ProtoPathway / README.md
AmayaGS's picture
Update model card
4c446c7 verified
|
raw
history blame
1.84 kB
metadata
license: mit
tags:
  - medical-imaging
  - computational-pathology
  - survival-analysis
  - multimodal
  - tcga
datasets:
  - TCGA
library_name: pytorch

ProtoPathway

Pretrained checkpoints, preprocessed cohort data, and the curated pathway graph for ProtoPathway, an interpretable-by-design multimodal framework for cancer survival prediction.

See the code repository for usage, training, and evaluation instructions.

Layout

pathways/                              shared curated Reactome + Hallmark pathways
cohorts/{cohort}/
    gene_expression.csv                preprocessed expression matrix
    bipartite_graph.pt                 cohort-specific gene-pathway graph
    labels.csv                         survival times, events, and bins
    data_splits.pkl                    5-fold CV splits (SurvPath-compatible)
    checkpoints/best_fold_{0..4}.pt    trained model weights

Cohorts

Five TCGA cohorts: BRCA (N=714), BLCA (N=359), COADREAD (N=227), HNSC (N=392), STAD (N=318). Gene expression is the preprocessed SurvPath release. WSI patch features (UNI2-h) are not redistributed here and should be obtained from the Mahmood Lab directly.

Quick load

from huggingface_hub import snapshot_download

# Everything for one cohort plus the shared pathway file
snapshot_download(
    repo_id="AmayaGS/ProtoPathway",
    local_dir="./assets",
    allow_patterns=["cohorts/TCGA-BLCA/*", "pathways/*"],
)

Citation

@article{protopathway2026,
  title   = {ProtoPathway: Interpretable Multimodal Cancer Survival Prediction
             via Prototype-Pathway Cross-Modal Attention},
  author  = {...},
  year    = {2026}
}