Scalable identification of lineage-specific gene regulatory networks from metacells with NetID

Abstract

The identification of gene regulatory networks (GRN) governing distinct cell fates in multilineage cellular differentiation systems is of critical importance for understanding cell fate decision. Single-cell RNA-sequencing (scRNA-seq) provides a powerful tool for the quantification of gene-level co-variation across the cell state manifold. However, accurate GRN reconstruction is hampered by the sparsity of scRNA-seq data introducing substantial technical noise. Moreover, the high dimensionality of typical scRNA-seq datasets limits the scalability of available approaches. To overcome these challenges, and to facilitate the inference of lineage-specific GRNs with directed regulator-target relations, we introduce NetID. This approach optimizes coverage of the cell state manifold by homogenous metacells and avoids spurious gene-gene correlations observed with available imputation methods. Benchmarking demonstrates superior performance of NetID compared to imputation-based GRN inference. By incorporating cell fate probability information, NetID facilitates prediction of lineage-specific GRNs and recovers known network motifs centered around lineage-determining transcription factors governing bone marrow hematopoiesis, making it a powerful toolkit for deciphering the gene regulatory control of cellular differentiation from large-scale single-cell transcriptome data.