def test_read_pangenome_filewrong(caplog):
"""
giving a wrong pangenome file, raises error
"""
caplog.set_level(logging.INFO)
logger = logging.getLogger("test_pan")
# create wrong pangenome file
pan_to_use = os.path.join(GENEPATH, "Pangenome.lst")
with open(pan_to_use, "w") as ptu:
ptu.write("I'm not a good pangenome file")
with pytest.raises(SystemExit):
upan.read_pangenome(pan_to_use, logger)
assert "Reading and getting information from pangenome file" in caplog.text
assert "Error in pangenome file. No family found" in caplog.text
assert not os.path.isfile(pan_to_use + ".bin")
def post_treat(families, pangenome):
"""
From clusters = {num: [members]}, create:
- a pan_quali matrix (lines = families, columns = genomes, 1 if genome present in\
family, 0 otherwise)
- a pan_quanti matrix (lines = families, columns = genomes, number of members from given\
genome in the given family)
- a summary file: lines = families. For each family:
- nb_members: total number of members
- sum_quanti: should be the same as nb_members!
- sum_quali: number of different genomes in family
- nb_0: number of missing genomes in family
- nb_mono: number of genomes with exactly 1 member
- nb_multi: number of genomes with more than 1 member
- sum_0-mono-multi: should be equal to the total number of genomes in dataset
- max_multi: maximum number of members from 1 genome
Parameters
----------
families : dict
{num_fam: [list of members]}. Can be None, and then they will be retrieved from the\
pangenome file
pangenome : str
file containing pangenome
"""
fams_by_strain, families, all_strains = utilsp.read_pangenome(
pangenome, logger, families)
open_outputs_to_write(fams_by_strain, families, all_strains, pangenome)
def test_read_pangenome_fams(caplog):
"""
Test that when giving a pangenome file, and families, it directly extracts strain information
from the families: pangenome file does not need to exist, and a binary file is created
"""
caplog.set_level(logging.DEBUG)
logger = logging.getLogger("test_pan")
panfile = os.path.join(GENEPATH, "toto.txt")
fbs, fams, ass = upan.read_pangenome(panfile, logger, families=FAMILIES)
assert fbs == FAMS_BY_STRAIN
assert fams == FAMILIES
assert ass == ALL_STRAINS
assert "Retrieving information from pan families" in caplog.text
assert "Saving all information to a binary file for later use" in caplog.text
assert os.path.isfile(panfile + ".bin")
def test_read_pangenome_filetxt(caplog):
"""
Test that when giving a pangenome file, it returns all families as expected.
"""
caplog.set_level(logging.INFO)
logger = logging.getLogger("test_pan")
# Copy pan file to folder for files generated by tests. It will also save its bin version
pan_to_use = os.path.join(GENEPATH, "Pangenome.lst")
shutil.copyfile(PAN_FILE, pan_to_use)
fbs, fams, ass = upan.read_pangenome(pan_to_use, logger)
assert fbs == FAMS_BY_STRAIN
assert fams == FAMILIES
assert ass == ALL_STRAINS
assert "Reading and getting information from pangenome file" in caplog.text
assert "Saving all information to a binary file for later use" in caplog.text
assert os.path.isfile(pan_to_use + ".bin")
def test_read_pangenome_filebin(caplog):
"""
Test that when giving only a pangenome filename, and the corresponding bin file exists,
it reads the binary file, and returns expected objects.
"""
caplog.set_level(logging.INFO)
logger = logging.getLogger("test_pan")
# Copy pan file to folder for files generated by tests. It will also save its bin version
pan_to_use = os.path.join(GENEPATH, "Pangenome.lst")
panbin_to_use = os.path.join(GENEPATH, "Pangenome.lst.bin")
test_panbin = os.path.join(PAN_TEST, "pangenome.bin")
shutil.copyfile(PAN_FILE, pan_to_use)
shutil.copyfile(test_panbin, panbin_to_use)
fbs, fams, ass = upan.read_pangenome(pan_to_use, logger)
assert fbs == FAMS_BY_STRAIN
assert fams == FAMILIES
assert ass == ALL_STRAINS
assert "Retrieving info from binary file" in caplog.text
def test_read_pangenome_fams_binok(caplog):
"""
Test that when giving a pangenome file, and families, it directly extracts strain information
from the families: pangenome file does not need to exist. However, the pangenome.bin file
already exists (whatever its content), and is then not recreated.
"""
caplog.set_level(logging.INFO)
logger = logging.getLogger("test_pan")
panfile = os.path.join(GENEPATH, "toto.txt")
# Create bn pangenome file (which is empty
open(panfile + ".bin", "w").close()
fbs, fams, ass = upan.read_pangenome(panfile, logger, FAMILIES)
assert fbs == FAMS_BY_STRAIN
assert fams == FAMILIES
assert ass == ALL_STRAINS
with open(panfile + ".bin", "r") as panf:
all_lines = panf.readlines()
assert all_lines == []
assert "Retrieving information from pan families" in caplog.text
assert os.path.isfile(panfile + ".bin")
with open(panfile + ".bin", "r") as pfb:
assert pfb.readlines() == []
def test_read_pangenome_filebin_strfamnum(caplog):
"""
Test that when giving only a pangenome filename, and the corresponding bin file exists,
it reads the binary file, and returns expected objects.
