Skip to main content

Edge-guided multiscale reconstruction of hierarchical spatial domains and transition interfaces in spatial transcriptomics

Project description

stEDGE: Edge-guided multiscale reconstruction of hierarchical spatial domains and transition interfaces in spatial transcriptomics

Documentation Status

stEDGE logo

Overview

stEDGE is an edge-guided and interpretable framework for reconstructing multiscale tissue architecture from spatial transcriptomics data. Instead of treating tissues as flat spatial partitions, stEDGE explicitly models local boundary probability and domain transition intensity to identify stable compartments, transition-rich interfaces, and hierarchical spatial states.

stEDGE integrates four major components: consensus-based boundary modeling, edge-guided fine-domain reconstruction, transition-aware hierarchy construction, and tree-guided gene program interpretation.

stEDGE overview

Using stEDGE, you can:

  • Reconstruct fine-grained spatial domains by modeling local boundary probability and growing domains from low-boundary core regions.

  • Identify transition-rich interfaces using boundary probability, gradient signals, and domain transition indices.

  • Build multiscale tissue hierarchies across fine, domain, and coarse spatial levels using domain graphs and hierarchy trees.

  • Interpret spatial gene programs with tree-guided gene attribution, distinguishing shared parent-level identity from branch-specific molecular programs.

  • Analyze diverse spatial transcriptomics datasets, including Visium, Slide-seqV2, Xenium, and other spatial omics platforms.


Installation

We recommend installing stEDGE in a clean conda environment.

Step 1. Create a conda environment

conda create -n stEDGE python=3.12.5
conda activate stEDGE

Step 2. Install dependency packages

pip install -r requirements.txt

Step 3. Install stEDGE

For local installation, we recommend editable mode:

pip install -e .

Alternatively, you can install stEDGE using the setup script:

pip install setuptools==58.2.0
python setup.py build
python setup.py install

The environment configuration is then completed.

Tutorials

For installation instructions and step-by-step tutorials, please refer to the online documentation:

https://stedge-tutorials.readthedocs.io/en/latest/

Tutorial source repository:

https://github.com/yihe-csu/stEDGE_Tutorials

Citation

If you use stEDGE in your work, please cite:

He, Y. stEDGE enables edge-guided multiscale reconstruction of hierarchical spatial domains and transition interfaces in spatial transcriptomics. 2026.

Citation information will be updated upon publication.

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

stedge-1.1.1.tar.gz (61.6 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

stedge-1.1.1-py3-none-any.whl (63.2 kB view details)

Uploaded Python 3

File details

Details for the file stedge-1.1.1.tar.gz.

File metadata

  • Download URL: stedge-1.1.1.tar.gz
  • Upload date:
  • Size: 61.6 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.12.5

File hashes

Hashes for stedge-1.1.1.tar.gz
Algorithm Hash digest
SHA256 b47d25649f33d5cac290f87a2ce9922f4f54aa6fb1d7b1fde326cf417b0f0cda
MD5 cd56cd543d297d9bddf5b7ec18e9e9b8
BLAKE2b-256 b3dbe327603da1ec1827a4b921c8527fe21a5f3886494719d7a170652c93c5b7

See more details on using hashes here.

File details

Details for the file stedge-1.1.1-py3-none-any.whl.

File metadata

  • Download URL: stedge-1.1.1-py3-none-any.whl
  • Upload date:
  • Size: 63.2 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.12.5

File hashes

Hashes for stedge-1.1.1-py3-none-any.whl
Algorithm Hash digest
SHA256 542853f134eed275e25e0aec5797602d7ffaa42a315cfdc91f56789f53222754
MD5 5d61862ae4533465029ce066e2fb242c
BLAKE2b-256 fc053cfa97d433426b0c6f33e6d41edd7f62d1d3841922ad8d9192bc8d3cb974

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page