Tooluniverse Single Cell

This handles scanpy/anndata workflows for single-cell RNA-seq, from h5ad loading through clustering and differential expression. The skill emphasizes checking for pre-computed results first (executed notebooks, existing CSVs) before rerunning analysis, which matters because reanalysis from raw data produces different numbers and burns through turns. It includes statistical rigor reminders (normalization, multiple testing correction), a decision tree for when to use scanpy DE versus pseudo-bulk DESeq2, and integration with ToolUniverse for searching datasets in CELLxGENE, GEO, and SRA. The workflow coverage is comprehensive: QC, PCA, UMAP, Leiden clustering, marker identification, batch correction with Harmony, and correlation analysis. Good for anyone doing routine scRNA-seq work who wants structured guidance without reinventing the wheel.