Update balsamic tags & upload a CGH file to Scout

cg/cli/workflow/balsamic/base.py

@@ -6,13 +6,15 @@
 from cg.apps.housekeeper.hk import HousekeeperAPI
 from cg.cli.workflow.balsamic.options import (
     OPTION_PANEL_BED,
-    OPTION_DRY,
     OPTION_QOS,
     OPTION_ANALYSIS_TYPE,
     OPTION_RUN_ANALYSIS,
+    OPTION_GENOME_VERSION,
+    OPTION_PON_CNN,
 )
 from cg.cli.workflow.commands import link, resolve_compression, ARGUMENT_CASE_ID
 from cg.constants import EXIT_FAIL, EXIT_SUCCESS
+from cg.constants.constants import DRY_RUN
 from cg.exc import CgError, DecompressionNeededError
 from cg.meta.workflow.analysis import AnalysisAPI
 from cg.meta.workflow.balsamic import BalsamicAnalysisAPI
@@ -42,17 +44,32 @@ def balsamic(context: click.Context):
 
 @balsamic.command("config-case")
 @ARGUMENT_CASE_ID
+@OPTION_GENOME_VERSION
 @OPTION_PANEL_BED
-@OPTION_DRY
+@OPTION_PON_CNN
+@DRY_RUN
 @click.pass_obj
-def config_case(context: CGConfig, panel_bed: str, case_id: str, dry_run: bool):
+def config_case(
+    context: CGConfig,
+    case_id: str,
+    genome_version: str,
+    panel_bed: str,
+    pon_cnn: click.Path,
+    dry_run: bool,
+):
     """Create config file for BALSAMIC analysis for a given CASE_ID"""
 
     analysis_api: AnalysisAPI = context.meta_apis["analysis_api"]
     try:
         LOG.info(f"Creating config file for {case_id}.")
         analysis_api.verify_case_id_in_statusdb(case_id=case_id)
-        analysis_api.config_case(case_id=case_id, panel_bed=panel_bed, dry_run=dry_run)
+        analysis_api.config_case(
+            case_id=case_id,
+            genome_version=genome_version,
+            panel_bed=panel_bed,
+            pon_cnn=pon_cnn,
+            dry_run=dry_run,
+        )
     except CgError as e:
         LOG.error(f"Could not create config: {e.message}")
         raise click.Abort()
@@ -63,7 +80,7 @@ def config_case(context: CGConfig, panel_bed: str, case_id: str, dry_run: bool):
 
 @balsamic.command("run")
 @ARGUMENT_CASE_ID
-@OPTION_DRY
+@DRY_RUN
 @OPTION_QOS
 @OPTION_ANALYSIS_TYPE
 @OPTION_RUN_ANALYSIS
@@ -103,7 +120,7 @@ def run(
 
 @balsamic.command("report-deliver")
 @ARGUMENT_CASE_ID
-@OPTION_DRY
+@DRY_RUN
 @OPTION_ANALYSIS_TYPE
 @click.pass_obj
 def report_deliver(context: CGConfig, case_id: str, analysis_type: str, dry_run: bool):
@@ -156,17 +173,21 @@ def store_housekeeper(context: CGConfig, case_id: str):
 
 @balsamic.command("start")
 @ARGUMENT_CASE_ID
+@OPTION_GENOME_VERSION
 @OPTION_ANALYSIS_TYPE
 @OPTION_QOS
-@OPTION_DRY
+@DRY_RUN
 @OPTION_PANEL_BED
+@OPTION_PON_CNN
 @OPTION_RUN_ANALYSIS
 @click.pass_context
 def start(
     context: click.Context,
     case_id: str,
+    genome_version: str,
     analysis_type: str,
     panel_bed: str,
+    pon_cnn: str,
     slurm_quality_of_service: str,
     run_analysis: bool,
     dry_run: bool,
@@ -176,7 +197,14 @@ def start(
     try:
         context.invoke(resolve_compression, case_id=case_id, dry_run=dry_run)
         context.invoke(link, case_id=case_id, dry_run=dry_run)
-        context.invoke(config_case, case_id=case_id, panel_bed=panel_bed, dry_run=dry_run)
+        context.invoke(
+            config_case,
+            case_id=case_id,
+            genome_version=genome_version,
+            panel_bed=panel_bed,
+            pon_cnn=pon_cnn,
+            dry_run=dry_run,
+        )
         context.invoke(
             run,
             case_id=case_id,
@@ -190,7 +218,7 @@ def start(
 
