feat: add sex check

BALSAMIC/assets/scripts/collect_qc_metrics.py

@@ -25,10 +25,17 @@
 @click.argument("output_path", type=click.Path(exists=False), required=True)
 @click.argument("multiqc_data_path", type=click.Path(exists=True), required=True)
 @click.argument("counts_path", nargs=-1, type=click.Path(exists=True), required=False)
+@click.option(
+    "--sex-prediction-path",
+    type=click.Path(exists=True),
+    required=False,
+    help="Path to sex prediction json (optional for balsamic-qc)",
+)
 def collect_qc_metrics(
     config_path: Path,
     output_path: Path,
     multiqc_data_path: Path,
+    sex_prediction_path: Path,
     counts_path: List[Path],
 ):
     """Extracts the requested metrics from a JSON multiqc file and saves them to a YAML file
@@ -37,6 +44,7 @@ def collect_qc_metrics(
         config_path: Path; case config file path
         output_path: Path; destination path for the extracted YAML formatted metrics
         multiqc_data_path: Path; multiqc JSON path from which the metrics will be extracted
+        sex_prediction_path: Path; sex prediction JSON path from which sex prediction info will be extracted
         counts_path: Path; list of variant caller specific files containing the number of variants
     """
 
@@ -50,6 +58,10 @@ def collect_qc_metrics(
     for count in counts_path:
         metrics += get_variant_metrics(count)
 
+    # Sex check
+    if sex_prediction_path:
+        metrics += get_sex_check_metrics(sex_prediction_path, config)
+
     # Relatedness
     analysis_type = get_analysis_type(config)
     if analysis_type == "paired" and "Somalier" in multiqc_data["report_data_sources"]:
@@ -108,6 +120,43 @@ def get_multiqc_data_source(multiqc_data: dict, sample: str, tool: str) -> str:
                     )
 
 
+def get_sex_check_metrics(sex_prediction_path: str, config: dict) -> list:
+    """Retrieves the sex check metrics and returns them as a Metric list."""
+    metric = "compare_predicted_to_given_sex"
+    case_id: str = config["analysis"]["case_id"]
+    sex_prediction = read_json(sex_prediction_path)
+
+    given_sex: str = config["analysis"]["gender"]
+    tumor_predicted_sex: str = sex_prediction["tumor"]["predicted_sex"]
+
+    tumor_sex_prediction_metrics = Metric(
+        id=f"{case_id}_tumor",
+        input=os.path.basename(sex_prediction_path),
+        name=metric.upper(),
+        step="sex_check",
+        value=tumor_predicted_sex,
+        condition={"norm": "eq", "threshold": given_sex},
+    ).model_dump()
+
+    sex_check_metrics = [tumor_sex_prediction_metrics]
+
+    if "normal" in sex_prediction:
+        normal_predicted_sex: str = sex_prediction["normal"]["predicted_sex"]
+
+        normal_sex_prediction_metrics = Metric(
+            id=f"{case_id}_normal",
+            input=os.path.basename(sex_prediction_path),
+            name=metric.upper(),
+            step="sex_check",
+            value=normal_predicted_sex,
+            condition={"norm": "eq", "threshold": given_sex},
+        ).model_dump()
+
+        sex_check_metrics.append(normal_sex_prediction_metrics)
+
+    return sex_check_metrics
+
+
 def get_relatedness_metrics(multiqc_data: dict) -> list:
     """Retrieves the relatedness metrics and returns them as a Metric list."""
     source_tool = "Somalier"