pywombat 1.0.0__py3-none-any.whl → 1.0.2__py3-none-any.whl

pywombat/cli.py

@@ -1198,15 +1198,18 @@ def read_pedigree(pedigree_path: Path) -> pl.DataFrame:
     pedigree_df = df.select(select_cols)
 
     # Replace 0 and -9 with null (indicating no parent)
+    # Explicit cast to Utf8 ensures type is preserved even when all values become null
     pedigree_df = pedigree_df.with_columns(
         [
             pl.when(pl.col("father_id").cast(pl.Utf8).is_in(["0", "-9"]))
             .then(None)
             .otherwise(pl.col("father_id"))
+            .cast(pl.Utf8)
             .alias("father_id"),
             pl.when(pl.col("mother_id").cast(pl.Utf8).is_in(["0", "-9"]))
             .then(None)
             .otherwise(pl.col("mother_id"))
+            .cast(pl.Utf8)
             .alias("mother_id"),
         ]
     )
@@ -1313,6 +1316,10 @@ def format_expand_annotations(df: pl.DataFrame) -> pl.DataFrame:
     This is a separate step that can be applied after filtering to avoid
     expensive annotation expansion on variants that will be filtered out.
 
+    Handles two types of INFO fields:
+    - Key-value pairs (e.g., "DP=30") -> extracted as string values
+    - Boolean flags (e.g., "PASS", "DB") -> created as True/False columns
+
     Args:
         df: DataFrame with (null) column
 
@@ -1324,9 +1331,10 @@ def format_expand_annotations(df: pl.DataFrame) -> pl.DataFrame:
         # Already expanded or missing - return as-is
         return df
 
-    # Extract all unique field names from the (null) column
+    # Extract all unique field names and flags from the (null) column
     null_values = df.select("(null)").to_series()
     all_fields = set()
+    all_flags = set()
 
     for value in null_values:
         if value and not (isinstance(value, float)):  # Skip null/NaN values
@@ -1335,8 +1343,10 @@ def format_expand_annotations(df: pl.DataFrame) -> pl.DataFrame:
                 if "=" in pair:
                     field_name = pair.split("=", 1)[0]
                     all_fields.add(field_name)
+                elif pair.strip():  # Boolean flag (no '=')
+                    all_flags.add(pair.strip())
 
-    # Create expressions to extract each field
+    # Create expressions to extract each key-value field
     for field in sorted(all_fields):
         # Extract the field value from the (null) column
         # Pattern: extract value after "field=" and before ";" or end of string
@@ -1344,6 +1354,14 @@ def format_expand_annotations(df: pl.DataFrame) -> pl.DataFrame:
             pl.col("(null)").str.extract(f"{field}=([^;]+)").alias(field)
         )
 
+    # Create boolean columns for flags
+    for flag in sorted(all_flags):
+        # Check if flag appears in the (null) column (as whole word)
+        # Use regex to match flag as a separate field (not part of another field name)
+        df = df.with_columns(
+            pl.col("(null)").str.contains(f"(^|;){flag}(;|$)").alias(flag)
+        )
+
     # Drop the original (null) column
     df = df.drop("(null)")
 

{pywombat-1.0.0.dist-info → pywombat-1.0.2.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: pywombat
-Version: 1.0.0
+Version: 1.0.2
 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
@@ -35,6 +35,7 @@ A high-performance CLI tool for processing and filtering bcftools tabulated TSV
 🧬 **De Novo Detection**: Sex-chromosome-aware DNM identification  
 📊 **Flexible Output**: TSV, compressed TSV, or Parquet formats  
 🎯 **Expression Filters**: Complex filtering with logical expressions  
+🏷️ **Boolean Flag Support**: INFO field flags (PASS, DB, etc.) extracted as True/False columns  
 ⚡ **Streaming Mode**: Memory-efficient processing of large files
 
 ---
@@ -77,7 +78,7 @@ uv run wombat input.tsv -o output
 
 PyWombat transforms bcftools tabulated TSV files into analysis-ready formats by:
 
