, Info-VAE, and scTour, across 13 datasets.
89
89
 
90
- ### 5. Superior Gene Trend Analysis Performance
90
+ ### 5. Gene Trend Analysis
91
91
 
92
- Quantitative evaluation shows GNODEVAE significantly outperforms existing methods (69.97% improvement over Palantir, 63.58% over Diffmap) in Calinski-Harabasz index, demonstrating clearer clustering and stronger category discrimination.
92
+ The accompanying study also reports stronger Calinski-Harabasz scores than selected baselines for gene trend analysis.
93
93
 
94
94
 
95
95
  ## Installation
@@ -307,7 +307,7 @@ If you use GNODEVAE in your research, please cite:
307
307
  ```bibtex
308
308
  @article{fu2025gnodevae,
309
309
  title={GNODEVAE: a graph-based ODE-VAE enhances clustering for single-cell data},
310
- author={Fu, Z. and Chen, C. and Wang, S. and others},
310
+ author={Fu, Zeyu and Chen, Chunlin and Wang, Song and Wang, Junping and Chen, Shilei},
311
311
  journal={BMC Genomics},
312
312
  volume={26},
313
313
  pages={767},
@@ -6,35 +6,35 @@
6
6
 
7
7
  ## Introduction
8
8
 
9
- GNODEVAE is an innovative computational framework that integrates Graph Attention Networks (GAT), Neural Ordinary Differential Equations (NODE), and Variational Autoencoders (VAE). It addresses three critical challenges in single-cell RNA sequencing data analysis:
9
+ GNODEVAE is a computational framework that integrates Graph Attention Networks (GAT), Neural Ordinary Differential Equations (NODE), and Variational Autoencoders (VAE). It targets three common challenges in single-cell RNA sequencing data analysis:
10
10
 
11
11
  1. Capturing complex topological relationships between cells
12
12
  2. Modeling continuous dynamic processes of cell differentiation
13
13
  3. Handling high levels of technical noise and biological variation
14
14
 
15
- This novel integration significantly improves the accurate identification of cell subpopulations, reconstruction of developmental trajectories, and understanding of cellular heterogeneity.
15
+ The integration is intended to support identification of cell subpopulations, reconstruction of developmental trajectories, and analysis of cellular heterogeneity.
16
16
 
17
17
  ## Key Contributions
18
18
 
19
19
  ### 1. Dynamic Attention Weighting for Biological Significance
20
20
 
21
- The GAT's attention mechanism adaptively weights gene expression profiles, prioritizing meaningful biological relationships while minimizing technical noise - particularly valuable for heterogeneous cell populations.
21
+ The GAT attention mechanism adaptively weights gene expression profiles, prioritizing biological relationships while reducing technical noise in heterogeneous cell populations.
22
22
 
23
23
  ### 2. Continuous-Time Developmental Modeling via Neural ODEs
24
24
 
25
- Integration of neural ordinary differential equations transforms static representations into dynamic systems, with time variables providing natural parameterization of developmental processes and enabling predictions at any point in cellular development.
25
+ Neural ordinary differential equations transform static representations into dynamic systems, with time variables providing a continuous parameterization of developmental processes.
26
26
 
27
27
  ### 3. Biologically Consistent Latent Space Representations
28
28
 
29
- The model's latent space effectively captures biological phenomena like varying rates of cell differentiation, while attention weights align with established developmental relationships between cell types.
29
+ The model's latent space is designed to capture variation in cell differentiation rates, while attention weights can be inspected alongside known developmental relationships between cell types.
30
30
 
31
- ### 4. Comprehensive Benchmark Leadership
31
+ ### 4. Benchmarking Summary
32
32
 
33
- When compared with six advanced single-cell analysis methods (scVI, DIP-VAE, TC-VAE, β-VAE, Info-VAE, and scTour), GNODEVAE ranked first across all 13 test datasets, demonstrating exceptional versatility across diverse biological contexts.
33
+ The accompanying study compares GNODEVAE with several single-cell analysis methods, including scVI, DIP-VAE, TC-VAE, beta-VAE, Info-VAE, and scTour, across 13 datasets.
34
34
 
35
- ### 5. Superior Gene Trend Analysis Performance
35
+ ### 5. Gene Trend Analysis
36
36
 
37
- Quantitative evaluation shows GNODEVAE significantly outperforms existing methods (69.97% improvement over Palantir, 63.58% over Diffmap) in Calinski-Harabasz index, demonstrating clearer clustering and stronger category discrimination.
37
+ The accompanying study also reports stronger Calinski-Harabasz scores than selected baselines for gene trend analysis.
38
38
 
39
39
 
40
40
  ## Installation
@@ -252,7 +252,7 @@ If you use GNODEVAE in your research, please cite:
252
252
  ```bibtex
253
253
  @article{fu2025gnodevae,
254
254
  title={GNODEVAE: a graph-based ODE-VAE enhances clustering for single-cell data},
255
- author={Fu, Z. and Chen, C. and Wang, S. and others},
255
+ author={Fu, Zeyu and Chen, Chunlin and Wang, Song and Wang, Junping and Chen, Shilei},
256
256
  journal={BMC Genomics},
257
257
  volume={26},
258
258
  pages={767},
@@ -1,6 +1,6 @@
1
1
  Metadata-Version: 2.4
2
2
  Name: gnodevae
3
- Version: 0.0.3
3
+ Version: 0.0.4
4
4
  Summary: A Graph-Based ODE-VAE Enhances Clustering for Single-Cell Data
5
5
  Author-email: Zeyu Fu <fuzeyu99@126.com>
6
6
  License: MIT License
@@ -61,35 +61,35 @@ Dynamic: license-file
61
61
 
