Add raredisease scout upload (#3591)(minor)

## Description

### Added

- scout upload for raredisease

### Changed

- unified scout upload for balsamic, rnafusion, raredisease and mip-dna using inherited functions

cg/cli/upload/scout.py

@@ -20,6 +20,7 @@
 from cg.meta.workflow.balsamic_umi import BalsamicUmiAnalysisAPI
 from cg.meta.workflow.mip_dna import MipDNAAnalysisAPI
 from cg.meta.workflow.mip_rna import MipRNAAnalysisAPI
+from cg.meta.workflow.raredisease import RarediseaseAnalysisAPI
 from cg.meta.workflow.rnafusion import RnafusionAnalysisAPI
 from cg.meta.workflow.tomte import TomteAnalysisAPI
 from cg.models.cg_config import CGConfig
@@ -88,11 +89,11 @@ def create_scout_load_config(context: CGConfig, case_id: str, print_console: boo
     except SyntaxError as error:
         LOG.warning(repr(error))
         raise click.Abort from error
-    LOG.info(f"Found load config {scout_load_config}")
+    LOG.info(f"Found load config: {scout_load_config}")
+
     root_dir: str = context.meta_apis["upload_api"].analysis_api.root
     LOG.info(f"Set root dir to {root_dir}")
     file_path: Path = Path(root_dir, case_id, "scout_load.yaml")
-
     if print_console:
         click.echo(
             WriteStream.write_stream_from_content(
@@ -315,6 +316,7 @@ def get_upload_api(case: Case, cg_config: CGConfig) -> UploadAPI:
         Workflow.BALSAMIC_UMI: BalsamicUmiAnalysisAPI,
         Workflow.MIP_RNA: MipRNAAnalysisAPI,
         Workflow.MIP_DNA: MipDNAAnalysisAPI,
+        Workflow.RAREDISEASE: RarediseaseAnalysisAPI,
         Workflow.RNAFUSION: RnafusionAnalysisAPI,
         Workflow.TOMTE: TomteAnalysisAPI,
     }

cg/constants/scout.py

@@ -41,6 +41,25 @@ class ScoutUploadKey(StrEnum):
 
 
 RAREDISEASE_CASE_TAGS = dict(
+    delivery_report={"delivery-report"},
+    multiqc={"multiqc-html"},
+    peddy_check={"ped-check", "peddy"},
+    peddy_ped={"ped", "peddy"},
+    peddy_sex={"sex-check", "peddy"},
+    smn_tsv={"smn-calling"},
+    vcf_mei={"mobile-elements", "clinical", "vcf"},
+    vcf_mei_research={"mobile-elements", "research", "vcf"},
+    vcf_snv_research={"vcf-snv-research"},
+    vcf_snv={"vcf-snv-clinical"},
+    vcf_snv_research_mt={"vcf-sv-research", "mitochondria"},
+    vcf_snv_mt={"vcf-sv-clinical", "mitochondria"},
+    str_catalog={"expansionhunter", "variant-catalog"},
+    vcf_sv_research={"vcf-sv-research"},
+    vcf_sv={"vcf-sv-clinical"},
+    vcf_str={"vcf-str"},
+)
+
+MIP_CASE_TAGS: dict[str, set[str]] = dict(
     delivery_report={"delivery-report"},
     multiqc_report={"multiqc-html"},
     peddy_check={"ped-check", "peddy"},
@@ -57,8 +76,6 @@ class ScoutUploadKey(StrEnum):
     vcf_str={"vcf-str"},
 )
 
-MIP_CASE_TAGS: dict[str, set[str]] = RAREDISEASE_CASE_TAGS
-
 BALSAMIC_CASE_TAGS = dict(
     sv_vcf={"vcf-sv-clinical"},
     snv_vcf={"vcf-snv-clinical"},
@@ -87,7 +104,22 @@ class ScoutUploadKey(StrEnum):
     vcf_fusion={"vcf-fusion"},
 )
 
