def test_Otyping(caplog):
"""
Giving E.coli fasta genomes with truncated wzx and wzy genes with reference coverage <50 predict O and H antigens
:return: None
"""
caplog.set_level(logging.DEBUG)
file = os.path.join(
TEST_ROOT, 'Data/Escherichia_O26H11.fasta'
) #+","+os.path.join(TEST_ROOT, 'Data/Escherichia.fna')
tmpdir = tempfile.mkdtemp()
set_input(input=file,
cores=4,
print_sequence=True,
verify=True,
output=tmpdir,
debug=False)
ectyper.run_program()
with open(os.path.join(tmpdir, "output.tsv")) as outfp:
secondrow = outfp.readlines()[1].split("\t")
Otype = secondrow[2]
Htype = secondrow[3]
assert Otype == "-", "Expected no call but reported O-type:" + Otype
assert Htype == "H11", "Expected H11 but reported H-type:" + Htype
def test_valid_fastq_file_with_verify(caplog):
"""
Given a valid fastq file with low genome coverage, test species verification fail
Use a temp dir for the test output
:return: None
"""
file = os.path.join(TEST_ROOT, 'Data/Escherichia.fastq')
set_input(file, verify=True)
ectyper.run_program()
assert "Escherichia coli" in caplog.text
def test_integration_validfasta_noverify(caplog):
"""
Tests for fasta files without E.coli species verify function (--verify) do not fail as per issue #76 (https://github.com/phac-nml/ecoli_serotyping/issues/76)
:return: None
"""
file = os.path.join(TEST_ROOT, 'Data/Escherichia.fna')
set_input(file, verify=False)
ectyper.run_program()
assert "O103\tH2\tO103:H2" in caplog.text
assert "Escherichia\t-\tO103\tH2" in caplog.text
def test_integration_invalid_file(caplog):
"""
Giving a non-fasta file in fasta-file name.
:return: None
"""
caplog.set_level(logging.DEBUG)
file = os.path.join(TEST_ROOT, 'Data/test_dir/badfasta.fasta')
set_input(input=file)
ectyper.run_program()
assert "Non fasta / fastq file" in caplog.text
def test_integration_yersinia(caplog):
"""
Ensure a non-E. coli gets categorized as such
:return: None
"""
file = os.path.join(TEST_ROOT, 'Data/Yersinia.fasta')
set_input(file)
ectyper.run_program()
assert "Yersinia pestis" in caplog.text
assert "WARNING (WRONG SPECIES)" in caplog.text
def test_valid_fastq_file(caplog):
"""
Given a valid fastq file, get the correct results.
Use a temp dir for the test output
:return: None
"""
file = os.path.join(TEST_ROOT, 'Data/Escherichia.fastq')
set_input(file, verify=False)
ectyper.run_program()
assert "O22:H8" in caplog.text
def test_integration_no_file():
"""
Giving no input to the program.
:return: None
"""
file = ''
set_input(file)
with pytest.raises(FileNotFoundError) as se:
ectyper.run_program()
assert se.type == FileNotFoundError
assert str(se.value) == "No files were found to run on"
def test_integration_valid_file(caplog):
"""
Ensure a valid E. coli fasta passes
:return: None
"""
file = os.path.join(TEST_ROOT, 'Data/Escherichia.fna')
set_input(file)
ectyper.run_program()
print(caplog.text)
assert "PASS (REPORTABLE)" in caplog.text
assert "O103:H2" in caplog.text
assert "Escherichia coli" in caplog.text
def test_non_existing_accession_in_meta(caplog):
"""
GCA_900059685.2 - Streptococcus pneumoniae - ftp://ftp.ncbi.nlm.nih.gov/genomes/all/GCA/900/059/685/GCA_900059685.2_12291_5_44
is not present in assembly_summary_refseq.txt and is a perfect candidate to try to test
species identification function
:param caplog:
:return:
"""
caplog.set_level(logging.DEBUG)
file = os.path.join(TEST_ROOT, 'Data/GCA_900059685.2.fna')
set_input(input=file, verify=False)
ectyper.run_program()
assert "No O and H antigen determinant E.coli genes were found" in caplog.text
def test_multiple_directories(caplog):
"""
Check a number of small files, some good, some bad,
within a nested directory structure.
