Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

WikiPathways consistent spelling #13

Closed
wants to merge 6 commits into from
Closed

WikiPathways consistent spelling #13

Show file tree
Hide file tree
Changes from 3 commits
Commits
Show all changes
6 commits
Select commit Hold shift + click to select a range
04500fe
WikiPathways consistent spelling
egonw Oct 31, 2023
efd43a1
document format
tabbassidaloii Nov 1, 2023
8d8a37f
document format fix
tabbassidaloii Nov 1, 2023
774014a
Merge branch 'main' into patch-2
tabbassidaloii Nov 1, 2023
52dd864
fix document
tabbassidaloii Nov 1, 2023
f354384
database name fix
tabbassidaloii Nov 1, 2023
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
4 changes: 3 additions & 1 deletion src/pyBiodatafuse/annotators/opentargets.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -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
Expand Down
22 changes: 17 additions & 5 deletions src/pyBiodatafuse/annotators/stringdb.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -59,7 +59,9 @@ def annotate_genes_with_stringdb(bridgedb_df: pd.DataFrame):

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)

# for i, row in stringdb_ids_df.iterrows():
Expand All @@ -75,7 +77,9 @@ def annotate_genes_with_stringdb(bridgedb_df: pd.DataFrame):
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
}
Expand All @@ -86,7 +90,9 @@ def annotate_genes_with_stringdb(bridgedb_df: pd.DataFrame):

# ---------- Add the interactions of each protein (row) to a new column ('stringdb') ---------------#

data_df["stringdb"] = data_df.apply(get_protein_interactions, network_df=network_df, axis=1)
data_df["stringdb"] = data_df.apply(
get_protein_interactions, network_df=network_df, axis=1
)

# Record the end time
end_time = datetime.datetime.now()
Expand Down Expand Up @@ -130,14 +136,20 @@ def get_protein_interactions(row, network_df):
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"])

Expand Down
16 changes: 11 additions & 5 deletions src/pyBiodatafuse/annotators/wikipathways.py
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -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
Expand All @@ -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")
Expand All @@ -28,7 +30,9 @@ def get_version_wikipathways() -> dict:

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

Expand Down Expand Up @@ -57,7 +61,9 @@ def get_gene_wikipathway(bridgedb_df: pd.DataFrame):
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")
Expand Down