Merge branch 'master' into write_config_taxprofiler

.bumpversion.cfg

@@ -1,5 +1,5 @@
 [bumpversion]
-current_version = 67.0.9
+current_version = 67.0.19
 commit = True
 tag = True
 tag_name = v{new_version}

cg/__init__.py

@@ -1,2 +1,2 @@
 __title__ = "cg"
-__version__ = "67.0.9"
+__version__ = "67.0.19"

cg/cli/workflow/nallo/base.py

@@ -4,13 +4,15 @@
 
 import rich_click as click
 
-from cg.cli.utils import CLICK_CONTEXT_SETTINGS
-
-from cg.cli.workflow.nf_analysis import config_case, run, start
 
+from cg.cli.utils import CLICK_CONTEXT_SETTINGS, echo_lines
+from cg.cli.workflow.commands import ARGUMENT_CASE_ID
+from cg.constants.cli_options import DRY_RUN
+from cg.cli.workflow.nf_analysis import config_case, metrics_deliver, report_deliver, run, start
 from cg.constants.constants import MetaApis
 from cg.meta.workflow.analysis import AnalysisAPI
 from cg.meta.workflow.nallo import NalloAnalysisAPI
+from cg.models.cg_config import CGConfig
 
 LOG = logging.getLogger(__name__)
 
@@ -24,5 +26,24 @@ def nallo(context: click.Context) -> None:
 
 
 nallo.add_command(config_case)
+nallo.add_command(report_deliver)
 nallo.add_command(run)
 nallo.add_command(start)
+nallo.add_command(metrics_deliver)
+
+
+@nallo.command("panel")
+@DRY_RUN
+@ARGUMENT_CASE_ID
+@click.pass_obj
+def panel(context: CGConfig, case_id: str, dry_run: bool) -> None:
+    """Write aggregated gene panel file exported from Scout."""
+
+    analysis_api: NalloAnalysisAPI = context.meta_apis["analysis_api"]
+    analysis_api.status_db.verify_case_exists(case_internal_id=case_id)
+
+    bed_lines: list[str] = analysis_api.get_gene_panel(case_id=case_id)
+    if dry_run:
+        echo_lines(lines=bed_lines)
+        return
+    analysis_api.write_panel_as_tsv(case_id=case_id, content=bed_lines)

cg/constants/nf_analysis.py

@@ -15,6 +15,10 @@ class NfTowerStatus(StrEnum):
     UNKNOWN: str = "UNKNOWN"
 
 
+NALLO_METRIC_CONDITIONS: dict[str, dict[str, Any]] = {
+    "median_coverage": {"norm": "gt", "threshold": 25},
+}
+
 RAREDISEASE_PREDICTED_SEX_METRIC = "predicted_sex_sex_check"
 
 RAREDISEASE_METRIC_CONDITIONS: dict[str, dict[str, Any]] = {

cg/constants/scout.py

@@ -14,6 +14,7 @@ class GenomeBuild(StrEnum):
 class ScoutExportFileName(StrEnum):
     MANAGED_VARIANTS: str = f"managed_variants{FileExtensions.VCF}"
     PANELS: str = f"gene_panels{FileExtensions.BED}"
+    PANELS_TSV: str = f"gene_panels{FileExtensions.TSV}"
 
 
 class UploadTrack(StrEnum):

cg/meta/upload/scout/uploadscoutapi.py

@@ -4,7 +4,6 @@
 from pathlib import Path
 
 from housekeeper.store.models import File, Version
-from pydantic.dataclasses import dataclass
 
 from cg.apps.housekeeper.hk import HousekeeperAPI
 from cg.apps.lims import LimsAPI
@@ -26,22 +25,13 @@
 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.models.scout.scout_load_config import ScoutLoadConfig
+from cg.store.api.data_classes import RNADNACollection
 from cg.store.models import Analysis, Case, Customer, Sample
 from cg.store.store import Store
 
 LOG = logging.getLogger(__name__)
 
 
-@dataclass
-class RNADNACollection:
-    """Contains the id for an RNA sample, the name of its connected DNA sample,
-    and a list of connected, uploaded DNA cases."""
-
-    rna_sample_internal_id: str
-    dna_sample_name: str
-    dna_case_ids: list[str]
-
-
 class UploadScoutAPI:
     """Class that handles everything that has to do with uploading to Scout."""
 
