# HeartMAP: Heart Multi-chamber Analysis Platform
[](https://badge.fury.io/py/heartmap)
[](https://opensource.org/licenses/Apache-2.0)
[](https://www.python.org/downloads/)
[](https://github.com/Tumo505/HeartMap/actions)
[](https://doi.org/10.5281/zenodo.16745118)
> **A production-ready Python package for comprehensive single-cell heart analysis with chamber-specific insights**
## 🫀 Package Overview
HeartMAP is a specialized bioinformatics package that decodes cellular communication across all four chambers of the human heart. Unlike general single-cell tools, HeartMAP is purpose-built for cardiac biology, offering chamber-specific insights crucial for understanding heart function, disease, and therapeutic opportunities.
**✨ Key Features:**
- 🔧 **Production Ready**: Fully tested, documented, and deployed on PyPI
- 🚀 **Multiple Interfaces**: CLI, Python API, REST API, and Web interface
- 📦 **Easy Installation**: `pip install heartmap`
- ⚙️ **Configurable**: Works on 8GB+ RAM with memory optimization
- 🧪 **Validated**: Tested on real human heart datasets
- 📊 **Comprehensive**: From basic QC to advanced communication analysis
## 📦 Quick Installation
```bash
# Install from PyPI
pip install heartmap
# Install with all features
pip install heartmap[all]
# Verify installation
python -c "import heartmap; print('✅ HeartMAP ready!')"
```
## 🚀 Quick Start
### 30-Second Analysis
```bash
# Analyze your heart data with one command
heartmap your_heart_data.h5ad
```
### 2-Minute Python Analysis
```python
from heartmap import Config
from heartmap.pipelines import ComprehensivePipeline
# Quick analysis
config = Config.default()
pipeline = ComprehensivePipeline(config)
results = pipeline.run('your_data.h5ad', 'results/')
print("✅ Analysis complete! Check 'results/' directory.")
```
## 📚 Documentation
| Document | Description | Use When |
|----------|-------------|----------|
| **[📖 User Guide](USER_GUIDE.md)** | Complete step-by-step tutorials | Learning HeartMAP |
| **[🔧 API Documentation](API_DOCUMENTATION.md)** | Full API reference | Programming with HeartMAP |
| **[📦 Package README](PACKAGE_README.md)** | Package-specific documentation | Installing/using the package |
| **[📝 Original README](README_ORIGINAL.md)** | Development documentation | Contributing to HeartMAP |
## 🔬 What HeartMAP Can Do
### Analysis Pipelines
| Pipeline | Purpose | Output | Runtime |
|----------|---------|---------|---------|
| **Basic** | Quality control, cell typing | Cell annotations, QC metrics | 5-10 min |
| **Communication** | Cell-cell interactions | Communication networks, hubs | 10-15 min |
| **Multi-Chamber** | Chamber-specific analysis | Chamber markers, comparisons | 15-20 min |
| **Comprehensive** | Complete analysis | All of the above + reports | 20-30 min |
### Real-World Applications
```python
# Clinical Research: Chamber-specific targets
from heartmap.pipelines import MultiChamberPipeline
pipeline = MultiChamberPipeline(config)
results = pipeline.run('patient_data.h5ad')
lv_targets = results['chamber_markers']['LV']
# Drug Discovery: Communication pathways
from heartmap.pipelines import AdvancedCommunicationPipeline
pipeline = AdvancedCommunicationPipeline(config)
results = pipeline.run('disease_data.h5ad')
drug_targets = results['communication_hubs']
# Education: Comparative analysis
results1 = pipeline.run('healthy_heart.h5ad')
results2 = pipeline.run('diseased_heart.h5ad')
```
## ⚡ Performance
| Hardware | Dataset Size | Memory | Runtime | Status |
|----------|-------------|--------|---------|---------|
| 8GB RAM | 30K cells | ~6GB | 15 min | ✅ Recommended |
| 16GB RAM | 50K cells | ~12GB | 25 min | ✅ Optimal |
| 32GB RAM | 100K cells | ~24GB | 45 min | ✅ Production |
## 🛠️ Development
### For Contributors
```bash
# Development setup
git clone https://github.com/Tumo505/HeartMap.git
cd HeartMap
pip install -e .[dev]
# Run tests
python -m pytest tests/
python -m flake8 src/heartmap/
python -m mypy src/heartmap/
```
### For Package Users
The package is production-ready and maintained. See the [User Guide](USER_GUIDE.md) for complete usage instructions.
## 📊 Scientific Impact
- **🏥 Clinical**: Chamber-specific therapeutic strategies
- **🔬 Research**: First comprehensive multi-chamber communication atlas
- **📚 Education**: Accessible cardiac biology analysis platform
- **🏭 Industry**: Production-ready bioinformatics tool
## 🎯 Use Cases
- **Pharmaceutical Research**: Drug target discovery, safety assessment
- **Clinical Cardiology**: Precision medicine, disease mechanisms
- **Basic Research**: Cardiac development, evolutionary biology
- **Computational Biology**: Method benchmarking, data integration
## 📋 Requirements
- **Python**: 3.8+ (tested on 3.8-3.11)
- **Memory**: 8GB+ RAM (configurable)
- **Storage**: 2GB+ for package and results
- **OS**: Linux, macOS, Windows
## 🤝 Contributing
We welcome contributions! See our [development documentation](README_ORIGINAL.md) for details.
## 📖 Citation
```bibtex
@software{heartmap2025,
title={HeartMAP: Heart Multi-chamber Analysis Platform},
author={Kgabeng, Tumo and Wang, Lulu and Ngwangwa, Harry and Pandelani, Thanyani},
year={2025},
url={https://github.com/Tumo505/HeartMap},
version={1.0.0}
}
```
## 📄 License
Apache 2.0 License - see [LICENSE](LICENSE) for details.
## 🆘 Support
- **📖 Documentation**: [User Guide](USER_GUIDE.md) | [API Docs](API_DOCUMENTATION.md)
- **💬 Community**: [GitHub Discussions](https://github.com/Tumo505/HeartMap/discussions)
- **🐛 Issues**: [GitHub Issues](https://github.com/Tumo505/HeartMap/issues)
