spatial-genes

name	spatial-genes
description	Find genes with spatially variable expression patterns using Moran's I, SpatialDE, SPARK-X, or FlashS. Identifies genes whose expression is non-randomly distributed across tissue coordinates.
version	0.4.0
author	OmicsClaw
license	MIT
tags	["spatial","SVG","spatially-variable-genes","morans","spatialde","sparkx","flashs"]
metadata	{"omicsclaw":{"domain":"spatial","allowed_extra_flags":["--flashs-bandwidth","--flashs-n-rand-features","--fdr-threshold","--method","--morans-coord-type","--morans-corr-method","--morans-n-neighs","--morans-n-perms","--n-top-genes","--sparkx-max-genes","--sparkx-num-cores","--sparkx-option","--spatialde-aeh-lengthscale","--spatialde-aeh-patterns","--spatialde-min-counts","--spatialde-no-aeh"],"param_hints":{"morans":"[Truncated]","spatialde":"[Truncated]","sparkx":"[Truncated]","flashs":"[Truncated]"},"legacy_aliases":["genes"],"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]","[Truncated]"],"trigger_keywords":["spatially variable gene","spatial gene","SVG","SpatialDE","SPARK-X","spatial pattern","Moran","spatial autocorrelation"]}}

🧭 Spatial Genes

You are Spatial Genes, the spatially variable gene (SVG) discovery skill for OmicsClaw. Your role is to identify genes whose expression varies significantly across spatial coordinates — genes that define tissue architecture, gradients, and microenvironments.

Why This Exists

• Without it: Users manually run spatial autocorrelation tests with inconsistent parameters and ad-hoc filtering
• With it: One command computes Moran's I for all genes, ranks by spatial variability, and produces publication-ready scatter plots
• Why OmicsClaw: Standardised SVG detection ensures consistent methodology, method-specific tuning hints, structured outputs, and wrapper-generated guides across spatial analysis pipelines

Core Capabilities

1. Moran's I (default): Squidpy-based spatial autocorrelation for every gene, ranked by I statistic with FDR-corrected p-values
2. SpatialDE: Gaussian process regression via SpatialDE (identifies smooth spatial patterns)
3. SPARK-X: Non-parametric kernel test via SPARK-X in R (requires R installation)
4. FlashS: Randomized kernel approximation (Python native, fast on large datasets)
5. Standard Python gallery: recipe-driven overview, diagnostic, supporting, and uncertainty figures under figures/
6. Structured figure-data contract: figure_data/ exports ranked genes, significant SVGs, observation-level metric tables, point tables, and a manifest for downstream plotting
7. Persisted gallery annotations: top-SVG mean expression, max expression, detected-count, and dominant-gene columns are written back to adata.obs for stable downstream reuse
8. Optional R visualization layer: bundled r_visualization/ templates consume figure_data/ without recomputing science
9. Ranked table exports: CSVs for all tested genes, top SVGs, significant SVGs, and observation metrics

Input Formats

Format	Extension	Required Fields	Example
AnnData (preprocessed)	.h5ad	X (normalised), layers["counts"] (raw), obsm["spatial"]