-RAREDISEASE_SAMPLE_TAGS = dict(
+RAREDISEASE_SAMPLE_TAGS: dict[str, set[str]] = dict(
+    alignment_file={AlignmentFileTag.CRAM},
+    vcf2cytosure={"vcf2cytosure"},
+    mt_bam={"bam-mt"},
+    eklipse_path={"eklipse-png"},
+    chromograph_autozyg={"chromograph", "autozyg"},
+    chromograph_coverage={"chromograph", "tcov"},
+    chromograph_regions={"chromograph", "regions"},
+    chromograph_sites={"chromograph", "sites"},
+    reviewer_alignment={"expansionhunter", "bam"},
+    reviewer_alignment_index={"expansionhunter", "bam-index"},
+    reviewer_vcf={"expansionhunter", "vcf-str"},
+    mitodel_file={"mitodel"},
+)
+
+MIP_SAMPLE_TAGS: dict[str, set[str]] = dict(
     bam_file={"bam"},
     alignment_file={"cram"},
     vcf2cytosure={"vcf2cytosure"},
@@ -102,8 +134,6 @@ class ScoutUploadKey(StrEnum):
     mitodel_file={"mitodel"},
 )
 
-MIP_SAMPLE_TAGS: dict[str, set[str]] = RAREDISEASE_SAMPLE_TAGS
-
 BALSAMIC_SAMPLE_TAGS = dict(
     bam_file={"bam"},
     alignment_file={"cram"},

cg/meta/upload/raredisease/raredisease.py

@@ -34,8 +34,16 @@ def upload(self, ctx: click.Context, case: Case, restart: bool) -> None:
         ctx.invoke(upload_observations_to_loqusdb, case_id=case.internal_id)
         ctx.invoke(upload_to_gens, case_id=case.internal_id)
 
+        # Delivery report generation
+        if case.data_delivery in REPORT_SUPPORTED_DATA_DELIVERY:
+            ctx.invoke(generate_delivery_report, case_id=case.internal_id)
+
+        # Clinical delivery upload
         self.upload_files_to_customer_inbox(case)
 
+        # Scout specific upload
+        if DataDelivery.SCOUT in case.data_delivery:
+            ctx.invoke(upload_to_scout, case_id=case.internal_id, re_upload=restart)
         LOG.info(
             f"Upload of case {case.internal_id} was successful. Uploaded at {dt.datetime.now()} in StatusDB"
         )

cg/meta/upload/scout/balsamic_config_builder.py

@@ -5,7 +5,7 @@
 from cg.apps.lims import LimsAPI
 from cg.constants.constants import SampleType
 from cg.constants.housekeeper_tags import HK_DELIVERY_REPORT_TAG
-from cg.constants.scout import BALSAMIC_CASE_TAGS, BALSAMIC_SAMPLE_TAGS, UploadTrack
+from cg.constants.scout import BALSAMIC_CASE_TAGS, BALSAMIC_SAMPLE_TAGS, GenomeBuild, UploadTrack
 from cg.constants.subject import PhenotypeStatus
 from cg.meta.upload.scout.hk_tags import CaseTags, SampleTags
 from cg.meta.upload.scout.scout_config_builder import ScoutConfigBuilder
@@ -19,25 +19,21 @@
 class BalsamicConfigBuilder(ScoutConfigBuilder):
     def __init__(self, hk_version_obj: Version, analysis_obj: Analysis, lims_api: LimsAPI):
         super().__init__(
-            hk_version_obj=hk_version_obj, analysis_obj=analysis_obj, lims_api=lims_api
+            hk_version_obj=hk_version_obj,
+            analysis_obj=analysis_obj,
+            lims_api=lims_api,
         )
         self.case_tags: CaseTags = CaseTags(**BALSAMIC_CASE_TAGS)
         self.sample_tags: SampleTags = SampleTags(**BALSAMIC_SAMPLE_TAGS)
-        self.load_config: BalsamicLoadConfig = BalsamicLoadConfig(
-            track=UploadTrack.CANCER.value,
-            delivery_report=self.get_file_from_hk({HK_DELIVERY_REPORT_TAG}),
-        )
 