- **📧 Contact**: 28346416@mylife.unisa.ac.za
---
**🎉 HeartMAP: Production-ready cardiac single-cell analysis for researchers worldwide** 🫀✨
*Install today: `pip install heartmap`*
### Supporting Files
```
├── scripts/ # Setup and utility scripts
│ ├── setup.sh # Automated environment setup
│ ├── validate.py # Installation validation
│ ├── migrate.py # Legacy code migration
│ └── deploy_huggingface.sh # HuggingFace deployment
├── tests/ # Comprehensive test suite
├── notebooks/ # Jupyter notebook examples
├── config.yaml # Default configuration
├── setup.py # Package installation
├── Dockerfile # Container deployment
├── docker-compose.yml # Multi-service orchestration
└── app.py # Gradio web interface
```
## 🚀 Quick Start
### Option 1: Automated Setup (Recommended)
```bash
# Clone the repository
git clone https://github.com/Tumo505/HeartMap.git
cd HeartMap
# Run automated setup script
./scripts/setup.sh
# Activate the environment
source heartmap_env/bin/activate # Linux/Mac
# OR: heartmap_env\Scripts\activate # Windows
# Validate installation
python scripts/validate.py
# Start analyzing!
heartmap data/raw/your_data.h5ad --analysis-type comprehensive
```
### Option 2: Manual Installation
```bash
# Create virtual environment
python3 -m venv heartmap_env
source heartmap_env/bin/activate
# Install dependencies
pip install -r requirements-dev.txt
# Install HeartMAP in development mode
pip install -e .[all]
# Validate installation
python scripts/validate.py
```
### Option 3: Package Installation
```bash
# Install from PyPI (when available)
pip install heartmap[all]
# Or install specific features
pip install heartmap[communication] # Communication analysis only
pip install heartmap[api] # API features only
```
## 📊 Usage Examples
### 1. Command Line Interface
```bash
# Basic analysis
heartmap data/raw/heart_data.h5ad
# Comprehensive analysis with custom output
heartmap data/raw/heart_data.h5ad \
--analysis-type comprehensive \
--output-dir results/comprehensive \
--config my_config.yaml
# Specific analysis types
heartmap data/raw/heart_data.h5ad --analysis-type annotation
heartmap data/raw/heart_data.h5ad --analysis-type communication
heartmap data/raw/heart_data.h5ad --analysis-type multi-chamber
# Memory-optimized for large datasets
heartmap data/raw/large_dataset.h5ad \
--analysis-type comprehensive \
--config config_large.yaml
```
### 2. Python API
```python
from heartmap import Config, HeartMapModel
from heartmap.pipelines import ComprehensivePipeline
# Load and customize configuration
config = Config.from_yaml('config.yaml')
config.data.max_cells_subset = 50000 # Optimize for your memory
config.data.max_genes_subset = 5000
# Option A: Use full HeartMAP model
model = HeartMapModel(config)
results = model.analyze('data/raw/heart_data.h5ad')
# Option B: Use specific pipeline
pipeline = ComprehensivePipeline(config)
results = pipeline.run('data/raw/heart_data.h5ad', 'results/')
# Save model for reuse
model.save('models/my_heartmap_model')
# Load and reuse saved model
loaded_model = HeartMapModel.load('models/my_heartmap_model')
new_results = loaded_model.predict(new_data)
```
### 3. REST API
```bash
# Start API server
python scripts/run_api_server.py
# Server available at http://localhost:8000
# API docs at http://localhost:8000/docs
# Use the API
curl -X POST "http://localhost:8000/analyze" \
-H "Content-Type: multipart/form-data" \
-F "file=@data/raw/heart_data.h5ad" \
-F "analysis_type=comprehensive"
# Check available models
curl http://localhost:8000/models
# Update configuration
curl -X POST "http://localhost:8000/config" \
-H "Content-Type: application/json" \
-d '{"data": {"max_cells_subset": 30000}}'
```
### 4. Web Interface (Gradio)
```bash
# Start web interface
python app.py
# Access at http://localhost:7860
# Features:
# - Upload .h5ad files
# - Select analysis type
# - Configure memory settings
# - Download results
```
### 5. Jupyter Notebooks
```bash
# Install Jupyter
pip install jupyter
# Start notebook server
jupyter lab
# Open example notebooks:
# - notebooks/01_basic_analysis.ipynb
# - notebooks/02_advanced_communication.ipynb
# - notebooks/03_multi_chamber_analysis.ipynb
# - notebooks/04_comprehensive_analysis.ipynb
```
## ⚙️ Configuration
HeartMAP uses YAML configuration files for easy customization:
```yaml
# config.yaml or my_config.yaml
data:
min_genes: 200
min_cells: 3
max_cells_subset: 50000 # Adjust based on your RAM
max_genes_subset: 5000 # Reduce for faster analysis
target_sum: 10000.0
n_top_genes: 2000
random_seed: 42
test_mode: false # Set true for quick testing
analysis:
n_components_pca: 50
n_neighbors: 10
n_pcs: 40
resolution: 0.5
n_marker_genes: 25
use_leiden: true
use_liana: true # Cell-cell communication
model:
model_type: "comprehensive"
save_intermediate: true
use_gpu: false # Set true if GPU available
batch_size: null
max_memory_gb: null # Auto-detect memory
paths:
data_dir: "data"
raw_data_dir: "data/raw"
processed_data_dir: "data/processed"
results_dir: "results"
figures_dir: "figures"
models_dir: "models"
```
### Memory Optimization Guidelines
| System RAM | max_cells_subset | max_genes_subset | Use Case |
|------------|------------------|------------------|----------|
| 8GB | 10,000 | 2,000 | Laptop/Desktop |
| 16GB | 30,000 | 4,000 | Workstation |
| 32GB | 50,000 | 5,000 | Server |
| 64GB+ | 100,000+ | 10,000+ | HPC/Cloud |
## 🔬 Analysis Components
### 1. Basic Pipeline
- **Data Preprocessing**: Quality control, normalization, scaling
- **Cell Type Annotation**: Clustering and cell type identification
- **Basic Visualization**: UMAP, t-SNE, cluster plots
- **Quality Metrics**: Cell and gene filtering statistics
### 2. Advanced Communication Analysis
- **Cell-Cell Communication**: Ligand-receptor interaction analysis
- **Communication Hubs**: Identification of key signaling cells
- **Pathway Enrichment**: Cardiac development and disease pathways
- **Network Analysis**: Communication network topology
### 3. Multi-Chamber Atlas
- **Chamber-Specific Analysis**: RA, RV, LA, LV specific patterns
- **Marker Identification**: Chamber-specific biomarkers
- **Cross-Chamber Correlations**: Inter-chamber relationship analysis
- **Comparative Analysis**: Chamber-to-chamber differences
### 4. Comprehensive Pipeline
- **Integrated Analysis**: All components combined
- **Advanced Visualizations**: Multi-panel figures and dashboards
- **Comprehensive Reports**: Automated result summaries
- **Model Persistence**: Save complete analysis state
## 🚀 Deployment Guide
### Local Development Setup
#### Prerequisites
- Python 3.8+ (recommended: Python 3.10)
- Git
- Docker (optional, for containerized deployment)
- 8GB+ RAM (16GB+ recommended for larger datasets)
#### Quick Setup
```bash
# Clone and setup environment
git clone https://github.com/Tumo505/HeartMap.git
cd HeartMap
# Create virtual environment
python -m venv heartmap_env
source heartmap_env/bin/activate # On Windows: heartmap_env\Scripts\activate
# Install dependencies
pip install --upgrade pip
pip install -r requirements-dev.txt
pip install -e .[all]
# Configure the platform
cp config.yaml my_config.yaml
# Edit my_config.yaml to match your system resources
# Test installation
python scripts/validate.py
python scripts/run_examples.py
```
### Docker Deployment
```bash
# Single service
docker build -t heartmap .
