| """Inspect the E-MTAB-5009 count table and sample metadata.""" |
|
|
| from pathlib import Path |
|
|
| import pandas as pd |
|
|
|
|
| PROJECT_ROOT = Path(__file__).resolve().parents[1] |
| DATA_DIR = PROJECT_ROOT / "data" / "raw" / "E-MTAB-5009" |
| COUNTS_PATH = DATA_DIR / "WP2_100acc.htseq.txt" |
| METADATA_PATH = DATA_DIR / "E-MTAB-5009.sdrf.txt" |
|
|
|
|
| def inspect_counts() -> None: |
| |
| |
| counts = pd.read_csv(COUNTS_PATH, sep="\t", index_col=0) |
| counts.index.name = "gene_id" |
|
|
| library_sizes = counts.sum(axis=0) |
|
|
| print("COUNT TABLE") |
| print(f"Path: {COUNTS_PATH}") |
| print(f"Shape: {counts.shape[0]:,} genes x {counts.shape[1]:,} count columns") |
| print(f"Duplicate gene IDs: {counts.index.duplicated().sum():,}") |
| print(f"Duplicate column names: {counts.columns.duplicated().sum():,}") |
| print(f"Missing values: {counts.isna().sum().sum():,}") |
| print(f"Smallest count: {counts.min().min():,}") |
| print(f"Largest count: {counts.max().max():,}") |
| print(f"Genes with zero counts in every column: {(counts.sum(axis=1) == 0).sum():,}") |
| print( |
| "Library sizes (min / median / max): " |
| f"{library_sizes.min():,.0f} / " |
| f"{library_sizes.median():,.0f} / " |
| f"{library_sizes.max():,.0f}" |
| ) |
| print("\nFirst 5 genes and first 5 count columns:") |
| print(counts.iloc[:5, :5].to_string()) |
|
|
|
|
| def inspect_metadata() -> None: |
| metadata = pd.read_csv(METADATA_PATH, sep="\t") |
|
|
| |
| |
| |
| assays = metadata.drop_duplicates(subset="Assay Name") |
|
|
| print("\nMETADATA") |
| print(f"Path: {METADATA_PATH}") |
| print(f"Raw metadata shape: {metadata.shape[0]:,} rows x {metadata.shape[1]:,} columns") |
| print(f"Unique assays: {assays['Assay Name'].nunique():,}") |
| print(f"Unique ecotypes: {assays['Factor Value[ecotype]'].nunique():,}") |
| print("Unique assays by condition:") |
| print(assays["Factor Value[environmental stress]"].value_counts().to_string()) |
| print(f"Missing cells in metadata: {metadata.isna().sum().sum():,}") |
| print("\nSelected metadata columns for the first 5 unique assays:") |
| selected = [ |
| "Assay Name", |
| "Factor Value[ecotype]", |
| "Factor Value[environmental stress]", |
| "Factor Value[block]", |
| ] |
| print(assays[selected].head().to_string(index=False)) |
|
|
|
|
| def main() -> None: |
| for required_path in (COUNTS_PATH, METADATA_PATH): |
| if not required_path.exists(): |
| raise FileNotFoundError( |
| f"Missing {required_path}. Run scripts/download_data.ps1 first." |
| ) |
|
|
| inspect_counts() |
| inspect_metadata() |
|
|
|
|
| if __name__ == "__main__": |
| main() |
|
|
|
|
