Multiple string profiling now respects grouped queries (for non-WGS)

pyproject.toml

@@ -13,11 +13,12 @@ dependencies = [
 ]
 requires-python = ">=3.12"
 description = "A library to rapidly fetch fetch MLST profiles given sequences for various diseases."
+license = {text = "GPL-3.0-or-later"}
 
 [project.urls]
-Homepage = "https://github.com/RealYHD/autoBIGS.engine"
-Source = "https://github.com/RealYHD/autoBIGS.engine"
-Issues = "https://github.com/RealYHD/autoBIGS.engine/issues"
+Homepage = "https://github.com/Syph-and-VPD-Lab/autoBIGS.engine"
+Source = "https://github.com/Syph-and-VPD-Lab/autoBIGS.engine"
+Issues = "https://github.com/Syph-and-VPD-Lab/autoBIGS.engine/issues"
 
 [tool.setuptools_scm]
 

src/autobigs/engine/analysis/bigsdb.py

@@ -124,13 +124,17 @@ class RemoteBIGSdbMLSTProfiler(BIGSdbMLSTProfiler):
 
     async def profile_multiple_strings(self, query_named_string_groups: AsyncIterable[Iterable[NamedString]], stop_on_fail: bool = False) -> AsyncGenerator[NamedMLSTProfile, Any]:
         async for named_strings in query_named_string_groups:
+            names: list[str] = list()
+            sequences: list[str] = list()
             for named_string in named_strings:
-                try:
-                    yield NamedMLSTProfile(named_string.name, (await self.profile_string([named_string.sequence])))
-                except NoBIGSdbMatchesException as e:
-                    if stop_on_fail:
-                        raise e
-                    yield NamedMLSTProfile(named_string.name, None)
+                names.append(named_string.name)
+                sequences.append(named_string.sequence)
+            try:
+                yield NamedMLSTProfile("-".join(names), (await self.profile_string(sequences)))
+            except NoBIGSdbMatchesException as e:
+                if stop_on_fail:
+                    raise e
+                yield NamedMLSTProfile("-".join(names), None)
 
     async def close(self):
         await self._http_client.close()

src/autobigs/engine/reading.py

@@ -5,12 +5,13 @@ from Bio import SeqIO
 
 from autobigs.engine.structures.genomics import NamedString
 
-async def read_fasta(handle: Union[str, TextIOWrapper]) -> AsyncGenerator[NamedString, Any]:
+async def read_fasta(handle: Union[str, TextIOWrapper]) -> Iterable[NamedString]:
     fasta_sequences = asyncio.to_thread(SeqIO.parse, handle=handle, format="fasta")
+    results = []
     for fasta_sequence in await fasta_sequences:
-        yield NamedString(fasta_sequence.id, str(fasta_sequence.seq))
+        results.append(NamedString(fasta_sequence.id, str(fasta_sequence.seq)))
+    return results
 
-async def read_multiple_fastas(handles: Iterable[Union[str, TextIOWrapper]]) -> AsyncGenerator[NamedString, Any]:
+async def read_multiple_fastas(handles: Iterable[Union[str, TextIOWrapper]]) -> AsyncGenerator[Iterable[NamedString], Any]:
     for handle in handles:
-        async for named_seq in read_fasta(handle):
-            yield named_seq
+        yield await read_fasta(handle)

tests/autobigs/engine/test_reading.py

@@ -2,6 +2,6 @@ from autobigs.engine.reading import read_fasta
 
 
 async def test_fasta_reader_not_none():
-    named_strings = read_fasta("tests/resources/tohama_I_bpertussis.fasta")
-    async for named_string in named_strings:
+    named_strings = await read_fasta("tests/resources/tohama_I_bpertussis.fasta")
+    for named_string in named_strings:
         assert named_string.name == "BX470248.1"