docker run -p 8000:8000 -v $(pwd)/data:/app/data heartmap
# Multi-service with docker-compose
docker-compose up
# Services:
# - API server: http://localhost:8000
# - Gradio interface: http://localhost:7860
# - Worker processes for batch analysis
```
### Hugging Face Spaces Deployment
```bash
# Prepare deployment files
./scripts/deploy_huggingface.sh
# Upload to your Hugging Face Space:
# 1. Create new Space at https://huggingface.co/new-space
# 2. Choose Gradio SDK
# 3. Upload generated files:
# - app.py (Gradio interface)
# - requirements.txt (Dependencies)
# - src/ (Source code)
# - config.yaml (Configuration)
```
### Cloud Platforms
#### AWS Deployment
```bash
# ECS deployment
docker build -t heartmap .
aws ecr get-login-password --region us-east-1 | docker login --username AWS --password-stdin $ECR_URI
docker tag heartmap:latest $ECR_URI/heartmap:latest
docker push $ECR_URI/heartmap:latest
# Lambda deployment for serverless
sam build
sam deploy --guided
```
#### Google Cloud Platform
```bash
# Cloud Run deployment
gcloud builds submit --tag gcr.io/$PROJECT_ID/heartmap
gcloud run deploy --image gcr.io/$PROJECT_ID/heartmap --platform managed
```
#### Azure
```bash
# Container Instances
az container create --resource-group myResourceGroup \
--name heartmap --image myregistry.azurecr.io/heartmap:latest
```
## 📊 Scientific Results
### Chamber Distribution
- **RA (Right Atrium):** 28.4% of cells
- **LV (Left Ventricle):** 27.0% of cells
- **LA (Left Atrium):** 26.4% of cells
- **RV (Right Ventricle):** 18.2% of cells
### Chamber-Specific Markers
- **RA:** NPPA, MIR100HG, MYL7, MYL4, PDE4D
- **RV:** NEAT1, MYH7, FHL2, C15orf41, PCDH7
- **LA:** NPPA, ELN, MYL7, EBF2, RORA
- **LV:** CD36, LINC00486, FHL2, RP11-532N4.2, MYH7
### Cross-Chamber Correlations
- **RV vs LV:** r = 0.985 (highest correlation)
- **RA vs LA:** r = 0.960
- **LA vs LV:** r = 0.870 (lowest correlation)
## 🧪 Testing & Validation
### Run Tests
```bash
# Full test suite
python tests/test_heartmap.py
# Validation suite
python scripts/validate.py
# Example analysis with mock data
python scripts/demo.py
```
### Performance Benchmarks
| Dataset Size | Memory Usage | Processing Time | Output |
|-------------|--------------|-----------------|--------|
| 10K cells | 2GB RAM | 5 minutes | Complete analysis |
| 50K cells | 8GB RAM | 15 minutes | Complete analysis |
| 100K cells | 16GB RAM | 30 minutes | Complete analysis |
## 🎯 Use Cases
### Research Applications
- **Interactive Analysis**: Jupyter notebooks for exploration
- **Batch Processing**: Command-line analysis of multiple datasets
- **Pipeline Integration**: Python API for custom workflows
- **Collaborative Research**: Shared configurations and models
### Production Applications
- **Web Services**: REST API for applications
- **Public Access**: Hugging Face Spaces for community use
- **Microservices**: Containerized deployment in cloud
- **High-Throughput**: Scalable analysis for large cohorts
### Educational Use
- **Teaching Platform**: Web interface for students
- **Reproducible Science**: Containerized environments
- **Method Comparison**: Multiple analysis approaches
- **Best Practices**: Clean, documented codebase
## 🔒 Data Integrity & Reproducibility
### SHA-256 Checksums
- **Purpose**: Ensure data file integrity during storage/transfer
- **Implementation**: Automatic verification before analysis
- **Usage**: `python utils/sha256_checksum.py verify data/raw data/raw/checksums.txt`
### Fixed Random Seeds
- **Purpose**: Ensure reproducible results across runs
- **Implementation**: Fixed seeds in all stochastic processes
- **Scope**: Random sampling, clustering, mock data generation
### Examples of Reproducible Components
1. **Random Sampling**:
```python
np.random.seed(42)
cell_indices = np.random.choice(adata.n_obs, size=50000, replace=False)
```
2. **Clustering**:
```python
kmeans = KMeans(n_clusters=n_clusters, random_state=42)
```
3. **LIANA Analysis**:
```python
li.mt.rank_aggregate.by_sample(
adata, groupby=cell_type_col, resource_name='consensus',
n_perms=100, seed=42, verbose=True
)
```
## 🔧 Development & Contributing
### Development Setup
```bash
# Development setup
git clone https://github.com/Tumo505/HeartMap.git
cd HeartMap
./scripts/setup.sh
source heartmap_env/bin/activate
# Install development dependencies
pip install -e .[dev]
# Run tests before committing
python tests/test_heartmap.py
python scripts/validate.py
# Code quality checks
black src/ tests/ scripts/ # Code formatting
flake8 src/ --max-line-length=100 # Linting
mypy src/heartmap --ignore-missing-imports # Type checking
```
### Adding New Features
1. **New Models**: Inherit from `BaseModel` in `src/heartmap/models/`
2. **New Pipelines**: Inherit from `BasePipeline` in `src/heartmap/pipelines/`
3. **API Endpoints**: Add to `src/heartmap/api/rest.py`
4. **Configuration**: Extend dataclasses in `src/heartmap/config/`
### Testing Guidelines
```python
# Test structure
tests/
├── test_config.py # Configuration management
├── test_data.py # Data processing
├── test_models.py # Analysis models
├── test_pipelines.py # Analysis pipelines
└── test_api.py # API interfaces
```
## 🆘 Troubleshooting
### Common Issues
#### Memory Errors
```bash
# Reduce dataset size in config
data:
max_cells_subset: 10000
max_genes_subset: 2000
```
#### Import Errors
```bash
# Reinstall with all dependencies
pip install -e .[all]
# Check Python path
python -c "import heartmap; print(heartmap.__file__)"
```
#### Data Loading Issues
```bash
# Verify data format
python -c "import scanpy as sc; print(sc.read_h5ad('data/raw/your_file.h5ad'))"
# Check file permissions
ls -la data/raw/
```
#### Performance Issues
```bash
# Enable test mode for quick validation
test_mode: true # in config.yaml
# Use GPU acceleration (if available)
model:
use_gpu: true
```
### Getting Help
1. **Validation**: `python scripts/validate.py`
2. **Logs**: Check logs in `results/` directory
3. **Test Mode**: Set `test_mode: true` in configuration
4. **Mock Data**: `python scripts/demo.py` for testing
5. **Documentation**: Comprehensive docstrings in source code
## 📋 Requirements
### System Requirements
- **Python**: 3.8+ (recommended: 3.10)
- **Memory**: 8GB+ recommended (configurable)
- **Storage**: 5GB+ for data and results
- **OS**: Linux, macOS, Windows
### Dependencies
- **Core**: scanpy, pandas, numpy, scipy, scikit-learn
- **Visualization**: matplotlib, seaborn, plotly
- **Communication**: liana, cellphonedb (optional)
- **API**: fastapi, uvicorn (optional)
- **Web**: gradio (optional)
## 🎯 Clinical Applications
- **Personalized Medicine**: Chamber-specific treatment strategies
- **Drug Development**: Chamber-specific therapeutic targets
- **Disease Understanding**: Chamber-specific disease mechanisms
- **Biomarker Discovery**: Chamber and communication-specific markers
## 🤝 Contributing
1. Fork the repository
2. Create a feature branch: `git checkout -b feature-name`
3. Install development dependencies: `pip install -e .[dev]`
4. Run tests: `python tests/test_heartmap.py`
5. Submit a pull request
## 📄 License
This project is licensed under the Apache License 2.0 - see the [LICENSE](LICENSE) file for details.
