Merge pull request #1 from a-r-j/master

Merge changes

.requirements/base.in

@@ -1,6 +1,6 @@
 biopandas>=0.4.1
 biopython
-bioservices
+bioservices>=1.10.0
 deepdiff
 loguru
 matplotlib>=3.4.3
@@ -15,7 +15,7 @@ rich-click
 seaborn
 pyyaml>=5.1,<6.*
 scikit-learn
-scipy
+scipy 
 tqdm
 typing_extensions
 wget

CHANGELOG.md

@@ -1,4 +1,10 @@
-### 1.5.0 - UNRELEASED
+### 1.5.1
+
+#### Changes
+
+* #187 updates sequence retrieval due to UniProt API changes.
+
+### 1.5.0
 
 #### Protein
 

graphein/grn/features/node_features.py

@@ -1,4 +1,5 @@
 import logging
+from typing import Any, Dict
 
 from graphein.utils.utils import import_message
 
@@ -16,12 +17,15 @@
     log.warning(message)
 
 
-def add_sequence_to_nodes(n, d):
+def add_sequence_to_nodes(n: str, d: Dict[str, Any]):
     """
-    Maps UniProt ACC to UniProt ID. Retrieves sequence from UniProt and adds it to the node
+    Maps UniProt ACC to UniProt ID. Retrieves sequence from UniProt and adds
+    it to the node
 
-    :param n: Graph node.
+    :param n: Graph node. Unused (retained for a consistent function signature).
+    :type n: str
     :param d: Graph attribute dictionary.
+    :type d: Dict[str, Any]
     """
 
     h = HGNC(verbose=False)
@@ -35,4 +39,4 @@ def add_sequence_to_nodes(n, d):
     # Todo mapping with bioservices to support other protein IDs?
 
     for id in d["uniprot_ids"]:
-        d[f"sequence_{id}"] = u.get_fasta_sequence(id)
+        d[f"sequence_{id}"] = u.search(id, columns="sequence").split("\n")[1]

graphein/ppi/features/node_features.py

@@ -48,7 +48,7 @@ def add_sequence_to_nodes(n: str, d: Dict[str, Any]):
     # Todo mapping with bioservices to support other protein IDs?
 
     for id in d["uniprot_ids"]:
-        d[f"sequence_{id}"] = u.get_fasta_sequence(id)
+        d[f"sequence_{id}"] = u.search(id, columns="sequence").split("\n")[1]
 
 
 if __name__ == "__main__":