def test_main_norefseq_wrongdbpath(capsys):
"""
We run with option norefseq, but given db_dir does not exist.
-> error message
"""
NCBI_species_name = ""
NCBI_species_taxid = ""
NCBI_taxid = ""
NCBI_strains = ""
NCBI_section = "refseq"
levels = ""
outdir = GENEPATH
tmp_dir = os.path.join(outdir, "temporary_directory")
threads = 1
norefseq = True
db_dir = "dbdir"
only_mash = False
l90 = 100
nbcont = 999
cutn = 5
min_dist = 1e-4
max_dist = 0.06
verbose = 15
quiet = False
info_file = ""
with pytest.raises(SystemExit):
prepare.main("cmd", NCBI_species_name, NCBI_species_taxid, NCBI_taxid,
NCBI_strains, levels, NCBI_section, outdir, tmp_dir,
threads, norefseq, db_dir, only_mash, info_file, l90,
nbcont, cutn, min_dist, max_dist, verbose, quiet)
_, err = capsys.readouterr()
assert ("You asked to skip refseq downloads") in err
assert (
"Database folder dbdir supposed to contain fasta sequences does not exist. Please "
"give a valid folder, or leave the default directory (no '-d' option)"
) in err
# Check output files
summary = os.path.join(GENEPATH, "assembly_summary-123.txt")
assert not os.path.isfile(summary)
ngd_outdir = os.path.join(GENEPATH, "refseq", "bacteria")
assert not os.path.isdir(ngd_outdir)
# Check logfiles are here
log_files = glob.glob(os.path.join(GENEPATH, "*log*"))
assert len(log_files) == 4 #.log.debug as we put verbose = 15
# Check tmp files folder created, but empty asnothing is downloaded
assert len(os.listdir(tmp_dir)) == 0
# Check Database_init folder created, with at list 4 ".fna" genomes
assert not os.path.isdir(os.path.join(GENEPATH, "Database_init"))
def test_main_wrong_taxid(capsys):
"""
We run without option only_mash, but still provide a lstinfo file
-> will change its name to .back to save it when the new file will be created
"""
NCBI_species_name = ""
NCBI_taxid = "123"
NCBI_species_taxid = ""
NCBI_strains = ""
NCBI_section = "genbank"
levels = ""
outdir = GENEPATH
tmp_dir = os.path.join(GENEPATH, "123", "temporary_directory")
threads = 1
norefseq = False
info_file = ""
db_dir = ""
only_mash = False
l90 = 100
nbcont = 999
cutn = 5
min_dist = 1e-4
max_dist = 0.06
verbose = 2
quiet = False
with pytest.raises(SystemExit):
prepare.main("cmd", NCBI_species_name, NCBI_species_taxid, NCBI_taxid,
NCBI_strains, levels, NCBI_section, outdir, tmp_dir,
threads, norefseq, db_dir, only_mash, info_file, l90,
nbcont, cutn, min_dist, max_dist, verbose, quiet)
_, err = capsys.readouterr()
assert (
"No strain correspond to your request. If you are sure there should have "
"some, check that you gave valid NCBI taxid and/or "
"NCBI species name and/or NCBI strain name. If you gave several, check that "
"given taxIDs and names are compatible.") in err
# Check output files
summary = os.path.join(outdir, "assembly_summary-123.txt")
assert not os.path.isfile(summary)
ngd_outdir = os.path.join(outdir, "genbank", "bacteria")
assert not os.path.isdir(ngd_outdir)
# # Check logfiles are here
log_files = glob.glob(os.path.join(outdir, "*log*"))
assert len(log_files) == 3
# Check tmp files folder created, but empty asnothing is downloaded
assert len(os.listdir(tmp_dir)) == 0
# Check Database_init folder created, with at list 4 ".fna" genomes
assert not os.path.isdir(os.path.join(outdir, "Database_init"))
def test_only_mash_empty_lstinfo(capsys):
"""
Running only mash step giving an empty lstinfo file -> error, no genome found
"""
NCBI_species_name = ""
NCBI_species_taxid = ""
NCBI_taxid = ""
NCBI_strains = ""
NCBI_section = "refseq"
levels = ""
outdir = GENEPATH
tmp_dir = ""
threads = 1
norefseq = False
db_dir = ""
only_mash = True
# Create empty lstinfo file
info_file = os.path.join(GENEPATH, "LSTINFO-empty.lst")
open(info_file, "w").close()
l90 = 100
nbcont = 999
cutn = 5
min_dist = 1e-4
max_dist = 0.06
verbose = 1
quiet = False
with pytest.raises(SystemExit):
prepare.main("cmd", NCBI_species_name, NCBI_species_taxid, NCBI_taxid,
NCBI_strains, levels, NCBI_section, outdir, tmp_dir,
threads, norefseq, db_dir, only_mash, info_file, l90,
nbcont, cutn, min_dist, max_dist, verbose, quiet)