62
62
  ## Introduction
63
63
 
64
- GNODEVAE is an innovative computational framework that integrates Graph Attention Networks (GAT), Neural Ordinary Differential Equations (NODE), and Variational Autoencoders (VAE). It addresses three critical challenges in single-cell RNA sequencing data analysis:
64
+ GNODEVAE is a computational framework that integrates Graph Attention Networks (GAT), Neural Ordinary Differential Equations (NODE), and Variational Autoencoders (VAE). It targets three common challenges in single-cell RNA sequencing data analysis:
65
65
 
66
66
  1. Capturing complex topological relationships between cells
67
67
  2. Modeling continuous dynamic processes of cell differentiation
68
68
  3. Handling high levels of technical noise and biological variation
69
69
 
70
- This novel integration significantly improves the accurate identification of cell subpopulations, reconstruction of developmental trajectories, and understanding of cellular heterogeneity.
70
+ The integration is intended to support identification of cell subpopulations, reconstruction of developmental trajectories, and analysis of cellular heterogeneity.
71
71
 
72
72
  ## Key Contributions
73
73
 
74
74
  ### 1. Dynamic Attention Weighting for Biological Significance
75
75
 
76
- The GAT's attention mechanism adaptively weights gene expression profiles, prioritizing meaningful biological relationships while minimizing technical noise - particularly valuable for heterogeneous cell populations.
76
+ The GAT attention mechanism adaptively weights gene expression profiles, prioritizing biological relationships while reducing technical noise in heterogeneous cell populations.
77
77
 
78
78
  ### 2. Continuous-Time Developmental Modeling via Neural ODEs
79
79
 
80
- Integration of neural ordinary differential equations transforms static representations into dynamic systems, with time variables providing natural parameterization of developmental processes and enabling predictions at any point in cellular development.
80
+ Neural ordinary differential equations transform static representations into dynamic systems, with time variables providing a continuous parameterization of developmental processes.
81
81
 
82
82
  ### 3. Biologically Consistent Latent Space Representations
83
83
 
84
- The model's latent space effectively captures biological phenomena like varying rates of cell differentiation, while attention weights align with established developmental relationships between cell types.
84
+ The model's latent space is designed to capture variation in cell differentiation rates, while attention weights can be inspected alongside known developmental relationships between cell types.
85
85
 
86
- ### 4. Comprehensive Benchmark Leadership
86
+ ### 4. Benchmarking Summary
87
87
 
88
- When compared with six advanced single-cell analysis methods (scVI, DIP-VAE, TC-VAE, β-VAE, Info-VAE, and scTour), GNODEVAE ranked first across all 13 test datasets, demonstrating exceptional versatility across diverse biological contexts.
88
+ The accompanying study compares GNODEVAE with several single-cell analysis methods, including scVI, DIP-VAE, TC-VAE, beta-VAE, Info-VAE, and scTour, across 13 datasets.
89
89
 
90
- ### 5. Superior Gene Trend Analysis Performance
90
+ ### 5. Gene Trend Analysis
91
91
 
92
- Quantitative evaluation shows GNODEVAE significantly outperforms existing methods (69.97% improvement over Palantir, 63.58% over Diffmap) in Calinski-Harabasz index, demonstrating clearer clustering and stronger category discrimination.
92
+ The accompanying study also reports stronger Calinski-Harabasz scores than selected baselines for gene trend analysis.
93
93
 
94
94
 
95
95
  ## Installation
@@ -307,7 +307,7 @@ If you use GNODEVAE in your research, please cite:
307
307
  ```bibtex
308
308
  @article{fu2025gnodevae,
309
309
  title={GNODEVAE: a graph-based ODE-VAE enhances clustering for single-cell data},
310
- author={Fu, Z. and Chen, C. and Wang, S. and others},
310
+ author={Fu, Zeyu and Chen, Chunlin and Wang, Song and Wang, Junping and Chen, Shilei},
311
311
  journal={BMC Genomics},
312
312
  volume={26},
313
313
  pages={767},
@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
4
4
 
5
5
  [project]
6
6
  name = "gnodevae"
7
- version = "0.0.3"
7
+ version = "0.0.4"
8
8
  description = "A Graph-Based ODE-VAE Enhances Clustering for Single-Cell Data"
9
9
  readme = "README.md"
10
10
  license = {file = "LICENSE"}
File without changes
File without changes
File without changes
File without changes
File without changes
File without changes
File without changes
File without changes
File without changes
File without changes
File without changes
File without changes
File without changes
File without changes
File without changes