-    def include_case_files(self):
+    def include_case_files(self, load_config: BalsamicLoadConfig) -> None:
         LOG.info("Including BALSAMIC specific case level files")
-        self.load_config.vcf_cancer = self.get_file_from_hk(
-            hk_tags=self.case_tags.snv_vcf, latest=True
-        )
-        self.load_config.vcf_cancer_sv = self.get_file_from_hk(
+        load_config.vcf_cancer = self.get_file_from_hk(hk_tags=self.case_tags.snv_vcf, latest=True)
+        load_config.vcf_cancer_sv = self.get_file_from_hk(
             hk_tags=self.case_tags.sv_vcf, latest=True
         )
-        self.include_cnv_report()
-        self.include_multiqc_report()
+        self.include_cnv_report(load_config)
+        self.include_multiqc_report(load_config)
 
     def include_sample_files(self, config_sample: ScoutCancerIndividual) -> None:
         LOG.info("Including BALSAMIC specific sample level files.")
@@ -78,16 +74,21 @@ def get_balsamic_analysis_type(self, sample: Sample) -> str:
 
         return analysis_type
 
-    def build_load_config(self) -> None:
+    def build_load_config(self) -> BalsamicLoadConfig:
         LOG.info("Build load config for balsamic case")
-        self.add_common_info_to_load_config()
-        self.load_config.human_genome_build = "37"
-        self.load_config.rank_score_threshold = -100
-
-        self.include_case_files()
+        load_config: BalsamicLoadConfig = BalsamicLoadConfig(
+            track=UploadTrack.CANCER.value,
+            delivery_report=self.get_file_from_hk({HK_DELIVERY_REPORT_TAG}),
+        )
+        self.add_common_info_to_load_config(load_config)
+        load_config.human_genome_build = GenomeBuild.hg19
+        load_config.rank_score_threshold = -100
+        self.include_case_files(load_config)
 
         LOG.info("Building samples")
         db_sample: CaseSample
 
         for db_sample in self.analysis_obj.case.links:
-            self.load_config.samples.append(self.build_config_sample(case_sample=db_sample))
+            load_config.samples.append(self.build_config_sample(case_sample=db_sample))
+
+        return load_config

cg/meta/upload/scout/balsamic_umi_config_builder.py

@@ -4,26 +4,48 @@
 
 from cg.apps.lims import LimsAPI
 from cg.constants.housekeeper_tags import HK_DELIVERY_REPORT_TAG
-from cg.constants.scout import BALSAMIC_UMI_CASE_TAGS, BALSAMIC_UMI_SAMPLE_TAGS, UploadTrack
+from cg.constants.scout import (
+    BALSAMIC_UMI_CASE_TAGS,
+    BALSAMIC_UMI_SAMPLE_TAGS,
+    GenomeBuild,
+    UploadTrack,
+)
 from cg.meta.upload.scout.balsamic_config_builder import BalsamicConfigBuilder
 from cg.meta.upload.scout.hk_tags import CaseTags, SampleTags
 from cg.models.scout.scout_load_config import BalsamicUmiLoadConfig, ScoutCancerIndividual
-from cg.store.models import Analysis, Sample
+from cg.store.models import Analysis, CaseSample, Sample
 