@@ -182,15 +172,6 @@ def get_rna_omics_outrider(self, case_id: str) -> File | None:
         tags: set[str] = {AnalysisTag.OUTRIDER, case_id, AnalysisTag.CLINICAL}
         return self.housekeeper.get_file_from_latest_version(bundle_name=case_id, tags=tags)
 
-    def get_unique_dna_cases_related_to_rna_case(self, case_id: str) -> set[str]:
-        """Return a set of unique DNA cases related to an RNA case."""
-        case: Case = self.status_db.get_case_by_internal_id(case_id)
-        rna_dna_collections: list[RNADNACollection] = self.create_rna_dna_collections(case)
-        unique_dna_cases_related_to_rna_case: set[str] = set()
-        for rna_dna_collection in rna_dna_collections:
-            unique_dna_cases_related_to_rna_case.update(rna_dna_collection.dna_case_ids)
-        return unique_dna_cases_related_to_rna_case
-
     def get_rna_alignment_cram(self, case_id: str, sample_id: str) -> File | None:
         """Return an RNA alignment CRAM file for a case in Housekeeper."""
         tags: set[str] = {AlignmentFileTag.CRAM, sample_id}
@@ -206,9 +187,11 @@ def get_rna_alignment_cram(self, case_id: str, sample_id: str) -> File | None:
     def upload_rna_alignment_file(self, case_id: str, dry_run: bool) -> None:
         """Upload RNA alignment file to Scout."""
         rna_case: Case = self.status_db.get_case_by_internal_id(case_id)
-        rna_dna_collections: list[RNADNACollection] = self.create_rna_dna_collections(rna_case)
+        rna_dna_collections: list[RNADNACollection] = (
+            self.status_db.get_related_dna_cases_with_samples(rna_case)
+        )
         for rna_dna_collection in rna_dna_collections:
-            rna_sample_internal_id: str = rna_dna_collection.rna_sample_internal_id
+            rna_sample_internal_id: str = rna_dna_collection.rna_sample_id
             dna_sample_name: str = rna_dna_collection.dna_sample_name
             rna_alignment_cram: File | None = self.get_rna_alignment_cram(
                 case_id=case_id, sample_id=rna_sample_internal_id
@@ -346,9 +329,11 @@ def upload_rna_coverage_bigwig_to_scout(self, case_id: str, dry_run: bool) -> No
 
