SCENIC (Single Cell rEgulatory Network Inference and Clustering) is a computational resource designed to simultaneously reconstruct gene regulatory networks (GRNs) and identify stable cell states from single-cell RNA-seq data. The method combines co-expression network inference, transcription factor motif analysis, and network-based prediction of cellular subpopulations. SCENIC outperforms existing approaches in cell clustering and transcription factor identification, demonstrating robustness to batch effects and technical biases. Applied to mouse and human brain data, SCENIC identifies specific combinations of transcription factors, target genes, enhancers, and cell types. In melanoma, SCENIC maps a proliferative state driven by MITF and STAT, and an invasive state governed by NFATC2 and NFIB. SCENIC is available as an R workflow using three new R/Bioconductor packages: GENIE3, RcisTarget, and AUCell, with a scalable alternative, GRNboost, for large datasets. SCENIC provides a network-centric approach to analyzing single-cell RNA-seq data, allowing for the simultaneous tracing of genomic regulatory programs and the mapping of cellular identities.SCENIC (Single Cell rEgulatory Network Inference and Clustering) is a computational resource designed to simultaneously reconstruct gene regulatory networks (GRNs) and identify stable cell states from single-cell RNA-seq data. The method combines co-expression network inference, transcription factor motif analysis, and network-based prediction of cellular subpopulations. SCENIC outperforms existing approaches in cell clustering and transcription factor identification, demonstrating robustness to batch effects and technical biases. Applied to mouse and human brain data, SCENIC identifies specific combinations of transcription factors, target genes, enhancers, and cell types. In melanoma, SCENIC maps a proliferative state driven by MITF and STAT, and an invasive state governed by NFATC2 and NFIB. SCENIC is available as an R workflow using three new R/Bioconductor packages: GENIE3, RcisTarget, and AUCell, with a scalable alternative, GRNboost, for large datasets. SCENIC provides a network-centric approach to analyzing single-cell RNA-seq data, allowing for the simultaneous tracing of genomic regulatory programs and the mapping of cellular identities.