WikiPathways consistent spelling

src/pyBiodatafuse/annotators/opentargets.py

@@ -432,7 +432,9 @@ def get_gene_drug_interactions(bridgedb_df: pd.DataFrame) -> Tuple[pd.DataFrame,
     return merged_df, version_metadata
 
 
-def get_gene_disease_associations(bridgedb_df: pd.DataFrame) -> Tuple[pd.DataFrame, dict]:
+def get_gene_disease_associations(
+    bridgedb_df: pd.DataFrame,
+) -> Tuple[pd.DataFrame, dict]:
     """Get information about diseases associated with genes based on OpenTargets.
 
     :param bridgedb_df: BridgeDb output for creating the list of gene ids to query

src/pyBiodatafuse/annotators/stringdb.py

@@ -15,7 +15,7 @@
 
 
 def get_version_stringdb() -> dict:
-    """Get version of StringDB API.
+    """Get version of STRING-DB API.
 
     :returns: a dictionary containing the version information
     """
@@ -32,11 +32,11 @@
 
 
 def _format_data(row, network_df):
-    """Helper function to reformat StringDB response.
+    """Helper function to reformat STRING-DB response.
 
     :param row: input_df row
-    :param network_df: StringDB response annotation DataFrame
-    :returns: StringDB reformatted annotation.
+    :param network_df: STRING-DB response annotation DataFrame
+    :returns: STRING-DB reformatted annotation.
     """
     gene_ppi_links = list()
 
@@ -46,25 +46,31 @@
         if row_arr["preferredName_A"] == row["identifier"]:
             if row_arr["preferredName_B"] not in target_links_set:
                 gene_ppi_links.append(
-                    {"stringdb_link_to": row_arr["preferredName_B"], "score": row_arr["score"]}
+                    {
+                        "stringdb_link_to": row_arr["preferredName_B"],
+                        "score": row_arr["score"],
+                    }
                 )
                 target_links_set.add(row_arr["preferredName_B"])
 
         elif row_arr["preferredName_B"] == row["identifier"]:
             if row_arr["preferredName_A"] not in target_links_set:
                 gene_ppi_links.append(
-                    {"stringdb_link_to": row_arr["preferredName_A"], "score": row_arr["score"]}
+                    {
+                        "stringdb_link_to": row_arr["preferredName_A"],
+                        "score": row_arr["score"],
+                    }
                 )
                 target_links_set.add(row_arr["preferredName_A"])
 
     return gene_ppi_links
 
 
 def get_ppi(bridgedb_df: pd.DataFrame):
-    """Annotate genes with protein-protein interactions from StringDB.
+    """Annotate genes with protein-protein interactions from STRING-DB.
 
     :param bridgedb_df: BridgeDb output for creating the list of gene ids to query
-    :returns: a DataFrame containing the StringDB output and dictionary of the metadata.
+    :returns: a DataFrame containing the STRING-DB output and dictionary of the metadata.
     """
     # Record the start time
     start_time = datetime.datetime.now()
@@ -89,7 +95,9 @@
 
     results = requests.post(request_url, data=params)
 
-    stringdb_ids_df = pd.read_csv(io.StringIO(results.content.decode("utf-8")), sep="\t")
+    stringdb_ids_df = pd.read_csv(
+        io.StringIO(results.content.decode("utf-8")), sep="\t"
+    )
     stringdb_ids_df.queryIndex = stringdb_ids_df.queryIndex.astype(str)
 
     # ---------- Get String PPI network using the String identifiers ---------------#
@@ -98,7 +106,9 @@
     request_url = "/".join([string_api_url, output_format, method])
 
     params = {
-        "identifiers": "%0d".join(list(stringdb_ids_df.stringId.unique())),  # your protein
+        "identifiers": "%0d".join(
+            list(stringdb_ids_df.stringId.unique())
+        ),  # your protein
         "species": 9606,  # species NCBI identifier
         "caller_identity": "github.com",  # your app name
     }
@@ -125,7 +135,7 @@
 
     # Add the datasource, query, query time, and the date to metadata
     string_metadata = {
-        "datasource": "StringDB",
+        "datasource": "STRING-DB",
         "metadata": {"source_version": string_version},
         "query": {
             "size": len(gene_list),

src/pyBiodatafuse/annotators/wikipathways.py

@@ -1,7 +1,7 @@
 #!/usr/bin/env python
 # -*- coding: utf-8 -*-
 
-"""Python file for queriying Wikipathways SPARQL endpoint (https://sparql.wikipathways.org/sparql)."""
+"""Python file for queriying WikiPathways SPARQL endpoint (https://sparql.wikipathways.org/sparql)."""
 
 import datetime
 import os
@@ -14,11 +14,13 @@
 
 
 def get_version_wikipathways() -> dict:
-    """Get version of Wikipathways.
+    """Get version of WikiPathways.
 
     :returns: a dictionary containing the version information
     """
-    with open(os.path.dirname(__file__) + "/queries/wikipathways-metadata.rq", "r") as fin:
+    with open(
+        os.path.dirname(__file__) + "/queries/wikipathways-metadata.rq", "r"
+    ) as fin:
         sparql_query = fin.read()
 
     sparql = SPARQLWrapper("https://sparql.wikipathways.org/sparql")
@@ -28,7 +30,9 @@
 
     res = sparql.queryAndConvert()
 
-    wikipathways_version = {"wikipathways_version": res["results"]["bindings"][0]["title"]["value"]}
+    wikipathways_version = {
+        "wikipathways_version": res["results"]["bindings"][0]["title"]["value"]
+    }
 
     return wikipathways_version
 
@@ -57,7 +61,9 @@
     else:
         query_gene_lists.append(" ".join(f'"{g}"' for g in hgnc_gene_list))
 
-    with open(os.path.dirname(__file__) + "/queries/wikipathways-genes-pathways.rq", "r") as fin:
+    with open(
+        os.path.dirname(__file__) + "/queries/wikipathways-genes-pathways.rq", "r"
+    ) as fin:
         sparql_query = fin.read()
 
     sparql = SPARQLWrapper("https://sparql.wikipathways.org/sparql")