## 📖 Citation
```bibtex
@software{heartmap2025,
title={HeartMAP: A Multi-Chamber Spatial Framework for Cardiac Cell-Cell Communication},
author={Kgabeng, Tumo and Wang, Lulu and Ngwangwa, Harry and Pandelani, Thanyani},
year={2024},
url={https://github.com/Tumo505/HeartMap},
version={1.0.0},
doi={10.5281/zenodo.16745118}
}
```
## 🆘 Support
- **Issues**: [GitHub Issues](https://github.com/Tumo505/HeartMap/issues)
- **Discussions**: [GitHub Discussions](https://github.com/Tumo505/HeartMap/discussions)
- **Email**: 28346416@mylife.unisa.ac.za
## 🎉 Acknowledgments
- Department of Mechanical, Bioresources and Biomedical Engineering, University of South Africa
- Department of Engineering, Reykjavik University
- Single Cell Portal (SCP498) for providing the heart dataset
- The open-source scientific Python community
---
**🎉 HeartMAP is now production-ready and available for research, deployment, and collaboration!**
Whether you're a researcher exploring cardiac biology, a developer building applications, or an educator teaching single-cell analysis, HeartMAP provides the tools and flexibility you need.
Raw data
{
"_id": null,
"home_page": "https://github.com/Tumo505/HeartMap",
"name": "heartmap",
"maintainer": null,
"docs_url": null,
"requires_python": ">=3.8",
"maintainer_email": null,
"keywords": "single-cell, RNA-seq, heart, cell-communication, bioinformatics, spatial-transcriptomics",
"author": "Tumo Kgabeng, Lulu Wang, Harry Ngwangwa, Thanyani Pandelani",
"author_email": "28346416@mylife.unisa.ac.za",
"download_url": "https://files.pythonhosted.org/packages/77/8e/9341cedd9261c2e09f07b65225efab3f518b7491e0b7f1fdde80836923a2/heartmap-1.1.1.tar.gz",
"platform": null,
"description": "# HeartMAP: Heart Multi-chamber Analysis Platform\n\n[](https://badge.fury.io/py/heartmap)\n[](https://opensource.org/licenses/Apache-2.0)\n[](https://www.python.org/downloads/)\n[](https://github.com/Tumo505/HeartMap/actions)\n[](https://doi.org/10.5281/zenodo.16745118)\n\n> **A production-ready Python package for comprehensive single-cell heart analysis with chamber-specific insights**\n\n## \ud83e\udec0 Package Overview\n\nHeartMAP is a specialized bioinformatics package that decodes cellular communication across all four chambers of the human heart. Unlike general single-cell tools, HeartMAP is purpose-built for cardiac biology, offering chamber-specific insights crucial for understanding heart function, disease, and therapeutic opportunities.\n\n**\u2728 Key Features:**\n- \ud83d\udd27 **Production Ready**: Fully tested, documented, and deployed on PyPI\n- \ud83d\ude80 **Multiple Interfaces**: CLI, Python API, REST API, and Web interface \n- \ud83d\udce6 **Easy Installation**: `pip install heartmap`\n- \u2699\ufe0f **Configurable**: Works on 8GB+ RAM with memory optimization\n- \ud83e\uddea **Validated**: Tested on real human heart datasets\n- \ud83d\udcca **Comprehensive**: From basic QC to advanced communication analysis\n\n## \ud83d\udce6 Quick Installation\n\n```bash\n# Install from PyPI\npip install heartmap\n\n# Install with all features\npip install heartmap[all]\n\n# Verify installation\npython -c \"import heartmap; print('\u2705 HeartMAP ready!')\"\n```\n\n## \ud83d\ude80 Quick Start\n\n### 30-Second Analysis\n```bash\n# Analyze your heart data with one command\nheartmap your_heart_data.h5ad\n```\n\n### 2-Minute Python Analysis\n```python\nfrom heartmap import Config\nfrom heartmap.pipelines import ComprehensivePipeline\n\n# Quick analysis\nconfig = Config.default()\npipeline = ComprehensivePipeline(config)\nresults = pipeline.run('your_data.h5ad', 'results/')\n\nprint(\"\u2705 Analysis complete! Check 'results/' directory.\")\n```\n\n## \ud83d\udcda Documentation\n\n| Document | Description | Use When |\n|----------|-------------|----------|\n| **[\ud83d\udcd6 User Guide](USER_GUIDE.md)** | Complete step-by-step tutorials | Learning HeartMAP |\n| **[\ud83d\udd27 API Documentation](API_DOCUMENTATION.md)** | Full API reference | Programming with HeartMAP |\n| **[\ud83d\udce6 Package README](PACKAGE_README.md)** | Package-specific documentation | Installing/using the package |\n| **[\ud83d\udcdd Original README](README_ORIGINAL.md)** | Development documentation | Contributing to HeartMAP |\n\n## \ud83d\udd2c What HeartMAP Can Do\n\n### Analysis Pipelines\n\n| Pipeline | Purpose | Output | Runtime |\n|----------|---------|---------|---------|\n| **Basic** | Quality control, cell typing | Cell annotations, QC metrics | 5-10 min |\n| **Communication** | Cell-cell interactions | Communication networks, hubs | 10-15 min |\n| **Multi-Chamber** | Chamber-specific analysis | Chamber markers, comparisons | 15-20 min |\n| **Comprehensive** | Complete analysis | All of the above + reports | 20-30 min |\n\n### Real-World Applications\n\n```python\n# Clinical Research: Chamber-specific targets\nfrom heartmap.pipelines import MultiChamberPipeline\npipeline = MultiChamberPipeline(config)\nresults = pipeline.run('patient_data.h5ad')\nlv_targets = results['chamber_markers']['LV']\n\n# Drug Discovery: Communication pathways\nfrom heartmap.pipelines import AdvancedCommunicationPipeline \npipeline = AdvancedCommunicationPipeline(config)\nresults = pipeline.run('disease_data.h5ad')\ndrug_targets = results['communication_hubs']\n\n# Education: Comparative analysis\nresults1 = pipeline.run('healthy_heart.h5ad')\nresults2 = pipeline.run('diseased_heart.h5ad')\n```\n\n## \u26a1 Performance\n\n| Hardware | Dataset Size | Memory | Runtime | Status |\n|----------|-------------|--------|---------|---------|\n| 8GB RAM | 30K cells | ~6GB | 15 min | \u2705 Recommended |\n| 16GB RAM | 50K cells | ~12GB | 25 min | \u2705 Optimal |\n| 32GB RAM | 100K cells | ~24GB | 45 min | \u2705 Production |\n\n## \ud83d\udee0\ufe0f Development\n\n### For Contributors\n\n```bash\n# Development setup\ngit clone https://github.com/Tumo505/HeartMap.git\ncd HeartMap\npip install -e .