Perform end-to-end single-cell RNA-seq analysis with Scanpy.
npx skills add https://github.com/Victory-Hugo/S2-Agent-Skill --skill scanpy-victory-hugo
Please help me install this Agent Skill. Skill: scanpy Source: https://github.com/Victory-Hugo/S2-Agent-Skill/tree/main/skills/genomics/scanpy Command: npx skills add https://github.com/Victory-Hugo/S2-Agent-Skill --skill scanpy-victory-hugo
This Skill helps researchers perform end-to-end single-cell RNA-seq analysis using Scanpy, providing a reproducible workflow from raw data to insights.
Example workflow: adata = sc.read_h5ad('path/to/data.h5ad') sc.pp.filter_cells(adata, min_genes=200) sc.pp.normalize_total(adata, target_sum=1e4) sc.tl.pca(adata, svd_solver='arpack') sc.tl.umap(adata) sc.tl.leiden(adata, resolution=0.5)
High-intent search queries and answers about installing and using this skill.
To analyze a 10X h5ad dataset, read the file, filter cells with min_genes, normalize total counts, compute PCA, generate a UMAP embedding, and apply Leiden clustering. This pipeline yields clustered cell populations for annotation.
To analyze a 10X h5ad dataset, read the file, filter cells with min_genes, normalize total counts, compute PCA, generate a UMAP embedding, and apply Leiden clustering. This pipeline yields clustered cell populations for annotation.
End-to-end single-cell RNA-seq analysis involves quality control, normalization, HVG selection, dimensionality reduction, clustering, and marker gene identification. This workflow processes raw 10X, h5ad, or CSV data to identify cell types and infer trajectories.
Yes, the Scanpy workflow relies on the Python ecosystem and uses AnnData structures to store single-cell data. It builds neighbor graphs and applies Leiden clustering to group cells based on highly variable gene expression.
Filter cells by setting minimum gene counts, then apply total normalization to scale expressions. Select highly variable genes to capture meaningful biological variation while reducing noise before performing dimensionality reduction.
Leiden clustering and UMAP dimensionality reduction effectively group similar cells and project high-dimensional single-cell data into 2D space. This reveals distinct cell populations and transcriptomic relationships for downstream annotation.
zongtingweiPreprocess single-cell RNA-seq data into analysis-ready AnnData objects.
Hung-3008Analyze single-cell RNA-seq data to produce QC metrics, embeddings, clusters, and marker genes.
Estrella-231Run scanpy workflows on AnnData objects for single-cell RNA-seq preprocessing and exploratory analysis.
yf8578Automates single-cell RNA-seq workflows including QC, normalization, clustering, and annotation using scanpy Python package.
