Standardize single-cell RNA-seq workflows with Scanpy for QC, clustering, and annotation.
npx skills add https://github.com/tassiovale/claude-code-kit --skill scanpy-tassiovale
Please help me install this Agent Skill. Skill: scanpy Source: https://github.com/tassiovale/claude-code-kit/tree/main/skills/scanpy Command: npx skills add https://github.com/tassiovale/claude-code-kit --skill scanpy-tassiovale
This Skill addresses the complex and time-consuming process of single-cell RNA-seq analysis by providing a standardized, scalable toolkit for various stages of the analysis.
To analyze a single-cell RNA-seq dataset using Scanpy, first load the data into an AnnData object and then run the following commands:
sc.read_h5ad('path/to/data.h5ad')
sc.pp.calculate_qc_metrics(adata)
sc.pp.filter_cells(adata, min_genes=200)
sc.pp.filter_genes(adata, min_cells=3)
sc.pp.normalize_total(adata, target_sum=1e4)
sc.pp.log1p(adata)
sc.tl.pca(adata)
sc.tl.umap(adata)
sc.tl.leiden(adata)
sc.tl.rank_genes_groups(adata, 'leiden')
sc.tl.dpt(adata)
High-intent search queries and answers about installing and using this skill.
To automate single-cell RNA-seq analysis, you can standardize the workflow using Scanpy to handle quality control, normalization, dimensionality reduction, and Leiden clustering. Load your data into an AnnData object to run the complete processing pipeline.
The best way to identify marker genes and annotate cell types in scRNA-seq data is using automated ranking functions on clustered data. Scanpy calculates gene expression ranks for Leiden clusters, enabling accurate cell type annotation based on those markers.
Yes, you need Python 3.12+ and AnnData to perform dimensionality reduction on single-cell RNA-seq datasets. These dependencies are required to load your data into an AnnData object and apply PCA, UMAP, and t-SNE for visualization.
Yes, you can use UMAP and t-SNE for visualization in a single-cell RNA-seq analysis pipeline. Scanpy applies these dimensionality reduction techniques alongside PCA to prepare your normalized data for accurate Leiden clustering.
Quality control filtering for single-cell RNA-seq datasets works by removing low-quality cells and genes based on calculated metrics. Scanpy filters cells by minimum gene counts and genes by minimum cell counts to ensure experimental consistency.
Limitations of using Scanpy for large-scale single-cell RNA-seq analysis include its strict dependency on Python 3.12+, AnnData, and SciPy. Processing extremely large datasets requires sufficient memory to handle the NumPy and Pandas array operations.
KetomihineAutomate BANKSY spatial transcriptomics analysis for multisample clustering and visualization.
PharMolixProcess single-cell transcriptomes into AnnData objects with Scanpy.
Estrella-231Run scanpy workflows on AnnData objects for single-cell RNA-seq preprocessing and exploratory analysis.
frumu-aiPerform deep learning-based single-cell RNA sequencing analysis with scvi-tools.