Views
No views yet
README.md and USAGE.md. This top-level document explains how the five sub-projects fit together, what data flows between them, and where to find detailed instructions.
demo project is the joint inference stage that combines their outputs.1Morphology branch (WSI):
2 image_preprocess -> compute_uni_features -> src_wsi2rna_model
3
4Function branch (molecular / GO):
5 src_surv_model (GeneExpression / CNA / RPPA)
6
7Joint inference (uses checkpoints and resources from both branches):
8 demo1Morphology_Function_Framework/
2├── img/ overview/data-download/evaluation figures used in this README
3├── image_preprocess/ Step 1 (Morphology): organize 40x WSIs, cut into patches
4├── compute_uni_features/ Step 2 (Morphology): patches -> HDF5 -> UNI features -> KMeans cluster_features
5├── src_wsi2rna_model/ Step 3 (Morphology): ViS model, cluster_features -> predicted (simulated) gene expression
6├── src_surv_model/ Function branch: Functional Extraction Module (FEM) + CoxGNN survival model,
7│ trained directly from GeneExpression / CNA / RPPA molecular data
8├── demo/ Joint inference: WSI -> simulated GE -> survival risk -> GO interpretation -> R figures
9├── README.md this file
10└── USAGE.md end-to-end setup and run instructions| Order | Sub-project | Reads | Produces | Docs |
|---|---|---|---|---|
| 1 | image_preprocess | raw TCGA WSIs, gene-expression matrix | data/40x_grouped_with_gene_expression/<SAMPLE_ID>/wsi/*.png + gene_expression.csv | README / USAGE |
| 2 | compute_uni_features | output of step 1 | data/Patches_hdf5, data/uni_features/<PROJECT>/<SLIDE_ID>/<SLIDE_ID>.h5 (dataset cluster_features) | README / USAGE |
| 3 | src_wsi2rna_model | cluster_features from step 2 | trained checkpoints under log/<cohort>/<exp_name>/model_best*.pt | README / USAGE |
| — | src_surv_model | raw GeneExpression / CNA / RPPA + GO ontology resources (independent of steps 1-3) | FEM resources (FEM_files/<MODAL>/files/) + trained survival checkpoints under model/log/ | README / USAGE |
| 4 | demo | UNI features (step 2) + WSI2RNA checkpoints (step 3) + FEM resources and a survival checkpoint (from src_surv_model) | pipeline_results/ predictions, GO scores, GO-occlusion results, R figures | README / USAGE |
demo reads from more than one sub-project at once; every other sub-project reads only the single upstream directory named in the table above. See USAGE.md for the exact directory layout expected between projects and every runnable command.
USAGE.md documents exactly which files must be placed under which path before its scripts can run, and which resources (e.g. the UNI checkpoint, the ViS checkpoint, go-basic.obo) can be downloaded automatically when network access is available.
src_wsi2rna_model (WSI2RNA metrics), src_surv_model (five-fold CV and hold-out survival metrics, model/figure_script.R), and demo (joint hold-out evaluation and figure_script.R). See each project's USAGE.md for the exact output files..gitignore that excludes these paths by default.