:param caplog: Capture logging output for pytest
:return: None
"""
the_dir = os.path.join(TEST_ROOT, 'Data/test_dir')
set_input(the_dir, cores=4, verify=True, print_sequence=True)
ectyper.run_program()
assert any([
True if re.match(
r".+sample2.+WARNING\s+\(WRONG\s+SPECIES\).+Sample identified as -",
line) else False for line in caplog.text.splitlines()
]) #O148:H44
assert any([
True if re.match(
r".+sample3.+WARNING\s+\(WRONG\s+SPECIES\).+Sample identified as -",
line) else False for line in caplog.text.splitlines()
]) #O148:H44
assert any([
True if re.match(
r".+sample4.+WARNING\s+\(WRONG\s+SPECIES\).+Sample identified as -",
line) else False for line in caplog.text.splitlines()
]) #O148:H44
assert any([
True if re.match(
r".+badfasta.+WARNING\s+\(WRONG\s+SPECIES\).+Non fasta / fastq file",
line) else False for line in caplog.text.splitlines()
])
assert any([
True if re.match(
r".+sample.fasta.+WARNING\s+\(WRONG\s+SPECIES\).+Non fasta / fastq file",
line) else False for line in caplog.text.splitlines()
])
assert any([
True if re.match(
r".+sampletar.+WARNING\s+\(WRONG\s+SPECIES\).+Non fasta / fastq file",
line) else False for line in caplog.text.splitlines()
])
assert any([
True if re.match(
r".+test_junk.+WARNING\s+\(WRONG\s+SPECIES\).+Non fasta / fastq file",
line) else False for line in caplog.text.splitlines()
])
def test_Ecoli_O17H18(caplog):
caplog.set_level(logging.DEBUG)
file = os.path.join(TEST_ROOT, 'Data/EscherichiaO17H18.fasta')
tmpdir = tempfile.mkdtemp()
set_input(input=file,
cores=4,
print_sequence=False,
verify=True,
debug=True,
output=tmpdir)
ectyper.run_program()
with open(os.path.join(tmpdir, "output.tsv")) as outfp:
rows = outfp.readlines()
secondrow = rows[1:][0] #check only second row
assert "Escherichia coli\tO77/O17/O44/O106\tH18\tO77/O17/O44/O106:H18\tWARNING MIXED O-TYPE" in secondrow
def test_Shigella_typing(caplog):
caplog.set_level(logging.DEBUG)
file = os.path.join(
TEST_ROOT, 'Data/DRR015915_Shigella_boydii.fasta'
) # +","+os.path.join(TEST_ROOT, 'Data/Escherichia.fna')
tmpdir = tempfile.mkdtemp()
set_input(input=file,
cores=4,
print_sequence=True,
debug=True,
verify=True,
output=tmpdir)
ectyper.run_program()
with open(os.path.join(tmpdir, "output.tsv")) as outfp:
secondrow = outfp.readlines()[1].split("\t")
species = secondrow[1]
assert species == "Shigella boydii"
def test_closeOalles_O42_O28(caplog):
caplog.set_level(logging.DEBUG)
file = os.path.join(
TEST_ROOT, 'Data/EscherichiaO28H5.fasta'
) # +","+os.path.join(TEST_ROOT, 'Data/Escherichia.fna')
tmpdir = tempfile.mkdtemp()
set_input(input=file,
cores=4,
print_sequence=True,
verify=True,
debug=False,
output=tmpdir)
ectyper.run_program()
with open(os.path.join(tmpdir, "output.tsv")) as outfp:
secondrow = outfp.readlines()[1]
print(secondrow)
assert re.match(r".+Escherichia coli.+O42\/O28\tH25\tO42\/O28:H25",
secondrow)
def test_Ealbertii_1(caplog): #error
LOG.info(
"Starting 1 of 3 test on EnteroBase on sample ESC_HA8355AA_AS: Escherichia albertii O65:H5"
)
caplog.set_level(logging.DEBUG)
file = os.path.join(TEST_ROOT, 'Data/ESC_HA8355AA_AS_Ealberii_O65H5.fasta')
