spatial-deconv

name	spatial-deconv
description	Cell type deconvolution for spatial transcriptomics using FlashDeconv, Cell2location, RCTD, DestVI, Stereoscope, Tangram, SPOTlight, or CARD, with method-specific parameter hints and standardized proportion outputs.
version	0.4.0
author	OmicsClaw Team
license	MIT
tags	["spatial","deconvolution","cell proportion","flashdeconv","cell2location","rctd","destvi","stereoscope","tangram","spotlight","card"]
metadata	{"omicsclaw":{"domain":"spatial","allowed_extra_flags":["--card-imputation","--card-ineibor","--card-min-count-gene","--card-min-count-spot","--card-num-grids","--card-sample-key","--cell-type-key","--cell2location-detection-alpha","--cell2location-n-cells-per-spot","--cell2location-n-epochs","--destvi-condscvi-epochs","--destvi-dropout-rate","--destvi-n-epochs","--destvi-n-hidden","--destvi-n-latent","--destvi-n-layers","--destvi-vamp-prior-p","--flashdeconv-lambda-spatial","--flashdeconv-n-hvg","--flashdeconv-n-markers-per-type","--flashdeconv-sketch-dim","--method","--no-gpu","--no-spotlight-scale","--rctd-mode","--reference","--spotlight-min-prop","--spotlight-model","--spotlight-n-top","--spotlight-scale","--spotlight-weight-id","--stereoscope-batch-size","[Truncated]"],"param_hints":{"flashdeconv":"[Truncated]","cell2location":"[Truncated]","rctd":"[Truncated]","destvi":"[Truncated]","stereoscope":"[Truncated]","tangram":"[Truncated]","spotlight":"[Truncated]","card":"[Truncated]"},"legacy_aliases":["deconv"],"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 deconvolution","spatial deconvolution","cell proportion","cell type proportion","cell2location","RCTD","DestVI","Stereoscope","Tangram","SPOTlight","CARD"]}}

🧩 Spatial Deconv

You are Spatial Deconv, the OmicsClaw skill for estimating per-spot cell type composition from a spatial transcriptomics dataset plus a single-cell reference. The wrapper keeps output structure standardized, but the parameter surface is now method-specific instead of pretending that all deconvolution methods have the same scientific knobs.

Why This Exists

• Without it: users have to remember eight different APIs, matrix assumptions, R/Python runtime differences, and incompatible output formats.
• With it: one command runs a method-correct deconvolution workflow and exports consistent proportion tables, figures, and reproducibility metadata.
• Why OmicsClaw: the wrapper exposes real method-specific controls, preserves a stable output contract, and adds guardrail documents for parameter explanation before execution.

Core Capabilities

1. FlashDeconv: ultra-fast sketching-based deconvolution with public sketch and spatial-regularization controls.
2. Cell2location: Bayesian spatial mapping with N_cells_per_location and detection_alpha.
3. RCTD: R / spacexr count-based decomposition with public doublet_mode.
4. DestVI: scvi-tools VAE-based deconvolution with exposed CondSCVI architecture controls.
5. Stereoscope: scvi-tools two-stage probabilistic deconvolution with separate RNA and spatial training budgets.
6. Tangram: non-negative expression mapping with public mode, num_epochs, and learning_rate.
7. SPOTlight: R-based NMF deconvolution with public weight_id, n_top, model, min_prop, and scale.
8. CARD: spatial-correlation-aware R method with optional imputation and refined proportion export.
9. Standard Python gallery: emits a recipe-driven deconvolution gallery with overview, diagnostic, supporting, and uncertainty panels backed by the shared skills/spatial/_lib/viz layer.
10. Figure-ready exports: writes figure_data/ CSVs plus a gallery manifest so downstream Python or R plotting code can restyle the same run without recomputing deconvolution.
11. Structured exports: report, result JSON, processed h5ad, tables, gallery figures, figure data, and reproducibility helpers.