Added synthetic data generator

sc_gen/generate_synthetic_singlecell.py

+import argparse
+import numpy as np
+import pandas as pd
+import random
+
+def generate_data(N, F, V, T, G,
+                  expr_sparsity, var_sparsity,
+                  expr_error, var_error, label_noise,
+                  expr_out, var_out, truth_out, cell_metadata_out):
+
+    np.random.seed(42)
+    random.seed(42)
+
+    # Define labels
+    cell_types = [f"CellType_{i}" for i in range(T)]
+    genotypes = [f"Genotype_{i}" for i in range(G)]
+    cells = [f"Cell_{i}" for i in range(N)]
+
+    # Assign true labels
+    true_cell_types = np.random.choice(cell_types, size=N)
+    celltype_to_genotypes = {
+        ct: sorted(random.sample(genotypes, random.randint(1, G))) for ct in cell_types
+    }
+    true_genotypes = [
+        random.choice(celltype_to_genotypes[ct]) for ct in true_cell_types
+    ]
+
+    # Corrupt labels if needed
+    noisy_cell_types = true_cell_types.copy()
+    noisy_genotypes = true_genotypes.copy()
+    n_noisy = int(label_noise * N)
+    noisy_indices = np.random.choice(N, n_noisy, replace=False)
+
+    for i in noisy_indices:
+        wrong_ct = list(set(cell_types) - {true_cell_types[i]})
+        noisy_cell_types[i] = random.choice(wrong_ct)
+        wrong_genos = list(set(genotypes) - set(celltype_to_genotypes[true_cell_types[i]]))
+        if wrong_genos:
+            noisy_genotypes[i] = random.choice(wrong_genos)
+
+    # ---------------------------------------------
+    # Generate reference transcriptome per CellType
+    # ---------------------------------------------
+    expr_reference = {
+        ct: np.random.lognormal(mean=1.0, sigma=0.5, size=F)
+        for ct in cell_types
+    }
+
+    # Per-gene noise variance for each cell type (gene-specific)
+    gene_noise_factors = np.random.uniform(0.5, 1.5, size=F)
+
+    # Generate expression matrix with noise per cell
+    expr_data = np.zeros((F, N))  # genes x cells
+
+    for i in range(N):
+        ct = noisy_cell_types[i]
+        profile = expr_reference[ct]
+        noise_std = expr_error * gene_noise_factors
+        expr_data[:, i] = np.random.normal(loc=profile, scale=noise_std)
+
+    # Apply sparsity (dropouts): zero out expr_sparsity% of genes in each cell
+    for i in range(N):
+        zero_indices = np.random.choice(F, size=int(expr_sparsity * F), replace=False)
+        expr_data[zero_indices, i] = 0.0
+
+    expr_data[np.abs(expr_data) < 1e-10] = 0.0  # clean -0
+    expr_df = pd.DataFrame(expr_data, index=[f"Gene_{i}" for i in range(F)], columns=cells)
+    expr_df.to_csv(expr_out)
+
+    # ------------------------------------------
+    # Generate reference genotype profiles
+    # ------------------------------------------
+    variant_reference = {
+        g: np.random.binomial(1, 0.1, size=V)
+        for g in genotypes
+    }
+
+    # Generate variant matrix for each cell from its genotype
+    var_data = np.zeros((V, N), dtype=int)
+
+    for i in range(N):
+        g = noisy_genotypes[i]
+        profile = variant_reference[g].copy()
+
+        # Introduce random changes: replace var_error * V entries with 0 or 1
+        n_changes = int(var_error * V)
+        indices_to_modify = np.random.choice(V, size=n_changes, replace=False)
+        profile[indices_to_modify] = np.random.randint(0, 2, size=n_changes)
+
+        # Apply sparsity (dropouts): zero out var_sparsity% of variants
+        n_zeros = int(var_sparsity * V)
+        zero_indices = np.random.choice(V, size=n_zeros, replace=False)
+        profile[zero_indices] = 0
+
+        var_data[:, i] = profile
