deconvolution-flashdeconv

Community

Ultra-fast spot deconvolution with FlashDeconv

Authorchenyhvvvv
Version1.0.0
Installs0

System Documentation

What problem does it solve?

Fast and scalable deconvolution of spatial transcriptomics spots by using a reference-based method to estimate cell-type composition per spot.

Core Features & Use Cases

  • Ultra-fast, reference-based deconvolution (FlashDeconv) with outputs stored in adata.obsm['flashdeconv'] and per-spot dominant cell type in adata.obs['celltype']
  • Compatible with single-slice gene-expression data and a properly formatted scRNA-seq reference (.h5ad) with a celltype column
  • No GPU needed; Python-based workflow designed for large spatial datasets

Quick Start

Run the FlashDeconv workflow on a spatial slice with a reference scRNA-seq dataset to obtain per-spot proportions and dominant cell types.

Dependency Matrix

Required Modules

scanpypandasnumpyflashdeconv

Components

Standard package

💻 Claude Code Installation

Recommended: Let Claude install automatically. Simply copy and paste the text below to Claude Code.

Please help me install this Skill:
Name: deconvolution-flashdeconv
Download link: https://github.com/chenyhvvvv/STAT-agent/archive/main.zip#deconvolution-flashdeconv

Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
View Source Repository

Agent Skills Search Helper

Install a tiny helper to your Agent, search and equip skill from 471,000+ vetted skills library on demand.