This repository is for code related to the MesoGraph cancer cell paper.
The data referenced in the paper can be found at: https://drive.google.com/drive/folders/1AjH3J4oUb6rezBTKj_KvQviEa9U19Sml?usp=sharing
Model output can be visualized in a demo available here: https://mesograph.dcs.warwick.ac.uk/
This is built using the visualization tool here: https://github.com/measty/tiatoolbox which uses tiatoolbox (https://github.com/TissueImageAnalytics/tiatoolbox) and bokeh (https://bokeh.org/).
A graph can be constructed using mk_graph.py (for mesothelioma TMA core data) or generic_mk_graph (for generic datasets)
Train the model using MesoGraph.py
Model explanations can be calculated using gnn_explain.py
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
