def run(options):
if options.no_cdhit and options.cdhit_clusters is not None:
sys.exit('Cannot use both --no_cdhit and --cdhit_clusters. Neither or exactly one of those options must be used')
extern_progs, version_report_lines = versions.get_all_versions(using_spades=False)
if options.verbose:
print(*version_report_lines, sep='\n')
preparer = ref_preparer.RefPreparer(
options.fasta_files,
extern_progs,
metadata_tsv_files=options.tsv_files,
all_coding=options.all_coding,
version_report_lines=version_report_lines,
min_gene_length=options.min_gene_length,
max_gene_length=options.max_gene_length,
genetic_code=options.genetic_code,
cdhit_min_id=options.cdhit_min_id,
cdhit_min_length=options.cdhit_min_length,
cdhit_max_memory=options.cdhit_max_memory,
run_cdhit=not options.no_cdhit,
clusters_file=options.cdhit_clusters,
threads=options.threads,
verbose=options.verbose,
force=options.force,
)
preparer.run(options.outdir)
def test_run_all_noncoding(self):
'''test run with no metadata input, all sequences are noncoding'''
fasta_in = [
os.path.join(data_dir, 'ref_preparer_test_run.in.1.fa'),
os.path.join(data_dir, 'ref_preparer_test_run.in.2.fa'),
os.path.join(data_dir, 'ref_preparer_test_run.in.3.fa'),
]
extern_progs = external_progs.ExternalProgs()
refprep = ref_preparer.RefPreparer(fasta_in, extern_progs, all_coding='no', genetic_code=1)
tmp_out = 'tmp.ref_preparer_test_run'
refprep.run(tmp_out)
expected_outdir = os.path.join(data_dir, 'ref_preparer_test_run_all_noncoding.out')
test_files = [
'00.auto_metadata.tsv',
'01.filter.check_metadata.tsv',
'01.filter.check_genes.log',
'01.filter.check_noncoding.log',
'01.filter.check_metadata.log',
'02.cdhit.all.fa',
'02.cdhit.clusters.tsv',
'02.cdhit.gene.fa',
'02.cdhit.gene.varonly.fa',
'02.cdhit.noncoding.fa',
'02.cdhit.noncoding.varonly.fa',
]
for filename in test_files:
expected = os.path.join(expected_outdir, filename)
got = os.path.join(tmp_out, filename)
self.assertTrue(filecmp.cmp(expected, got, shallow=False))
common.rmtree(tmp_out)
def test_run(self):
'''test run'''
fasta_in = [
os.path.join(data_dir, 'ref_preparer_test_run.in.1.fa'),
os.path.join(data_dir, 'ref_preparer_test_run.in.2.fa'),
os.path.join(data_dir, 'ref_preparer_test_run.in.3.fa'),
]
tsv_in = [
os.path.join(data_dir, 'ref_preparer_test_run.in.1.tsv'),
os.path.join(data_dir, 'ref_preparer_test_run.in.2.tsv'),
]
extern_progs = external_progs.ExternalProgs()
refprep = ref_preparer.RefPreparer(fasta_in,
extern_progs,
metadata_tsv_files=tsv_in,
genetic_code=1)
tmp_out = 'tmp.ref_preparer_test_run'
refprep.run(tmp_out)
expected_outdir = os.path.join(data_dir, 'ref_preparer_test_run.out')
test_files = [
'01.filter.check_metadata.tsv',
'01.filter.check_genes.log',
'01.filter.check_metadata.log',
'02.cdhit.all.fa',
'02.cdhit.clusters.tsv',
'02.cdhit.gene.fa',
'02.cdhit.gene.varonly.fa',
'02.cdhit.noncoding.fa',
'02.cdhit.noncoding.varonly.fa',
]
for filename in test_files:
expected = os.path.join(expected_outdir, filename)
got = os.path.join(tmp_out, filename)
self.assertTrue(filecmp.cmp(expected, got, shallow=False))
shutil.rmtree(tmp_out)
def make_prepareref_dir(outdir):
if os.path.exists(outdir):
raise Exception('Output directory ' + outdir +
' already exists. Cannot continue')
tmpdir = tempfile.mkdtemp(prefix=outdir + '.tmp', dir=os.getcwd())
tmp_prefix = os.path.join(tmpdir, 'out')
make_prepareref_files(tmp_prefix)
ref_prep = ref_preparer.RefPreparer(
[tmp_prefix + '.fa'],
None,
metadata_tsv_files=[tmp_prefix + '.tsv'],
run_cdhit=False,
threads=1,
)
ref_prep.run(outdir)
common.rmtree(tmpdir)
json_data = {'tb': True}
json_file = os.path.join(outdir, '00.params.json')
with open(json_file, 'w') as f:
json.dump(json_data, f)
def run(self):
try:
os.mkdir(self.outdir)
except:
raise Error('Error making output directory ' + self.outdir)
pubmlst = pubmlst_getter.PubmlstGetter(debug=self.debug,
verbose=self.verbose)
pubmlst.get_species_files(self.species, self.mlst_download_dir)
if self.verbose:
print('Downloaded data from pubmlst')
profile_file = os.path.join(self.mlst_download_dir, 'profile.txt')
self.profile = mlst_profile.MlstProfile(profile_file,
duplicate_warnings=True)
if self.verbose:
print('Loaded mlst profile file', profile_file)
self._load_fasta_files_and_write_clusters_file(self.mlst_download_dir)
if self.verbose:
print('Loaded fasta files and wrote clusters file')
print('Putting data in ariba db directory', self.prepareref_dir)
refprep = ref_preparer.RefPreparer(
self.fasta_files,
self.extern_progs,
all_coding='no',
clusters_file=self.clusters_file,
verbose=self.verbose,
)
refprep.run(self.prepareref_dir)
shutil.copy(profile_file,
os.path.join(self.prepareref_dir, 'pubmlst.profile.txt'))
print('ariba db directory prepared. You can use it like this:')
print('ariba run', self.prepareref_dir,
'reads_1.fq reads_2.fq output_directory')
def test_run_noncoding_checks(self):
'''test run with noncoding sequences that are outside of the allowed size range'''
fasta_in = [
os.path.join(data_dir, 'ref_preparer_test_run.in.4.fa')
]
tsv_in = [
os.path.join(data_dir, 'ref_preparer_test_run.in.4.tsv')
]
extern_progs = external_progs.ExternalProgs()
refprep = ref_preparer.RefPreparer(
fasta_in, extern_progs, min_noncoding_length=6, max_noncoding_length=20,
metadata_tsv_files=tsv_in, genetic_code=1)
tmp_out = 'tmp.ref_preparer_test_run_noncoding_checks'
refprep.run(tmp_out)
expected_outdir = os.path.join(data_dir, 'ref_preparer_test_run_noncoding_checks.out')
test_files = [
'01.filter.check_metadata.tsv',
'01.filter.check_genes.log',
'01.filter.check_noncoding.log',
'01.filter.check_metadata.log',
'02.cdhit.all.fa',
'02.cdhit.clusters.tsv',
'02.cdhit.gene.fa',
'02.cdhit.gene.varonly.fa',
'02.cdhit.noncoding.fa',
'02.cdhit.noncoding.varonly.fa',
]
for filename in test_files:
expected = os.path.join(expected_outdir, filename)
got = os.path.join(tmp_out, filename)
self.assertTrue(filecmp.cmp(expected, got, shallow=False))
common.rmtree(tmp_out)