make sample sheet entry one line per bam file

Author: peterpru

cg/meta/workflow/nallo.py

@@ -3,11 +3,11 @@
 import logging
 from cg.constants import Workflow
 from cg.constants.subject import PlinkPhenotypeStatus, PlinkSex
-from cg.constants.tb import AnalysisType
 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.store.models import CaseSample
+from pathlib import Path
 
 LOG = logging.getLogger(__name__)
 
@@ -47,17 +47,21 @@ def sample_sheet_headers(self) -> list[str]:
     def get_sample_sheet_content_per_sample(self, case_sample: CaseSample) -> list[list[str]]:
         """Collect and format information required to build a sample sheet for a single sample."""
         bam_unmapped_read_paths = self.get_unmapped_bam_read_paths(sample=case_sample.sample)
-        sample_sheet_entry = NalloSampleSheetEntry(
-            project=case_sample.case.internal_id,
-            sample=case_sample.sample.internal_id,
-            bam_unmapped_read_paths=bam_unmapped_read_paths,
-            family_id=case_sample.case.internal_id,
-            paternal_id=case_sample.get_paternal_sample_id,
-            maternal_id=case_sample.get_maternal_sample_id,
-            sex=self.get_sex_code(case_sample.sample.sex),
-            phenotype=self.get_phenotype_code(case_sample.status),
-        )
-        return sample_sheet_entry.reformat_sample_content
+        sample_sheet_entries = []
+
+        for bam_path in bam_unmapped_read_paths:
+            sample_sheet_entry = NalloSampleSheetEntry(
+                project=case_sample.case.internal_id,
+                sample=case_sample.sample.internal_id,
+                bam_unmapped_read_path=Path(bam_path),
+                family_id=case_sample.case.internal_id,
+                paternal_id=case_sample.get_paternal_sample_id or "0",
+                maternal_id=case_sample.get_maternal_sample_id or "0",
+                sex=self.get_sex_code(case_sample.sample.sex),
+                phenotype=self.get_phenotype_code(case_sample.status),
+            )
+            sample_sheet_entries.extend(sample_sheet_entry.reformat_sample_content)
+        return sample_sheet_entries
 
     @staticmethod
     def get_phenotype_code(phenotype: str) -> int:

cg/models/nallo/nallo.py

@@ -1,7 +1,7 @@
 from enum import StrEnum
 from pathlib import Path
 
-from pydantic import BaseModel, conlist, field_validator
+from pydantic import BaseModel, field_validator
 
 from cg.exc import NfSampleSheetError
 from cg.models.nf_analysis import WorkflowParameters
@@ -12,7 +12,7 @@ class NalloSampleSheetEntry(BaseModel):
 
     project: str
     sample: str
-    bam_unmapped_read_paths: conlist(Path)
+    bam_unmapped_read_path: Path
     family_id: str
     paternal_id: str
     maternal_id: str
@@ -26,7 +26,7 @@ def reformat_sample_content(self) -> list[list[str]]:
             [
                 self.project,
                 self.sample,
-                self.bam_unmapped_read_paths,
+                self.bam_unmapped_read_path,
                 self.family_id,
                 self.paternal_id,
                 self.maternal_id,
@@ -35,14 +35,13 @@ def reformat_sample_content(self) -> list[list[str]]:
             ]
         ]
 
-    @field_validator("bam_unmapped_read_paths")
+    @field_validator("bam_unmapped_read_path")
     @classmethod
-    def unmapped_bam_file_exists(cls, bam_paths: list[Path]) -> list[Path]:
+    def unmapped_bam_file_exists(cls, bam_path: Path) -> Path:
         """Verify that bam files exist."""
-        for bam_path in bam_paths:
-            if not bam_path.is_file():
-                raise NfSampleSheetError(f"Bam file does not exist: {str(bam_path)}")
-        return bam_paths
+        if not bam_path.is_file():
+            raise NfSampleSheetError(f"Bam file does not exist: {str(bam_path)}")
+        return bam_path
 
 
 class NalloSampleSheetHeaders(StrEnum):