"""
caplog.set_level(logging.INFO)
logger = logging.getLogger("test_pan")
# Copy pan file to folder for files generated by tests. It will also save its bin version
pan_to_use = os.path.join(GENEPATH, "Pangenome.lst")
panbin_to_use = os.path.join(GENEPATH, "Pangenome.lst.bin")
test_panbin = os.path.join(PAN_TEST, "pangenome-strfamnum.bin")
shutil.copyfile(PAN_FILE, pan_to_use)
shutil.copyfile(test_panbin, panbin_to_use)
fbs, fams, ass = upan.read_pangenome(pan_to_use, logger)
assert fbs == {"family1": {"gene1": ["gene1_5"],
"gene2": ["gene2_6"],
"gene3": ["gene3_8"]},
"2": {"gene1": ["gene1_", "gene1_toto"],
"gene3": ["gene3_5"]}}
assert fams == {"family1": ["gene1_5", "gene2_6", "gene3_8"],
"2": ["gene1_", "gene3_5", "gene1_toto"]}
assert ass == ["gene1", "gene2", "gene3"]
assert "Retrieving info from binary file" in caplog.text
def test_read_pangenome_strfamnum(caplog):
"""
giving a wrong pangenome file, raises error
"""
caplog.set_level(logging.INFO)
logger = logging.getLogger("test_pan")
# create wrong pangenome file
panfile = os.path.join(GENEPATH, "panfile_wrong")
with open(panfile, "w") as pfw:
pfw.write("family1 gene1_5 gene2_6 gene3_8\n")
pfw.write("2 gene1_ gene3_5 gene1_toto")
fbs, fams, sas = upan.read_pangenome(panfile, logger)
assert fbs == {"family1": {"gene1": ["gene1_5"],
"gene2": ["gene2_6"],
"gene3": ["gene3_8"]},
"2": {"gene1": ["gene1_", "gene1_toto"],
"gene3": ["gene3_5"]}}
assert fams == {"family1": ["gene1_5", "gene2_6", "gene3_8"],
"2": ["gene1_", "gene3_5", "gene1_toto"]}
assert sas == ["gene1", "gene2", "gene3"]
assert "Reading and getting information from pangenome file" in caplog.text
assert "Saving all information to a binary file for later use" in caplog.text
assert os.path.isfile(panfile + ".bin")
def main(cmd, pangenome, tol, multi, mixed, outputdir, lstinfo_file, floor,
verbose, quiet):
"""
Read pangenome and deduce Persistent genome according to the user criteria
Parameters
----------
pangenome : str
file containing pangenome
tol : float
min % of genomes present in a family to consider it as persistent (between 0 and 1)
multi : bool
True if multigenic families are allowed, False otherwise
mixed : bool
True if mixed families are allowed, False otherwise
outputdir : str or None
Specific directory for the generated persistent genome. If not given, pangenome directory is used.
lstinfo_file : str
list of genomes to include in the core/persistent genome. If not given, include all genomes of pan
floor : bool
Require at least floor(nb_genomes*tol) genomes if True, ceil(nb_genomes*tol) if False
verbose : int
verbosity:
- defaut 0 : stdout contains INFO, stderr contains ERROR.
- 1: stdout contains INFO, stderr contains WARNING and ERROR
- 2: stdout contains (DEBUG), DETAIL and INFO, stderr contains WARNING and ERROR
- >=15: Add DEBUG in stdout
quiet : bool
True if nothing must be sent to stdout/stderr, False otherwise
"""
# import needed packages
import logging
from PanACoTA import utils
from PanACoTA import utils_pangenome as utilsp
import PanACoTA.corepers_module.persistent_functions as pers
from PanACoTA import __version__ as version
# get pangenome name info
_, base_pan = os.path.split(pangenome)
if lstinfo_file:
_, base_lst = os.path.split(lstinfo_file)
else:
base_lst = "all"
# Define output filename
output_name = f"PersGenome_{base_pan}-{base_lst}_"
if floor:
output_name += "F"
output_name += str(tol)
if multi:
output_name += "-multi.lst"
elif mixed:
output_name += "-mixed.lst"
else:
output_name += ".lst"
# Define output directory and filename path
if not os.path.isdir(outputdir):
os.makedirs(outputdir)
outputfile = os.path.join(outputdir, output_name)
logfile_base = os.path.join(outputdir, "PanACoTA-corepers")
# level is the minimum level that will be considered.
# for verbose = 0 or 1, ignore details and debug, start from info
if verbose <= 1:
level = logging.INFO
# for verbose = 2, ignore only debug
if verbose >= 2 and verbose < 15:
level = 15 # int corresponding to detail level
# for verbose >= 15, write everything
if verbose >= 15:
level = logging.DEBUG
utils.init_logger(logfile_base,
level,
'corepers',
verbose=verbose,
quiet=quiet)
logger = logging.getLogger("corepers")
logger.info(f'PanACoTA version {version}')
logger.info("Command used\n \t > " + cmd)
logger.info(get_info(tol, multi, mixed, floor))
# Read pangenome
fams_by_strain, families, all_strains = utilsp.read_pangenome(
pangenome, logger)
# If list of genomes given, get subset of previous dicts, including only the genomes aksed
if lstinfo_file:
fams_by_strain, families, all_strains = pers.get_subset_genomes(
fams_by_strain, families, lstinfo_file)
# Generate persistent genome
fams = pers.get_pers(fams_by_strain, families, len(all_strains), tol,
multi, mixed, floor)
# Write persistent genome to file
pers.write_persistent(fams, outputfile)
logger.info("Persistent genome step done.")
return outputfile