Refactor prep category (#3961)

### Changed

- Rename PrpeCategory to SeqLibPrepCategory
- Move the class to sequencing.py under constants
- Removed implicit import from constant/__init__.py
- DRY: Removed SequencingMethod as it is dictated by SeqLibPrepCategory

cg/apps/gens.py

@@ -2,7 +2,7 @@
 
 import logging
 
-from cg.constants.constants import PrepCategory
+from cg.constants.sequencing import SeqLibraryPrepCategory
 from cg.store.models import Case
 from cg.utils import Process
 from cg.utils.dict import get_list_from_dictionary
@@ -51,7 +51,8 @@ def load(
     def is_suitable_for_upload(case: Case) -> bool:
         """Check if a cancer case supports Gens upload."""
         return all(
-            sample.prep_category == PrepCategory.WHOLE_GENOME_SEQUENCING for sample in case.samples
+            sample.prep_category == SeqLibraryPrepCategory.WHOLE_GENOME_SEQUENCING
+            for sample in case.samples
         )
 
     def __str__(self):

cg/apps/orderform/excel_orderform_parser.py

@@ -25,7 +25,7 @@ class ExcelOrderformParser(OrderformParser):
     SHEET_NAMES: list[str] = ["Orderform", "orderform", "order form", "Order Form"]
     VALID_ORDERFORMS: list[str] = [
         f"{Orderform.MIP_DNA}:{Orderform.get_current_orderform_version(Orderform.MIP_DNA)}",  # Orderform MIP-DNA, Balsamic, sequencing only, MIP-RNA
-        f"{Orderform.MICROSALT}:{Orderform.get_current_orderform_version(Orderform.MICROSALT)}",  # Microbial WGS
+        f"{Orderform.MICROSALT}:{Orderform.get_current_orderform_version(Orderform.MICROSALT)}",  # Microbial WHOLE_GENOME_SEQUENCING
         f"{Orderform.RML}:{Orderform.get_current_orderform_version(Orderform.RML)}",  # Orderform Ready made libraries (RML)
         f"{Orderform.METAGENOME}:{Orderform.get_current_orderform_version(Orderform.METAGENOME)}",  # Microbial meta genomes
         f"{Orderform.SARS_COV_2}:{Orderform.get_current_orderform_version(Orderform.SARS_COV_2)}",  # Orderform SARS-CoV-2

cg/cli/workflow/balsamic/options.py

@@ -40,7 +40,7 @@
     type=click.Path(exists=True),
     multiple=True,
     required=False,
-    help="VCF paths of clinical and/or cancer SNVs and SVs observations (WGS analysis only). Set this option to "
+    help="VCF paths of clinical and/or cancer SNVs and SVs observations (WHOLE_GENOME_SEQUENCING analysis only). Set this option to "
     "override the latest Loqusdb dump files.",
 )
 

cg/constants/__init__.py

@@ -9,7 +9,6 @@
     STATUS_OPTIONS,
     DataDelivery,
     FileExtensions,
-    PrepCategory,
     SequencingRunDataAvailability,
     SexOptions,
 )

cg/constants/constants.py

@@ -102,16 +102,6 @@ class CancerAnalysisType(StrEnum):
     TUMOR_WGS = auto()
 
 
-class PrepCategory(StrEnum):
-    COVID: str = "cov"
-    MICROBIAL: str = "mic"
-    READY_MADE_LIBRARY: str = "rml"
-    TARGETED_GENOME_SEQUENCING: str = "tgs"
-    WHOLE_EXOME_SEQUENCING: str = "wes"
-    WHOLE_GENOME_SEQUENCING: str = "wgs"
-    WHOLE_TRANSCRIPTOME_SEQUENCING: str = "wts"
-
-
 class SexOptions(StrEnum):
     MALE: str = "male"
     FEMALE: str = "female"

cg/constants/observations.py

@@ -3,7 +3,7 @@
 from enum import Enum, StrEnum
 
 from cg.constants.constants import CancerAnalysisType, CustomerId, Workflow
-from cg.constants.sequencing import SequencingMethod
+from cg.constants.sequencing import SeqLibraryPrepCategory
 