out, err = capsys.readouterr()
assert ("You asked to run only mash steps") in err
assert (
"You want to run only mash steps. Getting information from "
"test/data/prepare/generated_by_func-tests/LSTINFO-empty.lst") in out
assert (
"No genome listed in test/data/prepare/generated_by_func-tests/LSTINFO-empty.lst "
"was found.") in err
# Check output files
assert len(os.listdir(os.path.join(outdir, "tmp_files"))) == 0
# Check logfiles are here
log_files = glob.glob(os.path.join(outdir, "*log*"))
assert len(log_files) == 3
# Check lstinfo file is still here and still empty
assert os.stat(info_file).st_size == 0
def test_only_mash_no_lstinfo(capsys):
"""
Running only mash step giving an info file which does not exist -> error missing infofile
"""
NCBI_species_name = ""
NCBI_species_taxid = ""
NCBI_taxid = ""
NCBI_strains = ""
NCBI_section = "refseq"
levels = ""
outdir = GENEPATH
tmp_dir = ""
threads = 1
norefseq = False
db_dir = ""
only_mash = True
# Create empty lstinfo file
info_file = "info_file.lst"
l90 = 100
nbcont = 999
cutn = 5
min_dist = 1e-4
max_dist = 0.06
verbose = 1
quiet = False
with pytest.raises(SystemExit):
prepare.main("cmd", NCBI_species_name, NCBI_species_taxid, NCBI_taxid,
NCBI_strains, levels, NCBI_section, outdir, tmp_dir,
threads, norefseq, db_dir, only_mash, info_file, l90,
nbcont, cutn, min_dist, max_dist, verbose, quiet)
out, err = capsys.readouterr()
assert ("You asked to run only mash steps") in err
assert ("Your info file info_file.lst does not exist. Please provide the "
"right name/path, or remove the '--mash-only option to rerun "
"quality control.") in err
# Check output files
assert len(os.listdir(os.path.join(outdir, "tmp_files"))) == 0
# Check logfiles are here
log_files = glob.glob(os.path.join(outdir, "*log*"))
assert len(log_files) == 3
# Check that outdir contains only 4 elements: 3 logs + tmp_files repo
files = os.listdir(outdir)
files = [f for f in files if "fuse" not in f]
assert len(files) == 4
def test_main_not_only_mash_infoexists():
"""
We run without option only_mash, but still provide a lstinfo file
-> will change its name to .back to save it when the new file will be created
"""
NCBI_species_name = ""
NCBI_species_taxid = "104099"
NCBI_taxid = ""
NCBI_section = "refseq"
NCBI_strains = ""
levels = ""
outdir = GENEPATH
tmp_dir = os.path.join(outdir, "temporary_directory")
threads = 1
norefseq = False
db_dir = ""
only_mash = False
info_file = os.path.join(outdir, "LSTINFO-existing.lst")
open(info_file,
"w").close() #create empty info file, to check it is renamed
l90 = 100
nbcont = 999
cutn = 5
min_dist = 1e-4
max_dist = 0.06
verbose = 2
quiet = False
out_info_file = os.path.join(outdir,
"LSTINFO-104099-filtered-0.0001_0.06.txt")
assert prepare.main("cmd", NCBI_species_name, NCBI_species_taxid,
NCBI_taxid, NCBI_strains, levels, NCBI_section, outdir,
tmp_dir, threads, norefseq, db_dir, only_mash,
info_file, l90, nbcont, cutn, min_dist, max_dist,
verbose, quiet) == out_info_file
# Check output files
summary = os.path.join(GENEPATH, "assembly_summary-104099.txt")
assert os.path.isfile(summary)
# Check that the NCBI_genome_download output directory exists
ngd_outdir = os.path.join(GENEPATH, "refseq", "bacteria")
# And that it contains folders
assert os.path.isdir(ngd_outdir)
assert len(os.listdir(ngd_outdir)) >= 4
# Check logfiles are here
log_files = glob.glob(os.path.join(GENEPATH, "*log*"))
assert len(log_files) == 3
# Check tmp files folder created, but empty as we do not split
tmp_files = glob.glob(os.path.join(tmp_dir, "*.fna_prepare-split5N.fna"))
assert len(tmp_files) >= 4
# Check Database_init folder created, with at list 4 ".fna" genomes
fna_files = glob.glob(os.path.join(GENEPATH, "Database_init", "*.fna"))
assert len(fna_files) >= 4
# Check that LSTINFO file existing was renamed and still empty
# And new LSTINFO file created
assert os.path.isfile(info_file + ".back")
assert os.stat(info_file + ".back").st_size == 0
def test_main_norefseq_defaultdbdir(capsys):
"""
We run with option norefseq, but given db_dir does not exist.
