refactor: finalize karyotype GCS loading and simulated tests

- Replace arbitrary '20231213' analysis value with clearly synthetic 'simtest'
- Remove unnecessary config keys (KARYOTYPE_INVERSIONS, KARYOTYPE_TAG_SNPS_FILENAME)
- Hardcode filename in production code, matching site_filters/aim patterns
- Use explicit (contig, inversion) tuples in simulator instead of string slicing
- Align test fixtures with test_aim_data.py pattern (AnophelesKaryotypeAnalysis)
- Use correct Af1 GFF params in test fixture
- Delete empty MANIFEST.in

Author: adilraza99

MANIFEST.in

@@ -70,12 +70,9 @@ def _require_karyotype_analysis(self):
     def load_inversion_tags(self, inversion: inversion_param) -> pd.DataFrame:
         self._require_karyotype_analysis()
 
-        filename = self.config.get(
-            "KARYOTYPE_TAG_SNPS_FILENAME", "karyotype_tag_snps.csv"
-        )
         path = (
             f"{self._base_path}/{self._major_version_path}"
-            f"/snp_karyotype/{self._karyotype_analysis}/{filename}"
+            f"/snp_karyotype/{self._karyotype_analysis}/karyotype_tag_snps.csv"
         )
         with self._fs.open(path) as f:
             df_tag_snps = pd.read_csv(f, sep=",")

malariagen_data/anoph/karyotype.py

@@ -1154,10 +1154,7 @@ def init_config(self):
             "SITE_ANNOTATIONS_ZARR_PATH": "reference/genome/agamp4/Anopheles-gambiae-PEST_SEQANNOTATION_AgamP4.12.zarr",
             "DEFAULT_AIM_ANALYSIS": "20220528",
             "DEFAULT_SITE_FILTERS_ANALYSIS": "dt_20200416",
-            # Simulated placeholder; real value will be set in production config.
-            "DEFAULT_KARYOTYPE_ANALYSIS": "20231213",
-            "KARYOTYPE_INVERSIONS": ["2La", "2Rb"],
-            "KARYOTYPE_TAG_SNPS_FILENAME": "karyotype_tag_snps.csv",
+            "DEFAULT_KARYOTYPE_ANALYSIS": "simtest",
             "DEFAULT_COHORTS_ANALYSIS": "20230516",
             "SITE_MASK_IDS": ["gamb_colu_arab", "gamb_colu", "arab"],
             "PHASING_ANALYSIS_IDS": ["gamb_colu_arab", "gamb_colu", "arab"],
@@ -1529,13 +1526,12 @@ def init_snp_sites(self):
 
     def init_karyotype_tags(self):
         analysis = self.config["DEFAULT_KARYOTYPE_ANALYSIS"]
-        inversions = self.config["KARYOTYPE_INVERSIONS"]
-        filename = self.config["KARYOTYPE_TAG_SNPS_FILENAME"]
 
         # Generate tag SNP data using positions from simulated SNP sites.
+        # N.B., inversions are defined here with their contigs explicitly
+        # rather than derived via string slicing, for robustness.
         tags = []
-        for inversion in inversions:
-            contig = inversion[:2]
+        for contig, inversion in [("2L", "2La"), ("2R", "2Rb")]:
             snp_pos = self.snp_sites[contig]["variants"]["POS"][:]
             snp_alt = self.snp_sites[contig]["variants"]["ALT"][:]
             n_tags = min(20, len(snp_pos))
@@ -1552,7 +1548,13 @@ def init_karyotype_tags(self):
                 )
 
         df = pd.DataFrame(tags)
-        path = self.bucket_path / "v3" / "snp_karyotype" / analysis / filename
+        path = (
+            self.bucket_path
+            / "v3"
+            / "snp_karyotype"
+            / analysis
+            / "karyotype_tag_snps.csv"
+        )
         path.parent.mkdir(parents=True, exist_ok=True)
         df.to_csv(path, index=False)
 

tests/anoph/conftest.py

@@ -1,32 +1,38 @@
 import pandas as pd
 import pytest
 
-from malariagen_data import Af1, Ag3
+from malariagen_data import ag3 as _ag3
+from malariagen_data import af1 as _af1
+from malariagen_data.anoph.karyotype import AnophelesKaryotypeAnalysis
 
 
 @pytest.fixture
-def ag3_sim_api(ag3_sim_fixture, tmp_path):
-    data_path = ag3_sim_fixture.bucket_path.as_posix()
-    return Ag3(
-        url=data_path,
-        public_url=data_path,
+def ag3_sim_api(ag3_sim_fixture):
+    return AnophelesKaryotypeAnalysis(
+        url=ag3_sim_fixture.url,
+        public_url=ag3_sim_fixture.url,
+        config_path=_ag3.CONFIG_PATH,
+        major_version_number=_ag3.MAJOR_VERSION_NUMBER,
+        major_version_path=_ag3.MAJOR_VERSION_PATH,
         pre=True,
-        check_location=False,
-        bokeh_output_notebook=False,
-        results_cache=tmp_path.as_posix(),
+        gff_gene_type="gene",
+        gff_gene_name_attribute="Name",
+        gff_default_attributes=("ID", "Parent", "Name", "description"),
     )
 
 
 @pytest.fixture
-def af1_sim_api(af1_sim_fixture, tmp_path):
-    data_path = af1_sim_fixture.bucket_path.as_posix()
-    return Af1(
-        url=data_path,
-        public_url=data_path,
+def af1_sim_api(af1_sim_fixture):
+    return AnophelesKaryotypeAnalysis(
+        url=af1_sim_fixture.url,
+        public_url=af1_sim_fixture.url,
+        config_path=_af1.CONFIG_PATH,
+        major_version_number=_af1.MAJOR_VERSION_NUMBER,
+        major_version_path=_af1.MAJOR_VERSION_PATH,
         pre=True,
-        check_location=False,
-        bokeh_output_notebook=False,
-        results_cache=tmp_path.as_posix(),
+        gff_gene_type="protein_coding_gene",
+        gff_gene_name_attribute="Note",
+        gff_default_attributes=("ID", "Parent", "Note", "description"),
     )