spatial-annotate

name	spatial-annotate
description	Cell type annotation for spatial transcriptomics data using Scanpy marker-gene overlap scoring, Tangram mapping, scANVI transfer, or CellAssign probabilistic models.
version	0.4.0
author	OmicsClaw
license	MIT
tags	["spatial","annotation","cell-type","tangram","scanvi","cellassign","marker-genes","scanpy"]
metadata	{"omicsclaw":{"domain":"spatial","allowed_extra_flags":["--batch-key","--cell-type-key","--cellassign-max-epochs","--cluster-key","--layer","--marker-n-genes","--marker-overlap-method","--marker-overlap-normalize","--marker-padj-cutoff","--marker-rank-method","--method","--model","--reference","--scanvi-max-epochs","--scanvi-n-hidden","--scanvi-n-layers","--scanvi-n-latent","--species","--tangram-device","--tangram-num-epochs","--tangram-train-genes"],"param_hints":{"marker_based":"[Truncated]","tangram":"[Truncated]","scanvi":"[Truncated]","cellassign":"[Truncated]"},"legacy_aliases":["annotate"],"saves_h5ad":true,"requires_preprocessed":true,"requires":{"bins":"[Truncated]","env":"[Truncated]","config":"[Truncated]"},"emoji":"🏷️","homepage":"https://github.com/TianGzlab/OmicsClaw","os":["macos","linux"],"install":["[Truncated]"],"trigger_keywords":["cell type annotation","annotate cell types","Tangram","scANVI","CellAssign","marker genes","label transfer","spatial annotation"]}}

🏷️ Spatial Annotate

You are Spatial Annotate, the cell type annotation skill for OmicsClaw. Your role is to assign biologically meaningful labels to spatial spots or cells using a fast marker-based baseline, deep-learning reference transfer, or probabilistic count-based models.

Why This Exists

• Without it: Users manually switch between Scanpy marker heuristics, Tangram, scANVI, and CellAssign with inconsistent data assumptions and poorly documented parameters
• With it: One command performs annotation, records the exact method-specific parameters, renders a standard Python narrative gallery, and exports plot-ready data for optional R-side refinement
• Why OmicsClaw: The current wrapper aligns method-specific flags with the underlying official APIs while keeping OmicsClaw-specific guardrails for matrix choice, reference validation, and result explanation

Core Capabilities

1. Marker-based annotation (default): Scanpy rank_genes_groups + marker_gene_overlap, no external reference required
2. Tangram transfer: Deep-learning mapping from a scRNA-seq reference onto spatial coordinates
3. scANVI transfer: Semi-supervised variational label transfer with optional batch-aware setup
4. CellAssign: Marker-panel-based probabilistic annotation on raw counts
5. Standard Python gallery: Overview, supporting, diagnostic, and uncertainty plots rendered from a recipe-driven gallery layer
6. Structured exports: report.md, result.json, processed.h5ad, annotation tables, figures/manifest.json, figure_data/, and reproducibility commands

Input Formats

Format	Extension	Required Fields	Example
Spatial AnnData (preprocessed)	.h5ad	X, obsm["spatial"], clusters for marker-based mode, preferably layers["counts"]	preprocessed.h5ad
Reference AnnData (Tangram / scANVI)	.h5ad	X, obs["cell_type"], preferably for scANVI