[dev]\n\n# Run tests\npython -m pytest tests/\npython -m flake8 src/heartmap/\npython -m mypy src/heartmap/\n```\n\n### For Package Users\n\nThe package is production-ready and maintained. See the [User Guide](USER_GUIDE.md) for complete usage instructions.\n\n## \ud83d\udcca Scientific Impact\n\n- **\ud83c\udfe5 Clinical**: Chamber-specific therapeutic strategies\n- **\ud83d\udd2c Research**: First comprehensive multi-chamber communication atlas \n- **\ud83d\udcda Education**: Accessible cardiac biology analysis platform\n- **\ud83c\udfed Industry**: Production-ready bioinformatics tool\n\n## \ud83c\udfaf Use Cases\n\n- **Pharmaceutical Research**: Drug target discovery, safety assessment\n- **Clinical Cardiology**: Precision medicine, disease mechanisms\n- **Basic Research**: Cardiac development, evolutionary biology\n- **Computational Biology**: Method benchmarking, data integration\n\n## \ud83d\udccb Requirements\n\n- **Python**: 3.8+ (tested on 3.8-3.11)\n- **Memory**: 8GB+ RAM (configurable)\n- **Storage**: 2GB+ for package and results\n- **OS**: Linux, macOS, Windows\n\n## \ud83e\udd1d Contributing\n\nWe welcome contributions! See our [development documentation](README_ORIGINAL.md) for details.\n\n## \ud83d\udcd6 Citation\n\n```bibtex\n@software{heartmap2025,\n title={HeartMAP: Heart Multi-chamber Analysis Platform},\n author={Kgabeng, Tumo and Wang, Lulu and Ngwangwa, Harry and Pandelani, Thanyani},\n year={2025},\n url={https://github.com/Tumo505/HeartMap},\n version={1.0.0}\n}\n```\n\n## \ud83d\udcc4 License\n\nApache 2.0 License - see [LICENSE](LICENSE) for details.\n\n## \ud83c\udd98 Support\n\n- **\ud83d\udcd6 Documentation**: [User Guide](USER_GUIDE.md) | [API Docs](API_DOCUMENTATION.md)\n- **\ud83d\udcac Community**: [GitHub Discussions](https://github.com/Tumo505/HeartMap/discussions)\n- **\ud83d\udc1b Issues**: [GitHub Issues](https://github.com/Tumo505/HeartMap/issues)\n- **\ud83d\udce7 Contact**: 28346416@mylife.unisa.ac.za\n\n---\n\n**\ud83c\udf89 HeartMAP: Production-ready cardiac single-cell analysis for researchers worldwide** \ud83e\udec0\u2728\n\n*Install today: `pip install heartmap`*\n\n### Supporting Files\n\n```\n\u251c\u2500\u2500 scripts/ # Setup and utility scripts\n\u2502 \u251c\u2500\u2500 setup.sh # Automated environment setup\n\u2502 \u251c\u2500\u2500 validate.py # Installation validation\n\u2502 \u251c\u2500\u2500 migrate.py # Legacy code migration\n\u2502 \u2514\u2500\u2500 deploy_huggingface.sh # HuggingFace deployment\n\u251c\u2500\u2500 tests/ # Comprehensive test suite\n\u251c\u2500\u2500 notebooks/ # Jupyter notebook examples\n\u251c\u2500\u2500 config.yaml # Default configuration\n\u251c\u2500\u2500 setup.py # Package installation\n\u251c\u2500\u2500 Dockerfile # Container deployment\n\u251c\u2500\u2500 docker-compose.yml # Multi-service orchestration\n\u2514\u2500\u2500 app.py # Gradio web interface\n```\n\n## \ud83d\ude80 Quick Start\n\n### Option 1: Automated Setup (Recommended)\n\n```bash\n# Clone the repository\ngit clone https://github.com/Tumo505/HeartMap.git\ncd HeartMap\n\n# Run automated setup script\n./scripts/setup.sh\n\n# Activate the environment\nsource heartmap_env/bin/activate # Linux/Mac\n# OR: heartmap_env\\Scripts\\activate # Windows\n\n# Validate installation\npython scripts/validate.py\n\n# Start analyzing!\nheartmap data/raw/your_data.h5ad --analysis-type comprehensive\n```\n\n### Option 2: Manual Installation\n\n```bash\n# Create virtual environment\npython3 -m venv heartmap_env\nsource heartmap_env/bin/activate\n\n# Install dependencies\npip install -r requirements-dev.txt\n\n# Install HeartMAP in development mode\npip install -e .[all]\n\n# Validate installation\npython scripts/validate.py\n```\n\n### Option 3: Package Installation\n\n```bash\n# Install from PyPI (when available)\npip install heartmap[all]\n\n# Or install specific features\npip install heartmap[communication] # Communication analysis only\npip install heartmap[api] # API features only\n```\n\n## \ud83d\udcca Usage Examples\n\n### 1. Command Line Interface\n\n```bash\n# Basic analysis\nheartmap data/raw/heart_data.h5ad\n\n# Comprehensive analysis with custom output\nheartmap data/raw/heart_data.h5ad \\\n --analysis-type comprehensive \\\n --output-dir results/comprehensive \\\n --config my_config.yaml\n\n# Specific analysis types\nheartmap data/raw/heart_data.h5ad --analysis-type annotation\nheartmap data/raw/heart_data.h5ad --analysis-type communication \nheartmap data/raw/heart_data.h5ad --analysis-type multi-chamber\n\n# Memory-optimized for large datasets\nheartmap data/raw/large_dataset.h5ad \\\n --analysis-type comprehensive \\\n --config config_large.yaml\n```\n\n### 2. Python API\n\n```python\nfrom heartmap import Config, HeartMapModel\nfrom heartmap.pipelines import ComprehensivePipeline\n\n# Load and customize configuration\nconfig = Config.from_yaml('config.yaml')\nconfig.data.max_cells_subset = 50000 # Optimize for your memory\nconfig.data.max_genes_subset = 5000\n\n# Option A: Use full HeartMAP model\nmodel = HeartMapModel(config)\nresults = model.analyze('data/raw/heart_data.h5ad')\n\n# Option B: Use specific pipeline\npipeline = ComprehensivePipeline(config)\nresults = pipeline.run('data/raw/heart_data.h5ad', 'results/')\n\n# Save model for