pywombat 0.3.0__py3-none-any.whl → 0.5.0__py3-none-any.whl

pywombat/cli.py

@@ -40,6 +40,11 @@ import yaml
     type=click.Path(exists=True, path_type=Path),
     help="Filter configuration YAML file to apply quality and impact filters.",
 )
+@click.option(
+    "--debug",
+    type=str,
+    help="Debug mode: show rows matching chrom:pos (e.g., chr11:70486013). Displays #CHROM, POS, VEP_SYMBOL, and columns from filter expression.",
+)
 def cli(
     input_file: Path,
     output: Optional[str],
@@ -47,6 +52,7 @@ def cli(
     verbose: bool,
     pedigree: Optional[Path],
     filter_config: Optional[Path],
+    debug: Optional[str],
 ):
     """
     Wombat: A tool for processing bcftools tabulated TSV files.
@@ -94,6 +100,11 @@ def cli(
                 click.echo(f"Reading filter config: {filter_config}", err=True)
             filter_config_data = load_filter_config(filter_config)
 
+        # Debug mode: show specific variant
+        if debug:
+            debug_variant(input_file, pedigree_df, filter_config_data, debug, verbose)
+            return
+
         # Determine output prefix
         if output is None:
             # Generate default output prefix from input filename
@@ -116,7 +127,20 @@ def cli(
             click.echo("Processing with streaming mode...", err=True)
 
         # Build lazy query
-        lazy_df = pl.scan_csv(input_file, separator="\t")
+        # Force certain columns to string type
+        string_columns = [
+            "FID",
+            "sample_id",
+            "father_id",
+            "mother_id",
+            "FatherBarcode",
+            "MotherBarcode",
+            "sample",
+        ]
+        schema_overrides = {col: pl.Utf8 for col in string_columns}
+        lazy_df = pl.scan_csv(
+            input_file, separator="\t", schema_overrides=schema_overrides
+        )
 
         # Apply formatting transformations
         lazy_df = format_bcftools_tsv_lazy(lazy_df, pedigree_df)
@@ -147,6 +171,106 @@ def cli(
         raise click.Abort()
 
 
+def debug_variant(
+    input_file: Path,
+    pedigree_df: Optional[pl.DataFrame],
+    filter_config: Optional[dict],
+    debug_pos: str,
+    verbose: bool,
+):
+    """Debug mode: display rows matching a specific chrom:pos."""
+    # Parse debug position
+    if ":" not in debug_pos:
+        click.echo(
+            "Error: Debug position must be in format 'chrom:pos' (e.g., chr11:70486013)",
+            err=True,
+        )
+        raise click.Abort()
+
+    chrom, pos = debug_pos.split(":", 1)
+    try:
+        pos = int(pos)
+    except ValueError:
+        click.echo(f"Error: Position must be an integer, got '{pos}'", err=True)
+        raise click.Abort()
+
+    if verbose:
+        click.echo(f"Debug mode: searching for {chrom}:{pos}", err=True)
+
+    # Read and format the data
+    # Force certain columns to string type
+    string_columns = [
+        "FID",
+        "sample_id",
+        "father_id",
+        "mother_id",
+        "FatherBarcode",
+        "MotherBarcode",
+        "sample",
+    ]
+    schema_overrides = {col: pl.Utf8 for col in string_columns}
+    df = pl.read_csv(input_file, separator="\t", schema_overrides=schema_overrides)
+    formatted_df = format_bcftools_tsv(df, pedigree_df)
+
+    # Filter to matching rows
+    matching_rows = formatted_df.filter(
+        (pl.col("#CHROM") == chrom) & (pl.col("POS") == pos)
+    )
+
+    if matching_rows.shape[0] == 0:
+        click.echo(f"No rows found matching {chrom}:{pos}", err=True)
+        return
+
+    # Determine which columns to display
+    columns_to_show = ["#CHROM", "POS"]
+
+    # Add VEP_SYMBOL if it exists
+    if "VEP_SYMBOL" in matching_rows.columns:
+        columns_to_show.append("VEP_SYMBOL")
+
+    # Extract column names from expression if filter config provided
+    if filter_config and "expression" in filter_config:
+        expression = filter_config["expression"]
+        # Extract column names from expression using regex
+        # Match patterns like "column_name" before operators
+        column_pattern = r"\b([A-Za-z_][A-Za-z0-9_]*)\b\s*[=!<>]"
+        found_columns = re.findall(column_pattern, expression)
+
+        for col in found_columns:
+            if col in matching_rows.columns and col not in columns_to_show:
+                columns_to_show.append(col)
+
+    # Select only the columns we want to display
+    display_df = matching_rows.select(
+        [col for col in columns_to_show if col in matching_rows.columns]
+    )
+
+    # Replace null and NaN values with <null> and <NaN> for display
+    for col in display_df.columns:
+        if display_df[col].dtype in [pl.Float32, pl.Float64]:
+            # For numeric columns, handle both NaN and null
+            display_df = display_df.with_columns(
+                pl.when(pl.col(col).is_null())
+                .then(pl.lit("<null>"))
+                .when(pl.col(col).is_nan())
+                .then(pl.lit("<NaN>"))
+                .otherwise(pl.col(col).cast(pl.Utf8))
+                .alias(col)
+            )
+        else:
+            # For non-numeric columns, only handle null
+            display_df = display_df.with_columns(
+                pl.when(pl.col(col).is_null())
+                .then(pl.lit("<null>"))
+                .otherwise(pl.col(col).cast(pl.Utf8))
+                .alias(col)
+            )
+
+    # Display the results
+    click.echo(f"\nFound {matching_rows.shape[0]} row(s) matching {chrom}:{pos}:\n")
+    click.echo(display_df.write_csv(separator="\t"))
+
+
 def load_filter_config(config_path: Path) -> dict:
     """Load and parse filter configuration from YAML file."""
     with open(config_path, "r") as f:
@@ -366,6 +490,30 @@ def parse_impact_filter_expression(expression: str, df: pl.DataFrame) -> pl.Expr
                     if col_name not in df.columns:
                         raise ValueError(f"Column '{col_name}' not found in dataframe")
 
