Website for CancerSTFormer

This is the website for CancerSTFormer. CancerSTFormer consists of a pair of spatially aware transcriptomic foundation models to accommodate niche modeling at different length scales. These models, at the 50um-Local and 250um-Extended scales, possess unique capabilities to recover ligand-target gene relationships, niche-specific differentially expressed genes, and organ-specific metastasis associated genes in diverse cancer applications. CancerSTFormer can also reveal the responses of immune-checkpoint blockade therapies, and other targeted therapies, on patients’ tumors given their ST profiles through gene perturbation analysis.

Here you find the codes for generating figures and results in the paper.

Description Script Individual inputs
Spatial perturbation response visualization (replot.py) - ganitumab sensitivity, 250um-Extended Model replot.py.html
  • replot_bundle_1000_run-1ecffb18.pkl (file)
Spatial perturbation response visualization (replot.py) - ganitumab sensitivity, 50um-Local Model replot.local.pyhtml
  • replot_bundle_1000_run-1ecffb18.pkl (file)