def test_main_default(capsys):
"""
Test that with default parameters, it creates the expected core genome.
"""
tol = 1
multi = False
mixed = False
cmd = "cmd"
floor = False
verbose = 0
quiet = False
lstinfo = ""
out_pers = os.path.join(GENEPATH, "PersGenome_pangenome.lst-all_1.lst")
assert corepers.main(cmd, UPAN, tol, multi, mixed, GENEPATH, lstinfo,
floor, verbose, quiet) == out_pers
# Check creation of binary file for pangenome, and remove it
assert os.path.isfile(UPAN + ".bin")
# Check presence of persistent genome, and its content, and remove it
exp_pers = os.path.join(EXP_PATH, "exp_coregenome.txt")
assert os.path.isfile(out_pers)
assert tutil.compare_order_content(out_pers, exp_pers)
# Check presence of log files and remove them
logfile = os.path.join(GENEPATH, "PanACoTA-corepers.log")
assert os.path.isfile(logfile)
assert os.path.isfile(logfile + ".err")
# Check log messages
out, err = capsys.readouterr()
assert "Will generate a CoreGenome." in out
assert "Saving all information to a binary file for later use" in out
assert "Generating Persistent genome of a dataset containing 4 genomes" in out
assert ("The core genome contains 2 families, each one having exactly "
"4 members, from the 4 different genomes.") in out
def test_main_pers_floor_multi(capsys):
"""
Test that with default parameters, it creates the expected core genome.
"""
tol = 0.99
multi = True
mixed = False
floor = True
verbose = 15
lstinfo = os.path.join(GENEPATH, "lstinfo-ok.lst")
with open(lstinfo, "w") as lst:
lst.write("GEN4.1111.00001 toto we don't use other fields\n")
lst.write("GENO.1216.00003\n")
quiet = False
cmd = "cmd"
outdir = os.path.join(GENEPATH, "outdir")
out_pers = os.path.join(
outdir, "PersGenome_pangenome.lst-lstinfo-ok.lst_F0.99-multi.lst")
assert corepers.main(cmd, UPAN, tol, multi, mixed, outdir, lstinfo, floor,
verbose, quiet) == out_pers
# Check creation of binary file for pangenome, and remove it
assert os.path.isfile(UPAN + ".bin")
# Check presence of persistent genome, and its content, and remove it
exp_pers = os.path.join(EXP_PATH, "exp_pers-floor-multi_subset.txt")
assert os.path.isfile(out_pers)
assert tutil.compare_order_content(out_pers, exp_pers)
# Check presence of log files and remove them
logfile = os.path.join(outdir, "PanACoTA-corepers.log")
assert os.path.isfile(logfile)
assert os.path.isfile(logfile + ".err")
# Check log messages
out, err = capsys.readouterr()
assert (
"Will generate a Persistent genome with member(s) in at least 99.0% "
"of all genomes in each family.") in out
assert (
"Multigenic families are allowed (several members in any genome of a family)."
) in out
assert "Saving all information to a binary file for later use" in out
assert "Generating Persistent genome of a dataset containing 2 genomes" in out
assert (
"The persistent genome contains 9 families with members present in "
"at least 1 different genomes (99.0% of the total number of genomes)."
) in out
def test_main_pers_floor_mixed_debug(capsys):
"""
Test that with default parameters, it creates the expected core genome.
"""
tol = 0.99
multi = False
mixed = True
floor = True
verbose = 15
quiet = False
lstinfo = ""
cmd = "cmd"
out_pers = os.path.join(GENEPATH,
"PersGenome_pangenome.lst-all_F0.99-mixed.lst")
assert corepers.main(cmd, UPAN, tol, multi, mixed, GENEPATH, lstinfo,
floor, verbose, quiet) == out_pers
# Check creation of binary file for pangenome, and remove it
assert os.path.isfile(UPAN + ".bin")
# Check presence of persistent genome, and its content, and remove it
exp_pers = os.path.join(EXP_PATH, "exp_pers-floor-mixed.txt")
assert os.path.isfile(out_pers)
assert tutil.compare_order_content(out_pers, exp_pers)
# Check presence of log files and remove them
logfile = os.path.join(GENEPATH, "PanACoTA-corepers.log")
assert os.path.isfile(logfile)
assert os.path.isfile(logfile + ".details")
assert os.path.isfile(logfile + ".debug")
assert os.path.isfile(logfile + ".err")
# Check log messages
out, err = capsys.readouterr()
assert (
"Will generate a Persistent genome with member(s) in at least 99.0% "
"of all genomes in each family.") in out
assert (
"Mixed families are allowed. To be considered as persistent, "
"a family must have exactly 1 member in 99.0% of the genomes, but in the "
"remaining 1.0% genomes, there can be 0, 1 or several members.") in out
assert "Saving all information to a binary file for later use" in out
assert "Generating Persistent genome of a dataset containing 4 genomes" in out
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 out
def test_main_pers(capsys):
"""
Test that with default parameters, it creates the expected core genome.