 LOG = logging.getLogger(__name__)
 
 
 class BalsamicUmiConfigBuilder(BalsamicConfigBuilder):
     def __init__(self, hk_version_obj: Version, analysis_obj: Analysis, lims_api: LimsAPI):
         super().__init__(
-            hk_version_obj=hk_version_obj, analysis_obj=analysis_obj, lims_api=lims_api
+            hk_version_obj=hk_version_obj,
+            analysis_obj=analysis_obj,
+            lims_api=lims_api,
         )
         self.case_tags: CaseTags = CaseTags(**BALSAMIC_UMI_CASE_TAGS)
         self.sample_tags: SampleTags = SampleTags(**BALSAMIC_UMI_SAMPLE_TAGS)
-        self.load_config: BalsamicUmiLoadConfig = BalsamicUmiLoadConfig(
+
+    def build_load_config(self) -> BalsamicUmiLoadConfig:
+        LOG.info("Build load config for balsamic case")
+        load_config: BalsamicUmiLoadConfig = BalsamicUmiLoadConfig(
             track=UploadTrack.CANCER.value,
             delivery_report=self.get_file_from_hk({HK_DELIVERY_REPORT_TAG}),
         )
+        self.add_common_info_to_load_config(load_config)
+        load_config.human_genome_build = GenomeBuild.hg19
+        load_config.rank_score_threshold = -100
+        self.include_case_files(load_config)
+
+        LOG.info("Building samples")
+        db_sample: CaseSample
+
+        for db_sample in self.analysis_obj.case.links:
+            load_config.samples.append(self.build_config_sample(case_sample=db_sample))
+
+        return load_config
 
     def include_sample_files(self, config_sample: ScoutCancerIndividual) -> None:
         LOG.info("Including BALSAMIC specific sample level files")

cg/meta/upload/scout/hk_tags.py

@@ -12,6 +12,18 @@ class CaseTags(BaseModel):
         None, description="vcf_cancer_sv for rare disease and vcf_sv_cancer for cancer"
     )
     sv_research_vcf: set[str] | None = Field(None, description="vcf_sv_research for rare disease")
+    vcf_snv: set[str] | None = Field(
+        None, description="vcf_snv for rare disease and vcf_cancer for cancer"
+    )
+    vcf_snv_research: set[str] | None = Field(None, description="vcf_snv_research for rare disease")
+    vcf_snv_mt: set[str] | None = Field(None, description="vcf_snv for rare disease, mitochondria")
+    vcf_snv_research_mt: set[str] | None = Field(
+        None, description="vcf_snv_research for rare disease, mitochondria"
+    )
+    vcf_sv: set[str] | None = Field(
+        None, description="vcf_cancer_sv for rare disease and vcf_sv_cancer for cancer"
+    )
+    vcf_sv_research: set[str] | None = Field(None, description="vcf_sv_research for rare disease")
     vcf_str: set[str] = Field(
         None, description="Short Tandem Repeat variants, only for rare disease"
     )
@@ -21,6 +33,7 @@ class CaseTags(BaseModel):
     peddy_sex: set[str] | None = Field(None, description="Peddy sex check, only for rare disease")
     peddy_check: set[str] = Field(None, description="Peddy pedigree check, only for rare disease")
     multiqc_report: set[str] | None = Field(None, description="MultiQC report")
+    multiqc: set[str] | None = Field(None, description="MultiQC report")
     delivery_report: set[str] | None = Field(None, description="Delivery report")
     str_catalog: set[str] | None = Field(
         None, description="Variant catalog used with expansionhunter"
@@ -57,13 +70,16 @@ class SampleTags(BaseModel):
     # If cram does not exist
     bam_file: set[str] | None = None
     alignment_file: set[str] | None = None
+    alignment_path: set[str] | None = None
     vcf2cytosure: set[str] | None = None
+    eklipse_path: set[str] | None = None
     mt_bam: set[str] | None = None
     chromograph_autozyg: set[str] | None = None
     chromograph_coverage: set[str] | None = None
     chromograph_regions: set[str] | None = None
     chromograph_sites: set[str] | None = None
     reviewer_alignment: set[str] | None = None
     reviewer_alignment_index: set[str] | None = None
+    reviewer_catalog: set[str] | None = None
     reviewer_vcf: set[str] | None = None
     mitodel_file: set[str] | None = None