Integrate and analyze single-cell genomics data with scvi-tools pipelines.
npx skills add https://github.com/ilove323/comlan-skills --skill scvi-tools-ilove323
Please help me install this Agent Skill. Skill: scvi-tools Source: https://github.com/ilove323/comlan-skills/tree/main/bio-research/skills/scvi-tools Command: npx skills add https://github.com/ilove323/comlan-skills --skill scvi-tools-ilove323
Integrates and analyzes diverse single-cell genomics datasets using deep generative models so researchers can perform robust batch correction, label transfer, multi-modal integration, and downstream analyses without bespoke model engineering.
Run the prepared AnnData through the scvi-tools pipeline to train scVI or scANVI (if labels exist), extract the latent embedding, and generate clustered results for downstream interpretation.
High-intent search queries and answers about installing and using this skill.
Batch correction on scRNA-seq data uses deep generative models like scVI to integrate cell-by-gene matrices, requiring raw integer counts in AnnData format and setup_anndata conventions to extract latent embeddings for clustering.
Yes, label transfer from a reference to a new single-cell query uses scANVI and scArches to map and annotate new datasets, requiring pre-trained models and raw integer count inputs in AnnData or MuData formats.
Multi-modal integration of CITE-seq and scATAC-seq data uses totalVI and MultiVI to jointly analyze RNA and protein or RNA and ATAC matrices, requiring MuData formats for multi-modal setup and deep generative model training.
Differential expression after single-cell dataset integration requires extracting latent embeddings from a trained scVI or scANVI model, then using downstream clustering tools to perform differential testing on the corrected cell-by-gene matrices.
scvi-tools single-cell analysis requires raw integer count inputs in AnnData or MuData formats, not normalized data, ensuring the deep generative models correctly process cell-by-gene matrices for integration and denoising.
For spatial transcriptomics and velocity analysis, DestVI and veloVI provide specialized deep generative workflows, requiring appropriate setup_anndata calls and scientific Python packages like scvelo to extract biological embeddings.
dralkhAnalyze single-cell omics data with probabilistic deep generative models.
KetomihineAccelerate single-cell RNA-seq preprocessing and clustering on AnnData with RAPIDS.
jaechang-hitsIntegrate RNA, ATAC, and protein modalities with WNN graphs in MuData.
jackspaceModel single-cell omics data with scvi-tools for batch-corrected analysis.