"""
tol = 0.99
multi = False
mixed = False
lstinfo = os.path.join(TEST_PATH, "test_lstinfo.txt")
floor = False
verbose = 0
quiet = False
cmd = "cmd"
out_pers = os.path.join(
GENEPATH, "PersGenome_pangenome.lst-test_lstinfo.txt_0.99.lst")
assert corepers.main(cmd, UPAN, tol, multi, mixed, GENEPATH, lstinfo,
floor, verbose, quiet) == out_pers
# Check creation of binary file for pangenome, and remove it
assert os.path.isfile(UPAN + ".bin")
# Check presence of persistent genome, and its content, and remove it
exp_pers = os.path.join(EXP_PATH, "exp_coregenome.txt")
assert os.path.isfile(out_pers)
assert tutil.compare_order_content(out_pers, exp_pers)
# Check presence of log files and remove them
logfile = os.path.join(GENEPATH, "PanACoTA-corepers.log")
assert os.path.isfile(logfile)
assert os.path.isfile(logfile + ".err")
# Check log messages
out, err = capsys.readouterr()
assert (
"Will generate a Persistent genome with member(s) in at least 99.0% "
"of all genomes in each family.") in out
assert ("To be considered as persistent, a family "
"must contain exactly 1 member in at least 99.0% of all genomes. "
"The other genomes are absent from the family.") in out
assert ("Getting subset of pangenome for genomes in "
"test/data/persgenome/test_files/test_lstinfo.txt") in out
assert "Saving all information to a binary file for later use" in out
assert "Generating Persistent genome of a dataset containing 4 genomes" in out
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 out
def test_main_core_subset(capsys):
"""
Test that with default parameters, it creates the expected core genome.
"""
tol = 1
multi = False
mixed = False
cmd = "cmd"
floor = False
verbose = 0
quiet = False
lstinfo = os.path.join(GENEPATH, "lstinfo-ok.lst")
with open(lstinfo, "w") as lst:
lst.write("GEN4.1111.00001 toto we don't use other fields\n")
lst.write("GENO.1216.00003\n")
out_pers = os.path.join(GENEPATH,
"PersGenome_pangenome.lst-lstinfo-ok.lst_1.lst")
assert corepers.main(cmd, UPAN, tol, multi, mixed, GENEPATH, lstinfo,
floor, verbose, quiet) == out_pers
# Check creation of binary file for pangenome
assert os.path.isfile(UPAN + ".bin")
# Check presence of persistent genome, and its content
exp_pers = os.path.join(EXP_PATH, "exp_coregenome_subset.txt")
assert os.path.isfile(out_pers)
assert tutil.compare_order_content(out_pers, exp_pers)
# Check presence of log files
logfile = os.path.join(GENEPATH, "PanACoTA-corepers.log")
assert os.path.isfile(logfile)
assert os.path.isfile(logfile + ".err")
# Check log messages
out, err = capsys.readouterr()
assert "Will generate a CoreGenome." in out
assert "Saving all information to a binary file for later use" in out
assert "Generating Persistent genome of a dataset containing 2 genomes" in out
assert ("The core genome contains 3 families, each one having exactly "
"2 members, from the 2 different genomes.") in out
def main(cmd, args_all, args_prepare, args_annot, args_pan, args_corepers,
args_align, args_tree):
"""
Call all modules, one by one, using output of one as input for the next one
Parameters
----------
cmd : str
command line used to launch the program
args_all : tuple
arguments common to all modules: output directory (str),
threads (int), verbose (int), quiet (bool)
args_prepare : tuple
arguments for prepare module (see subcommands.prepare.py): NCBI_species_taxid (int),
NCBI_species_name (str), NCBI_species_taxid (int), NCBI_taxid (int), NCBI_strains (str), levels (str), NCBI_section (str),
tmp_dir (str), norefseq (bool), db_dir (str),
only_mash (bool), info_file (str), l90 (int), nbcont (int), cutn (int),
min_dist (float), max_dist (float)
args_annot : tuple
arguments for annotate module (see subcommands/annotate.py): name (str), qc_only (bool),
date (str), prodigal_only (bool), small (bool)
args_pan : tuple
arguments for pangenome module (see subcommands/pangenome.py): min_id (float),
clust_mode (int), spe_dir (str), outfile (str)
args_corepers : tuple
arguments for corepers module (see subcommands.corepers.py): tol (float), mixed (bool),
multi (bool), floor (bool)
args_align : tuple
arguments for align module (see subcommands.align.py): prot_ali (bool)
args_tree : tuple
arguments for tree module (see subcommands.tree.py): soft (str), model (str), boot (bool),
write_boot (bool), memory (str), fast (bool)
"""
outdir, threads, verbose, quiet = args_all
os.makedirs(outdir, exist_ok=True)