 LOQUSDB_ID = "_id"
 LOQUSDB_SUPPORTED_WORKFLOWS = [Workflow.BALSAMIC, Workflow.MIP_DNA, Workflow.RAREDISEASE]
@@ -14,7 +14,10 @@
     CustomerId.CUST143,
     CustomerId.CUST147,
 ]
-LOQUSDB_RARE_DISEASE_SEQUENCING_METHODS = [SequencingMethod.WGS, SequencingMethod.WES]
+LOQUSDB_RARE_DISEASE_SEQUENCING_METHODS = [
+    SeqLibraryPrepCategory.WHOLE_GENOME_SEQUENCING,
+    SeqLibraryPrepCategory.WHOLE_EXOME_SEQUENCING,
+]
 LOQUSDB_CANCER_SEQUENCING_METHODS = [
     CancerAnalysisType.TUMOR_WGS,
     CancerAnalysisType.TUMOR_NORMAL_WGS,

cg/constants/report.py

@@ -227,7 +227,7 @@
     "mean_length_r1",
 ]
 
-# WTS metadata required fields (OPTIONAL: "rin", "dv200")
+# WHOLE_TRANSCRIPTOME_SEQUENCING metadata required fields (OPTIONAL: "rin", "dv200")
 _REQUIRED_SAMPLE_METADATA_WTS_FIELDS: list[str] = _REQUIRED_SAMPLE_METADATA_SEQUENCING_FIELDS + [
     "bias_5_3",
     "input_amount",

cg/constants/sequencing.py

@@ -47,15 +47,6 @@ class Sequencers(StrEnum):
 }
 
 
-class SequencingMethod(StrEnum):
-    """Sequencing method types."""
-
-    TGS: str = "tgs"
-    WES: str = "wes"
-    WGS: str = "wgs"
-    WTS: str = "wts"
-
-
 class Variants(StrEnum):
     """Type of variants."""
 
@@ -71,3 +62,13 @@ class RecordType(StrEnum):
 class SequencingPlatform(StrEnum):
     ILLUMINA: str = "ILLUMINA"
     OXFORD_NANOPORE: str = "OXFORD_NANOPORE"
+
+
+class SeqLibraryPrepCategory(StrEnum):
+    COVID: str = "cov"
+    MICROBIAL: str = "mic"
+    READY_MADE_LIBRARY: str = "rml"
+    TARGETED_GENOME_SEQUENCING: str = "tgs"
+    WHOLE_EXOME_SEQUENCING: str = "wes"
+    WHOLE_GENOME_SEQUENCING: str = "wgs"
+    WHOLE_TRANSCRIPTOME_SEQUENCING: str = "wts"

cg/meta/delivery_report/balsamic.py

@@ -28,11 +28,7 @@
     BalsamicTargetedSampleMetadataModel,
     BalsamicWGSSampleMetadataModel,
 )
-from cg.models.delivery_report.report import (
-    CaseModel,
-    ReportRequiredFields,
-    ScoutVariantsFiles,
-)
+from cg.models.delivery_report.report import CaseModel, ReportRequiredFields, ScoutVariantsFiles
 from cg.models.delivery_report.sample import SampleModel
 from cg.store.models import Bed, BedVersion, Case, Sample
 
@@ -78,7 +74,7 @@ def get_panel_metadata(
         sample_metrics: BalsamicTargetedQCMetrics,
         analysis_metadata: BalsamicAnalysis,
     ) -> BalsamicTargetedSampleMetadataModel:
-        """Return report metadata for Balsamic TGS analysis."""
+        """Return report metadata for Balsamic TARGETED_GENOME_SEQUENCING analysis."""
         bed_version: BedVersion = self.status_db.get_bed_version_by_file_name(
             analysis_metadata.balsamic_config.panel.capture_kit
         )
@@ -105,7 +101,7 @@ def get_wgs_metadata(
         passed_initial_qc: bool | None,
         sample_metrics: BalsamicWGSQCMetrics,
     ) -> BalsamicWGSSampleMetadataModel:
-        """Return report metadata for Balsamic WGS analysis."""
+        """Return report metadata for Balsamic WHOLE_GENOME_SEQUENCING analysis."""
         return BalsamicWGSSampleMetadataModel(
             duplicates=sample_metrics.percent_duplication if sample_metrics else None,
             fold_80=sample_metrics.fold_80_base_penalty if sample_metrics else None,

cg/meta/delivery_report/raredisease.py

@@ -1,7 +1,6 @@
 """Raredisease Delivery Report API."""
 
