Add the correct nomenclature for genes in anopheles.py to enable CNVs…

… for Af (#500)

* Tried to corect the nomenclature for genes for Af

* Used Alistair's solution

* Added a parameter

* Needed to update some tests with the new param

* Changed 'gff_gene_name' to 'gff_gene_name_attribute'

malariagen_data/af1.py

@@ -117,6 +117,7 @@ def __init__(
             major_version_number=MAJOR_VERSION_NUMBER,
             major_version_path=MAJOR_VERSION_PATH,
             gff_gene_type="protein_coding_gene",
+            gff_gene_name_attribute="Note",
             gff_default_attributes=("ID", "Parent", "Note", "description"),
             storage_options=storage_options,  # used by fsspec via init_filesystem()
             tqdm_class=tqdm_class,

malariagen_data/ag3.py

@@ -183,6 +183,7 @@ def __init__(
             major_version_number=MAJOR_VERSION_NUMBER,
             major_version_path=MAJOR_VERSION_PATH,
             gff_gene_type="gene",
+            gff_gene_name_attribute="Name",
             gff_default_attributes=("ID", "Parent", "Name", "description"),
             storage_options=storage_options,  # used by fsspec via init_filesystem()
             tqdm_class=tqdm_class,

malariagen_data/anoph/genome_features.py

@@ -25,6 +25,7 @@ def __init__(
         self,
         *,
         gff_gene_type: str,
+        gff_gene_name_attribute: str,
         gff_default_attributes: Tuple[str, ...],
         gene_names: Optional[Mapping[str, str]] = None,
         **kwargs,
@@ -37,6 +38,7 @@ def __init__(
         # TODO Consider moving these parameters to configuration, as they could
         # change if the GFF ever changed.
         self._gff_gene_type = gff_gene_type
+        self._gff_gene_name_attribute = gff_gene_name_attribute
         self._gff_default_attributes = gff_default_attributes
 
         # Allow manual override of gene names.

malariagen_data/anopheles.py

@@ -139,6 +139,7 @@ def __init__(
         major_version_number: int,
         major_version_path: str,
         gff_gene_type: str,
+        gff_gene_name_attribute: str,
         gff_default_attributes: Tuple[str, ...],
         tqdm_class,
         storage_options: Mapping,  # used by fsspec via init_filesystem(url, **kwargs)
@@ -160,6 +161,7 @@ def __init__(
             major_version_path=major_version_path,
             storage_options=storage_options,
             gff_gene_type=gff_gene_type,
+            gff_gene_name_attribute=gff_gene_name_attribute,
             gff_default_attributes=gff_default_attributes,
             cohorts_analysis=cohorts_analysis,
             aim_analysis=aim_analysis,
@@ -877,7 +879,7 @@ def _gene_cnv(self, *, region, sample_sets, sample_query, max_coverage_variance)
 
         debug("access genes")
         df_genome_features = self.genome_features(region=region)
-        df_genes = df_genome_features.query("type == 'gene'")
+        df_genes = df_genome_features.query(f"type == '{self._gff_gene_type}'")
 
         debug("setup intermediates")
         windows = []
@@ -921,7 +923,10 @@ def _gene_cnv(self, *, region, sample_sets, sample_query, max_coverage_variance)
                 "gene_start": (["genes"], df_genes["start"].values),
                 "gene_end": (["genes"], df_genes["end"].values),
                 "gene_windows": (["genes"], windows),
-                "gene_name": (["genes"], df_genes["Name"].values),
+                "gene_name": (
+                    ["genes"],
+                    df_genes[self._gff_gene_name_attribute].values,
+                ),
                 "gene_strand": (["genes"], df_genes["strand"].values),
                 "gene_description": (["genes"], df_genes["description"].values),
                 "CN_mode": (["genes", "samples"], modes),