tmpdir = tempfile.mkdtemp()
set_input(input=file,
cores=4,
print_sequence=True,
verify=True,
output=tmpdir)
ectyper.run_program()
with open(os.path.join(tmpdir, "output.tsv")) as outfp:
rows = outfp.readlines()
secondrow = rows[1:][0] #remove header line
assert "Escherichia albertii" in secondrow
assert "WARNING (WRONG SPECIES)" in secondrow
def test_Ealbertii_3(caplog):
LOG.info(
"Starting 3 of 3 test Escherichia albertii O49:NM"
) #can not type O49 due to poor sequence quality of uncertainty of wet-lab O49 typing
caplog.set_level(logging.DEBUG)
file = os.path.join(TEST_ROOT, 'Data/Ealbertii_O49NM.fasta')
tmpdir = tempfile.mkdtemp()
set_input(input=file,
cores=4,
print_sequence=True,
verify=True,
output=tmpdir)
ectyper.run_program()
with open(os.path.join(tmpdir, "output.tsv")) as outfp:
rows = outfp.readlines()
secondrow = rows[1:][0] #check only second row
assert "Escherichia albertii" in secondrow
assert "WARNING (WRONG SPECIES)" in secondrow
def test_Ealbertii_2(): #error
LOG.info(
"Starting 2 of 3 test on EnteroBase on sample on ESC_HA8509AA_AS: Escherichia albertii O5:H5"
)
file = os.path.join(TEST_ROOT, 'Data/ESC_HA8509AA_AS_EalbertiiO5H5.fasta')
tmpdir = tempfile.mkdtemp()
set_input(input=file,
cores=4,
print_sequence=True,
verify=True,
output=tmpdir)
ectyper.run_program()
with open(os.path.join(tmpdir, "output.tsv")) as outfp:
rows = outfp.readlines()
secondrow = rows[1:][0] #check only second row
assert "Escherichia albertii" in secondrow
assert "WARNING (WRONG SPECIES)" in secondrow
def test_mixofspecies(caplog):
caplog.set_level(logging.DEBUG)
file = os.path.join(TEST_ROOT,
'Data/Campylobacter.fasta') +","+os.path.join(TEST_ROOT, 'Data/Salmonella.fasta')+","\
+ os.path.join(TEST_ROOT, 'Data/Escherichia.fastq')
tmpdir = tempfile.mkdtemp()
set_input(input=file,
cores=4,
print_sequence=True,
verify=True,
output=tmpdir)
ectyper.run_program()
with open(os.path.join(tmpdir, "output.tsv")) as outfp:
rows = outfp.readlines()
rows = rows[1:] #remove header line
serovars = []
genomenames = []
QCflag = []
confidence = []
for row in rows:
rowlist = row.split("\t")
print(rowlist)
serovars.append(rowlist[4])
genomenames.append(rowlist[1])
QCflag.append(rowlist[5])
confidence.append(rowlist[6])
assert serovars == ['-:-', 'O22:H8', '-:-']
expectedspecies_list = [
"Campylobacter jejuni", "Escherichia coli", "Salmonella enterica"
]
for i in range(0, 3):
assert bool(re.match(expectedspecies_list[i], genomenames[i])) == True
assert QCflag == [
"WARNING (WRONG SPECIES)", "PASS (REPORTABLE)",
"WARNING (WRONG SPECIES)"
]
def test_failed_species_identification_nospeciesverify(caplog):
caplog.set_level(logging.DEBUG)
file = os.path.join(TEST_ROOT, 'Data/GCF_001672015.1.fna')
set_input(input=file, verify=False)
ectyper.run_program()
assert "GCF_001672015.1\t-\t-\tH8\t-:H8\t-" in caplog.text
def test_failed_species_identification(caplog):
caplog.set_level(logging.DEBUG)
file = os.path.join(TEST_ROOT, 'Data/GCF_001672015.1.fna')
set_input(input=file, verify=True)
ectyper.run_program()
assert "GCF_001672015.1\tEscherichia coli\t-\tH8\t-:H8\tWARNING (-:H TYPING)" in caplog.text
