SpaMeanImpute 0.1.0

Spatial Transcriptomics Imputation Tool (SpaMean-Impute)

SpaMeanImpute

Spatial Transcriptomics Imputation Tool (SpaMean-Impute)

SpaMeanImpute is a Python package for imputing missing gene expression values in spatial transcriptomics datasets.
It leverages spatial neighborhood information to improve downstream clustering and analysis.

---

✨ Features

• Spatially-aware imputation using k-nearest neighbors in spatial coordinates.
• Highly variable gene selection with scanpy.
• Evaluation pipeline for imputation and clustering performance.
• Command-line interface (CLI) for easy integration into workflows.
• Compatible with .h5ad AnnData files.

---

📦 Installation

You can install SpaMeanImpute from PyPI:

pip install SpaMeanImpute

Or install directly from the GitHub repository:

git clone https://github.com/FahimHafiz/SpaMean-Impute/tree/main/SpaMeanImpute
cd SpaMeanImpute
pip install -e .

🚀 Usage

After installation, you can run:

spamean-impute input_file.h5ad \
    -k 9 \
    --threshold 0.1 \
    --n_top 5000 \
    --output_file imputed_output.h5ad

Arguments:

input_file — Path to input .h5ad file.

-k — Number of spatial neighbors (default: 9).

--threshold — Drop threshold for zero imputation (default: 0.1).

--n_top — Number of highly variable genes (default: 5000, use 'all' to skip filtering).

--output_file — Path to save the imputed .h5ad file.

🐍 Python API

import spa_mean_impute
from spa_mean_impute.imputer import SpaMeanImpute

imputer = SpaMeanImpute(k=9, threshold=0.1, n_top=5000)
results = imputer.run("input_file.h5ad", output_file="imputed_output.h5ad")

print("Results:", results)

📁 Project Structure

spa_mean_impute/ init.py imputer.py cli.py utils.py tests/ test_imputer.py setup.py pyproject.toml README.md LICENSE.txt

✅ Running Tests

python -m unittest discover tests

📄 License

This project is licensed under the MIT License — see the LICENSE.txt file for details. For any problem, feel free to contact [e-mail] or create an issue!