         status_db: Store = self.status_db
         rna_case = status_db.get_case_by_internal_id(case_id)
-        rna_dna_collections: list[RNADNACollection] = self.create_rna_dna_collections(rna_case)
+        rna_dna_collections: list[RNADNACollection] = (
+            self.status_db.get_related_dna_cases_with_samples(rna_case)
+        )
         for rna_dna_collection in rna_dna_collections:
-            rna_sample_internal_id: str = rna_dna_collection.rna_sample_internal_id
+            rna_sample_internal_id: str = rna_dna_collection.rna_sample_id
             dna_sample_name: str = rna_dna_collection.dna_sample_name
             rna_coverage_bigwig: File | None = self.get_rna_coverage_bigwig(
                 case_id=case_id, sample_id=rna_sample_internal_id
@@ -382,7 +367,7 @@ def upload_omics_sample_id_to_scout(
         self, dry_run: bool, rna_dna_collections: list[RNADNACollection]
     ) -> None:
         for rna_dna_collection in rna_dna_collections:
-            rna_sample_internal_id: str = rna_dna_collection.rna_sample_internal_id
+            rna_sample_internal_id: str = rna_dna_collection.rna_sample_id
             dna_sample_name: str = rna_dna_collection.dna_sample_name
             for dna_case_id in rna_dna_collection.dna_case_ids:
                 LOG.info(
@@ -406,7 +391,7 @@ def upload_rna_fraser_outrider_to_scout(
         """Upload omics fraser and outrider file for a case to Scout."""
         status_db: Store = self.status_db
         for rna_dna_collection in rna_dna_collections:
-            rna_sample_internal_id: str = rna_dna_collection.rna_sample_internal_id
+            rna_sample_internal_id: str = rna_dna_collection.rna_sample_id
             dna_sample_name: str = rna_dna_collection.dna_sample_name
             rna_fraser: File | None = self.get_rna_omics_fraser(case_id=case_id)
             rna_outrider: File | None = self.get_rna_omics_outrider(case_id=case_id)
@@ -442,7 +427,7 @@ def upload_rna_fraser_outrider_to_scout(
     def upload_rna_genome_build_to_scout(
         self,
         dry_run: bool,
-        rna_case: str,
+        rna_case: Case,
         rna_dna_collections: list[RNADNACollection],
     ) -> None:
         """Upload RNA genome built for a RNA/DNA case to Scout."""
@@ -502,9 +487,11 @@ def upload_splice_junctions_bed_to_scout(self, dry_run: bool, case_id: str) -> N
         status_db: Store = self.status_db
         rna_case: Case = status_db.get_case_by_internal_id(case_id)
 
-        rna_dna_collections: list[RNADNACollection] = self.create_rna_dna_collections(rna_case)
+        rna_dna_collections: list[RNADNACollection] = (
+            self.status_db.get_related_dna_cases_with_samples(rna_case)
+        )
         for rna_dna_collection in rna_dna_collections:
-            rna_sample_internal_id: str = rna_dna_collection.rna_sample_internal_id
+            rna_sample_internal_id: str = rna_dna_collection.rna_sample_id
             dna_sample_name: str = rna_dna_collection.dna_sample_name
             splice_junctions_bed: File | None = self.get_splice_junctions_bed(
                 case_id=case_id, sample_id=rna_sample_internal_id
@@ -615,7 +602,9 @@ def upload_rna_omics_to_scout(self, dry_run: bool, case_id: str) -> None:
         """Upload RNA omics files to Scout."""
         status_db: Store = self.status_db
         rna_case = status_db.get_case_by_internal_id(case_id)
-        rna_dna_collections: list[RNADNACollection] = self.create_rna_dna_collections(rna_case)
+        rna_dna_collections: list[RNADNACollection] = (
+            self.status_db.get_related_dna_cases_with_samples(rna_case)
+        )
         self.upload_omics_sample_id_to_scout(
             dry_run=dry_run, rna_dna_collections=rna_dna_collections
         )
@@ -675,45 +664,6 @@ def get_config_builder(self, analysis, hk_version) -> ScoutConfigBuilder:
 
         return config_builders[analysis.workflow]
 
