Spaces:
Running
Running
| #!/usr/bin/env python3 | |
| """ | |
| Create a small synthetic dataset so you can try the pipeline and the dashboard | |
| without downloading TCGA. The data are random numbers, NOT real patient data; | |
| do not draw any biological conclusion from the demo results. | |
| python make_demo_data.py # writes ./demo/ | |
| python surrogate_test.py --expr demo/expr.csv --signatures demo/signatures.csv \ | |
| --labels demo/labels.csv --survival demo/survival.csv --out results | |
| """ | |
| from pathlib import Path | |
| import numpy as np | |
| import pandas as pd | |
| rng = np.random.default_rng(0) | |
| out = Path("demo") | |
| out.mkdir(exist_ok=True) | |
| n_genes, n_tumor, n_normal = 3000, 130, 20 | |
| samples = [f"T{i:03d}" for i in range(n_tumor)] + [f"N{i:03d}" for i in range(n_normal)] | |
| genes = [f"GENE{i:04d}" for i in range(n_genes)] | |
| base = rng.normal(5, 2, size=n_genes).clip(0.5, 12) | |
| expr = base[:, None] + rng.normal(0, 0.8, size=(n_genes, len(samples))) | |
| # 300 genes differ between tumor and normal, so tumor-vs-normal is easy | |
| diff_genes = rng.choice(n_genes, 300, replace=False) | |
| expr[np.ix_(diff_genes, np.arange(n_tumor, len(samples)))] += rng.normal(1.5, 0.4, (300, n_normal)) | |
| # a real "tumor-vs-normal" signature: 8 strongly different genes | |
| real_sig = list(rng.choice(diff_genes, 8, replace=False)) | |
| # a "random-like" signature: 8 genes that do not differ | |
| non_diff = np.setdiff1d(np.arange(n_genes), diff_genes) | |
| null_sig = list(rng.choice(non_diff, 8, replace=False)) | |
| # survival signature: 6 genes tied weakly to survival time | |
| os_sig = list(rng.choice(non_diff, 6, replace=False)) | |
| risk = expr[os_sig].mean(axis=0) | |
| risk = (risk - risk.mean()) / risk.std() | |
| time = rng.exponential(1000 * np.exp(-0.4 * risk)) | |
| event = (rng.random(len(samples)) < 0.6).astype(int) | |
| pd.DataFrame(expr, index=genes, columns=samples).round(4).to_csv(out / "expr.csv") | |
| pd.DataFrame({"label": ["tumor"] * n_tumor + ["normal"] * n_normal}, index=samples).to_csv(out / "labels.csv") | |
| pd.DataFrame({"time": time.round(1), "event": event}, index=samples).to_csv(out / "survival.csv") | |
| g = lambda idx: ";".join(genes[i] for i in idx) # noqa: E731 | |
| pd.DataFrame({ | |
| "Signature": ["Demo real signature", "Demo random-like signature", "Demo OS signature"], | |
| "Endpoint": ["tumor_normal", "tumor_normal", "os"], | |
| "Genes": [g(real_sig), g(null_sig), g(os_sig)], | |
| "Note": ["", "", ""], | |
| }).to_csv(out / "signatures.csv", index=False) | |
| print("Wrote demo/expr.csv, labels.csv, survival.csv, signatures.csv") | |