SecActPy¶
Secreted Protein Activity Inference using Ridge Regression
Python implementation of SecAct for inferring secreted protein activities from gene expression data.
Key Features¶
- SecAct Compatible: Matches R SecAct (with RidgeFast/RidgeCuda accelerators) on the same platform (
rng_method='srand') - GPU Acceleration: Optional CuPy backend for large-scale analysis
- Million-Sample Scale: Batch processing with streaming output for massive datasets
- Built-in Signatures: Includes SecAct and CytoSig signature matrices
- Multi-Platform Support: Bulk RNA-seq, scRNA-seq, and Spatial Transcriptomics (Visium, CosMx)
- Smart Caching: Optional permutation table caching for faster repeated analyses
- Sparse-Aware: Automatic memory-efficient processing for sparse single-cell data
Getting Started¶
- Installation — install SecActPy from PyPI or GitHub
- Quick Start — run your first analysis in minutes
User Guide¶
- Batch Processing — handle large datasets with memory-efficient batching and streaming H5AD for >5M cells
- GPU Acceleration — speed up computation with CuPy
- Reproducibility — RNG backends for cross-platform reproducibility
- Docker — run SecActPy in Docker containers
- CLI Reference — command-line interface documentation
API Reference¶
- API Reference — full function signatures and parameters
- Advanced API — low-level
ridge()/ridge_batch()usage
Citation¶
If you use SecActPy in your research, please cite:
Beibei Ru, Lanqi Gong, Emily Yang, Seongyong Park, George Zaki, Kenneth Aldape, Lalage Wakefield, Peng Jiang. Inference of secreted protein activities in intercellular communication. Nature Methods, 2026 (In press)
Related Projects¶
- SecAct — Original R implementation (R-native)
- RidgeFast — Optional CPU accelerator (R + C, cross-platform)
- RidgeCuda — Optional GPU accelerator (R + CUDA, Linux only)
- SpaCET — Spatial transcriptomics cell type analysis
- CytoSig — Cytokine signaling inference
License¶
MIT License — see LICENSE for details.