-> error message
"""
NCBI_species_name = ""
NCBI_species_taxid = ""
NCBI_taxid = ""
NCBI_strains = ""
NCBI_section = "refseq"
levels = ""
# Copy refseq/bacteria and content into outdirectory
outdir = GENEPATH
tmp_dir = ""
threads = 1
norefseq = True
orig_dbdir = os.path.join(GEN_PATH, "genomes_comparison")
refseq_db_dir = os.path.join(GENEPATH, "Database_init")
shutil.copytree(orig_dbdir, refseq_db_dir)
db_dir = ""
only_mash = False
l90 = 100
nbcont = 999
cutn = 0
min_dist = 1e-4
max_dist = 0.06
verbose = 2
quiet = False
info_file = ""
out_info_file = os.path.join(outdir, "LSTINFO-NA-filtered-0.0001_0.06.txt")
assert prepare.main("cmd", NCBI_species_name, NCBI_species_taxid,
NCBI_taxid, NCBI_strains, levels, NCBI_section, outdir,
tmp_dir, threads, norefseq, db_dir, only_mash,
info_file, l90, nbcont, cutn, min_dist, max_dist,
verbose, quiet) == out_info_file
out, err = capsys.readouterr()
assert ("You asked to skip refseq downloads") in err
assert ("Total number of genomes for NA: 5") in out
assert ("Computing pairwise distances between all genomes") in out
assert ("Final number of genomes in dataset: 1") in out
# Check output files
# Check that the NCBI_genome_download output directory exists
ngd_outdir = os.path.join(GENEPATH, "refseq", "bacteria")
assert not os.path.isdir(ngd_outdir)
# Check logfiles are here
log_files = glob.glob(os.path.join(GENEPATH, "*log*"))
assert len(log_files) == 3
# Check tmp files folder created, but empty as we do not split
tmp_folder = os.listdir(os.path.join(GENEPATH, "tmp_files"))
assert len(tmp_folder) == 0
# Check Database_init folder created, with the 3 ".fna" genomes
fna_files = glob.glob(os.path.join(GENEPATH, "Database_init", "*.fna"))
assert len(fna_files) == 5
def test_main_only_strainname():
"""
Only give strain names (no spe taxid etc). Chack that they are downloaded,
and that the summary file has the expected name.
