Completed NCBI lookup, FASTA reading, ABIF reading, and Institut Pasteur querying

tests/mlstmyfasta/engine/local/test_abif.py

@@ -0,0 +1,8 @@
+import os
+
+from mlstmyfasta.engine.local.abif import load_sanger_sequence
+
+async def test_load_sanger_sequence_has_data():
+    assert os.path.exists("tests/resources/1I1_F_P1815443_047.ab1")
+    result_data = await load_sanger_sequence("tests/resources/1I1_F_P1815443_047.ab1")
+    assert result_data is not None

tests/mlstmyfasta/engine/local/test_fasta.py

@@ -0,0 +1,7 @@
+from mlstmyfasta.engine.local.fasta 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:
+        assert named_string.name == "BX470248.1"

tests/mlstmyfasta/engine/remote/databases/institutpasteur/test_profiles.py

@@ -0,0 +1,16 @@
+from Bio import SeqIO
+from mlstmyfasta.engine.data.MLST import Allele
+from mlstmyfasta.engine.remote.databases.institutpasteur.profiling import InstitutPasteurProfiler
+
+
+async def test_profiling_results_in_exact_matches_when_exact():
+    sequence = str(SeqIO.read("tests/resources/tohama_I_bpertussis.fasta", "fasta").seq)
+    async with InstitutPasteurProfiler(database_name="pubmlst_bordetella_seqdef") as dummy_profiler:
+        exact_matches = dummy_profiler.fetch_mlst_profile(sequence_string=sequence)
+        targets_left = {"adk", "fumC", "glyA", "tyrB", "icd", "pepA", "pgm"}
+        async for exact_match in exact_matches:
+            assert isinstance(exact_match, Allele)
+            assert exact_match.allele_variant == '1' # All of Tohama I has allele id I
+            targets_left.remove(exact_match.allele_loci)
+
+        assert len(targets_left) == 0

tests/mlstmyfasta/engine/remote/databases/ncbi/test_genbank.py

@@ -0,0 +1,5 @@
+from mlstmyfasta.engine.remote.databases.ncbi.genbank import fetch_ncbi_genbank
+
+
+async def test_fetch_ncbi_genbank_with_id_works():
+    assert len((await fetch_ncbi_genbank("CP011448.1")).sequence) > 0 

tests/mlstmyfasta/engine/test_annotate.py

@@ -1,14 +1,11 @@
-from mlstmyfasta.engine.annotations import annotate_from_genbank, fetch_ncbi_genbank
+from mlstmyfasta.engine.annotate import annotate_from_genbank, fetch_ncbi_genbank
 from Bio import SeqIO
 
 from mlstmyfasta.engine.data.genomics import AnnotatedString
 
-async def test_fetch_ncbi_genbank_with_id_works():
-    assert len((await fetch_ncbi_genbank("CP011448.1")).sequence) > 0 
-
 async def test_annotate_from_genbank_for_adk_annotation():
-    sequence = SeqIO.read("tests/resources/tohama_I_bpertussis.fasta", "fasta").seq
-    annotated_sequence = await annotate_from_genbank("CP011448.1", "bpertussis_tohamaI", str(sequence), max_annotation_length=750, gene_targets=set(["adk"]))
+    sequence = str(SeqIO.read("tests/resources/tohama_I_bpertussis.fasta", "fasta").seq)
+    annotated_sequence = await annotate_from_genbank("CP011448.1", "bpertussis_tohamaI", sequence, max_annotation_length=750, gene_targets=set(["adk"]))
     assert isinstance(annotated_sequence, AnnotatedString)
     assert len(annotated_sequence.annotations) >= 1
     assert annotated_sequence.annotations[0].type == "gene"