ratschlab/he2st
Code of the paper "DeepSpot: Leveraging Spatial Context for Enhanced Spatial Transcriptomics Prediction from H&E Images"
This project helps cancer researchers and pathologists predict spatial transcriptomics, which show gene activity within tissue, directly from standard H&E stained pathology images. By inputting these widely available images, it outputs detailed spatial gene expression maps, offering insights into the molecular landscape of cancer tissues. It's designed for biomedical scientists who want to understand gene distribution in tumors without needing specialized and expensive spatial transcriptomics experiments.
No commits in the last 6 months.
Use this if you need to generate spatial gene expression profiles for cancer tissue samples using only routine H&E stained slides, especially for large datasets like those from TCGA.
Not ideal if you require ground-truth spatial transcriptomics data rather than predictions, or if you are not working with cancer pathology images.
Stars
13
Forks
1
Language
Jupyter Notebook
License
MIT
Category
Last pushed
May 10, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/ratschlab/he2st"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
scverse/scanpy
Single-cell analysis in Python. Scales to >100M cells.
scverse/scvi-tools
Deep probabilistic analysis of single-cell and spatial omics data
Teichlab/celltypist
A tool for semi-automatic cell type classification
theislab/scarches
Reference mapping for single-cell genomics
Teichlab/cellhint
A tool for semi-automatic cell type harmonization and integration