计划执行与检查节点
executing-plans
按既定实施计划完成工作,保持过程检查和反馈。
multimodal-and-spatial【效率与协作】Route scvi-tools tasks involving multimodal, ATAC, spatial, methylation, velocity, perturbation, contrastive, and external specialized model families.
独立 GitHub 快照 · 自动分类 · 以原作者文档为准
Use this sub-skill when a user needs scvi-tools guidance for non-basic single-cell models beyond core RNA-only workflows: CITE-seq, RNA+protein, RNA+ATAC, ATAC-only, methylation, spatial mapping/deconvolution, velocity, perturbation/contrastive analysis, or external specialized models.
scvi.model.TOTALVI; for semi-supervised labels with protein, use scvi.external.TOTALANVI.scvi.model.MULTIVI on MuData; for ATAC-only use scvi.model.PEAKVI.scvi.external.Tangram, scvi.external.RNAStereoscope, and scvi.external.SpatialStereoscope; verify reference labels before choosing Stereoscope.scvi.external.METHYLVI or scvi.external.METHYLANVI depending on whether labels are needed.scvi.external.VELOVI, MRVI, RESOLVI, ContrastiveVI, SysVI, DIAGVI, or Decipher only after matching their required data keys.CYTOVI, SCAR, SCBASSET, GIMVI, or Tangram when their input assumptions match; expect optional extras for some workflows.AnnData registration, setup_anndata, count layers, batches, labels, covariates, and MuData basics, route to the data-setup sub-skill first.SCVI, SCANVI, LinearSCVI, AUTOZI, or SOLO, route to the core-models sub-skill.