scInTime: A Computational Method Leveraging Single-Cell Trajectory and Gene Regulatory Networks to Identify Master Regulators of Cellular Differentiation

Trajectory inference (TI) or pseudotime analysis has dramatically extended the analytical framework of single-cell RNA-seq data, allowing regulatory genes contributing to cell differentiation and those involved in various dynamic cellular processes to be identified. However, most TI analysis procedures deal with individual genes independently while overlooking the regulatory relations between genes. Integrating information from gene regulatory networks (GRNs) at different pseudotime points may lead to more interpretable TI results. To this end, we introduce scInTime-an unsupervised machine learning framework coupling inferred trajectory with single-cell GRNs (scGRNs) to identify master regulatory genes. We validated the performance of our method by analyzing multiple scRNA-seq data sets. In each of the cases, top-ranking genes predicted by scInTime supported their functional relevance with corresponding signaling pathways, in line with the results of available functional studies. Overall results demonstrated that scInTime is a powerful tool to exploit pseudotime-series scGRNs, allowing for a clear interpretation of TI results toward more significant biological insights.

Automated summary

Trajectory inference and pseudotime analysis are important methods for analyzing single-cell RNA-seq data, which can identify regulatory genes involved in cell differentiation and dynamic cellular processes. Existing methods treat genes independently and overlook regulatory relations between genes. We introduce scInTime, an unsupervised machine learning framework that combines inferred trajectories with gene regulatory networks to identify master regulatory genes. The performance of our method is validated using multiple scRNA-seq datasets.