"""
NCBI_species_name = ""
NCBI_species_taxid = ""
NCBI_taxid = ""
NCBI_section = "refseq"
NCBI_strains = "AS001254,KPPR1,LMG 1583"
levels = ""
outdir = GENEPATH
tmp_dir = os.path.join(outdir, 'tmp')
threads = 1
norefseq = False
db_dir = ""
only_mash = False
info_file = ""
l90 = 100
nbcont = 999
cutn = 5
min_dist = 1e-4
max_dist = 0.06
verbose = 2
quiet = False
out_info_file = os.path.join(
outdir,
"LSTINFO-AS001254_and_KPPR1_and_LMG_1583-filtered-0.0001_0.06.txt")
assert prepare.main("cmd", NCBI_species_name, NCBI_species_taxid,
NCBI_taxid, NCBI_strains, levels, NCBI_section, outdir,
tmp_dir, threads, norefseq, db_dir, only_mash,
info_file, l90, nbcont, cutn, min_dist, max_dist,
verbose, quiet) == out_info_file
# Check output files
summary = os.path.join(
GENEPATH, "assembly_summary-AS001254_and_KPPR1_and_LMG_1583.txt")
assert os.path.isfile(summary)
# Check that the NCBI_genome_download output directory exists
ngd_outdir = os.path.join(GENEPATH, "refseq", "bacteria")
# And that it contains folders
assert os.path.isdir(ngd_outdir)
assert len(os.listdir(ngd_outdir)) == 3
# Check logfiles are here
log_files = glob.glob(os.path.join(GENEPATH, "*log*"))
assert len(log_files) == 3
# Check tmp files folder created, with the 3 strain files
tmp_files = glob.glob(os.path.join(tmp_dir, "*.fna_prepare-split5N.fna"))
assert len(tmp_files) == 3
# Check Database_init folder created, with all 3 ".fna" genomes
fna_files = glob.glob(os.path.join(GENEPATH, "Database_init", "*.fna"))
assert len(fna_files) == 3
def test_only_mash(capsys):
"""
Running only mash step (giving genomes and corresponding LSTINFO file)
"""
NCBI_species_name = ""
NCBI_species_taxid = ""
NCBI_taxid = ""
NCBI_strains = ""
NCBI_section = "refseq"
levels = ""
outdir = GENEPATH
tmp_dir = ""
threads = 1
norefseq = False
db_dir = ""
only_mash = True
info_file = os.path.join(TEST_DIR, "test_lstinfo_onlymash.lst")
l90 = 100
nbcont = 999
cutn = 5
min_dist = 1e-4
max_dist = 0.06
verbose = 1
quiet = False
out_info_file = os.path.join(outdir, "LSTINFO-NA-filtered-0.0001_0.06.txt")
assert prepare.main("cmd", NCBI_species_name, NCBI_species_taxid,
NCBI_taxid, NCBI_strains, levels, NCBI_section, outdir,
tmp_dir, threads, norefseq, db_dir, only_mash,
info_file, l90, nbcont, cutn, min_dist, max_dist,
verbose, quiet) == out_info_file
out, err = capsys.readouterr()
assert ("You asked to run only mash steps") in err
assert ("You want to run only mash steps. Getting information from "
"test/data/prepare/test_files/test_lstinfo_onlymash.lst") in out
assert ("Found 5 genomes in total") in out
assert ("Computing pairwise distances between all genomes") in out
assert ("Sorting all 5 genomes by quality") in out
assert ("Final number of genomes in dataset: 1") in out
# Check output files
assert len(os.listdir(os.path.join(outdir, "tmp_files"))) == 0
# Check logfiles are here
log_files = glob.glob(os.path.join(outdir, "*log*"))
assert len(log_files) == 3
# Check content of output lstinfo file
out_lst = os.path.join(outdir, "LSTINFO-NA-filtered-0.0001_0.06.txt")
exp_lst = os.path.join(DBDIR, "exp_files", "exp_lstinfo_run_only-mash.lst")
assert tutil.compare_order_content(out_lst, exp_lst)
def test_main_norefseq_nodefault_dbdir_but_refseq(capsys):
"""
We run with option norefseq, but given db_dir does not exist.
