Finished writing genbank fetching function

src/mlstmyfasta/engine/annotations/wgs.py

@@ -0,0 +1,24 @@
+from typing import Any, Generator, List, Sequence
+from Bio.Align import PairwiseAligner
+from Bio import Entrez
+from Bio import SeqIO
+
+from mlstmyfasta.engine.data.genomics import Strand, StrandFeature
+
+async def fetch_ncbi_genbank(genbank_id: str) -> Strand:
+    with Entrez.efetch(db="nucleotide", id=genbank_id, rettype="gb", retmode="text") as fetch_stream:
+        record = SeqIO.read(fetch_stream, "genbank")
+        sequence_features = list()
+        for feature in record.features:
+            start, end = feature.location.split("..")
+            start = int(start)
+            end = int(end)
+            feature_properties = dict()
+            for qualifier in feature.qualifiers:
+                feature_properties[qualifier.key] = qualifier.value
+            sequence_features.append(StrandFeature(name=feature.key,
+                                  start=start,
+                                  end=end,
+                                  feature_properties=feature_properties
+                                 ))
+        return Strand(name=genbank_id, coding=record.sequence, features=sequence_features)

src/mlstmyfasta/engine/data/genomics.py

@@ -1,12 +1,18 @@
 from dataclasses import dataclass
+from typing import Mapping, Sequence
+
 
 @dataclass
-class Sequence:
+class StrandFeature:
     name: str
-    sequence: str
+    start: int
+    end: int
+    feature_properties: Mapping[str, str]
     
 @dataclass
-class SequenceFeature:
+class Strand:
-    type: str
     name: str
+    coding: str
+    features: Sequence[StrandFeature]
+