notebooks/plot_cnv.ipynb

@@ -7,7 +7,8 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "import malariagen_data"
+    "import malariagen_data\n",
+    "import dask"
    ]
   },
   {
@@ -24,6 +25,19 @@
     "ag3"
    ]
   },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "af1 = malariagen_data.Af1(\n",
+    "    \"simplecache::gs://vo_afun_release\",\n",
+    "    simplecache=dict(cache_storage=\"../gcs_cache\"),\n",
+    ")\n",
+    "af1"
+   ]
+  },
   {
    "cell_type": "markdown",
    "id": "74c46a04",
@@ -32,6 +46,13 @@
     "## CNV HMM coverage"
    ]
   },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Ag3"
+   ]
+  },
   {
    "cell_type": "code",
    "execution_count": null,
@@ -116,6 +137,26 @@
     ")"
    ]
   },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Af1"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# sample with a small CNV\n",
+    "af1.plot_cnv_hmm_coverage_track(\n",
+    "    sample=\"VBS24196\",\n",
+    "    region=\"2RL:28,460,000-28,580,000\",\n",
+    ")"
+   ]
+  },
   {
    "cell_type": "markdown",
    "id": "a302d86c",
@@ -124,6 +165,13 @@
     "## CNV HMM heatmap"
    ]
   },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Ag3"
+   ]
+  },
   {
    "cell_type": "code",
    "execution_count": null,
@@ -234,12 +282,32 @@
     ")"
    ]
   },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Af1"
+   ]
+  },
   {
    "cell_type": "code",
    "execution_count": null,
    "id": "5c4dcf97",
    "metadata": {},
    "outputs": [],
+   "source": [
+    "af1.plot_cnv_hmm_heatmap(\n",
+    "    sample_sets=\"1230-VO-GA-CF-AYALA-VMF00045\",\n",
+    "    region=\"2RL:28,520,000-28,570,000\",\n",
+    "    max_coverage_variance=None,\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
    "source": []
   }
  ],
@@ -259,7 +327,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.8.16"
+   "version": "3.10.11"
   }
  },
  "nbformat": 4,

tests/anoph/test_aim_data.py

@@ -30,6 +30,7 @@ def ag3_sim_api(ag3_sim_fixture):
         aim_ids=("gambcolu_vs_arab", "gamb_vs_colu"),
         aim_palettes=_ag3.AIM_PALETTES,
         gff_gene_type="gene",
+        gff_gene_name_attribute="Name",
         gff_default_attributes=("ID", "Parent", "Name", "description"),
     )
 

tests/anoph/test_cnv_data.py

@@ -32,6 +32,7 @@ def ag3_sim_api(ag3_sim_fixture):
             "aim_species": object,
         },
         gff_gene_type="gene",
+        gff_gene_name_attribute="Name",
         gff_default_attributes=("ID", "Parent", "Name", "description"),
         results_cache=ag3_sim_fixture.results_cache_path.as_posix(),
         default_coverage_calls_analysis="gamb_colu",
@@ -48,6 +49,7 @@ def af1_sim_api(af1_sim_fixture):
         major_version_path=_af1.MAJOR_VERSION_PATH,
         pre=False,
         gff_gene_type="protein_coding_gene",
+        gff_gene_name_attribute="Note",
         gff_default_attributes=("ID", "Parent", "Note", "description"),
         results_cache=af1_sim_fixture.results_cache_path.as_posix(),
         default_coverage_calls_analysis="funestus",

tests/anoph/test_fst.py

@@ -30,6 +30,7 @@ def ag3_sim_api(ag3_sim_fixture):
             "aim_species": object,
         },
         gff_gene_type="gene",
+        gff_gene_name_attribute="Name",
         gff_default_attributes=("ID", "Parent", "Name", "description"),
         default_site_mask="gamb_colu_arab",
         results_cache=ag3_sim_fixture.results_cache_path.as_posix(),
@@ -48,6 +49,7 @@ def af1_sim_api(af1_sim_fixture):
         major_version_path=_af1.MAJOR_VERSION_PATH,
         pre=False,
         gff_gene_type="protein_coding_gene",
+        gff_gene_name_attribute="Note",
         gff_default_attributes=("ID", "Parent", "Note", "description"),
         default_site_mask="funestus",
         results_cache=af1_sim_fixture.results_cache_path.as_posix(),

tests/anoph/test_g123.py

@@ -27,6 +27,7 @@ def ag3_sim_api(ag3_sim_fixture):
             "aim_species": object,
         },
         gff_gene_type="gene",
+        gff_gene_name_attribute="Name",
         gff_default_attributes=("ID", "Parent", "Name", "description"),
         default_site_mask="gamb_colu_arab",
         results_cache=ag3_sim_fixture.results_cache_path.as_posix(),
@@ -46,6 +47,7 @@ def af1_sim_api(af1_sim_fixture):
         major_version_path=_af1.MAJOR_VERSION_PATH,
         pre=False,
         gff_gene_type="protein_coding_gene",
+        gff_gene_name_attribute="Note",
         gff_default_attributes=("ID", "Parent", "Note", "description"),
         default_site_mask="funestus",
         results_cache=af1_sim_fixture.results_cache_path.as_posix(),

tests/anoph/test_genome_features.py

@@ -21,6 +21,7 @@ def ag3_sim_api(ag3_sim_fixture):
         major_version_path=_ag3.MAJOR_VERSION_PATH,
         pre=True,
         gff_gene_type="gene",
+        gff_gene_name_attribute="Name",
         gff_default_attributes=("ID", "Parent", "Name", "description"),
         virtual_contigs=_ag3.VIRTUAL_CONTIGS,
     )
@@ -36,6 +37,7 @@ def af1_sim_api(af1_sim_fixture):
         major_version_path=_af1.MAJOR_VERSION_PATH,
         pre=False,
         gff_gene_type="protein_coding_gene",
+        gff_gene_name_attribute="Note",
         gff_default_attributes=("ID", "Parent", "Note", "description"),
     )
 
