dc-777/tcga-pancan-multiomics

How dc-777/tcga-pancan-multiomics works

This repository is a TCGA pan-cancer multiomics survival-analysis pipeline. Its main workflow obtains cohort data, aligns expression, mutation, copy-number and clinical records, derives MOFA+ factors, evaluates survival models, and interprets signals to prioritize therapeutic targets. Separate branches provide exploratory clustering and dimensionality reduction, modality ablation, and causal validation. The README documents these capabilities; sampled source confirms key preprocessing, factorization, model, and ablation behavior. Some downstream links are therefore documented rather than verified from their implementation.

Main entry points: preprocess.py Omics alignment · mofa_analysis.py MOFA+ factors · did_causal_layer.py Causal validation · shap_analysis.py SHAP attribution

Components 18

Cohort data

TCGA download download_tcga.py
TCGA cohort files data
Omics alignment src/preprocess.py

Molecular discovery

PCA and UMAP src/unsupervised/dim_reduction.py
Subtype clustering src/unsupervised/clustering.py
MOFA+ factors src/unsupervised/mofa_analysis.py

Survival prediction

Cox models src/supervised/cox_models.py
DeepSurv src/supervised/deepsurv.py
Model comparison src/supervised/model_comparison.py

Validation and delivery

SHAP attribution src/supervised/shap_analysis.py
Gene attribution src/analysis/marker_analysis.py
Modality ablation src/analysis/modality_ablation.py
Causal validation src/analysis/did_causal_layer.py
Therapeutic targets src/analysis
Interactive dashboard results/dashboard.html
Manuscripts src/analysis/build_manuscript.py

Other components

Analyst
UCSC Xena

Connections 23

Analyst → TCGA download: requests data README.md
TCGA download → UCSC Xena: downloads from README.md
TCGA download → TCGA cohort files: saves cohort README.md
TCGA cohort files → Omics alignment: loads and aligns src/preprocess.py
Omics alignment → MOFA+ factors: provides modalities src/unsupervised/mofa_analysis.py
Omics alignment → PCA and UMAP: provides expression src/unsupervised/dim_reduction.py
Omics alignment → Subtype clustering: provides features src/unsupervised/clustering.py
Omics alignment → Cox models: builds survival features src/supervised/cox_models.py
Omics alignment → DeepSurv: supplies cohort data src/supervised/deepsurv.py
MOFA+ factors → Model comparison: factor inputs README.md
Model comparison → SHAP attribution: attributes predictions
Cox models → SHAP attribution: explains risk src/supervised/shap_analysis.py
DeepSurv → SHAP attribution: explains risk src/supervised/shap_analysis.py
SHAP attribution → Gene attribution: traces factors to genes README.md
MOFA+ factors → Modality ablation: compares modalities src/analysis/modality_ablation.py
Model comparison → Modality ablation: scores conditions src/analysis/modality_ablation.py
MOFA+ factors → Causal validation: supports causal analysis
Gene attribution → Therapeutic targets: informs nominations README.md
Causal validation → Therapeutic targets: validates candidates README.md
Therapeutic targets → Interactive dashboard: appears in README.md
Causal validation → Interactive dashboard: reports findings README.md
Modality ablation → Interactive dashboard: reports comparison README.md
Causal validation → Manuscripts: documents results

More HTML diagrams: limmer55/streamdock · d3athly/blackbox · mickinthemiddle/cloak · sumitkumar1503/bloodbankmanagement · jaiswaladi246/boardgame

Drawn by GitDiagram on September 30, 2026 from the repository's file tree, README and source files. Read as Markdown ·