feat: Release v17.0.0

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 +120,32 @@ 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: dict = read_json(sex_prediction_path)
+
+    given_sex: str = config["analysis"]["gender"]
+
+    sex_check_metrics = []
+
+    for sample_type in ["tumor", "normal"]:
+        if sample_type in sex_prediction:
+            predicted_sex = sex_prediction[sample_type]["predicted_sex"]
+            sex_prediction_metrics = Metric(
+                id=f"{case_id}_{sample_type}",
+                input=os.path.basename(sex_prediction_path),
+                name=metric.upper(),
+                step="sex_check",
+                value=predicted_sex,
+                condition={"norm": "eq", "threshold": given_sex},
+            ).model_dump()
+            sex_check_metrics.append(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"
@@ -186,7 +224,7 @@ def get_metric_condition(
     req_metrics = requested_metrics[metric]["condition"]
     if sequencing_type == "wgs" and (
         (metric == "PCT_60X" and sample_type == "normal")
-        or (metric == "PCT_15X" and sample_type == "tumor")
+        or (metric == "MEDIAN_COVERAGE" and sample_type == "tumor")
     ):
         req_metrics = None
 

BALSAMIC/assets/scripts/edit_vcf_info.py

@@ -42,7 +42,7 @@ def edit_vcf_info(input_vcf, output_vcf, variant_caller):
 
     with open(output_vcf, "wb"):
         for variant in vcf:
-            variant.INFO["FOUND_IN"] = variant_caller + "|" + output_vcf
+            variant.INFO["FOUND_IN"] = variant_caller
             new_vcf.write_record(variant)
     new_vcf.close()
     vcf.close()

BALSAMIC/assets/scripts/igh_dux4_detection.sh

@@ -55,11 +55,11 @@ get_supporting_reads() {
 # Set information for tumor and normal
 supporting_reads_tumor=$(get_supporting_reads $tumor_bam)
 samples_header="TUMOR"
-samples_field="${supporting_reads_tumor}"
+samples_field="0/1:${supporting_reads_tumor}"
 if [ -n "$normal_bam" ]; then
     supporting_reads_normal=$(get_supporting_reads $normal_bam)
     samples_header="NORMAL\tTUMOR"
-    samples_field="${supporting_reads_normal}\t${supporting_reads_tumor}"
+    samples_field="0/0:${supporting_reads_normal}\t0/1:${supporting_reads_tumor}"
 fi
 
 
@@ -82,7 +82,7 @@ echo "vcf filter: $vcf_filter"
   echo '##INFO=<ID=IMPRECISE,Number=0,Type=Flag,Description="Imprecise structural variation">'
   echo '##FORMAT=<ID=DV,Number=1,Type=Integer,Description="Number of paired-ends that support the event">'
   echo -e "#CHROM\tPOS\tID\tREF\tALT\tQUAL\tFILTER\tINFO\tFORMAT\t${samples_header}"
-  echo -e "${igh_chr}\t${igh_pos}\tsamtools_igh_dux4\tN\tN[${dux4_chr}:${dux4_pos}[\t.\t${vcf_filter}\tSVTYPE=BND;IMPRECISE;\tDV\t${samples_field}"
+  echo -e "${igh_chr}\t${igh_pos}\tsamtools_igh_dux4\tN\tN[${dux4_chr}:${dux4_pos}[\t.\t${vcf_filter}\tSVTYPE=BND;IMPRECISE;\tGT:DV\t${samples_field}"
 } >> $output_vcf_tmp
 
 bgzip $output_vcf_tmp