ratschlab/DeepSpot

DeepSpot: Deep learning model for predicting spatial transcriptomics from H&E histopathology images. Supports spot-level (Visium) and single-cell (Xenium) resolution.

53
/ 100
Established

DeepSpot helps cancer researchers and pathologists predict detailed gene expression patterns directly from standard H&E stained tissue images. You provide an H&E histopathology image, and the system outputs a map of spatial gene expression, showing which genes are active in different areas of the tissue. This allows for virtual spatial transcriptomics analysis without needing additional specialized lab procedures.

Use this if you need to understand gene expression at a spot or single-cell level within tissue samples, but only have H&E images available or want to reduce the cost and complexity of generating spatial transcriptomics data.

Not ideal if you already have direct spatial transcriptomics data and are looking for advanced analysis tools, rather than a prediction method from H&E images.

cancer-research pathology-diagnostics spatial-transcriptomics histology-imaging biomarker-discovery
No Package No Dependents
Maintenance 10 / 25
Adoption 8 / 25
Maturity 16 / 25
Community 19 / 25

How are scores calculated?

Stars

65

Forks

18

Language

Jupyter Notebook

License

MIT

Last pushed

Mar 09, 2026

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/ratschlab/DeepSpot"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.