 from cg.clients.chanjo2.models import CoverageMetrics
-from cg.constants.constants import PrepCategory
 from cg.constants.report import (
     REQUIRED_APPLICATION_FIELDS,
     REQUIRED_CASE_FIELDS,
@@ -15,14 +14,15 @@
     REQUIRED_SAMPLE_TIMESTAMP_FIELDS,
 )
 from cg.constants.scout import ScoutUploadKey
+from cg.constants.sequencing import SeqLibraryPrepCategory
 from cg.meta.delivery_report.data_validators import get_million_read_pairs
 from cg.meta.delivery_report.delivery_report_api import DeliveryReportAPI
 from cg.meta.workflow.raredisease import RarediseaseAnalysisAPI
 from cg.models.analysis import AnalysisModel, NextflowAnalysis
-from cg.models.raredisease.raredisease import RarediseaseQCMetrics
 from cg.models.delivery_report.metadata import RarediseaseSampleMetadataModel
 from cg.models.delivery_report.report import CaseModel, ReportRequiredFields, ScoutVariantsFiles
 from cg.models.delivery_report.sample import SampleModel
+from cg.models.raredisease.raredisease import RarediseaseQCMetrics
 from cg.store.models import Case, Sample
 
 
@@ -85,7 +85,8 @@ def get_sample_metadata_required_fields(case: CaseModel) -> dict:
         for sample in case.samples:
             required_fields = (
                 REQUIRED_SAMPLE_METADATA_RAREDISEASE_WGS_FIELDS
-                if PrepCategory.WHOLE_GENOME_SEQUENCING in sample.application.prep_category.lower()
+                if SeqLibraryPrepCategory.WHOLE_GENOME_SEQUENCING
+                in sample.application.prep_category.lower()
                 else REQUIRED_SAMPLE_METADATA_RAREDISEASE_FIELDS
             )
             required_sample_metadata_fields.update({sample.id: required_fields})

cg/meta/observations/mip_dna_observations_api.py

@@ -13,7 +13,7 @@
     MipDNALoadParameters,
     MipDNAObservationsAnalysisTag,
 )
-from cg.constants.sequencing import SequencingMethod
+from cg.constants.sequencing import SeqLibraryPrepCategory
 from cg.exc import CaseNotFoundError, LoqusdbDuplicateRecordError
 from cg.meta.observations.observations_api import ObservationsAPI
 from cg.meta.workflow.mip_dna import MipDNAAnalysisAPI
@@ -64,10 +64,12 @@ def is_case_eligible_for_observations_upload(self, case: Case) -> bool:
 
     def set_loqusdb_instance(self, case_id: str) -> None:
         """Return the Loqusdb instance associated to the sequencing method."""
-        sequencing_method: SequencingMethod = self.analysis_api.get_data_analysis_type(case_id)
-        loqusdb_instances: dict[SequencingMethod, LoqusdbInstance] = {
-            SequencingMethod.WGS: LoqusdbInstance.WGS,
-            SequencingMethod.WES: LoqusdbInstance.WES,
+        sequencing_method: SeqLibraryPrepCategory = self.analysis_api.get_data_analysis_type(
+            case_id
+        )
+        loqusdb_instances: dict[SeqLibraryPrepCategory, LoqusdbInstance] = {
+            SeqLibraryPrepCategory.WHOLE_GENOME_SEQUENCING: LoqusdbInstance.WGS,
+            SeqLibraryPrepCategory.WHOLE_EXOME_SEQUENCING: LoqusdbInstance.WES,
         }
         self.loqusdb_api = self.get_loqusdb_api(loqusdb_instances[sequencing_method])
 
@@ -117,7 +119,8 @@ def get_observations_files_from_hk(
                 self.housekeeper_api.files(
                     version=hk_version.id, tags=[MipDNAObservationsAnalysisTag.SV_VCF]
                 ).first()
-                if self.analysis_api.get_data_analysis_type(case_id) == SequencingMethod.WGS
+                if self.analysis_api.get_data_analysis_type(case_id)
+                == SeqLibraryPrepCategory.WHOLE_GENOME_SEQUENCING
                 else None
             ),
             "profile_vcf_path": self.housekeeper_api.files(

cg/meta/observations/observations_api.py

@@ -11,7 +11,7 @@
 from cg.constants.constants import CustomerId
 from cg.constants.observations import LoqusdbInstance
 from cg.constants.sample_sources import SourceType
-from cg.constants.sequencing import SequencingMethod
+from cg.constants.sequencing import SeqLibraryPrepCategory
 from cg.exc import LoqusdbUploadCaseError
 from cg.meta.workflow.analysis import AnalysisAPI
 from cg.models.cg_config import CGConfig, CommonAppConfig
@@ -123,7 +123,7 @@ def is_customer_eligible_for_observations_upload(self, customer_id: str) -> bool
 
     def is_sequencing_method_eligible_for_observations_upload(self, case_id: str) -> bool:
         """Return whether a sequencing method is valid for observations upload."""
-        sequencing_method: SequencingMethod | None = self.analysis_api.get_data_analysis_type(
+        sequencing_method: SeqLibraryPrepCategory | None = self.analysis_api.get_data_analysis_type(
             case_id
         )
         if sequencing_method not in self.loqusdb_sequencing_methods:

