Fix typo

scout/build/genes/hgnc_gene.py

@@ -17,7 +17,7 @@ def build_phenotype(phenotype_info):
     return phenotype_obj
 
 
-def build_hgnc_gene(gene_info: dict, cyoband_coords: Dict[str, dict], build: str = "37") -> dict:
+def build_hgnc_gene(gene_info: dict, cytoband_coords: Dict[str, dict], build: str = "37") -> dict:
     """Build a hgnc_gene object
 
     Returns:
@@ -64,7 +64,7 @@ def build_hgnc_gene(gene_info: dict, cyoband_coords: Dict[str, dict], build: str
 
     if gene_info.get("chromosome") is None:  # Gene not present in Ensembl.
         # Try to use cytoband coordinates instead
-        cytoband_coords: Optional[dict] = cyoband_coords.get(gene_info["location"])
+        cytoband_coords: Optional[dict] = cytoband_coords.get(gene_info["location"])
         if not cytoband_coords:
             LOG.warning(
                 f"Gene {gene_info.get('hgnc_symbol') or gene_info.get('hgnc_id')} doesn't have coordinates and cytoband not present in database, skipping."

scout/load/hgnc_gene.py

@@ -83,13 +83,13 @@ def load_hgnc_genes(
     nr_genes = len(genes)
     LOG.info(f"Building info for {nr_genes} genes")
 
-    cyoband_coords: Dict[str, dict] = adapter.cytoband_to_coordinates(build=build)
+    cytoband_coords: Dict[str, dict] = adapter.cytoband_to_coordinates(build=build)
 
     with progressbar(genes.values(), label="Building genes", length=nr_genes) as bar:
         for gene_data in bar:
             gene_obj = build_hgnc_gene(
                 gene_data,
-                cyoband_coords=cyoband_coords,
+                cytoband_coords=cytoband_coords,
                 build=build,
             )
 

tests/build/test_build_hgnc_gene.py

@@ -1,5 +1,3 @@
-from pprint import pprint as pp
-
 import pytest
 
 from scout.build.genes.hgnc_gene import build_hgnc_gene
@@ -11,7 +9,7 @@ def test_build_hgnc_genes(genes):
     # WHEN building hgnc gene objecs
     for hgnc_id in genes:
         gene_info = genes[hgnc_id]
-        gene_obj = build_hgnc_gene(gene_info=gene_info, cyoband_coords={})
+        gene_obj = build_hgnc_gene(gene_info=gene_info, cytoband_coords={})
         # THEN check that the gene models have a hgnc id
         assert gene_obj["hgnc_id"]
 
@@ -25,20 +23,19 @@ def test_build_hgnc_gene():
         "start": 1,
         "end": 1000,
     }
-    gene_obj = build_hgnc_gene(gene_info=gene_info, cyoband_coords={})
+    gene_obj = build_hgnc_gene(gene_info=gene_info, cytoband_coords={})
 
     assert gene_obj["hgnc_id"] == gene_info["hgnc_id"]
     assert gene_obj["hgnc_symbol"] == gene_info["hgnc_symbol"]
     assert gene_obj["length"] == gene_info["end"] - gene_info["start"]
     assert gene_obj["ensembl_id"] == gene_info["ensembl_gene_id"]
 
 
-# TODO: are 'ensembl_gene_id' and 'ensembl_id' the same thing? -both seem to be used!
 @pytest.mark.parametrize("key", ["hgnc_id", "hgnc_symbol", "chromosome", "start", "end"])
 def test_build_hgnc_gene_missing_hgnc_symbol(test_gene, key):
     ## GIVEN a dictionary with gene information
 
     # WHEN deleting a required key
     test_gene.pop(key)
     # THEN calling build_hgnc_gene() will return None
-    assert build_hgnc_gene(gene_info=test_gene, cyoband_coords={}) is None
+    assert build_hgnc_gene(gene_info=test_gene, cytoband_coords={}) is None

tests/conftest.py

@@ -239,7 +239,7 @@ def gene_bulk(genes):
     """Return a list with HgncGene objects"""
     bulk = []
     for gene_key in genes:
-        bulk.append(build_hgnc_gene(genes[gene_key]))
+        bulk.append(build_hgnc_gene(genes[gene_key], cytoband_coords={}))
 
     return bulk
 
@@ -249,7 +249,7 @@ def gene_bulk_38(genes):
     """Return a list with HgncGene objects"""
     bulk = []
     for gene_key in genes:
-        gene_obj = build_hgnc_gene(genes[gene_key])
+        gene_obj = build_hgnc_gene(genes[gene_key], cytoband_coords={})
         gene_obj["build"] = "38"
         bulk.append(gene_obj)