 
 @balsamic.command("start-available")
-@OPTION_DRY
+@DRY_RUN
 @click.pass_context
 def start_available(context: click.Context, dry_run: bool = False):
     """Start full workflow for all cases ready for analysis"""
@@ -213,7 +241,7 @@ def start_available(context: click.Context, dry_run: bool = False):
 
 @balsamic.command("store")
 @ARGUMENT_CASE_ID
-@OPTION_DRY
+@DRY_RUN
 @OPTION_ANALYSIS_TYPE
 @click.pass_context
 def store(context: click.Context, case_id: str, analysis_type: str, dry_run: bool):
@@ -224,7 +252,7 @@ def store(context: click.Context, case_id: str, analysis_type: str, dry_run: boo
 
 
 @balsamic.command("store-available")
-@OPTION_DRY
+@DRY_RUN
 @click.pass_context
 def store_available(context: click.Context, dry_run: bool) -> None:
     """Store bundles for all finished analyses in Housekeeper"""

cg/cli/workflow/balsamic/options.py

@@ -1,9 +1,14 @@
 import click
 
+from cg.constants.constants import GenomeVersions
 from cg.constants.priority import SlurmQos
 
-OPTION_DRY = click.option(
-    "-d", "--dry-run", help="Print command to console without executing", is_flag=True
+OPTION_GENOME_VERSION = click.option(
+    "--genome-version",
+    show_default=True,
+    default=GenomeVersions.hg19,
+    type=click.Choice([GenomeVersions.hg19, GenomeVersions.hg38, GenomeVersions.canfam3]),
+    help="Type and build version of the reference genome. Set this option to override the default.",
 )
 OPTION_PANEL_BED = click.option(
     "--panel-bed",
@@ -28,6 +33,11 @@
     "-qos",
     "--slurm-quality-of-service",
     type=click.Choice([SlurmQos.LOW, SlurmQos.NORMAL, SlurmQos.HIGH, SlurmQos.EXPRESS]),
-    help="Job priority in SLURM. Will be set automatically according to priority in ClinicalDB, \
-         this option can be used to override server setting",
+    help="Job priority in SLURM. Setting this option will override the StatusDB case priority.",
+)
+OPTION_PON_CNN = click.option(
+    "--pon-cnn",
+    type=click.Path(exists=True),
+    required=False,
+    help="Panel of normal reference (.cnn) for cnvkit",
 )

cg/constants/constants.py

@@ -52,6 +52,12 @@
 STATUS_OPTIONS = ("affected", "unaffected", "unknown")
 
 
+class GenomeVersions(StrEnum):
+    hg19: str = "hg19"
+    hg38: str = "hg38"
+    canfam3: str = "canfam3"
+
+
 class DataDelivery(StrEnum):
     ANALYSIS_BAM_FILES: str = "analysis-bam"
     ANALYSIS_FILES: str = "analysis"

cg/constants/delivery.py

@@ -14,49 +14,44 @@
     "sarscov2",
 ]
 
-BALSAMIC_ANALYSIS_ONLY_CASE_TAGS = [
+BALSAMIC_ANALYSIS_CASE_TAGS = [
+    {"multiqc-html"},
+    {"metrics"},
+    {"visualization"},
+    {"vcf-sv-clinical"},
+    {"vcf-sv-clinical-index"},
+    {"vcf-sv-research"},
+    {"vcf-sv-research-index"},
     {"vcf-snv-clinical"},
     {"vcf-snv-clinical-index"},
-    {"vardict", "deliver"},
-    {"vcf", "sention", "haplotype-caller", "filtered"},
-    {"vcf-index", "sention", "haplotype-caller", "filtered"},
-    {"vcf-sv-clinical", "manta", "filtered"},
-    {"vcf-sv-clinical-index", "manta", "filtered"},
-    {"vcf-sv-research", "filtered"},
-    {"vcf-sv-research-index", "filtered"},
-    {"ascatngs", "visualization"},
-    {"cnvkit", "vcf-sv-research", "filtered"},
-    {"cnvkit", "vcf-sv-research-index", "filtered"},
-    {"cnvkit", "visualization"},
-    {"cnvkit", "visualization", "diagram"},
-    {"cnvkit", "regions"},
-    {"multiqc-html"},
+    {"vcf-snv-research"},
+    {"vcf-snv-research-index"},
+    {"germline", "vcf"},
+    {"germline", "vcf-index"},
+    {"vcf2cytosure"},
 ]
 
