Renaming project to NSBDiagnosisToolkit

tests/nsbdiagnosistoolkit/engine/local/test_abif.py

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

tests/nsbdiagnosistoolkit/engine/local/test_fasta.py

@@ -0,0 +1,7 @@
+from nsbdiagnosistoolkit.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/nsbdiagnosistoolkit/engine/remote/databases/institutpasteur/test_profiling.py

@@ -0,0 +1,35 @@
+from Bio import SeqIO
+from nsbdiagnosistoolkit.engine.data.MLST import Allele, MLSTProfile
+from nsbdiagnosistoolkit.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_allele_variants(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
+
+async def test_profiling_results_in_correct_st():
+    sequence = str(SeqIO.read("tests/resources/tohama_I_bpertussis.fasta", "fasta").seq)
+    dummy_alleles = [
+        Allele("adk", "1"),
+        Allele("fumC", "1"),
+        Allele("glyA", "1"),
+        Allele("tyrB", "1"),
+        Allele("icd", "1"),
+        Allele("pepA", "1"),
+        Allele("pgm", "1"),
+    ]
+    async with InstitutPasteurProfiler(database_name="pubmlst_bordetella_seqdef") as dummy_profiler:
+        exact_matches = dummy_profiler.fetch_mlst_allele_variants(sequence_string=sequence)
+        mlst_st_data = await dummy_profiler.fetch_mlst_st(dummy_alleles)
+        assert mlst_st_data is not None
+        assert isinstance(mlst_st_data, MLSTProfile)
+        assert mlst_st_data.clonal_complex == "ST-2 complex"
+        assert mlst_st_data.sequence_type == "1"

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

@@ -0,0 +1,5 @@
+from nsbdiagnosistoolkit.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/nsbdiagnosistoolkit/engine/test_annotate.py

@@ -0,0 +1,12 @@
+from nsbdiagnosistoolkit.engine.annotate import annotate_from_genbank, fetch_ncbi_genbank
+from Bio import SeqIO
+
+from nsbdiagnosistoolkit.engine.data.genomics import AnnotatedString
+
+async def test_annotate_from_genbank_for_adk_annotation():
+    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"
+    assert "adk" in annotated_sequence.annotations[0].feature_properties["gene"]