reuse\nmodel.save('models/my_heartmap_model')\n\n# Load and reuse saved model\nloaded_model = HeartMapModel.load('models/my_heartmap_model')\nnew_results = loaded_model.predict(new_data)\n```\n\n### 3. REST API\n\n```bash\n# Start API server\npython scripts/run_api_server.py\n# Server available at http://localhost:8000\n# API docs at http://localhost:8000/docs\n\n# Use the API\ncurl -X POST \"http://localhost:8000/analyze\" \\\n -H \"Content-Type: multipart/form-data\" \\\n -F \"file=@data/raw/heart_data.h5ad\" \\\n -F \"analysis_type=comprehensive\"\n\n# Check available models\ncurl http://localhost:8000/models\n\n# Update configuration\ncurl -X POST \"http://localhost:8000/config\" \\\n -H \"Content-Type: application/json\" \\\n -d '{\"data\": {\"max_cells_subset\": 30000}}'\n```\n\n### 4. Web Interface (Gradio)\n\n```bash\n# Start web interface\npython app.py\n# Access at http://localhost:7860\n\n# Features:\n# - Upload .h5ad files\n# - Select analysis type\n# - Configure memory settings\n# - Download results\n```\n\n### 5. Jupyter Notebooks\n\n```bash\n# Install Jupyter\npip install jupyter\n\n# Start notebook server\njupyter lab\n\n# Open example notebooks:\n# - notebooks/01_basic_analysis.ipynb\n# - notebooks/02_advanced_communication.ipynb\n# - notebooks/03_multi_chamber_analysis.ipynb\n# - notebooks/04_comprehensive_analysis.ipynb\n```\n\n## \u2699\ufe0f Configuration\n\nHeartMAP uses YAML configuration files for easy customization:\n\n```yaml\n# config.yaml or my_config.yaml\ndata:\n min_genes: 200\n min_cells: 3\n max_cells_subset: 50000 # Adjust based on your RAM\n max_genes_subset: 5000 # Reduce for faster analysis\n target_sum: 10000.0\n n_top_genes: 2000\n random_seed: 42\n test_mode: false # Set true for quick testing\n\nanalysis:\n n_components_pca: 50\n n_neighbors: 10\n n_pcs: 40\n resolution: 0.5\n n_marker_genes: 25\n use_leiden: true\n use_liana: true # Cell-cell communication\n\nmodel:\n model_type: \"comprehensive\"\n save_intermediate: true\n use_gpu: false # Set true if GPU available\n batch_size: null\n max_memory_gb: null # Auto-detect memory\n\npaths:\n data_dir: \"data\"\n raw_data_dir: \"data/raw\"\n processed_data_dir: \"data/processed\"\n results_dir: \"results\"\n figures_dir: \"figures\"\n models_dir: \"models\"\n```\n\n### Memory Optimization Guidelines\n\n| System RAM | max_cells_subset | max_genes_subset | Use Case |\n|------------|------------------|------------------|----------|\n| 8GB | 10,000 | 2,000 | Laptop/Desktop |\n| 16GB | 30,000 | 4,000 | Workstation |\n| 32GB | 50,000 | 5,000 | Server |\n| 64GB+ | 100,000+ | 10,000+ | HPC/Cloud |\n\n## \ud83d\udd2c Analysis Components\n\n### 1. Basic Pipeline\n- **Data Preprocessing**: Quality control, normalization, scaling\n- **Cell Type Annotation**: Clustering and cell type identification \n- **Basic Visualization**: UMAP, t-SNE, cluster plots\n- **Quality Metrics**: Cell and gene filtering statistics\n\n### 2. Advanced Communication Analysis\n- **Cell-Cell Communication**: Ligand-receptor interaction analysis\n- **Communication Hubs**: Identification of key signaling cells\n- **Pathway Enrichment**: Cardiac development and disease pathways\n- **Network Analysis**: Communication network topology\n\n### 3. Multi-Chamber Atlas\n- **Chamber-Specific Analysis**: RA, RV, LA, LV specific patterns\n- **Marker Identification**: Chamber-specific biomarkers\n- **Cross-Chamber Correlations**: Inter-chamber relationship analysis\n- **Comparative Analysis**: Chamber-to-chamber differences\n\n### 4. Comprehensive Pipeline\n- **Integrated Analysis**: All components combined\n- **Advanced Visualizations**: Multi-panel figures and dashboards\n- **Comprehensive Reports**: Automated result summaries\n- **Model Persistence**: Save complete analysis state\n\n## \ud83d\ude80 Deployment Guide\n\n### Local Development Setup\n\n#### Prerequisites\n- Python 3.8+ (recommended: Python 3.10)\n- Git\n- Docker (optional, for containerized deployment)\n- 8GB+ RAM (16GB+ recommended for larger datasets)\n\n#### Quick Setup\n\n```bash\n# Clone and setup environment\ngit clone https://github.com/Tumo505/HeartMap.git\ncd HeartMap\n\n# Create virtual environment\npython -m venv heartmap_env\nsource heartmap_env/bin/activate # On Windows: heartmap_env\\Scripts\\activate\n\n# Install dependencies\npip install --upgrade pip\npip install -r requirements-dev.txt\npip install -e .[all]\n\n# Configure the platform\ncp config.yaml my_config.yaml\n# Edit my_config.yaml to match your system resources\n\n# Test installation\npython scripts/validate.py\npython scripts/run_examples.py\n```\n\n### Docker Deployment\n\n```bash\n# Single service\ndocker build -t heartmap .\ndocker run -p 8000:8000 -v $(pwd)/data:/app/data heartmap\n\n# Multi-service with docker-compose\ndocker-compose up\n# Services:\n# - API server: http://localhost:8000 \n# - Gradio interface: http://localhost:7860\n# - Worker processes for batch analysis\n```\n\n### Hugging Face Spaces Deployment\n\n```bash\n# Prepare deployment files\n./scripts/deploy_huggingface.sh\n\n# Upload to your Hugging Face Space:\n# 1. Create new Space at https://huggingface.co/new-space\n# 2. Choose Gradio SDK\n# 3. Upload generated files:\n# - app.py (Gradio interface)\n# - requirements.txt (Dependencies)\n# - src/ (Source code)\n# - config.yaml (Configuration)\n```\n\n### Cloud Platforms\n\n#### AWS Deployment\n```bash\n# ECS deployment\ndocker build -t heartmap .