cg/meta/observations/raredisease_observations_api.py

@@ -13,11 +13,8 @@
     RarediseaseLoadParameters,
     RarediseaseObservationsAnalysisTag,
 )
-from cg.constants.sequencing import SequencingMethod
-from cg.exc import (
-    CaseNotFoundError,
-    LoqusdbDuplicateRecordError,
-)
+from cg.constants.sequencing import SeqLibraryPrepCategory
+from cg.exc import CaseNotFoundError, LoqusdbDuplicateRecordError
 from cg.meta.observations.observations_api import ObservationsAPI
 from cg.meta.workflow.raredisease import RarediseaseAnalysisAPI
 from cg.models.cg_config import CGConfig
@@ -67,10 +64,12 @@ def is_case_eligible_for_observations_upload(self, case: Case) -> bool:
 
     def set_loqusdb_instance(self, case_id: str) -> None:
         """Set the Loqusdb instance associated to the sequencing method."""
-        sequencing_method: SequencingMethod = self.analysis_api.get_data_analysis_type(case_id)
-        loqusdb_instances: dict[SequencingMethod, LoqusdbInstance] = {
-            SequencingMethod.WGS: LoqusdbInstance.WGS,
-            SequencingMethod.WES: LoqusdbInstance.WES,
+        sequencing_method: SeqLibraryPrepCategory = self.analysis_api.get_data_analysis_type(
+            case_id
+        )
+        loqusdb_instances: dict[SeqLibraryPrepCategory, LoqusdbInstance] = {
+            SeqLibraryPrepCategory.WHOLE_GENOME_SEQUENCING: LoqusdbInstance.WGS,
+            SeqLibraryPrepCategory.WHOLE_EXOME_SEQUENCING: LoqusdbInstance.WES,
         }
         self.loqusdb_api = self.get_loqusdb_api(loqusdb_instances[sequencing_method])
 
@@ -119,7 +118,8 @@ def get_observations_files_from_hk(
                 self.housekeeper_api.files(
                     version=hk_version.id, tags=[RarediseaseObservationsAnalysisTag.SV_VCF]
                 ).first()
-                if self.analysis_api.get_data_analysis_type(case_id) == SequencingMethod.WGS
+                if self.analysis_api.get_data_analysis_type(case_id)
+                == SeqLibraryPrepCategory.WHOLE_GENOME_SEQUENCING
                 else None
             ),
             "profile_vcf_path": self.housekeeper_api.files(

cg/meta/upload/balsamic/balsamic.py

@@ -12,7 +12,7 @@
 from cg.cli.upload.observations import upload_observations_to_loqusdb
 from cg.cli.upload.scout import upload_to_scout
 from cg.constants import REPORT_SUPPORTED_DATA_DELIVERY, DataDelivery
-from cg.constants.sequencing import SequencingMethod
+from cg.constants.sequencing import SeqLibraryPrepCategory
 from cg.meta.upload.gt import UploadGenotypesAPI
 from cg.meta.upload.upload_api import UploadAPI
 from cg.meta.workflow.balsamic import BalsamicAnalysisAPI
@@ -61,7 +61,7 @@ def upload(self, ctx: click.Context, case: Case, restart: bool) -> None:
         # Observations upload
         if (
             self.analysis_api.get_case_application_type(case_id=case.internal_id)
-            == SequencingMethod.WGS
+            == SeqLibraryPrepCategory.WHOLE_GENOME_SEQUENCING
         ):
             ctx.invoke(upload_observations_to_loqusdb, case_id=case.internal_id)
         else:

cg/meta/upload/gt.py

@@ -5,9 +5,10 @@
 
 from cg.apps.gt import GenotypeAPI
 from cg.apps.housekeeper.hk import HousekeeperAPI
-from cg.constants.constants import FileExtensions, FileFormat, PrepCategory, Workflow
+from cg.constants.constants import FileExtensions, FileFormat, Workflow
 from cg.constants.housekeeper_tags import GenotypeAnalysisTag, HkAnalysisMetricsTag
 from cg.constants.nf_analysis import RAREDISEASE_PREDICTED_SEX_METRIC
+from cg.constants.sequencing import SeqLibraryPrepCategory
 from cg.constants.subject import Sex
 from cg.io.controller import ReadFile
 from cg.models.deliverables.metric_deliverables import MetricsBase
@@ -69,10 +70,13 @@ def upload(self, genotype_load_config: dict, replace: bool = False):
 
