This repository provides a framework to investigate how pathology whole-slide image (WSI) embeddings can be transformed into biologically and clinically meaningful signals. The project integrates ProV-GigaPath embeddings with multi-omics and clinical data to explore how computational image features relate to molecular alterations, pathways, and patient outcomes. ⸻
Raw image embeddings are obtained from ProV-GigaPath model analysis and curatedTCGA
Scripts for analysis and data curation can be found under /vignettes/
Xu, Y. et al. (2024). A whole-slide foundation model for digital pathology from real-world data. Nature. https://doi.org/10.1038/s41586-024-07441-w
Ramos, M. et al. (2020). Multiomic integration of public oncology databases in Bioconductor. Cancer Research, 80(23), 5007–5011. PMC7608653