\naws ecr get-login-password --region us-east-1 | docker login --username AWS --password-stdin $ECR_URI\ndocker tag heartmap:latest $ECR_URI/heartmap:latest\ndocker push $ECR_URI/heartmap:latest\n\n# Lambda deployment for serverless\nsam build\nsam deploy --guided\n```\n\n#### Google Cloud Platform\n```bash\n# Cloud Run deployment\ngcloud builds submit --tag gcr.io/$PROJECT_ID/heartmap\ngcloud run deploy --image gcr.io/$PROJECT_ID/heartmap --platform managed\n```\n\n#### Azure\n```bash\n# Container Instances\naz container create --resource-group myResourceGroup \\\n --name heartmap --image myregistry.azurecr.io/heartmap:latest\n```\n\n## \ud83d\udcca Scientific Results\n\n### Chamber Distribution\n- **RA (Right Atrium):** 28.4% of cells\n- **LV (Left Ventricle):** 27.0% of cells \n- **LA (Left Atrium):** 26.4% of cells\n- **RV (Right Ventricle):** 18.2% of cells\n\n### Chamber-Specific Markers\n- **RA:** NPPA, MIR100HG, MYL7, MYL4, PDE4D\n- **RV:** NEAT1, MYH7, FHL2, C15orf41, PCDH7\n- **LA:** NPPA, ELN, MYL7, EBF2, RORA\n- **LV:** CD36, LINC00486, FHL2, RP11-532N4.2, MYH7\n\n### Cross-Chamber Correlations\n- **RV vs LV:** r = 0.985 (highest correlation)\n- **RA vs LA:** r = 0.960\n- **LA vs LV:** r = 0.870 (lowest correlation)\n\n## \ud83e\uddea Testing & Validation\n\n### Run Tests\n\n```bash\n# Full test suite\npython tests/test_heartmap.py\n\n# Validation suite\npython scripts/validate.py\n\n# Example analysis with mock data\npython scripts/demo.py\n```\n\n### Performance Benchmarks\n\n| Dataset Size | Memory Usage | Processing Time | Output |\n|-------------|--------------|-----------------|--------|\n| 10K cells | 2GB RAM | 5 minutes | Complete analysis |\n| 50K cells | 8GB RAM | 15 minutes | Complete analysis |\n| 100K cells | 16GB RAM | 30 minutes | Complete analysis |\n\n## \ud83c\udfaf Use Cases\n\n### Research Applications\n- **Interactive Analysis**: Jupyter notebooks for exploration\n- **Batch Processing**: Command-line analysis of multiple datasets\n- **Pipeline Integration**: Python API for custom workflows\n- **Collaborative Research**: Shared configurations and models\n\n### Production Applications\n- **Web Services**: REST API for applications\n- **Public Access**: Hugging Face Spaces for community use\n- **Microservices**: Containerized deployment in cloud\n- **High-Throughput**: Scalable analysis for large cohorts\n\n### Educational Use\n- **Teaching Platform**: Web interface for students\n- **Reproducible Science**: Containerized environments\n- **Method Comparison**: Multiple analysis approaches\n- **Best Practices**: Clean, documented codebase\n\n## \ud83d\udd12 Data Integrity & Reproducibility\n\n### SHA-256 Checksums\n- **Purpose**: Ensure data file integrity during storage/transfer\n- **Implementation**: Automatic verification before analysis\n- **Usage**: `python utils/sha256_checksum.py verify data/raw data/raw/checksums.txt`\n\n### Fixed Random Seeds\n- **Purpose**: Ensure reproducible results across runs\n- **Implementation**: Fixed seeds in all stochastic processes\n- **Scope**: Random sampling, clustering, mock data generation\n\n### Examples of Reproducible Components\n\n1. **Random Sampling**:\n ```python\n np.random.seed(42)\n cell_indices = np.random.choice(adata.n_obs, size=50000, replace=False)\n ```\n\n2. **Clustering**:\n ```python\n kmeans = KMeans(n_clusters=n_clusters, random_state=42)\n ```\n\n3. **LIANA Analysis**:\n ```python\n li.mt.rank_aggregate.by_sample(\n adata, groupby=cell_type_col, resource_name='consensus',\n n_perms=100, seed=42, verbose=True\n )\n ```\n\n## \ud83d\udd27 Development & Contributing\n\n### Development Setup\n\n```bash\n# Development setup\ngit clone https://github.com/Tumo505/HeartMap.git\ncd HeartMap\n./scripts/setup.sh\nsource heartmap_env/bin/activate\n\n# Install development dependencies\npip install -e .[dev]\n\n# Run tests before committing\npython tests/test_heartmap.py\npython scripts/validate.py\n\n# Code quality checks\nblack src/ tests/ scripts/ # Code formatting\nflake8 src/ --max-line-length=100 # Linting\nmypy src/heartmap --ignore-missing-imports # Type checking\n```\n\n### Adding New Features\n\n1. **New Models**: Inherit from `BaseModel` in `src/heartmap/models/`\n2. **New Pipelines**: Inherit from `BasePipeline` in `src/heartmap/pipelines/`\n3. **API Endpoints**: Add to `src/heartmap/api/rest.py`\n4. **Configuration**: Extend dataclasses in `src/heartmap/config/`\n\n### Testing Guidelines\n\n```python\n# Test structure\ntests/\n\u251c\u2500\u2500 test_config.py # Configuration management\n\u251c\u2500\u2500 test_data.py # Data processing\n\u251c\u2500\u2500 test_models.py # Analysis models\n\u251c\u2500\u2500 test_pipelines.py # Analysis pipelines\n\u2514\u2500\u2500 test_api.py # API interfaces\n```\n\n## \ud83c\udd98 Troubleshooting\n\n### Common Issues\n\n#### Memory Errors\n```bash\n# Reduce dataset size in config\ndata:\n max_cells_subset: 10000\n max_genes_subset: 2000\n```\n\n#### Import Errors\n```bash\n# Reinstall with all dependencies\npip install -e .[all]\n\n# Check Python path\npython -c \"import heartmap; print(heartmap.