-BALSAMIC_ANALYSIS_CASE_TAGS = copy.deepcopy(BALSAMIC_ANALYSIS_ONLY_CASE_TAGS)
-BALSAMIC_ANALYSIS_CASE_TAGS.extend(
-    [
-        {"cram", "normal"},
-        {"cram-index"},
-        {"cram", "tumor"},
-        {"cram-index", "tumor"},
-    ]
-)
-
 BALSAMIC_ANALYSIS_SAMPLE_TAGS = [
-    {"cram", "normal"},
+    {"cram"},
     {"cram-index"},
-    {"cram", "tumor"},
-    {"cram-index", "tumor"},
 ]
 
-BALSAMIC_QC_CASE_TAGS = [
-    {"multiqc-html"},
+BALSAMIC_UMI_ANALYSIS_CASE_TAGS = [
+    {"vcf-umi-clinical"},
+    {"vcf-umi-clinical-index"},
+    {"vcf-umi-research"},
+    {"vcf-umi-research-index"},
 ]
-BALSAMIC_QC_SAMPLE_TAGS = [
-    {"fastq"},
+
+BALSAMIC_UMI_ANALYSIS_CASE_TAGS.extend(BALSAMIC_ANALYSIS_CASE_TAGS)
+
+BALSAMIC_UMI_ANALYSIS_SAMPLE_TAGS = [
+    {"umi-cram"},
+    {"umi-cram-index"},
 ]
 
+BALSAMIC_UMI_ANALYSIS_SAMPLE_TAGS.extend(BALSAMIC_ANALYSIS_SAMPLE_TAGS)
+
 
 MIP_DNA_ANALYSIS_CASE_TAGS = [
     {"vcf-clinical-sv-bin"},
@@ -135,10 +130,9 @@
         "case_tags": BALSAMIC_ANALYSIS_CASE_TAGS,
         "sample_tags": BALSAMIC_ANALYSIS_SAMPLE_TAGS,
     },
-    "balsamic-analysis": {"case_tags": BALSAMIC_ANALYSIS_ONLY_CASE_TAGS, "sample_tags": []},
-    "balsamic-qc": {
-        "case_tags": BALSAMIC_QC_CASE_TAGS,
-        "sample_tags": BALSAMIC_QC_SAMPLE_TAGS,
+    "balsamic-umi": {
+        "case_tags": BALSAMIC_UMI_ANALYSIS_CASE_TAGS,
+        "sample_tags": BALSAMIC_UMI_ANALYSIS_SAMPLE_TAGS,
     },
     "mip-dna": {
         "case_tags": MIP_DNA_ANALYSIS_CASE_TAGS,

cg/constants/scout_upload.py

@@ -13,8 +13,8 @@
 )
 
 BALSAMIC_CASE_TAGS = dict(
-    snv_vcf={"vcf-snv-clinical"},
     sv_vcf={"vcf-sv-clinical"},
+    snv_vcf={"vcf-snv-clinical"},
     cnv_report={"ascatngs", "visualization"},
     multiqc_report={"multiqc-html"},
     delivery_report={"delivery-report"},
@@ -34,4 +34,5 @@
 BALSAMIC_SAMPLE_TAGS = dict(
     bam_file={"bam"},
     alignment_file={"cram"},
+    vcf2cytosure={"vcf2cytosure"},
 )

cg/meta/upload/scout/balsamic_config_builder.py

@@ -31,8 +31,12 @@ def include_case_files(self):
         self.include_multiqc_report()
         self.include_delivery_report()
 