# Initialize logger
import logging
# set level of logger: level is the minimum level that will be considered.
if verbose <= 1:
level = logging.INFO
# for verbose = 2, ignore only debug
if verbose >= 2 and verbose < 15:
level = utils.detail_lvl() # int corresponding to detail level
# for verbose >= 15, write everything
if verbose >= 15:
level = logging.DEBUG
logfile_base = os.path.join(outdir, "PanACoTA-all_modules")
logfile_base = utils.init_logger(logfile_base,
level,
name='all_modules',
verbose=verbose,
quiet=quiet)
logger = logging.getLogger('all_modules')
logger.info(f'PanACoTA version {version}')
logger.info("Command used\n \t > " + cmd)
# Run prepare module
outdir_prepare = os.path.join(outdir, "1-prepare_module")
(NCBI_species_name, NCBI_species_taxid, NCBI_taxid, NCBI_strains, levels,
NCBI_section, tmp_dir, norefseq, db_dir, only_mash, info_file, l90,
nbcont, cutn, min_dist, max_dist) = args_prepare
logger.info("prepare step")
info_file = prepare.main("PanACoTA prepare", NCBI_species_name,
NCBI_species_taxid, NCBI_taxid, NCBI_strains,
levels, NCBI_section, outdir_prepare, tmp_dir,
threads, norefseq, db_dir, only_mash, info_file,
l90, nbcont, cutn, min_dist, max_dist, verbose,
quiet)
# Run annotate module
list_file = ""
db_path = ""
tmp_dir = ""
force = False
outdir_annotate = os.path.join(outdir, "2-annotate_module")
(name, qc_only, date, prodigal_only, small) = args_annot
res_annot_dir = None
logger.info("annotate step")
lstinfo, nbgenomes = annotate.main("PanACoTA annotate",
list_file,
db_path,
outdir_annotate,
name,
date,
l90,
nbcont,
cutn,
threads,
force,
qc_only,
info_file,
tmp_dir,
res_annot_dir,
verbose,
quiet,
prodigal_only=prodigal_only,
small=small)
if qc_only:
return "QC_only done"
# Pangenome step
name_pan = f"{name}_{nbgenomes}"
outdir_pan = os.path.join(outdir, "3-pangenome_module")
dbpath = os.path.join(outdir_annotate, "Proteins")
(min_id, clust_mode, spe_dir, outfile) = args_pan
logger.info("pangenome step")
panfile = pangenome.main("PanACoTA pangenome",
lstinfo,
name_pan,
dbpath,
min_id,
outdir_pan,
clust_mode,
spe_dir,
threads,
outfile,
verbose=verbose,
quiet=quiet)
# Coregenome step
outdir_corpers = os.path.join(outdir, "4-corepers_module")
logger.info("corepers step")
(tol, mixed, multi, floor) = args_corepers
lstinfo_file = "" # include all genomes in core
corepers_file = corepers.main("PanACoTA corepers", panfile, tol, multi,
mixed, outdir_corpers, lstinfo_file, floor,
verbose, quiet)
# Align step
outdir_align = os.path.join(outdir, "5-align_module")
force = False
logger.info("align step")
(prot_ali) = args_align
align_file = align.main("PanACoTA align",
corepers_file,
lstinfo,
name_pan,
outdir_annotate,
outdir_align,
prot_ali,
threads,
force,
verbose=verbose,
quiet=quiet)
# Tree step
(soft, model, boot, write_boot, memory, fast) = args_tree
outdir_tree = os.path.join(outdir, "6-tree_module")
logger.info("tree step")
tree.main("PanACoTA tree",
align_file,
outdir_tree,
soft,
model,
threads,
boot,
write_boot,
memory,
fast,
verbose=verbose,
quiet=quiet)
logger.info("All modules of PanACOTA are finished.")
return 0