__file__)\"\n```\n\n#### Data Loading Issues\n```bash\n# Verify data format\npython -c \"import scanpy as sc; print(sc.read_h5ad('data/raw/your_file.h5ad'))\"\n\n# Check file permissions\nls -la data/raw/\n```\n\n#### Performance Issues\n```bash\n# Enable test mode for quick validation\ntest_mode: true # in config.yaml\n\n# Use GPU acceleration (if available)\nmodel:\n use_gpu: true\n```\n\n### Getting Help\n\n1. **Validation**: `python scripts/validate.py`\n2. **Logs**: Check logs in `results/` directory\n3. **Test Mode**: Set `test_mode: true` in configuration\n4. **Mock Data**: `python scripts/demo.py` for testing\n5. **Documentation**: Comprehensive docstrings in source code\n\n## \ud83d\udccb Requirements\n\n### System Requirements\n- **Python**: 3.8+ (recommended: 3.10)\n- **Memory**: 8GB+ recommended (configurable)\n- **Storage**: 5GB+ for data and results\n- **OS**: Linux, macOS, Windows\n\n### Dependencies\n- **Core**: scanpy, pandas, numpy, scipy, scikit-learn\n- **Visualization**: matplotlib, seaborn, plotly\n- **Communication**: liana, cellphonedb (optional)\n- **API**: fastapi, uvicorn (optional)\n- **Web**: gradio (optional)\n\n## \ud83c\udfaf Clinical Applications\n\n- **Personalized Medicine**: Chamber-specific treatment strategies\n- **Drug Development**: Chamber-specific therapeutic targets\n- **Disease Understanding**: Chamber-specific disease mechanisms\n- **Biomarker Discovery**: Chamber and communication-specific markers\n\n## \ud83e\udd1d Contributing\n\n1. Fork the repository\n2. Create a feature branch: `git checkout -b feature-name`\n3. Install development dependencies: `pip install -e .[dev]`\n4. Run tests: `python tests/test_heartmap.py`\n5. Submit a pull request\n\n## \ud83d\udcc4 License\n\nThis project is licensed under the Apache License 2.0 - see the [LICENSE](LICENSE) file for details.\n\n## \ud83d\udcd6 Citation\n\n```bibtex\n@software{heartmap2025,\n title={HeartMAP: A Multi-Chamber Spatial Framework for Cardiac Cell-Cell Communication},\n author={Kgabeng, Tumo and Wang, Lulu and Ngwangwa, Harry and Pandelani, Thanyani},\n year={2024},\n url={https://github.com/Tumo505/HeartMap},\n version={1.0.0},\n doi={10.5281/zenodo.16745118}\n}\n```\n\n## \ud83c\udd98 Support\n\n- **Issues**: [GitHub Issues](https://github.com/Tumo505/HeartMap/issues)\n- **Discussions**: [GitHub Discussions](https://github.com/Tumo505/HeartMap/discussions)\n- **Email**: 28346416@mylife.unisa.ac.za\n\n## \ud83c\udf89 Acknowledgments\n\n- Department of Mechanical, Bioresources and Biomedical Engineering, University of South Africa\n- Department of Engineering, Reykjavik University\n- Single Cell Portal (SCP498) for providing the heart dataset\n- The open-source scientific Python community\n\n---\n\n**\ud83c\udf89 HeartMAP is now production-ready and available for research, deployment, and collaboration!**\n\nWhether you're a researcher exploring cardiac biology, a developer building applications, or an educator teaching single-cell analysis, HeartMAP provides the tools and flexibility you need.\n",
"bugtrack_url": null,
"license": null,
"summary": "Heart Multi-chamber Analysis Platform for single-cell RNA-seq",
"version": "1.1.1",
"project_urls": {
"Documentation": "https://github.com/Tumo505/HeartMap/wiki",
"Homepage": "https://github.com/Tumo505/HeartMap",
"Source": "https://github.com/Tumo505/HeartMap",
"Tracker": "https://github.com/Tumo505/HeartMap/issues"
},
"split_keywords": [
"single-cell",
" rna-seq",
" heart",
" cell-communication",
" bioinformatics",
" spatial-transcriptomics"
],
"urls": [
{
"comment_text": null,
"digests": {
"blake2b_256": "d5a22d951e5a7852263fad8a6b2a20359069a907e92aa818f9c850b4fd2e5dd4",
"md5": "20fff3854fa489680319bcf9e4ead274",
"sha256": "decc669a0d6b3d5a148f435e4e3ffb46649cc92b9cad72a8279543de5aa876bf"
},
"downloads": -1,
"filename": "heartmap-1.1.1-py3-none-any.whl",
"has_sig": false,
"md5_digest": "20fff3854fa489680319bcf9e4ead274",
"packagetype": "bdist_wheel",
"python_version": "py3",
"requires_python": ">=3.8",
"size": 28104,
"upload_time": "2025-08-06T19:39:22",
"upload_time_iso_8601": "2025-08-06T19:39:22.614188Z",
"url": "https://files.pythonhosted.org/packages/d5/a2/2d951e5a7852263fad8a6b2a20359069a907e92aa818f9c850b4fd2e5dd4/heartmap-1.1.1-py3-none-any.whl",
"yanked": false,
"yanked_reason": null
},
{
"comment_text": null,
"digests": {
"blake2b_256": "778e9341cedd9261c2e09f07b65225efab3f518b7491e0b7f1fdde80836923a2",
"md5": "7e2da6dec4fa9566f54b028ced0f97e0",
"sha256": "b405fc8b372d73193094534333436dfe78a1f9e36d046af0d67a9f5616a21198"
},
"downloads": -1,
"filename": "heartmap-1.1.1.tar.gz",
"has_sig": false,
"md5_digest": "7e2da6dec4fa9566f54b028ced0f97e0",
"packagetype": "sdist",
"python_version": "source",
"requires_python": ">=3.8",
"size": 35756,
"upload_time": "2025-08-06T19:39:24",
"upload_time_iso_8601": "2025-08-06T19:39:24.340766Z",
"url": "https://files.pythonhosted.org/packages/77/8e/9341cedd9261c2e09f07b65225efab3f518b7491e0b7f1fdde80836923a2/heartmap-1.1.1.tar.gz",
"yanked": false,
"yanked_reason": null
}
],
"upload_time": "2025-08-06 19:39:24",
"github": true,
"gitlab": false,
"bitbucket": false,
"codeberg": false,
"github_user": "Tumo505",
"github_project": "HeartMap",
"travis_ci": false,
"coveralls": false,
"github_actions": true,
"requirements": [
{
"name": "scanpy",
"specs": [
[
">=",
"1.9.0"
]
]
},
{
"name": "pandas",
"specs": [
[
">=",
"1.5.0"
]
]
},
{
"name": "numpy",
"specs": [
[
">=",
"1.21.0"
]
]
},
{
"name": "matplotlib",
"specs": [
[
">=",
"3.5.0"
]
]
},
{
"name": "seaborn",
"specs": [
[
">=",
"0.11.0"
]
]
},
{
"name": "anndata",
"specs": [
[
">=",
"0.8.0"
]
]
},
{
"name": "cellphonedb",
"specs": [
[
">=",
"3.0.0"
]
]
},
{
"name": "liana",
"specs": [
[
">=",
"0.1.0"
]
]
},
{
"name": "omnipath",
"specs": [
[
">=",
"1.0.0"
]
]
},
{
"name": "plotly",
"specs": [
[
">=",
"5.0.0"
]
]
},
{
"name": "networkx",
"specs": [
[
">=",
"2.8.0"
]
]
},
{
"name": "scipy",
"specs": [
[
">=",
"1.9.0"
]
]
},
{
"name": "scikit-learn",
"specs": [
[
">=",
"1.1.0"
]
]
},
{
"name": "notebook",
"specs": []
},
{
"name": "jupyterlab",
"specs": []
},
{
"name": "ipython",
"specs": []
},
{
"name": "ipywidgets",
"specs": []
},
{
"name": "tqdm",
"specs": []
},
{
"name": "statsmodels",
"specs": []
}
],
"lcname": "heartmap"
}
JSON
