def test_get_core_multi(caplog):
"""
Getting a multi core genome (4 genomes, having at least 1 member)
"""
caplog.set_level(logging.DEBUG)
fams = persf.get_pers(FAMS_BY_STRAIN, FAMILIES, 4, multi=True)
exp_fams = {num: mems for num, mems in FAMILIES.items() if num in ['3', '5', '1', '12']}
assert exp_fams == fams
assert ("The persistent genome contains 4 families with members present in "
"at least 4 different genomes (100% of the total number of genomes)") in caplog.text
def test_get_core_strict(caplog):
"""
Getting a core genome (4 genomes, all having exactly 1 member)
"""
caplog.set_level(logging.DEBUG)
fams = persf.get_pers(FAMS_BY_STRAIN, FAMILIES, 4)
exp_fams = {num: mems for num, mems in FAMILIES.items() if num in ['3', '5']}
assert exp_fams == fams
assert ("The core genome contains 2 families, each one having "
"exactly 4 members, from the 4 different genomes.") in caplog.text
def test_get_99pers_multi(caplog):
"""
Getting a multi persistent genome at 99% (ceil) -> 3 genomes with exactly 1member,
other with anything
"""
caplog.set_level(logging.DEBUG)
fams = persf.get_pers(FAMS_BY_STRAIN, FAMILIES, 4, tol=0.99, multi=True)
exp_fams = {num: mems for num, mems in FAMILIES.items() if num in ['1', '3', '5', '12']}
assert exp_fams == fams
assert ("The persistent genome contains 4 families with members present in "
"at least 4 different genomes (99.0% of the total number of genomes).") in caplog.text
def test_get_99pers_mixed(caplog):
"""
Getting a mixed persistent genome at 99% (ceil) -> 4 genomes with exactly 1member
"""
caplog.set_level(logging.DEBUG)
fams = persf.get_pers(FAMS_BY_STRAIN, FAMILIES, 4, tol=0.99, mixed=True)
exp_fams = {num: mems for num, mems in FAMILIES.items() if num in ['3', '5']}
assert exp_fams == fams
assert ("The persistent genome contains 2 families, each one having exactly 1 member from at least "
"99.0% of the genomes (4 genomes). In the remaining "
"1.0% genomes, there can be 0, 1 or several members.") in caplog.text
def test_get_99pers_strict(caplog):
"""
Getting a persistent genome at 99% (ceil) -> 4 genomes with exactly 1member
"""
caplog.set_level(logging.DEBUG)
fams = persf.get_pers(FAMS_BY_STRAIN, FAMILIES, 4, tol=0.99)
exp_fams = {num: mems for num, mems in FAMILIES.items() if num in ['3', '5']}
assert exp_fams == fams
assert ("The persistent genome contains 2 families, each one "
"having exactly 1 member from at least 99.0% of the 4 different genomes "
"(that is 4 genomes). The other genomes are absent from the family.") in caplog.text
def test_get_99pers_floor_multi(caplog):
"""
Getting a multi persistent genome at floor(99%) -> at least 3 genomes (any number of members)
"""
caplog.set_level(logging.DEBUG)
fams = persf.get_pers(FAMS_BY_STRAIN, FAMILIES, 4, tol=0.99, floor=True, multi=True)
exp_fams = {num: mems for num, mems in FAMILIES.items() if num in ['1', '3', '5', '6', '8',
'10', '11', '12']}
assert exp_fams == fams
assert ("The persistent genome contains 8 families with members present in "
"at least 3 different genomes (99.0% of the total number of genomes).") in caplog.text
def test_get_99pers_floor_strict(caplog):
"""
Getting a strict persistent at floor(99%) -> at least 3 genomes with 1 member, others
absent.
"""
caplog.set_level(logging.DEBUG)
fams = persf.get_pers(FAMS_BY_STRAIN, FAMILIES, 4, tol=0.99, floor=True)
exp_fams = {num: mems for num, mems in FAMILIES.items() if num in ['3', '5', '8', '10', '11']}
assert exp_fams == fams
assert ("The persistent genome contains 5 families, each one "
"having exactly 1 member from at least 99.0% of the 4 different genomes "
"(that is 3 genomes). The other genomes are absent from the family.") in caplog.text
def test_get_99pers_floor_mixed(caplog):
"""
Getting a mixed persistent at floor(99%) -> at least 3 genomes with 1 member, others
anything
"""
caplog.set_level(logging.DEBUG)
fams = persf.get_pers(FAMS_BY_STRAIN, FAMILIES, 4, tol=0.99, floor=True, mixed=True)
exp_fams = {num: mems for num, mems in FAMILIES.items() if num in ['1', '3', '5', '8', '10',
'11', '12']}
assert exp_fams == fams
assert ("The persistent genome contains 7 families, each one having exactly 1 member from at least "
"99.0% of the genomes (3 genomes). In the remaining "
"1.0% genomes, there can be 0, 1 or several members.") in caplog.text
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