FedscGen: privacy-aware federated batch effect correction of single-cell RNA sequencing data: v1.0.0

FedscGen v1.0.0 – Federated Batch Effect Correction for scRNA-seq

This release contains the reproducible version of FedscGen, a privacy-preserving federated learning tool for batch effect correction in single-cell RNA sequencing (scRNA-seq) data.

Key features:

Centralized implementation of scGen.

Federated learning support with SMPC using CrypTen to prevent raw data exposure.

Two main workflows: training and correction.

Evaluation on multiple datasets with standardized benchmarking metrics.

License: Apache 2.0 and BSD 3-Clause (see LICENSE files).

Please cite the associated manuscript and Zenodo DOI when using this release in scientific publications.

Full Changelog: https://github.com/Mohammad-Bakhtiari/FedscGPT/commits/v1.0.0