-    def create_rna_dna_collections(self, rna_case: Case) -> list[RNADNACollection]:
-        return [self.create_rna_dna_collection(link.sample) for link in rna_case.links]
-
-    def create_rna_dna_collection(self, rna_sample: Sample) -> RNADNACollection:
-        """Creates a collection containing the given RNA sample id, its related DNA sample name, and
-        a list of ids for the DNA cases connected to the DNA sample."""
-        if not rna_sample.subject_id:
-            raise CgDataError(
-                f"Failed to link RNA sample {rna_sample.internal_id} to DNA samples - subject_id field is empty."
-            )
-
-        collaborators: set[Customer] = rna_sample.customer.collaborators
-        subject_id_samples: list[Sample] = (
-            self.status_db.get_samples_by_customer_ids_and_subject_id_and_is_tumour(
-                customer_ids=[customer.id for customer in collaborators],
-                subject_id=rna_sample.subject_id,
-                is_tumour=rna_sample.is_tumour,
-            )
-        )
-
-        subject_id_dna_samples: list[Sample] = self._get_application_prep_category(
-            subject_id_samples
-        )
-
-        if len(subject_id_dna_samples) != 1:
-            raise CgDataError(
-                f"Failed to upload files for RNA case: unexpected number of DNA sample matches for subject_id: "
-                f"{rna_sample.subject_id}. Number of matches: {len(subject_id_dna_samples)} "
-            )
-        dna_sample: Sample = subject_id_dna_samples[0]
-        dna_cases: list[str] = self._dna_cases_related_to_dna_sample(
-            dna_sample=dna_sample, collaborators=collaborators
-        )
-        return RNADNACollection(
-            rna_sample_internal_id=rna_sample.internal_id,
-            dna_sample_name=dna_sample.name,
-            dna_case_ids=dna_cases,
-        )
-
     def _dna_cases_related_to_dna_sample(
         self, dna_sample: Sample, collaborators: set[Customer]
     ) -> list[str]:
@@ -768,11 +718,6 @@ def _get_application_prep_category(
 
     def get_related_uploaded_dna_cases(self, rna_case_id: str) -> set[str]:
         """Returns all uploaded DNA cases related to the specified RNA case."""
-        unique_dna_case_ids: set[str] = self.get_unique_dna_cases_related_to_rna_case(rna_case_id)
-        uploaded_dna_cases: set[str] = set()
-        for dna_case_id in unique_dna_case_ids:
-            if self.status_db.get_case_by_internal_id(dna_case_id).is_uploaded:
-                uploaded_dna_cases.add(dna_case_id)
-            else:
-                LOG.warning(f"Related DNA case {dna_case_id} has not been completed.")
-        return uploaded_dna_cases
+        rna_case: Case = self.status_db.get_case_by_internal_id(rna_case_id)
+        dna_cases: list[Case] = self.status_db.get_uploaded_related_dna_cases(rna_case)
+        return {dna_case.internal_id for dna_case in dna_cases}

cg/meta/workflow/nallo.py

@@ -1,13 +1,19 @@
 """Module for Nallo Analysis API."""
 
 import logging
+from pathlib import Path
+
 from cg.constants import Workflow
+from cg.constants.constants import GenomeVersion, FileFormat
+from cg.constants.nf_analysis import NALLO_METRIC_CONDITIONS
+from cg.constants.scout import ScoutExportFileName
 from cg.constants.subject import PlinkPhenotypeStatus, PlinkSex
+from cg.io.controller import WriteFile
 from cg.meta.workflow.nf_analysis import NfAnalysisAPI
 from cg.models.cg_config import CGConfig
-from cg.models.nallo.nallo import NalloSampleSheetHeaders, NalloSampleSheetEntry, NalloParameters
+from cg.models.nallo.nallo import NalloParameters, NalloSampleSheetEntry, NalloSampleSheetHeaders
+from cg.resources import NALLO_BUNDLE_FILENAMES_PATH
 from cg.store.models import CaseSample
-from pathlib import Path
 
 LOG = logging.getLogger(__name__)
 
