Runnable notebooks
HistAgent tutorials
Five runnable notebooks that reproduce the manuscript workflows across spot, whole-slide and atlas scales.
Notebook directory
Choose a workflow
Generate and evaluate ranked molecular readouts
Calculate spot-level HitRate@50 and mAP@50, then compare measured ST and HistAgent spatial profiles across five held-out slides.
02Analyze spatial biological findings
Compare predicted and measured expression, localize an RCC TLS-like niche and review cross-study finding recovery.
03Run standard spatial transcriptomic analyses
Run SVG detection, spatial domain identification, cell-type deconvolution, differential expression and pathway enrichment.
04Interpret whole-slide clinical predictions
Inspect tissue regions associated with slide-level predictions, then compare patient-level risk groups.
05Search the spatial transcriptomics atlas
Explore measured tissue locations and run representative natural-language and H&E image queries.
Notebook format
How to use the notebooks
Open a tutorial and use Download .ipynb to save the notebook. Follow its installation cell, start Jupyter with python -m jupyter lab, open the downloaded file and choose Run All.
The first run downloads the required files from HistAgent-data. Each notebook downloads only the files required for its workflow. The clinical tutorial uses a released ABMIL model instead of training one from scratch.
Start the tutorials