VeloEV: Evaluation and Visualization for Benchmarking RNA Velocity Methods

VeloEV is a comprehensive Python package designed for post processing, evaluating, and visualizing RNA velocity methods. It streamlines the workflow into three core modules: post-processing, evaluation, and visualization.

🚀 Features

• Post-processing: Standardizes outputs from diverse RNA velocity methods into a unified format for consistent downstream analysis.
• Evaluation: Provides comprehensive metrics to assess RNA velocity and cell-specific latent time, including Directional Consistency (CBDir, ICVCoh), Temporal Precision (CTO, TSC), and Negative Control Robustness (STS, NTE).
• Visualization: Generates figures for both specific task analysis and aggregated global benchmark summaries.

📦 Installation

You can install veloev by cloning the repository and installing it via pip.

git clone https://github.com/edawu11/VeloEV.git
cd VeloEV
pip install .

📚 Documentation & Tutorials

👉 Detailed documentation and step-by-step tutorials are available to help you get started. For a quick start, you can download the demo datasets via the link.

📖 Reference

If you use VeloEV in your research, please cite our paper:

Yida Wu, Chuihan Kong, Xu Liao, Zhixiang Lin, Xiaobo Sun, Jin Liu. Comprehensive benchmarking of RNA velocity methods across single-cell datasets. Preprint. 2025.

📄 License

This project is licensed under the MIT License - see the LICENSE file for details.