     @staticmethod
     def is_suitable_for_genotype_upload(case: Case) -> bool:
-        """Returns True if there are any non-tumor WGS samples in the case."""
+        """Returns True if there are any non-tumor WHOLE_GENOME_SEQUENCING samples in the case."""
         samples: list[Sample] = case.samples
         return any(
-            (not sample.is_tumour and PrepCategory.WHOLE_GENOME_SEQUENCING == sample.prep_category)
+            (
+                not sample.is_tumour
+                and SeqLibraryPrepCategory.WHOLE_GENOME_SEQUENCING == sample.prep_category
+            )
             for sample in samples
         )
 

cg/meta/upload/scout/uploadscoutapi.py

@@ -11,13 +11,10 @@
 from cg.apps.madeline.api import MadelineAPI
 from cg.apps.scout.scoutapi import ScoutAPI
 from cg.constants import HK_MULTIQC_HTML_TAG, Workflow
-from cg.constants.constants import FileFormat, GenomeVersion, PrepCategory
-from cg.constants.housekeeper_tags import (
-    HK_DELIVERY_REPORT_TAG,
-    AlignmentFileTag,
-    AnalysisTag,
-)
+from cg.constants.constants import FileFormat, GenomeVersion
+from cg.constants.housekeeper_tags import HK_DELIVERY_REPORT_TAG, AlignmentFileTag, AnalysisTag
 from cg.constants.scout import ScoutCustomCaseReportTags
+from cg.constants.sequencing import SeqLibraryPrepCategory
 from cg.exc import CgDataError, HousekeeperBundleVersionMissingError
 from cg.io.controller import WriteFile
 from cg.meta.upload.scout.balsamic_config_builder import BalsamicConfigBuilder
@@ -27,10 +24,7 @@
 from cg.meta.upload.scout.rnafusion_config_builder import RnafusionConfigBuilder
 from cg.meta.upload.scout.scout_config_builder import ScoutConfigBuilder
 from cg.meta.workflow.analysis import AnalysisAPI
-from cg.meta.workflow.utils.genome_build_helpers import (
-    genome_to_scout_format,
-    get_genome_build,
-)
+from cg.meta.workflow.utils.genome_build_helpers import genome_to_scout_format, get_genome_build
 from cg.models.scout.scout_load_config import ScoutLoadConfig
 from cg.store.models import Analysis, Case, Customer, Sample
 from cg.store.store import Store
@@ -765,9 +759,9 @@ def _get_application_prep_category(
             for sample in subject_id_samples
             if sample.prep_category
             in [
-                PrepCategory.WHOLE_GENOME_SEQUENCING.value,
-                PrepCategory.TARGETED_GENOME_SEQUENCING.value,
-                PrepCategory.WHOLE_EXOME_SEQUENCING.value,
+                SeqLibraryPrepCategory.WHOLE_GENOME_SEQUENCING.value,
+                SeqLibraryPrepCategory.TARGETED_GENOME_SEQUENCING.value,
+                SeqLibraryPrepCategory.WHOLE_EXOME_SEQUENCING.value,
             ]
         ]
 

cg/meta/workflow/analysis.py

@@ -215,7 +215,7 @@ def get_case_source_type(self, case_id: str) -> str | None:
         return source_types.pop()
 
     def has_case_only_exome_samples(self, case_id: str) -> bool:
-        """Returns True if the application type for all samples in a case is WES."""
+        """Returns True if the application type for all samples in a case is WHOLE_EXOME_SEQUENCING."""
         application_type: str = self.get_case_application_type(case_id)
         return application_type == AnalysisType.WHOLE_EXOME_SEQUENCING
 

cg/meta/workflow/balsamic.py

@@ -207,7 +207,7 @@ def get_verified_bed(self, panel_bed: str, sample_data: dict) -> str | None:
             raise BalsamicStartError("Multiple application types found in LIMS")
         if not application_types.issubset(self.__BALSAMIC_BED_APPLICATIONS):
             if panel_bed:
-                raise BalsamicStartError("Cannot set panel_bed for WGS sample!")
+                raise BalsamicStartError("Cannot set panel_bed for WHOLE_GENOME_SEQUENCING sample!")
             return None
         if panel_bed:
             return panel_bed.as_posix()

cg/meta/workflow/raredisease.py

@@ -94,7 +94,7 @@ def is_gene_panel_required(self) -> bool:
 
     def get_target_bed(self, case_id: str, analysis_type: str) -> str:
         """
-        Return the target bed file from LIMS and use default capture kit for WGS.
+        Return the target bed file from LIMS and use default capture kit for WHOLE_GENOME_SEQUENCING.
         """
         target_bed: str = self.get_target_bed_from_lims(case_id=case_id)
         if not target_bed: