feat: add tga cnvkit to gens

BALSAMIC/assets/scripts/postprocess_gens_cnvkit.py

@@ -0,0 +1,91 @@
+import click
+from BALSAMIC.utils.io import read_csv, write_list_of_strings
+
+def calculate_log2_ratio(purity, log2_ratio, ploidy):
+    # Ensure that the inputs are within valid ranges
+    if not (0 <= purity <= 1):
+        raise ValueError("Purity must be between 0 and 1")
+
+    if ploidy <= 0:
+        raise ValueError("Ploidy must be a positive number")
+
+    # Ploidy and purity adjustment formula reference to PureCN issue: https://github.com/lima1/PureCN/issues/40
+    log2_adjusted = (
+        purity * log2_ratio * ploidy + 2 * (1 - purity) * log2_ratio - 2 * (1 - purity)
+    ) / (purity * ploidy)
+
+    return log2_adjusted
+
+
+@click.command()
+@click.option(
+    "-o",
+    "--output-file",
+    required=True,
+    type=click.Path(exists=False),
+    help="Name of output-file.",
+)
+@click.option(
+    "-c",
+    "--normalised-coverage-path",
+    required=True,
+    type=click.Path(exists=True),
+    help="Input CNVkit cnr. result.",
+)
+@click.option(
+    "-p",
+    "--tumor-purity-path",
+    required=True,
+    type=click.Path(exists=True),
+    help="Tumor purity file from PureCN",
+)
+def create_gens_cov_file(
+    output_file: str, normalised_coverage_path: str, tumor_purity_path: str
+):
+    """Post-processes the CNVkit .cnr output for upload to GENS.
+
+    Removes Antitarget regions, adjusts for purity and ploidy and outputs the coverages in multiple resolution-formats.
+
+    Args:
+        output_file: Path to GENS output.cov file
+        normalised_coverage_path: Path to input CNVkit cnr file.
+        tumor_purity_path: Path to PureCN purity estimate csv file
+    """
+    log2_data = []
+
+    # Process CNVkit file
+    cnr_dict_list: list[dict] = read_csv(
+        csv_path=normalised_coverage_path, delimeter="\t"
+    )
+
+    # Process PureCN purity file
+    purecn_dict_list: list[dict] = read_csv(csv_path=tumor_purity_path, delimeter=",")
+    purity = float(purecn_dict_list[0]["Purity"])
+    ploidy = float(purecn_dict_list[0]["Ploidy"])
+
+    for row in cnr_dict_list:
+        if row["gene"] == "Antitarget":
+            continue
+
+        # find midpoint
+        start: int = int(row["start"])
+        end: int = int(row["end"])
+        region_size: int = end - start
+        midpoint: int = start + int(region_size / 2)
+
+        # adjust log2 ratio
+        log2: float = float(row["log2"])
+        log2: float = calculate_log2_ratio(purity, log2, ploidy)
+        log2: float = round(log2, 4)
+
+        # store values in list
+        log2_data.append(f"{row['chromosome']}\t{midpoint - 1}\t{midpoint}\t{log2}")
+
+    # Write log2 data to output file
+    resolutions = ["o", "a", "b", "c", "d"]
+    resolution_log2_lines = [f"{resolution}_{line}" for resolution in resolutions for line in log2_data]
+    write_list_of_strings(resolution_log2_lines, output_file)
+
+
+if __name__ == "__main__":
+    create_gens_cov_file()

BALSAMIC/assets/scripts/preprocess_gens.py

@@ -26,7 +26,7 @@
     "-s",
     "--sequencing-type",
     required=True,
-    type=click.Choice([SequencingType.WGS]),
+    type=click.Choice([SequencingType.WGS, SequencingType.TARGETED]),
     help="Sequencing type used.",
 )
 @click.pass_context

BALSAMIC/commands/config/case.py

@@ -54,6 +54,7 @@
     get_bioinfo_tools_version,
     get_panel_chrom,
     get_sample_list,
+    get_gens_references,
 )
 from BALSAMIC.utils.io import read_json, write_json
 from BALSAMIC.utils.utils import get_absolute_paths_dict
@@ -131,29 +132,22 @@ def case_config(
     if cadd_annotations:
         references.update(cadd_annotations_path)
 
-    if any([genome_interval, gens_coverage_pon, gnomad_min_af5]):
-        if panel_bed:
-            raise click.BadParameter(
-                "GENS is currently not compatible with TGA analysis, only WGS."
-            )
-        if not all([genome_interval, gens_coverage_pon, gnomad_min_af5]):
-            raise click.BadParameter(
-                "All three arguments (genome_interval gens_coverage_pon, gnomad_min_af5) are required for GENS."
-            )
-
-        gens_ref_files = {
-            "genome_interval": genome_interval,
-            "gens_coverage_pon": gens_coverage_pon,
-            "gnomad_min_af5": gnomad_min_af5,
-        }
-
-        references.update(
-            {
-                gens_file: path
-                for gens_file, path in gens_ref_files.items()
-                if path is not None
-            }
+    if analysis_workflow is not AnalysisWorkflow.BALSAMIC_QC:
+        gens_references: dict[str, str] = get_gens_references(
+            genome_interval=genome_interval,
+            gens_coverage_pon=gens_coverage_pon,
+            gnomad_min_af5=gnomad_min_af5,
+            panel_bed=panel_bed,
         )
+        if gens_references:
+            # Update references dictionary with GENS reference-files
+            references.update(
+                {
+                    gens_file: path
+                    for gens_file, path in gens_references.items()
+                    if path is not None
+                }
+            )
 
     variants_observations = {
         "clinical_snv_observations": clinical_snv_observations,

BALSAMIC/constants/cluster_analysis.json

@@ -11,7 +11,7 @@
 		"time": "00:15:00",
 		"n": 1
 	},
-	"gens_preprocessing": {
+	"gens_preprocess": {
 		"time": "01:00:00",
 		"n": 4
 	},
@@ -108,7 +108,7 @@
 		"time": "10:00:00",
 		"n": 5
 	},
-	"gatk_denoisereadcounts":{
+	"gatk_denoise_read_counts":{
 		"time": "10:00:00",
 		"n": 10
 	},
@@ -168,6 +168,10 @@
 		"time": "24:00:00",
 		"n": 36
 	},
+	"sentieon_DNAscope_gnomad_tga": {
+		"time": "24:00:00",
+		"n": 12
+	},
 	"sentieon_TNhaplotyper": {
 		"time": "24:00:00",
 		"n": 36

BALSAMIC/constants/tools.py

@@ -40,6 +40,9 @@
                 "c": 1000,
                 "d": 100,
             },
-        }
+        },
+        SequencingType.TARGETED: {
+            "BAF_SKIP_N": {"o": 0, "a": 0, "b": 0, "c": 0, "d": 0},
+        },
     },
 }

BALSAMIC/containers/varcall_py3/varcall_py3.yaml

@@ -163,7 +163,6 @@ dependencies:
   - svdb=2.8.1
   - sysroot_linux-64=2.12
   - tabix=1.11
-  - tiddit=3.3.2
   - tk=8.6.12
   - tktable=2.10
   - toolz=0.12.0