@@ -152,6 +154,7 @@ def gh334_api(fixture_dir):
         major_version_path="v1.0",
         pre=False,
         gff_gene_type="protein_coding_gene",
+        gff_gene_name_attribute="Note",
         gff_default_attributes=("ID", "Parent"),
     )
 

tests/anoph/test_hap_data.py

@@ -30,6 +30,7 @@ def ag3_sim_api(ag3_sim_fixture):
             "aim_species": object,
         },
         gff_gene_type="gene",
+        gff_gene_name_attribute="Name",
         gff_default_attributes=("ID", "Parent", "Name", "description"),
         results_cache=ag3_sim_fixture.results_cache_path.as_posix(),
         default_phasing_analysis="gamb_colu_arab",
@@ -47,6 +48,7 @@ def af1_sim_api(af1_sim_fixture):
         major_version_path=_af1.MAJOR_VERSION_PATH,
         pre=False,
         gff_gene_type="protein_coding_gene",
+        gff_gene_name_attribute="Note",
         gff_default_attributes=("ID", "Parent", "Note", "description"),
         results_cache=af1_sim_fixture.results_cache_path.as_posix(),
         default_phasing_analysis="funestus",

tests/anoph/test_igv.py

@@ -27,6 +27,7 @@ def ag3_sim_api(ag3_sim_fixture):
             "aim_species": object,
         },
         gff_gene_type="gene",
+        gff_gene_name_attribute="Name",
         gff_default_attributes=("ID", "Parent", "Name", "description"),
         default_site_mask="gamb_colu_arab",
         results_cache=ag3_sim_fixture.results_cache_path.as_posix(),
@@ -43,6 +44,7 @@ def af1_sim_api(af1_sim_fixture):
         major_version_path=_af1.MAJOR_VERSION_PATH,
         pre=False,
         gff_gene_type="protein_coding_gene",
+        gff_gene_name_attribute="Note",
         gff_default_attributes=("ID", "Parent", "Note", "description"),
         default_site_mask="funestus",
         results_cache=af1_sim_fixture.results_cache_path.as_posix(),

tests/anoph/test_pca.py

@@ -29,6 +29,7 @@ def ag3_sim_api(ag3_sim_fixture):
             "aim_species": object,
         },
         gff_gene_type="gene",
+        gff_gene_name_attribute="Name",
         gff_default_attributes=("ID", "Parent", "Name", "description"),
         default_site_mask="gamb_colu_arab",
         results_cache=ag3_sim_fixture.results_cache_path.as_posix(),
@@ -47,6 +48,7 @@ def af1_sim_api(af1_sim_fixture):
         major_version_path=_af1.MAJOR_VERSION_PATH,
         pre=False,
         gff_gene_type="protein_coding_gene",
+        gff_gene_name_attribute="Note",
         gff_default_attributes=("ID", "Parent", "Note", "description"),
         default_site_mask="funestus",
         results_cache=af1_sim_fixture.results_cache_path.as_posix(),

tests/anoph/test_snp_data.py

@@ -35,6 +35,7 @@ def ag3_sim_api(ag3_sim_fixture):
             "aim_species": object,
         },
         gff_gene_type="gene",
+        gff_gene_name_attribute="Name",
         gff_default_attributes=("ID", "Parent", "Name", "description"),
         default_site_mask="gamb_colu_arab",
         results_cache=ag3_sim_fixture.results_cache_path.as_posix(),
@@ -52,6 +53,7 @@ def af1_sim_api(af1_sim_fixture):
         major_version_path=_af1.MAJOR_VERSION_PATH,
         pre=False,
         gff_gene_type="protein_coding_gene",
+        gff_gene_name_attribute="Note",
         gff_default_attributes=("ID", "Parent", "Note", "description"),
         default_site_mask="funestus",
         results_cache=af1_sim_fixture.results_cache_path.as_posix(),

tests/anoph/test_snp_frq.py

@@ -33,6 +33,7 @@ def ag3_sim_api(ag3_sim_fixture):
             "aim_species": object,
         },
         gff_gene_type="gene",
+        gff_gene_name_attribute="Name",
         gff_default_attributes=("ID", "Parent", "Name", "description"),
         default_site_mask="gamb_colu_arab",
         results_cache=ag3_sim_fixture.results_cache_path.as_posix(),
@@ -50,6 +51,7 @@ def af1_sim_api(af1_sim_fixture):
         major_version_path=_af1.MAJOR_VERSION_PATH,
         pre=False,
         gff_gene_type="protein_coding_gene",
+        gff_gene_name_attribute="Note",
         gff_default_attributes=("ID", "Parent", "Note", "description"),
         default_site_mask="funestus",
         results_cache=af1_sim_fixture.results_cache_path.as_posix(),