-1. **Expanding the `(null)` INFO column**: Extracts all `NAME=value` fields (e.g., `DP=30;AF=0.5;AC=2`) into separate columns
+1. **Expanding the `(null)` INFO column**: Extracts all `NAME=value` fields (e.g., `DP=30;AF=0.5;AC=2`) and boolean flags (e.g., `PASS`, `DB`) into separate columns
 2. **Melting sample columns**: Converts wide-format sample data into long format with one row per variant-sample combination
 3. **Extracting genotype data**: Parses `GT:DP:GQ:AD` format into separate columns with calculated VAF
 4. **Adding parent data**: Joins father/mother genotypes when pedigree is provided
@@ -88,20 +89,22 @@ PyWombat transforms bcftools tabulated TSV files into analysis-ready formats by:
 **Input (Wide Format):**
 
 ```tsv
-#CHROM  POS  REF  ALT  (null)              Sample1:GT:DP:GQ:AD  Sample2:GT:DP:GQ:AD
-chr1    100  A    T    DP=30;AF=0.5;AC=2   0/1:15:99:5,10      1/1:18:99:0,18
+#CHROM  POS  REF  ALT  (null)                      Sample1:GT:DP:GQ:AD  Sample2:GT:DP:GQ:AD
+chr1    100  A    T    DP=30;AF=0.5;PASS;AC=2      0/1:15:99:5,10      1/1:18:99:0,18
 ```
 
 **Output (Long Format):**
 
 ```tsv
-#CHROM  POS  REF  ALT  AC  AF   DP  sample   sample_gt  sample_dp  sample_gq  sample_ad  sample_vaf
-chr1    100  A    T    2   0.5  30  Sample1  0/1        15         99         10         0.6667
-chr1    100  A    T    2   0.5  30  Sample2  1/1        18         99         18         1.0
+#CHROM  POS  REF  ALT  AC  AF   DP  PASS  sample   sample_gt  sample_dp  sample_gq  sample_ad  sample_vaf
+chr1    100  A    T    2   0.5  30  true  Sample1  0/1        15         99         10         0.6667
+chr1    100  A    T    2   0.5  30  true  Sample2  1/1        18         99         18         1.0
 ```
 
 **Generated Columns:**
 
+- INFO fields with `=`: Extracted as separate columns (e.g., `DP`, `AF`, `AC`)
+- INFO boolean flags: Extracted as True/False columns (e.g., `PASS`, `DB`, `SOMATIC`)
 - `sample`: Sample identifier
 - `sample_gt`: Genotype (e.g., 0/1, 1/1)
 - `sample_dp`: Read depth (total coverage)

pywombat-1.0.2.dist-info/RECORD

@@ -0,0 +1,6 @@
+pywombat/__init__.py,sha256=iIPN9vJtsIUhl_DiKNnknxCamLinfayodLLFK8y-aJg,54
+pywombat/cli.py,sha256=76pVpYYyl9rCm6TCq86j7xAqEC9pOvjiWCX9MmrBB_o,74994
+pywombat-1.0.2.dist-info/METADATA,sha256=slcagFwSvA99GVzKLRZggFPy5dkLEh_09O3dIB8Hfr4,17168
+pywombat-1.0.2.dist-info/WHEEL,sha256=WLgqFyCfm_KASv4WHyYy0P3pM_m7J5L9k2skdKLirC8,87
+pywombat-1.0.2.dist-info/entry_points.txt,sha256=Vt7U2ypbiEgCBlEV71ZPk287H5_HKmPBT4iBu6duEcE,44
+pywombat-1.0.2.dist-info/RECORD,,

pywombat-1.0.0.dist-info/RECORD

@@ -1,6 +0,0 @@
-pywombat/__init__.py,sha256=iIPN9vJtsIUhl_DiKNnknxCamLinfayodLLFK8y-aJg,54
-pywombat/cli.py,sha256=FK1bEKtFD1Drp5LNdXaVie4zyjYbZc3wTbsjms-wISU,74176
-pywombat-1.0.0.dist-info/METADATA,sha256=bIm5-Az795PLluvA_6yBPcHkcq6EOZbvB_g-4jPjx_U,16828
-pywombat-1.0.0.dist-info/WHEEL,sha256=WLgqFyCfm_KASv4WHyYy0P3pM_m7J5L9k2skdKLirC8,87
-pywombat-1.0.0.dist-info/entry_points.txt,sha256=Vt7U2ypbiEgCBlEV71ZPk287H5_HKmPBT4iBu6duEcE,44
-pywombat-1.0.0.dist-info/RECORD,,