BayVel: A Bayesian Framework for RNA Velocity Estimation in Single-Cell Transcriptomics

2025-05-06

AI Summary

Existing RNA velocity methods (e.g., scVelo) rely heavily on heuristic preprocessing, suffer from parameter unidentifiability, and lack principled uncertainty quantification—undermining their statistical reliability. To address these limitations, we propose the first Bayesian hierarchical model that directly operates on raw UMI counts, enabling end-to-end probabilistic modeling within a fully Bayesian inference framework. Our approach obviates the need for normalization or gene filtering, inherently ensures parameter identifiability, and provides comprehensive posterior uncertainty estimates. We perform rigorous posterior inference via Markov chain Monte Carlo (MCMC). On synthetic data, our method accurately recovers ground-truth kinetic parameters. Applied to real pancreatic epithelial scRNA-seq data, it yields biologically more robust conclusions that diverge from those of scVelo—demonstrating both statistical rigor and biological interpretability. This work establishes a foundation for statistically sound, interpretable RNA velocity analysis.

Technology Category

• Reasoning under Uncertainty: Relational Probabilistic Models
• Machine Learning: Bayesian Learning
• Intelligent Robots: State Estimation

Application Category

• User Modeling, Personalization and Recommendation: Explainable and interpretable methods for personalization
• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs
• Web Mining and Content Analysis: Models for Web evolution

Abstract

RNA velocity is a model of gene expression dynamics designed to analyze single-cell RNA sequencing (scRNA-seq) data, and it has recently gained significant attention. However, despite its popularity, the model has raised several concerns, primarily related to three issues: its heavy dependence on data preprocessing, the need for post-processing of the results, and the limitations of the underlying statistical methodology. Current approaches, such as scVelo, suffer from notable statistical shortcomings. These include identifiability problems, reliance on heuristic preprocessing steps, and the absence of uncertainty quantification. To address these limitations, we propose BayVel, a Bayesian hierarchical model that directly models raw count data. BayVel resolves identifiability issues and provides posterior distributions for all parameters, including the RNA velocities themselves, without the need for any post processing. We evaluate BayVel's performance using simulated datasets. While scVelo fails to accurately reconstruct parameters, even when data are simulated directly from the model assumptions, BayVel demonstrates strong accuracy and robustness. This highlights BayVel as a statistically rigorous and reliable framework for studying transcriptional dynamics in the context of RNA velocity modeling. When applied to a real dataset of pancreatic epithelial cells previously analyzed with scVelo, BayVel does not replicate their findings, which appears to be strongly influenced by the postprocessing, supporting concerns raised in other studies about the reliability of scVelo.

Problem

• Addresses RNA velocity model's data preprocessing dependence
• Eliminates need for post-processing and uncertainty quantification
• Resolves identifiability issues in current RNA velocity methods

Innovation

• Bayesian hierarchical model for raw count data
• Resolves identifiability issues with posterior distributions
• No post-processing needed for RNA velocity estimation