+
+    var_df = pd.DataFrame(var_data, index=[f"Variant_{i}" for i in range(V)], columns=cells)
+    var_df.to_csv(var_out)
+
+    # ------------------------------------------
+    # Save CellType <-> Genotype mapping (truth)
+    # ------------------------------------------
+    ct_gt = pd.DataFrame(
+        [(ct, g) for ct, gs in celltype_to_genotypes.items() for g in gs],
+        columns=["CellType", "Genotype"]
+    )
+    ct_gt.to_csv(truth_out, index=False)
+
+    # ------------------------------------------
+    # Save per-cell metadata
+    # ------------------------------------------
+    metadata_df = pd.DataFrame({
+        "Cell": cells,
+        "CellType": noisy_cell_types,
+        "Genotype": noisy_genotypes,
+        "TrueCellType": true_cell_types,
+        "TrueGenotype": true_genotypes
+    })
+    metadata_df.to_csv(cell_metadata_out, index=False)
+
+    print(f"✔ Expression matrix saved to: {expr_out}")
+    print(f"✔ Variant matrix saved to: {var_out}")
+    print(f"✔ CellType–Genotype mapping saved to: {truth_out}")
+    print(f"✔ Cell metadata (true + noisy labels) saved to: {cell_metadata_out}")
+
+if __name__ == "__main__":
+    parser = argparse.ArgumentParser(description="Generate synthetic single-cell data with realistic transcriptome and variant noise.")
+    parser.add_argument("--cells", type=int, required=True)
+    parser.add_argument("--genes", type=int, required=True)
+    parser.add_argument("--variants", type=int, required=True)
+    parser.add_argument("--celltypes", type=int, required=True)
+    parser.add_argument("--genotypes", type=int, required=True)
+    parser.add_argument("--expr_out", type=str, required=True)
+    parser.add_argument("--var_out", type=str, required=True)
+    parser.add_argument("--truth_out", type=str, required=True)
+    parser.add_argument("--cell_metadata_out", type=str, required=True)
+
+    # Sparsity = dropout-like effect
+    parser.add_argument("--expr_sparsity", type=float, default=0.3,
+                        help="Fraction of genes set to 0 in each cell (simulates dropout)")
+    parser.add_argument("--var_sparsity", type=float, default=0.1,
+                        help="Fraction of variants set to 0 in each cell (simulates missed calls)")
+
+    # Noise = deviation from reference profile
+    parser.add_argument("--expr_error", type=float, default=0.3,
+                        help="Amount of expression noise per gene per cell")
+    parser.add_argument("--var_error", type=float, default=0.3,
+                        help="Fraction of variants changed arbitrarily per cell")
+
+    # Label noise = wrong labels
+    parser.add_argument("--label_noise", type=float, default=0.0,
+                        help="Fraction of cells with incorrect celltype/genotype labels")
+
+    args = parser.parse_args()
+
+    generate_data(
+        N=args.cells,
+        F=args.genes,
+        V=args.variants,
+        T=args.celltypes,
+        G=args.genotypes,
+        expr_sparsity=args.expr_sparsity,
+        var_sparsity=args.var_sparsity,
+        expr_error=args.expr_error,
+        var_error=args.var_error,
+        label_noise=args.label_noise,
+        expr_out=args.expr_out,
+        var_out=args.var_out,
+        truth_out=args.truth_out,
+        cell_metadata_out=args.cell_metadata_out,
+    )

sc_gen/ground_truth.csv

+CellType,Genotype
+CellType_0,Genotype_0
+CellType_1,Genotype_0
+CellType_1,Genotype_1
+CellType_1,Genotype_2
+CellType_2,Genotype_0
+CellType_3,Genotype_0
+CellType_3,Genotype_1
+CellType_3,Genotype_2
+CellType_3,Genotype_3
+CellType_4,Genotype_0
+CellType_4,Genotype_2