formalize

Author: bpblanken

v03_pipeline/lib/model/dataset_type.py

@@ -4,7 +4,7 @@
 import hail as hl
 
 from v03_pipeline.lib.annotations import gcnv, mito, shared, snv_indel, sv
-from v03_pipeline.lib.model.definitions import ReferenceGenome
+from v03_pipeline.lib.model.definitions import ReferenceGenome, SampleType
 
 MITO_MIN_HOM_THRESHOLD = 0.95
 ZERO = 0.0
@@ -155,6 +155,12 @@ def has_gencode_ensembl_to_refseq_id_mapping(
             self == DatasetType.SNV_INDEL and reference_genome == ReferenceGenome.GRCh38
         )
 
+    def expect_filters(
+        self,
+        sample_type: SampleType,
+    ) -> bool:
+        return self == DatasetType.SNV_INDEL and sample_type == SampleType.WES
+
     @property
     def has_gencode_gene_symbol_to_gene_id_mapping(self) -> bool:
         return self == DatasetType.SV

v03_pipeline/lib/paths.py

@@ -223,8 +223,7 @@ def valid_filters_path(
 ) -> str | None:
     if (
         not Env.EXPECT_WES_FILTERS
-        or dataset_type != DatasetType.SNV_INDEL
-        or sample_type != SampleType.WES
+        or not dataset_type.expect_filters(sample_type)
         or 'part_one_outputs' not in callset_path
     ):
         return None

v03_pipeline/lib/tasks/write_imported_callset.py

@@ -16,7 +16,7 @@
     validate_sample_type,
 )
 from v03_pipeline.lib.misc.vets import annotate_vets
-from v03_pipeline.lib.model import CachedReferenceDatasetQuery, DatasetType, SampleType
+from v03_pipeline.lib.model import CachedReferenceDatasetQuery
 from v03_pipeline.lib.model.environment import Env
 from v03_pipeline.lib.paths import (
     cached_reference_dataset_query_path,
@@ -56,8 +56,7 @@ def requires(self) -> list[luigi.Task]:
         requirements = []
         if (
             Env.EXPECT_WES_FILTERS
-            and self.dataset_type == DatasetType.SNV_INDEL
-            and self.sample_type == SampleType.WES
+            and self.dataset_type.expect_filters(self.sample_type)
         ):
             requirements = [
                 *requirements,