@@ -90,4 +96,47 @@ def get_built_workflow_parameters(self, case_id: str) -> NalloParameters:
         return NalloParameters(
             input=self.get_sample_sheet_path(case_id=case_id),
             outdir=outdir,
+            filter_variants_hgnc_ids=f"{outdir}/{ScoutExportFileName.PANELS_TSV}",
+        )
+
+    @property
+    def is_gene_panel_required(self) -> bool:
+        """Return True if a gene panel needs to be created using information in StatusDB and exporting it from Scout."""
+        return True
+
+    def create_gene_panel(self, case_id: str, dry_run: bool) -> None:
+        """Create and write an aggregated gene panel file exported from Scout as tsv file."""
+        LOG.info("Creating gene panel file")
+        bed_lines: list[str] = self.get_gene_panel(case_id=case_id, dry_run=dry_run)
+        if dry_run:
+            bed_lines: str = "\n".join(bed_lines)
+            LOG.debug(f"{bed_lines}")
+            return
+        self.write_panel_as_tsv(case_id=case_id, content=bed_lines)
+
+    def write_panel_as_tsv(self, case_id: str, content: list[str]) -> None:
+        """Write the gene panel to case dir."""
+        self._write_panel_as_tsv(out_dir=Path(self.root, case_id), content=content)
+
+    @staticmethod
+    def _write_panel_as_tsv(out_dir: Path, content: list[str]) -> None:
+        """Write the gene panel to case dir while omitted the commented BED lines."""
+        filtered_content = [line for line in content if not line.startswith("##")]
+        out_dir.mkdir(parents=True, exist_ok=True)
+        WriteFile.write_file_from_content(
+            content="\n".join(filtered_content),
+            file_format=FileFormat.TXT,
+            file_path=Path(out_dir, ScoutExportFileName.PANELS_TSV),
         )
+
+    def get_genome_build(self, case_id: str) -> GenomeVersion:
+        """Return reference genome for a Nallo case. Currently fixed for hg38."""
+        return GenomeVersion.HG38
+
+    @staticmethod
+    def get_bundle_filenames_path() -> Path:
+        """Return Nallo bundle filenames path."""
+        return NALLO_BUNDLE_FILENAMES_PATH
+
+    def get_workflow_metrics(self, metric_id: str) -> dict:
+        return NALLO_METRIC_CONDITIONS

cg/models/analysis.py

@@ -1,4 +1,4 @@
-from pydantic import BaseModel, ConfigDict
+from pydantic import BaseModel, ConfigDict, Field
 
 from cg.models.raredisease.raredisease import RarediseaseQCMetrics
 from cg.models.rnafusion.rnafusion import RnafusionQCMetrics
@@ -15,6 +15,9 @@ class AnalysisModel(BaseModel):
 class NextflowAnalysis(AnalysisModel):
     """Nextflow's analysis results model."""
 
-    sample_metrics: dict[
-        str, RarediseaseQCMetrics | RnafusionQCMetrics | TaxprofilerQCMetrics | TomteQCMetrics
-    ]
+    sample_metrics: (
+        dict[str, RarediseaseQCMetrics]
+        | dict[str, RnafusionQCMetrics]
+        | dict[str, TaxprofilerQCMetrics]
+        | dict[str, TomteQCMetrics]
+    ) = Field(union_mode="left_to_right")

cg/models/nallo/nallo.py

@@ -7,6 +7,12 @@
 from cg.models.nf_analysis import WorkflowParameters
 
 
+class NalloQCMetrics(BaseModel):
+    """Nallo QC metrics"""
+
+    median_coverage: float | None
+
+
 class NalloSampleSheetEntry(BaseModel):
     """Nallo sample model is used when building the sample sheet."""
 
@@ -61,3 +67,5 @@ def list(cls) -> list[str]:
 
 class NalloParameters(WorkflowParameters):
     """Model for Nallo parameters."""
+
+    filter_variants_hgnc_ids: str

cg/models/taxprofiler/taxprofiler.py

@@ -1,12 +1,13 @@
 from pathlib import Path
 
-from pydantic import BaseModel, Field
+from pydantic import Field
 
 from cg.constants.sequencing import SequencingPlatform
 from cg.models.nf_analysis import NextflowSampleSheetEntry, WorkflowParameters
+from cg.models.qc_metrics import QCMetrics
 
 
-class TaxprofilerQCMetrics(BaseModel):
+class TaxprofilerQCMetrics(QCMetrics):
     """Taxprofiler QC metrics."""
 
     after_filtering_gc_content: float