The Single-cell RNA sequencing pipeline is an extensible toolkit for analyzing single-cell gene expression data using the Scanpy framework. It includes methods for preprocessing, visualization, clustering, and differential expression testing. Its Python-based implementation efficiently handles datasets containing more than one million cells. We introduce ANNDATA, a generic class for managing annotated data matrices. The pipeline features: 1. Regression of confounding variables, normalization, and identification of highly variable genes. 2. t-SNE and graph-based (Fruchterman–Reingold) visualizations that show cell-type annotations derived from comparisons with bulk expression data. 3. Clustering of cells and visualization using the Louvain algorithm, with support for other clustering algorithms as well. 4. Ranking differentially expressed genes in clusters to identify marker genes corresponding to bulk expression labels.