-    def include_sample_files(self, config_sample: ScoutBalsamicIndividual):
+    def include_sample_files(self, config_sample: ScoutBalsamicIndividual) -> None:
         LOG.info("Including BALSAMIC specific sample level files")
+        if config_sample.alignment_path and "tumor" in config_sample.alignment_path:
+            config_sample.vcf2cytosure = self.fetch_sample_file(
+                hk_tags=self.sample_tags.vcf2cytosure, sample_id=self.load_config.family
+            )
 
     def include_delivery_report(self) -> None:
         LOG.info("Include coverage qc report to case")

cg/meta/workflow/balsamic.py

@@ -198,6 +198,24 @@ def get_verified_bed(self, sample_data: dict, panel_bed: Path) -> Optional[str]:
                 )
             return Path(self.bed_path, target_bed).as_posix()
 
+    @staticmethod
+    def get_verified_pon(panel_bed: Path, pon_cnn: str) -> Optional[str]:
+        """Returns the validated PoN path
+
+        Raises BalsamicStartError:
+            When there is a missmatch between the PoN and the panel bed file names
+        """
+        if pon_cnn:
+            pon_cnn = Path(str(pon_cnn))
+            if panel_bed.stem not in pon_cnn.stem:
+                raise BalsamicStartError(
+                    f"The specified PoN reference file {pon_cnn} does not match the panel bed {panel_bed}"
+                )
+
+            return pon_cnn.as_posix()
+
+        return pon_cnn
+
     @staticmethod
     def get_verified_tumor_path(sample_data: dict) -> str:
         """Takes a dict with samples and attributes, and returns the path
@@ -341,9 +359,7 @@ def get_normal_sample_name(self, case_id: str) -> Optional[str]:
             return sample_obj.internal_id
 
     def get_verified_config_case_arguments(
-        self,
-        case_id: str,
-        panel_bed: str,
+        self, case_id: str, genome_version: str, panel_bed: str, pon_cnn: str
     ) -> dict:
         """Takes a dictionary with per-sample parameters,
         validates them, and transforms into command line arguments
@@ -370,9 +386,11 @@ def get_verified_config_case_arguments(
 
         return {
             "case_id": case_id,
+            "genome_version": genome_version,
             "normal": self.get_verified_normal_path(sample_data=sample_data),
             "tumor": self.get_verified_tumor_path(sample_data=sample_data),
             "panel_bed": self.get_verified_bed(sample_data=sample_data, panel_bed=panel_bed),
+            "pon_cnn": self.get_verified_pon(pon_cnn=pon_cnn, panel_bed=panel_bed),
             "tumor_sample_name": self.get_tumor_sample_name(case_id=case_id),
             "normal_sample_name": self.get_normal_sample_name(case_id=case_id),
         }
@@ -508,18 +526,32 @@ def __build_command_str(options: dict) -> List[str]:
                 formatted_options.append(str(val))
         return formatted_options
 
-    def config_case(self, case_id: str, panel_bed: str, dry_run: bool = False) -> None:
+    def config_case(
+        self,
+        case_id: str,
+        genome_version: str,
+        panel_bed: str,
+        pon_cnn: str,
+        dry_run: bool = False,
+    ) -> None:
         """Create config file for BALSAMIC analysis"""
-        arguments = self.get_verified_config_case_arguments(case_id=case_id, panel_bed=panel_bed)
+        arguments = self.get_verified_config_case_arguments(
+            case_id=case_id,
+            genome_version=genome_version,
+            panel_bed=panel_bed,
+            pon_cnn=pon_cnn,
+        )
         command = ["config", "case"]
         options = self.__build_command_str(
             {
                 "--analysis-dir": self.root_dir,
                 "--balsamic-cache": self.balsamic_cache,
                 "--case-id": arguments.get("case_id"),
+                "--genome-version": arguments.get("genome_version"),
                 "--normal": arguments.get("normal"),
                 "--tumor": arguments.get("tumor"),
                 "--panel-bed": arguments.get("panel_bed"),
+                "--pon-cnn": arguments.get("pon_cnn"),
                 "--umi-trim-length": arguments.get("umi_trim_length"),
                 "--tumor-sample-name": arguments.get("tumor_sample_name"),
                 "--normal-sample-name": arguments.get("normal_sample_name"),
@@ -565,7 +597,7 @@ def report_deliver(
                 "--analysis-type": analysis_type or self.get_analysis_type(case_id),
             }
         )
-        parameters = command + options + ["--no-qc-metrics"]
+        parameters = command + options
         self.process.run_command(parameters=parameters, dry_run=dry_run)
 
     def get_analysis_type(self, case_id: str) -> Optional[str]: