diff --git a/MANIFEST.in b/MANIFEST.in
index 8c86eba637cb4ccb534a6f0f93c4e6717b1e6726..ab6b4aab9bc4cbeafde31abff774589cec1e6666 100755
--- a/MANIFEST.in
+++ b/MANIFEST.in
@@ -1 +1 @@
-include genomeAPCAT/align_module/prt2codon.awk
\ No newline at end of file
+include PanACoTA/align_module/prt2codon.awk
\ No newline at end of file
diff --git a/genomeAPCAT/__init__.py b/PanACoTA/__init__.py
similarity index 100%
rename from genomeAPCAT/__init__.py
rename to PanACoTA/__init__.py
diff --git a/genomeAPCAT/align_module/__init__.py b/PanACoTA/align_module/__init__.py
similarity index 100%
rename from genomeAPCAT/align_module/__init__.py
rename to PanACoTA/align_module/__init__.py
diff --git a/genomeAPCAT/align_module/alignment.py b/PanACoTA/align_module/alignment.py
similarity index 100%
rename from genomeAPCAT/align_module/alignment.py
rename to PanACoTA/align_module/alignment.py
diff --git a/genomeAPCAT/align_module/get_seqs.py b/PanACoTA/align_module/get_seqs.py
similarity index 100%
rename from genomeAPCAT/align_module/get_seqs.py
rename to PanACoTA/align_module/get_seqs.py
diff --git a/genomeAPCAT/align_module/pan_to_pergenome.py b/PanACoTA/align_module/pan_to_pergenome.py
similarity index 100%
rename from genomeAPCAT/align_module/pan_to_pergenome.py
rename to PanACoTA/align_module/pan_to_pergenome.py
diff --git a/genomeAPCAT/align_module/post_align.py b/PanACoTA/align_module/post_align.py
similarity index 100%
rename from genomeAPCAT/align_module/post_align.py
rename to PanACoTA/align_module/post_align.py
diff --git a/genomeAPCAT/align_module/prt2codon.awk b/PanACoTA/align_module/prt2codon.awk
similarity index 100%
rename from genomeAPCAT/align_module/prt2codon.awk
rename to PanACoTA/align_module/prt2codon.awk
diff --git a/genomeAPCAT/annote_module/__init__.py b/PanACoTA/annote_module/__init__.py
similarity index 100%
rename from genomeAPCAT/annote_module/__init__.py
rename to PanACoTA/annote_module/__init__.py
diff --git a/genomeAPCAT/annote_module/format_functions.py b/PanACoTA/annote_module/format_functions.py
similarity index 100%
rename from genomeAPCAT/annote_module/format_functions.py
rename to PanACoTA/annote_module/format_functions.py
diff --git a/genomeAPCAT/annote_module/genome_seq_functions.py b/PanACoTA/annote_module/genome_seq_functions.py
similarity index 100%
rename from genomeAPCAT/annote_module/genome_seq_functions.py
rename to PanACoTA/annote_module/genome_seq_functions.py
diff --git a/genomeAPCAT/annote_module/prokka_functions.py b/PanACoTA/annote_module/prokka_functions.py
similarity index 100%
rename from genomeAPCAT/annote_module/prokka_functions.py
rename to PanACoTA/annote_module/prokka_functions.py
diff --git a/genomeAPCAT/corepers_module/__init__.py b/PanACoTA/corepers_module/__init__.py
similarity index 100%
rename from genomeAPCAT/corepers_module/__init__.py
rename to PanACoTA/corepers_module/__init__.py
diff --git a/genomeAPCAT/corepers_module/persistent_functions.py b/PanACoTA/corepers_module/persistent_functions.py
similarity index 100%
rename from genomeAPCAT/corepers_module/persistent_functions.py
rename to PanACoTA/corepers_module/persistent_functions.py
diff --git a/genomeAPCAT/pangenome_module/__init__.py b/PanACoTA/pangenome_module/__init__.py
similarity index 100%
rename from genomeAPCAT/pangenome_module/__init__.py
rename to PanACoTA/pangenome_module/__init__.py
diff --git a/genomeAPCAT/pangenome_module/mmseqs_functions.py b/PanACoTA/pangenome_module/mmseqs_functions.py
similarity index 97%
rename from genomeAPCAT/pangenome_module/mmseqs_functions.py
rename to PanACoTA/pangenome_module/mmseqs_functions.py
index 3d3a98b4dbf2cbd05797f75e9dbd801f4c3ddd99..d8822f37100ba5d2be99e9ab250b4df101b335c9 100755
--- a/genomeAPCAT/pangenome_module/mmseqs_functions.py
+++ b/PanACoTA/pangenome_module/mmseqs_functions.py
@@ -162,6 +162,7 @@ def do_pangenome(outdir, prt_bank, mmseqdb, min_id, clust_mode, threads, start,
tmpdir = os.path.join(outdir, "tmp_" + prt_bank + "_" + infoname)
os.makedirs(tmpdir, exist_ok=True)
bar = None
+ logger.debug(mmseqclust)
if os.path.isfile(mmseqclust):
logger.warning(("mmseqs clustering {} already exists. The program will now convert "
"it to a pangenome file.").format(mmseqclust))
@@ -183,8 +184,9 @@ def do_pangenome(outdir, prt_bank, mmseqdb, min_id, clust_mode, threads, start,
bar.finish()
pool.join()
# Convert output to tsv file (one line per comparison done)
- families, outfile = mmseqs_to_pangenome(mmseqdb, mmseqclust, logmmseq, start, panfile)
- return families, outfile
+ # # Convert output to tsv file (one line per comparison done)
+ # -> returns (families, outfile)
+ return mmseqs_to_pangenome(mmseqdb, mmseqclust, logmmseq, start, panfile)
def run_mmseqs_clust(args):
@@ -200,15 +202,15 @@ def run_mmseqs_clust(args):
* mmseqclust: path to base filename for output of mmseq clustering
* tmpdir : path to folder which will contain mmseq temporary files
* logmmseq : path to file where logs must be written
- * min_id : min percentage of identity to be considered in the same family\
- (between 0 and 1)
+ * min_id : min percentage of identity to be considered in the same family
+ * (between 0 and 1)
* threads : max number of threads to use
* clust_mode : [0, 1, 2], 0 for 'set cover', 1 for 'single-linkage', 2 for 'CD-Hit'
"""
mmseqdb, mmseqclust, tmpdir, logmmseq, min_id, threads, clust_mode = args
cmd = ("mmseqs cluster {} {} {} --min-seq-id {} --threads {} --cluster-mode "
- "{} --kmer-per-seq 80 --max-seqs 300").format(mmseqdb, mmseqclust, tmpdir, min_id, threads, clust_mode)
+ "{}").format(mmseqdb, mmseqclust, tmpdir, min_id, threads, clust_mode)
msg = "Problem while clustering proteins with mmseqs. See log in {}".format(logmmseq)
with open(logmmseq, "a") as logm:
utils.run_cmd(cmd, msg, eof=False, stdout=logm, stderr=logm)
diff --git a/genomeAPCAT/pangenome_module/post_treatment.py b/PanACoTA/pangenome_module/post_treatment.py
similarity index 100%
rename from genomeAPCAT/pangenome_module/post_treatment.py
rename to PanACoTA/pangenome_module/post_treatment.py
diff --git a/genomeAPCAT/pangenome_module/protein_seq_functions.py b/PanACoTA/pangenome_module/protein_seq_functions.py
similarity index 100%
rename from genomeAPCAT/pangenome_module/protein_seq_functions.py
rename to PanACoTA/pangenome_module/protein_seq_functions.py
diff --git a/genomeAPCAT/subcommands/__init__.py b/PanACoTA/subcommands/__init__.py
similarity index 100%
rename from genomeAPCAT/subcommands/__init__.py
rename to PanACoTA/subcommands/__init__.py
diff --git a/genomeAPCAT/subcommands/align.py b/PanACoTA/subcommands/align.py
similarity index 100%
rename from genomeAPCAT/subcommands/align.py
rename to PanACoTA/subcommands/align.py
diff --git a/genomeAPCAT/subcommands/annote.py b/PanACoTA/subcommands/annote.py
similarity index 100%
rename from genomeAPCAT/subcommands/annote.py
rename to PanACoTA/subcommands/annote.py
diff --git a/genomeAPCAT/subcommands/corepers.py b/PanACoTA/subcommands/corepers.py
similarity index 100%
rename from genomeAPCAT/subcommands/corepers.py
rename to PanACoTA/subcommands/corepers.py
diff --git a/genomeAPCAT/subcommands/pangenome.py b/PanACoTA/subcommands/pangenome.py
similarity index 100%
rename from genomeAPCAT/subcommands/pangenome.py
rename to PanACoTA/subcommands/pangenome.py
diff --git a/genomeAPCAT/subcommands/tree.py b/PanACoTA/subcommands/tree.py
similarity index 100%
rename from genomeAPCAT/subcommands/tree.py
rename to PanACoTA/subcommands/tree.py
diff --git a/genomeAPCAT/tree_module/__init__.py b/PanACoTA/tree_module/__init__.py
similarity index 100%
rename from genomeAPCAT/tree_module/__init__.py
rename to PanACoTA/tree_module/__init__.py
diff --git a/genomeAPCAT/tree_module/fastme_func.py b/PanACoTA/tree_module/fastme_func.py
similarity index 100%
rename from genomeAPCAT/tree_module/fastme_func.py
rename to PanACoTA/tree_module/fastme_func.py
diff --git a/genomeAPCAT/tree_module/fasttree_func.py b/PanACoTA/tree_module/fasttree_func.py
similarity index 100%
rename from genomeAPCAT/tree_module/fasttree_func.py
rename to PanACoTA/tree_module/fasttree_func.py
diff --git a/genomeAPCAT/tree_module/quicktree_func.py b/PanACoTA/tree_module/quicktree_func.py
similarity index 100%
rename from genomeAPCAT/tree_module/quicktree_func.py
rename to PanACoTA/tree_module/quicktree_func.py
diff --git a/genomeAPCAT/utils.py b/PanACoTA/utils.py
similarity index 100%
rename from genomeAPCAT/utils.py
rename to PanACoTA/utils.py
diff --git a/genomeAPCAT/utils_pangenome.py b/PanACoTA/utils_pangenome.py
similarity index 100%
rename from genomeAPCAT/utils_pangenome.py
rename to PanACoTA/utils_pangenome.py
diff --git a/bin/genomeAPCAT b/bin/genomeAPCAT
deleted file mode 100755
index 3bf2de3f8ce2b99ee9fbff27af0f04e0d38f4e66..0000000000000000000000000000000000000000
--- a/bin/genomeAPCAT
+++ /dev/null
@@ -1,118 +0,0 @@
-#!/usr/bin/env python3
-# coding: utf-8
-
-import sys
-from textwrap import dedent
-
-from genomeAPCAT import __version__ as version
-
-from genomeAPCAT.subcommands import annote
-from genomeAPCAT.subcommands import pangenome
-from genomeAPCAT.subcommands import corepers
-from genomeAPCAT.subcommands import align
-from genomeAPCAT.subcommands import tree
-
-
-def main():
- """
- Start program according to arguments given by user.
- """
- action, args = parse_arguments(sys.argv[1:])
- action(args)
-
-
-def parse_arguments(argv):
- """
- Extract command-line arguments for different actions.
- """
- import argparse
-
- # Create main parser
-
- parser = argparse.ArgumentParser(
- epilog="For more details, visit the MacSyFinder website and see "
- "the MacSyFinder documentation.",
- formatter_class=argparse.RawDescriptionHelpFormatter,
- description=dedent('''
-
-
-
- ___ _____ ___ _____ _____
-( _`\ ( _ )( _`\ (_ _)( _ )
-| |_) ) _ _ ___ | (_) || ( (_) _ | | | (_) |
-| ,__/'/'_` )/' _ `\| _ || | _ /'_`\ | | | _ |
-| | ( (_| || ( ) || | | || (_( )( (_) )| | | | | |
-(_) `\__,_)(_) (_)(_) (_)(____/'`\___/'(_) (_) (_)
-
-
- Large scale comparative genomics tools
-
- -------------------------------------------
- ''') )
-
-
- parser.add_argument('-V', '--version', action='version',
- version='genomeAPCAT - v. ' + str(version),
- help="Print the version number and exit")
-
- # Create subparsers, for all submodules
- subparsers = parser.add_subparsers(dest='subparser_called')
- # dest: to be able to get the subparser called with args.subparser_called
- actions = {} # to add the action to do according to the subparser called
- checks = {} # to add the function to call to check the subparser arguments
-
- # QC and annotation part
- parser_annote = subparsers.add_parser('annotate',
- help="Quality control and annotation of genomes",
- add_help=False)
- annote.build_parser(parser_annote)
- actions["annotate"] = annote.main_from_parse
- checks["annotate"] = annote.check_args
-
- # Pan genome part
- parser_pan = subparsers.add_parser('pangenome', help="Generate a pan-genome of your dataset",
- add_help=False)
- pangenome.build_parser(parser_pan)
- actions["pangenome"] = pangenome.main_from_parse
-
- # Persistent genome part
- parser_corepers = subparsers.add_parser('corepers',
- help="Compute a Core or Persistent genome of your "
- "dataset",
- add_help=False)
- corepers.build_parser(parser_corepers)
- actions["corepers"] = corepers.main_from_parse
- checks["corepers"] = corepers.check_args
-
- # Alignment part
- parser_align = subparsers.add_parser('align',
- help="Align Core/Persistent familiest",
- add_help=False)
- align.build_parser(parser_align)
- actions["align"] = align.main_from_parse
-
- # tree part
- parser_tree = subparsers.add_parser('tree',
- help=("Infer phylogenetic tree based on "
- "core/persistent genome"),
- add_help=False)
- tree.build_parser(parser_tree)
- actions["tree"] = tree.main_from_parse
- checks["tree"] = tree.check_args
-
- # Parse arguments and execute corresponding action
- arguments = parser.parse_args(argv)
- arguments.argv = argv
- action_called = arguments.subparser_called
- # If checks are needed, do it (if some arguments are not compatible etc.)
- if action_called in checks:
- checks[action_called](parser, arguments)
-
- # If subparser called does not exist, error
- if action_called not in actions:
- parser.error("too few arguments. Use '-h' to get help.")
- return actions[action_called], arguments
-
-
-if __name__ == '__main__':
- main()
diff --git a/make b/make
index c257ae17d4105e3ff0d5a7baab7d550248ee0e11..f9bd8fd40452bbc9c57ebb73bc85fdc9eb1341df 100755
--- a/make
+++ b/make
@@ -46,11 +46,11 @@ def uninstall():
Uninstall PanACoTA python package
"""
logger.info("Uninstalling PanACoTA...")
- cmd = "pip3 uninstall -y genomeAPCAT"
+ cmd = "pip3 uninstall -y PanACoTA"
error = ("A problem occurred while trying to uninstall PanACoTA. If you have "
"permission errors, try to add 'sudo' before your command line.")
run_cmd(cmd, error)
- link_dest = os.path.join(os.sep + "usr", "local", "bin", "genomeAPCAT")
+ link_dest = os.path.join(os.sep + "usr", "local", "bin", "PanACoTA")
if os.path.exists(link_dest):
os.remove(link_dest)
@@ -99,7 +99,7 @@ def install_all(install_dir, target, dev=False, user=False):
"you do not have root access, install with the '--user' option")
run_cmd(cmd, error, eof=True)
if user:
- gapcat_bin = os.path.join(os.getcwd(), "bin", "genomeAPCAT")
+ gapcat_bin = os.path.join(os.getcwd(), "bin", "PanACoTA")
os.symlink(gapcat_bin, os.path.join(install_dir, os.path.basename(gapcat_bin)))
if to_install_user:
msg = ("Some dependencies needed for some subcommands of PanACoTA are not installed. "
diff --git a/setup.py b/setup.py
index 7e6dedde6b4c5dc82027331485eb33465c2c822c..b71649549536c85b0939f0ce32917b559e04254c 100755
--- a/setup.py
+++ b/setup.py
@@ -5,7 +5,7 @@
Setup script
"""
-import genomeAPCAT
+import PanACoTA
try:
from setuptools import setup
from setuptools.command.test import test as TestCommand
@@ -38,16 +38,16 @@ def parse_requirements(requirements):
and not l.startswith('#')]
-packages = ['genomeAPCAT', 'genomeAPCAT.annote_module',
- 'genomeAPCAT.pangenome_module', 'genomeAPCAT.corepers_module',
- 'genomeAPCAT.align_module', 'genomeAPCAT.tree_module', 'genomeAPCAT.subcommands']
+packages = ['PanACoTA', 'PanACoTA.annote_module',
+ 'PanACoTA.pangenome_module', 'PanACoTA.corepers_module',
+ 'PanACoTA.align_module', 'PanACoTA.tree_module', 'PanACoTA.subcommands']
requires = parse_requirements("requirements.txt")
-scripts = ['bin/genomeAPCAT']
+scripts = ['bin/PanACoTA']
classifiers = [
"Environment :: Console",
"Intended Audience :: Science/Research",
- "License :: ???",
+ "License :: AGPL v3",
"Programming Language :: Python :: 3",
"Operating System :: OS Independent",
"Topic :: Scientific/Engineering :: Bio-Informatics",
@@ -57,9 +57,9 @@ with open('README.md') as f:
long_description = f.read()
setup(
- name='genomeAPCAT',
+ name='PanACoTA',
packages=packages,
- version=genomeAPCAT.__version__,
+ version=PanACoTA.__version__,
description="Large scale comparative genomics tools: annotate genomes, do pangenome, "
"core/persistent genome, align core/persistent families, infer phylogenetic tree.",
long_description=long_description,
diff --git a/test/test_unit/test_pangenome/test_mmseq_func.py b/test/test_unit/test_pangenome/test_mmseq_func.py
index 5bca1d950be4b9b1dad0a59ebae3cf237c363278..56fe9a7403cb46a569148ba9d0a3680edb3b5775 100755
--- a/test/test_unit/test_pangenome/test_mmseq_func.py
+++ b/test/test_unit/test_pangenome/test_mmseq_func.py
@@ -98,7 +98,7 @@ FAMILIES4G = [["GEN2.1017.00001.i0002_00004", "GEN4.1111.00001.i0001_00002",
def test_create_mmseqdb(caplog):
"""
Test that mmseq DB is created. We do not check its content as it could change
- according to mmseq versions, and we are here testing genomeAPCAT, not mmseqs
+ according to mmseq versions, and we are here testing PanACoTA, not mmseqs
"""
caplog.set_level(logging.DEBUG)
filename = "test_create_mmseqsdb.msdb"
@@ -285,317 +285,331 @@ def test_tsv2pangenome_default():
os.remove(logmmseq)
-# def test_mmseq2pan_givenout():
-# """
-# From mmseq clust output, convert to pangenome (with steps inside, already tested by the other
-# functions called).+ write pangenome to ouput file
-# """
-# outfile1 = "test_mmseq2pan.lst"
-# mmseqclust = os.path.join(PATH_TEST_FILES, "mmseq_clust-out")
-# mmseqdb = os.path.join(PATH_TEST_FILES, "mmseq_db")
-# start = time.strftime('%Y-%m-%d_%H-%M-%S')
-# logmmseq = "test_mmseq2pan-out.log"
-# fams, outf = mmseqs.mmseqs_to_pangenome(mmseqdb, mmseqclust, logmmseq, start, outfile1)
-# assert outfile1 == outf
-# for num, fam in fams.items():
-# assert num in list(range(1, 17))
-# found = False
-# for expfam in list(EXP_CLUSTERS.values()):
-# if fam == expfam:
-# found = True
-# break
-# assert found
-# exp_pan = os.path.join(PATH_EXP_FILES, "exp_pangenome-4genomes.lst")
-# with open(exp_pan, "r") as ep, open(outf, "r") as pan:
-# lines_exp = []
-# lines_out = []
-# for line_exp, line in zip(ep, pan):
-# lines_exp.append(tuple(line_exp.split()[1:]))
-# lines_out.append(tuple(line.split()[1:]))
-# assert set(lines_exp) == set(lines_out)
-# os.remove(outf)
-# os.remove(logmmseq)
+def test_mmseq2pan_givenout():
+ """
+ From mmseq clust output, convert to pangenome (with steps inside, already tested by the other
+ functions called).+ write pangenome to ouput file
+ """
+ outfile1 = "test_mmseq2pan.lst"
+ mmseqclust = os.path.join(PATH_TEST_FILES, "mmseq_clust-out")
+ mmseqdb = os.path.join(PATH_TEST_FILES, "mmseq_db")
+ start = time.strftime('%Y-%m-%d_%H-%M-%S')
+ logmmseq = "test_mmseq2pan-out.log"
+ fams, outf = mmseqs.mmseqs_to_pangenome(mmseqdb, mmseqclust, logmmseq, start, outfile1)
+ # assert output filename was not changed
+ assert outfile1 == outf
+ for num, fam in fams.items():
+ # Check that the number of families return by the function is as expected
+ assert num in list(range(1, 17))
+ found = False
+ # Check that all expected families are found in fams
+ for expfam in list(EXP_CLUSTERS.values()):
+ if fam == expfam:
+ found = True
+ break
+ assert found
+ exp_pan = os.path.join(PATH_EXP_FILES, "exp_pangenome-4genomes.lst")
+ #Check that families written in output file are as expected
+ with open(exp_pan, "r") as ep, open(outf, "r") as pan:
+ lines_exp = []
+ lines_out = []
+ for line_exp, line in zip(ep, pan):
+ lines_exp.append(tuple(line_exp.split()[1:]))
+ lines_out.append(tuple(line.split()[1:]))
+ assert set(lines_exp) == set(lines_out)
+ os.remove(outf)
+ os.remove(logmmseq)
-# def test_run_clust():
-# """
-# Checks that, when we run mmseq clust, it creates all files needed for after to do
-# the pangenome. We do not check the content of the mmseq output files, as it could
-# depend on its version, and we are here testing genomeAPCAT.
-# """
-# mmseqdb = os.path.join(PATH_TEST_FILES, "mmseq_db")
-# mmseqclust = "test_mmseq_cluster-out"
-# tmpdir = "test_mmseq_tmp"
-# os.makedirs(tmpdir)
-# logmmseq = "test_mmseq_cluster.log"
-# min_id = 0.8
-# threads = 1
-# clust_mode = 1
-# args = (mmseqdb, mmseqclust, tmpdir, logmmseq, min_id, threads, clust_mode)
-# assert not os.path.isfile(mmseqclust)
-# mmseqs.run_mmseqs_clust(args)
-# assert os.path.isfile(mmseqclust)
-# assert os.path.isfile(mmseqclust + ".index")
-# assert os.path.isfile(logmmseq)
-# assert os.path.isdir(tmpdir)
-# shutil.rmtree(tmpdir)
-# os.remove(mmseqclust)
-# os.remove(mmseqclust + ".index")
-# os.remove(logmmseq)
-
-
-# def test_get_logmmseq():
-# """
-# Check that the given log filename is as expected according to given information
-# """
-# outdir = "toto"
-# prt_bank = "bank_prt"
-# infoname = "GENO115"
-# log = mmseqs.get_logmmseq(outdir, prt_bank, infoname)
-# assert log == "toto/mmseq_bank_prt_GENO115.log"
+def test_run_clust():
+ """
+ Checks that, when we run mmseq clust, it creates all files needed for after to do
+ the pangenome. We do not check the content of the mmseq output files, as it could
+ depend on its version, and we are here testing PanACoTA.
+ """
+ mmseqdb = os.path.join(PATH_TEST_FILES, "mmseq_db")
+ mmseqclust = "test_mmseq_cluster-out"
+ tmpdir = "test_mmseq_tmp"
+ os.makedirs(tmpdir)
+ logmmseq = "test_mmseq_cluster.log"
+ min_id = 0.8
+ threads = 1
+ clust_mode = 1
+ args = (mmseqdb, mmseqclust, tmpdir, logmmseq, min_id, threads, clust_mode)
+ # Check that output of mmseq does not already exist
+ assert not os.path.isfile(mmseqclust)
+ # Run run_mmseqs_clust on previous arguments
+ mmseqs.run_mmseqs_clust(args)
+ # Check that all expected files and temporary directory are created
+ # and check that no more outfile is create, in order to remove all of them !! !!
+ generated_outfiles = glob.glob(mmseqclust + "*")
+ assert len(generated_outfiles) == 3
+ assert set(generated_outfiles) == set([mmseqclust, mmseqclust + ".index",
+ mmseqclust + ".dbtype"])
+ assert os.path.isfile(logmmseq)
+ assert os.path.isdir(tmpdir)
+ # Remove files created by this test
+ shutil.rmtree(tmpdir)
+ for file in generated_outfiles:
+ os.remove(file)
+ os.remove(logmmseq)
-# def test_get_info():
-# """
-# Check that string given by get_info is as expected according to info given in input
-# """
-# threads = 1
-# min_id = 0.8
-# clust_mode = 1
-# start = "STARTTIME"
-# info = mmseqs.get_info(threads, min_id, clust_mode, start)
-# assert info == "0.8-mode1_STARTTIME"
+def test_get_logmmseq():
+ """
+ Check that the given log filename is as expected according to given information
+ """
+ outdir = "toto"
+ prt_bank = "bank_prt"
+ infoname = "GENO115"
+ log = mmseqs.get_logmmseq(outdir, prt_bank, infoname)
+ assert log == "toto/mmseq_bank_prt_GENO115.log"
-# def test_get_info_parallel():
-# """
-# Check that string given by get_info is as expected according to info given in input
-# """
-# threads = 12
-# min_id = 0.8
-# clust_mode = 1
-# start = "STARTTIME"
-# info = mmseqs.get_info(threads, min_id, clust_mode, start)
-# assert info == "0.8-mode1-th12_STARTTIME"
+def test_get_info():
+ """
+ Check that string given by get_info is as expected according to info given in input
+ """
+ threads = 1
+ min_id = 0.8
+ clust_mode = 1
+ start = "STARTTIME"
+ info = mmseqs.get_info(threads, min_id, clust_mode, start)
+ assert info == "0.8-mode1_STARTTIME"
-# def test_do_pangenome(caplog):
-# """
-# Check that expected output files are created,
-# and compare output pangenome to the expected one.
-# """
-# caplog.set_level(logging.DEBUG)
-# outdir = "test_do_pangenome_outdir"
-# prt_bank = "exp_EXEM.All.prt"
-# mmseqdb = os.path.join(PATH_TEST_FILES, "mmseq_db")
-# min_id = 0.8
-# clust_mode = 1
-# threads = 1
-# start = "STARTTIME"
-# quiet = False
-# assert not os.path.isdir(outdir)
-# fams, outfile = mmseqs.do_pangenome(outdir, prt_bank, mmseqdb, min_id,
-# clust_mode, threads, start, quiet=quiet)
-# # Check creation of output directory
-# assert os.path.isdir(outdir)
-# # Check creation of tmp directory
-# tmp_dir = os.path.join(outdir, "tmp_exp_EXEM.All.prt_0.8-mode1_STARTTIME")
-# assert os.path.isdir(tmp_dir)
-# # Check presence of pangenome file
-# exp_out = os.path.join(outdir, "PanGenome-exp_EXEM.All.prt-clust-0.8-mode1_STARTTIME.tsv.lst")
-# assert exp_out == outfile
-# assert os.path.isfile(outfile)
-# # Check families returned
-# for num, fam in fams.items():
-# assert num in list(range(1, 17))
-# found = False
-# for expfam in list(EXP_CLUSTERS.values()):
-# if fam == expfam:
-# found = True
-# break
-# assert found
-# # Check content of output pangenome file
-# exp_pan = os.path.join(PATH_EXP_FILES, "exp_pangenome-4genomes.lst")
-# with open(exp_pan, "r") as ep, open(outfile, "r") as pan:
-# lines_exp = []
-# lines_out = []
-# for line_exp, line in zip(ep, pan):
-# lines_exp.append(tuple(line_exp.split()[1:]))
-# lines_out.append(tuple(line.split()[1:]))
-# assert set(lines_exp) == set(lines_out)
-# assert "Clustering proteins..." in caplog.text
-# shutil.rmtree(outdir)
+def test_get_info_parallel():
+ """
+ Check that string given by get_info is as expected according to info given in input
+ """
+ threads = 12
+ min_id = 0.8
+ clust_mode = 1
+ start = "STARTTIME"
+ info = mmseqs.get_info(threads, min_id, clust_mode, start)
+ assert info == "0.8-mode1-th12_STARTTIME"
-# def test_do_pangenome_given_panfile(caplog):
-# """
-# Check that expected output files are created,
-# and compare output pangenome to the expected one.
-# """
-# caplog.set_level(logging.DEBUG)
-# outdir = "test_do_pangenome_outdir"
-# prt_bank = "exp_EXEM.All.prt"
-# mmseqdb = os.path.join(PATH_TEST_FILES, "mmseq_db")
-# min_id = 0.8
-# clust_mode = 1
-# threads = 1
-# start = "STARTTIME"
-# quiet = False
-# panfile = "test_res_pangenome"
-# assert not os.path.isdir(outdir)
-# fams, outfile = mmseqs.do_pangenome(outdir, prt_bank, mmseqdb, min_id,
-# clust_mode, threads, start, quiet=quiet, panfile=panfile)
-# print(outfile)
-# # Check creation of output directory
-# assert os.path.isdir(outdir)
-# # Check creation of tmp directory
-# tmp_dir = os.path.join(outdir, "tmp_exp_EXEM.All.prt_0.8-mode1_STARTTIME")
-# assert os.path.isdir(tmp_dir)
-# # Check presence of pangenome file
-# assert panfile == outfile
-# assert os.path.isfile(outfile)
-# # Check families returned
-# for num, fam in fams.items():
-# assert num in list(range(1, 17))
-# found = False
-# for expfam in list(EXP_CLUSTERS.values()):
-# if fam == expfam:
-# found = True
-# break
-# assert found
-# # Check content of output pangenome file
-# exp_pan = os.path.join(PATH_EXP_FILES, "exp_pangenome-4genomes.lst")
-# with open(exp_pan, "r") as ep, open(outfile, "r") as pan:
-# lines_exp = []
-# lines_out = []
-# for line_exp, line in zip(ep, pan):
-# lines_exp.append(tuple(line_exp.split()[1:]))
-# lines_out.append(tuple(line.split()[1:]))
-# assert set(lines_exp) == set(lines_out)
-# assert "Clustering proteins..." in caplog.text
-# shutil.rmtree(outdir)
-# os.remove(panfile)
+def test_do_pangenome_defaultname(caplog):
+ """
+ Check that expected output files are created,
+ and compare output pangenome to the expected one.
+ """
+ caplog.set_level(logging.DEBUG)
+ outdir = "test_do_pangenome_outdir"
+ prt_bank = "exp_EXEM.All.prt"
+ mmseqdb = os.path.join(PATH_TEST_FILES, "mmseq_db")
+ min_id = 0.8
+ clust_mode = 1
+ threads = 1
+ start = "STARTTIME"
+ quiet = False
+ assert not os.path.isdir(outdir)
+ fams, outfile = mmseqs.do_pangenome(outdir, prt_bank, mmseqdb, min_id,
+ clust_mode, threads, start, quiet=quiet)
+ # Check creation of output directory
+ assert os.path.isdir(outdir)
+ # Check creation of tmp directory
+ tmp_dir = os.path.join(outdir, "tmp_exp_EXEM.All.prt_0.8-mode1_STARTTIME")
+ assert os.path.isdir(tmp_dir)
+ # Check presence of pangenome file
+ exp_out = os.path.join(outdir, "PanGenome-exp_EXEM.All.prt-clust-0.8-mode1_STARTTIME.tsv.lst")
+ assert exp_out == outfile
+ assert os.path.isfile(outfile)
+ # Check families returned
+ for num, fam in fams.items():
+ assert num in list(range(1, 17))
+ found = False
+ for expfam in list(EXP_CLUSTERS.values()):
+ if fam == expfam:
+ found = True
+ break
+ assert found
+ # Check content of output pangenome file
+ exp_pan = os.path.join(PATH_EXP_FILES, "exp_pangenome-4genomes.lst")
+ with open(exp_pan, "r") as ep, open(outfile, "r") as pan:
+ lines_exp = []
+ lines_out = []
+ for line_exp, line in zip(ep, pan):
+ lines_exp.append(tuple(line_exp.split()[1:]))
+ lines_out.append(tuple(line.split()[1:]))
+ assert set(lines_exp) == set(lines_out)
+ assert "Clustering proteins..." in caplog.text
+ shutil.rmtree(outdir)
-# def test_do_pangenome_quiet(caplog):
-# """
-# Check that expected output files are created,
-# and compare output pangenome to the expected one.
-# Check that no error appears when choosing quiet option.
-# """
-# caplog.set_level(logging.DEBUG)
-# outdir = "test_do_pangenome_outdir"
-# prt_bank = "exp_EXEM.All.prt"
-# mmseqdb = os.path.join(PATH_TEST_FILES, "mmseq_db")
-# min_id = 0.8
-# clust_mode = 1
-# threads = 1
-# start = "STARTTIME"
-# quiet = True
-# assert not os.path.isdir(outdir)
-# fams, outfile = mmseqs.do_pangenome(outdir, prt_bank, mmseqdb, min_id,
-# clust_mode, threads, start, quiet=quiet)
-# # Check creation of output directory
-# assert os.path.isdir(outdir)
-# # Check creation of tmp directory
-# tmp_dir = os.path.join(outdir, "tmp_exp_EXEM.All.prt_0.8-mode1_STARTTIME")
-# assert os.path.isdir(tmp_dir)
-# # Check presence of pangenome file
-# exp_out = os.path.join(outdir, "PanGenome-exp_EXEM.All.prt-clust-0.8-mode1_STARTTIME.tsv.lst")
-# assert exp_out == outfile
-# assert os.path.isfile(outfile)
-# # Check families returned
-# for num, fam in fams.items():
-# assert num in list(range(1, 17))
-# found = False
-# for expfam in list(EXP_CLUSTERS.values()):
-# if fam == expfam:
-# found = True
-# break
-# assert found
-# # Check content of output pangenome file
-# exp_pan = os.path.join(PATH_EXP_FILES, "exp_pangenome-4genomes.lst")
-# with open(exp_pan, "r") as ep, open(outfile, "r") as pan:
-# lines_exp = []
-# lines_out = []
-# for line_exp, line in zip(ep, pan):
-# lines_exp.append(tuple(line_exp.split()[1:]))
-# lines_out.append(tuple(line.split()[1:]))
-# assert set(lines_exp) == set(lines_out)
-# assert "Clustering proteins..." in caplog.text
-# shutil.rmtree(outdir)
+def test_do_pangenome_given_panfile(caplog):
+ """
+ Check that expected output files are created,
+ and compare output pangenome to the expected one.
+ No possibility to check if quiet was not applied...
+ """
+ caplog.set_level(logging.DEBUG)
+ outdir = "test_do_pangenome_outdir_pan-name"
+ prt_bank = "exp_EXEM.All.prt"
+ mmseqdb = os.path.join(PATH_TEST_FILES, "mmseq_db")
+ min_id = 0.8
+ clust_mode = 1
+ threads = 1
+ start = "STARTTIME"
+ quiet = False
+ panfile = "test_res_pangenome_given-name"
+ # Check outdir does not exit before
+ assert not os.path.isdir(outdir)
+ fams, outfile = mmseqs.do_pangenome(outdir, prt_bank, mmseqdb, min_id,
+ clust_mode, threads, start, quiet=quiet, panfile=panfile)
+ # Check creation of output directory
+ assert os.path.isdir(outdir)
+ # Check creation of tmp directory
+ tmp_dir = os.path.join(outdir, "tmp_exp_EXEM.All.prt_0.8-mode1_STARTTIME")
+ assert os.path.isdir(tmp_dir)
+ # Check presence of pangenome file
+ assert panfile == outfile
+ assert os.path.isfile(outfile)
+ # Check families returned
+ for num, fam in fams.items():
+ assert num in list(range(1, 17))
+ found = False
+ for expfam in list(EXP_CLUSTERS.values()):
+ if fam == expfam:
+ found = True
+ break
+ assert found
+ # Check content of output pangenome file
+ exp_pan = os.path.join(PATH_EXP_FILES, "exp_pangenome-4genomes.lst")
+ with open(exp_pan, "r") as ep, open(outfile, "r") as pan:
+ lines_exp = []
+ lines_out = []
+ for line_exp, line in zip(ep, pan):
+ lines_exp.append(tuple(line_exp.split()[1:]))
+ lines_out.append(tuple(line.split()[1:]))
+ assert set(lines_exp) == set(lines_out)
+ assert "Clustering proteins..." in caplog.text
+ shutil.rmtree(outdir)
+ os.remove(panfile)
-# def test_do_pangenome_exist(caplog):
-# """
-# Check that if the mmseq output file of clustering already exists, it does not
-# run mmseq again, but just converts it to pangenome.
-# """
-# caplog.set_level(logging.DEBUG)
-# outdir = "test_do_pangenome_outdir_exist"
-# prt_bank = "exp_EXEM.All.prt"
-# mmseqdb = os.path.join(PATH_TEST_FILES, "mmseq_db")
-# min_id = 0.8
-# clust_mode = 1
-# threads = 1
-# start = "STARTTIME"
-# # Create clustering results in outdir
-# os.makedirs(outdir)
-# orig_clust = os.path.join(PATH_TEST_FILES, "mmseq_clust-out")
-# out_clust = os.path.join(outdir, "exp_EXEM.All.prt-clust-0.8-mode1_STARTTIME")
-# shutil.copyfile(orig_clust, out_clust)
-# shutil.copyfile(orig_clust + ".index", out_clust + ".index")
-# fams, outfile = mmseqs.do_pangenome(outdir, prt_bank, mmseqdb, min_id,
-# clust_mode, threads, start)
-# assert ("mmseqs clustering test_do_pangenome_outdir_exist/exp_EXEM.All.prt-clust-0.8-"
-# "mode1_STARTTIME already exists. The program will now convert it to a "
-# "pangenome file.") in caplog.text
-# # Check creation of empty tmp directory
-# tmp_dir = os.path.join(outdir, "tmp_exp_EXEM.All.prt_0.8-mode1_STARTTIME")
-# assert os.path.isdir(tmp_dir)
-# assert glob.glob(os.path.join(tmp_dir, "*")) == []
-# # Check presence of pangenome file
-# exp_out = os.path.join(outdir, "PanGenome-exp_EXEM.All.prt-clust-0.8-mode1_STARTTIME.tsv.lst")
-# assert exp_out == outfile
-# assert os.path.isfile(outfile)
-# # Check families returned
-# for num, fam in fams.items():
-# assert num in list(range(1, 17))
-# found = False
-# for expfam in list(EXP_CLUSTERS.values()):
-# if fam == expfam:
-# found = True
-# break
-# assert found
-# # Check content of output pangenome file
-# exp_pan = os.path.join(PATH_EXP_FILES, "exp_pangenome-4genomes.lst")
-# with open(exp_pan, "r") as ep, open(outfile, "r") as pan:
-# lines_exp = []
-# lines_out = []
-# for line_exp, line in zip(ep, pan):
-# lines_exp.append(tuple(line_exp.split()[1:]))
-# lines_out.append(tuple(line.split()[1:]))
-# assert set(lines_exp) == set(lines_out)
-# assert "Clustering proteins..." not in caplog.text
-# shutil.rmtree(outdir)
+def test_do_pangenome_quiet(caplog):
+ """
+ Check that expected output files are created,
+ and compare output pangenome to the expected one.
+ Check that no error appears when choosing quiet option.
+ No possibility to check if quiet was applied...
+ """
+ caplog.set_level(logging.DEBUG)
+ outdir = "test_do_pangenome_outdir_quiet"
+ prt_bank = "exp_EXEM.All.prt"
+ mmseqdb = os.path.join(PATH_TEST_FILES, "mmseq_db")
+ min_id = 0.8
+ clust_mode = 1
+ threads = 1
+ start = "STARTTIME"
+ quiet = True
+ assert not os.path.isdir(outdir)
+ fams, outfile = mmseqs.do_pangenome(outdir, prt_bank, mmseqdb, min_id,
+ clust_mode, threads, start, quiet=quiet)
+ # Check creation of output directory
+ assert os.path.isdir(outdir)
+ # Check creation of tmp directory
+ tmp_dir = os.path.join(outdir, "tmp_exp_EXEM.All.prt_0.8-mode1_STARTTIME")
+ assert os.path.isdir(tmp_dir)
+ # Check presence of pangenome file
+ exp_out = os.path.join(outdir, "PanGenome-exp_EXEM.All.prt-clust-0.8-mode1_STARTTIME.tsv.lst")
+ assert exp_out == outfile
+ assert os.path.isfile(outfile)
+ # Check families returned
+ for num, fam in fams.items():
+ assert num in list(range(1, 17))
+ found = False
+ for expfam in list(EXP_CLUSTERS.values()):
+ if fam == expfam:
+ found = True
+ break
+ assert found
+ # Check content of output pangenome file
+ exp_pan = os.path.join(PATH_EXP_FILES, "exp_pangenome-4genomes.lst")
+ with open(exp_pan, "r") as ep, open(outfile, "r") as pan:
+ lines_exp = []
+ lines_out = []
+ for line_exp, line in zip(ep, pan):
+ lines_exp.append(tuple(line_exp.split()[1:]))
+ lines_out.append(tuple(line.split()[1:]))
+ assert set(lines_exp) == set(lines_out)
+ assert "Clustering proteins..." in caplog.text
+ shutil.rmtree(outdir)
-# def test_run_all_pangenome(caplog):
-# """
-# Check that, given a prt bank, it creates mmseq db, mmseq clustering, and
-# outputs the expected pangenome file.
-# """
-# caplog.set_level(logging.DEBUG)
-# min_id = 0.8
-# clust_mode = 1
-# outdir = "test_run_allpangenome"
-# os.makedirs(outdir)
-# prt_path = os.path.join(PATH_EXP_FILES, "exp_EXEM.All.prt")
-# threads = 1
-# panfile = None
-# quiet = False
-# fams, outfile = mmseqs.run_all_pangenome(min_id, clust_mode, outdir, prt_path,
-# threads, panfile=panfile, quiet=quiet)
+def test_do_pangenome_exist(caplog):
+ """
+ Check that if the mmseq output file of clustering already exists, it does not
+ run mmseq again, but just converts it to pangenome.
+ """
+ caplog.set_level(logging.DEBUG)
+ outdir = "test_do_pangenome_outdir_exist"
+ prt_bank = "exp_EXEM.All.prt"
+ mmseqdb = os.path.join(PATH_TEST_FILES, "mmseq_db")
+ min_id = 0.8
+ clust_mode = 1
+ threads = 1
+ start = "STARTTIME"
+ # Create clustering results in outdir
+ os.makedirs(outdir)
+ orig_clust = os.path.join(PATH_TEST_FILES, "mmseq_clust-out")
+ out_clust = os.path.join(outdir, "exp_EXEM.All.prt-clust-0.8-mode1_STARTTIME")
+ shutil.copyfile(orig_clust, out_clust)
+ shutil.copyfile(orig_clust + ".index", out_clust + ".index")
+ fams, outfile = mmseqs.do_pangenome(outdir, prt_bank, mmseqdb, min_id,
+ clust_mode, threads, start)
+ assert ("mmseqs clustering test_do_pangenome_outdir_exist/exp_EXEM.All.prt-clust-0.8-"
+ "mode1_STARTTIME already exists. The program will now convert it to a "
+ "pangenome file.") in caplog.text
+ # Check creation of empty tmp directory
+ tmp_dir = os.path.join(outdir, "tmp_exp_EXEM.All.prt_0.8-mode1_STARTTIME")
+ assert os.path.isdir(tmp_dir)
+ assert glob.glob(os.path.join(tmp_dir, "*")) == []
+ # Check presence of pangenome file
+ exp_out = os.path.join(outdir, "PanGenome-exp_EXEM.All.prt-clust-0.8-mode1_STARTTIME.tsv.lst")
+ assert exp_out == outfile
+ assert os.path.isfile(outfile)
+ # Check families returned
+ for num, fam in fams.items():
+ assert num in list(range(1, 17))
+ found = False
+ for expfam in list(EXP_CLUSTERS.values()):
+ if fam == expfam:
+ found = True
+ break
+ assert found
+ # Check content of output pangenome file
+ exp_pan = os.path.join(PATH_EXP_FILES, "exp_pangenome-4genomes.lst")
+ with open(exp_pan, "r") as ep, open(outfile, "r") as pan:
+ lines_exp = []
+ lines_out = []
+ for line_exp, line in zip(ep, pan):
+ lines_exp.append(tuple(line_exp.split()[1:]))
+ lines_out.append(tuple(line.split()[1:]))
+ assert set(lines_exp) == set(lines_out)
+ assert "Clustering proteins..." not in caplog.text
+ shutil.rmtree(outdir)
+
+
+def test_run_all_pangenome(caplog):
+ """
+ Check that, given a prt bank, it creates mmseq db, mmseq clustering, and
+ outputs the expected pangenome file.
+ """
+ caplog.set_level(logging.DEBUG)
+ min_id = 0.8
+ clust_mode = 1
+ outdir = "test_run_allpangenome"
+ os.makedirs(outdir)
+ prt_path = os.path.join(PATH_EXP_FILES, "exp_EXEM.All.prt")
+ threads = 1
+ panfile = None
+ quiet = False
+ fams, outfile = mmseqs.run_all_pangenome(min_id, clust_mode, outdir, prt_path,
+ threads, panfile=panfile, quiet=quiet)
+ assert "toto" not in caplog.text
# # check that tmp dir was created and not empty
# tmp_dir = os.path.join(outdir, "tmp_exp_EXEM.All.prt_0.8-mode1_*")
# assert glob.glob(os.path.join(tmp_dir, "*")) != []