+                    # Check for null value
+                    if value.upper() == "NULL":
+                        col_expr = pl.col(col_name)
+                        if op == "=":
+                            return col_expr.is_null()
+                        elif op == "!=":
+                            return ~col_expr.is_null()
+                        else:
+                            raise ValueError(
+                                f"Operator '{op}' not supported for null comparison, use = or !="
+                            )
+
+                    # Check for NaN value
+                    if value.upper() == "NAN":
+                        col_expr = pl.col(col_name).cast(pl.Float64, strict=False)
+                        if op == "=":
+                            return col_expr.is_nan()
+                        elif op == "!=":
+                            return ~col_expr.is_nan()
+                        else:
+                            raise ValueError(
+                                f"Operator '{op}' not supported for NaN comparison, use = or !="
+                            )
+
                     # Try to convert value to number, otherwise treat as string
                     try:
                         value_num = float(value)
@@ -647,7 +795,18 @@ def read_pedigree(pedigree_path: Path) -> pl.DataFrame:
         DataFrame with columns: sample_id, father_id, mother_id
     """
     # Try reading with header first
-    df = pl.read_csv(pedigree_path, separator="\t")
+    # Force certain columns to string type
+    string_columns = [
+        "FID",
+        "sample_id",
+        "father_id",
+        "mother_id",
+        "FatherBarcode",
+        "MotherBarcode",
+        "sample",
+    ]
+    schema_overrides = {col: pl.Utf8 for col in string_columns}
+    df = pl.read_csv(pedigree_path, separator="\t", schema_overrides=schema_overrides)
 
     # Check if first row has 'FID' in first column (indicates header)
     if df.columns[0] == "FID" or "sample_id" in df.columns:

{pywombat-0.3.0.dist-info → pywombat-0.5.0.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: pywombat
-Version: 0.3.0
+Version: 0.5.0
 Summary: A CLI tool for processing and filtering bcftools tabulated TSV files with pedigree support
 Project-URL: Homepage, https://github.com/bourgeron-lab/pywombat
 Project-URL: Repository, https://github.com/bourgeron-lab/pywombat

pywombat-0.5.0.dist-info/RECORD

@@ -0,0 +1,6 @@
+pywombat/__init__.py,sha256=iIPN9vJtsIUhl_DiKNnknxCamLinfayodLLFK8y-aJg,54
+pywombat/cli.py,sha256=0nBlwyRu1Q01a0EHcVyIYtKmgezCWA85pQtEXpnuzL4,44535
+pywombat-0.5.0.dist-info/METADATA,sha256=2Py8xwNxZBD18u4r-tJI_mQezMBg4td3ruWOm61MbdA,4982
+pywombat-0.5.0.dist-info/WHEEL,sha256=WLgqFyCfm_KASv4WHyYy0P3pM_m7J5L9k2skdKLirC8,87
+pywombat-0.5.0.dist-info/entry_points.txt,sha256=Vt7U2ypbiEgCBlEV71ZPk287H5_HKmPBT4iBu6duEcE,44
+pywombat-0.5.0.dist-info/RECORD,,

pywombat-0.3.0.dist-info/RECORD

@@ -1,6 +0,0 @@
-pywombat/__init__.py,sha256=iIPN9vJtsIUhl_DiKNnknxCamLinfayodLLFK8y-aJg,54
-pywombat/cli.py,sha256=kv03IFXcwe9pdv-KyoT5Cu1pJ9r-O7ww-Kh0ZT2ysa4,38920
-pywombat-0.3.0.dist-info/METADATA,sha256=eASint-XgzgUGWshtZYr4nekDCs-VKSTilHLRupH5ic,4982
-pywombat-0.3.0.dist-info/WHEEL,sha256=WLgqFyCfm_KASv4WHyYy0P3pM_m7J5L9k2skdKLirC8,87
-pywombat-0.3.0.dist-info/entry_points.txt,sha256=Vt7U2ypbiEgCBlEV71ZPk287H5_HKmPBT4iBu6duEcE,44
-pywombat-0.3.0.dist-info/RECORD,,