-> error message
"""
NCBI_species_name = ""
NCBI_species_taxid = "123"
NCBI_taxid = ""
NCBI_strains = ""
NCBI_section = "genbank"
levels = ""
# Copy refseq/bacteria and content into outdirectory
outdir = GENEPATH
tmp_dir = ""
threads = 1
norefseq = True
orig_dbdir = os.path.join(GEN_PATH, "refseq")
refseq_db_dir = os.path.join(GENEPATH, "genbank")
shutil.copytree(orig_dbdir, refseq_db_dir)
db_dir = ""
only_mash = False
l90 = 100
nbcont = 999
cutn = 0
min_dist = 1e-4
max_dist = 0.06
verbose = 2
quiet = False
info_file = ""
out_info_file = os.path.join(outdir,
f"LSTINFO-123-filtered-0.0001_0.06.txt")
assert prepare.main("cmd", NCBI_species_name, NCBI_species_taxid,
NCBI_taxid, NCBI_strains, levels, NCBI_section, outdir,
tmp_dir, threads, norefseq, db_dir, only_mash,
info_file, l90, nbcont, cutn, min_dist, max_dist,
verbose, quiet) == out_info_file
out, err = capsys.readouterr()
assert ("You asked to skip genbank downloads") in err
assert (
"Database folder test/data/prepare/generated_by_func-tests/"
"Database_init supposed "
"to contain fasta sequences does not exist. We will check if the download folder "
"(with compressed sequences) exists.") in err
assert ("Uncompressing genome files") in out
assert ("Total number of genomes for 123: 3") in out
assert ("Computing pairwise distances between all genomes") in out
assert ("Final number of genomes in dataset: 1") in out
# Check output files
# Check that the NCBI_genome_download output directory exists
ngd_outdir = os.path.join(GENEPATH, "genbank", "bacteria")
# And that it contains folders
assert os.path.isdir(ngd_outdir)
assert len(os.listdir(ngd_outdir)) == 3
# Check logfiles are here
log_files = glob.glob(os.path.join(GENEPATH, "*log*"))
assert len(log_files) == 3
# Check tmp files folder created, but empty as we do not split
tmp_folder = os.listdir(os.path.join(GENEPATH, "tmp_files"))
assert len(tmp_folder) == 0
# Check Database_init folder created, with the 3 ".fna" genomes
fna_files = glob.glob(os.path.join(GENEPATH, "Database_init", "*.fna"))
assert len(fna_files) == 3
def test_main_norefseq_nodefault_dbdir_nor_refseq(capsys):
"""
We run with option norefseq, but given db_dir does not exist.
-> error message
"""
NCBI_species_name = ""
NCBI_species_taxid = ""
NCBI_taxid = ""
NCBI_strains = ""
NCBI_section = "genbank"
levels = ""
outdir = GENEPATH
tmp_dir = ""
threads = 1
norefseq = True
db_dir = ""
only_mash = False
l90 = 100
nbcont = 999
cutn = 5
min_dist = 1e-4
max_dist = 0.06
verbose = 2
quiet = False
info_file = ""
with pytest.raises(SystemExit):
prepare.main("cmd", NCBI_species_name, NCBI_species_taxid, NCBI_taxid,
NCBI_strains, levels, NCBI_section, outdir, tmp_dir,
threads, norefseq, db_dir, only_mash, info_file, l90,
nbcont, cutn, min_dist, max_dist, verbose, quiet)
_, err = capsys.readouterr()
assert ("You asked to skip genbank downloads") in err
assert (
"Database folder test/data/prepare/generated_by_func-tests/Database_init supposed "
"to contain fasta sequences does not exist. We will check if the download folder "
"(with compressed sequences) exists.") in err
assert (
"Folder test/data/prepare/generated_by_func-tests/genbank/bacteria "
"does not exist. You do not have any genome to analyse. Possible reasons:\n"
) in err
assert ("- if you want to rerun analysis in the same folder as "
"sequences were downloaded (my_outdir/Database_init or "
"my_outdir/genbank), make sure you have '-o my_outdir' option\n"
) in err
assert (
"- if you want to rerun analysis and save them in a new "
"output folder called 'new_outdir', make sure you have '-o new_outdir' option, "
"and you specified where the uncompressed sequences to use are "
"('-d sequence_database_path'") in err
# # Check output files
summary = os.path.join(GENEPATH, "assembly_summary-123.txt")
assert not os.path.isfile(summary)
ngd_outdir = os.path.join(GENEPATH, "genbank", "bacteria")
assert not os.path.isdir(ngd_outdir)
# Check logfiles are here
log_files = glob.glob(os.path.join(GENEPATH, "*log*"))
assert len(log_files) == 3
# Check tmp files folder created, but empty asnothing is downloaded
assert len(os.listdir(os.path.join(GENEPATH, "tmp_files"))) == 0
# Check Database_init folder created, with at list 4 ".fna" genomes
assert not os.path.isdir(os.path.join(GENEPATH, "Database_init"))
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