def testConfigFileMissingFile(self):
# Just to make different test cases independent of each other.
config._options_singelton = None
# Diasable main config path for this test
config.main_config_path = self.fp_config
sys.argv = [
sys.argv[0], "-c",
get_data_path("configs/test2.config"), "-f",
get_data_path("simulated/test.fas"), "-a",
get_data_path("simulated/test.small.fas")
]
assert isinstance(options().config_file, filetypes) and \
options().config_file.name.endswith(
"data/configs/test2.config"), \
"Commandline option -c not read properly"
assert isinstance(options().alignment_file, filetypes) and\
options().alignment_file.name.endswith(
"data/simulated/test.small.fas"), \
"Config file option alignment not read properly"
assert isinstance(options().fragment_file, filetypes) and\
options().fragment_file.name.endswith(
"data/simulated/test.fas"), \
"Command-line option -f alignment not read properly"
def setUp(self):
# ensure necessary settings are made
sepp.scheduler._jobPool = None
sys.argv = [sys.argv[0], "-c", get_data_path("configs/test3.config")]
self.x = UPPExhaustiveAlgorithm()
self.x.options.backbone_size = 407
self.x.options.alignment_size = 50
self.x.options.placement_size = None
self.x.options.backtranslation_sequence_file = None
self.x.options.long_branch_filter = 100000
self.x.options.molecule = 'amino'
self.x.molecule = 'amino'
self.x.options.alignment_file = open(
get_data_path("upp_frag/backbone_pasta.fasta"), "r")
self.x.options.sequence_file = open(
get_data_path("upp_frag/query.fas"), "r")
self.x.options.tree_file = open(
get_data_path("upp_frag/backbone_pasta.fasttree"), "r")
self.x.options.outdir = tempfile.mkdtemp()
suff_bit = "-64" if sys.maxsize > 2**32 else "-32"
if platform.system() == 'Darwin':
suff_bit = ""
for prog in ['hmmalign', 'hmmbuild', 'hmmsearch']:
setattr(
self.x.options, prog,
Namespace(
path=get_data_path("../../../tools/bundled/%s/%s%s" %
(platform.system(), prog, suff_bit))))
def testMainConfigFile(self):
# Just to make different test cases independent of each other.
config._options_singelton = None
sys.argv = [sys.argv[0], "-c", get_data_path("configs/test2.config")]
# set pplacer filepath to a file shipped with the code base
options().pplacer.path = get_data_path(
"../../../tools/bundled/Darwin/pplacer")
assert (options().pplacer is not None and os.path.exists(
options().pplacer.path)), \
("main config file options not read properly,"
"or nonexistent binaries: pplacer = %s" %
options().pplacer.path)
options().hmmalign.path = get_data_path(
"../../../tools/bundled/Darwin/hmmalign")
assert (options().hmmalign is not None and os.path.exists(
options().hmmalign.path)), \
("main config file options not read properly, or nonexistent "
"binaries: hmmalign = %s" % options().hmmalign.path)
options().hmmsearch.path = get_data_path(
"../../../tools/bundled/Darwin/hmmsearch")
assert (options().hmmsearch is not None and os.path.exists(
options().hmmsearch.path)), \
("main config file options not read properly, or nonexistent "
"binaries: hmmsearch = %s" % options().hmmsearch.path)
def setUp(self):
# ensure necessary settings are made
sepp.scheduler._jobPool = None
sys.argv = [sys.argv[0], "-c", get_data_path("configs/test2.config")]
self.x = ExhaustiveAlgorithm()
self.x.options.alignment_file = open(
get_data_path(
"q2-fragment-insertion/reference_alignment_tiny.fasta"), "r")
self.x.options.info_file = open(
get_data_path(
"q2-fragment-insertion/RAxML_info-reference-gg-raxml-bl.info"),
"r")
self.x.options.tree_file = open(
get_data_path(
"q2-fragment-insertion/reference_phylogeny_tiny.nwk"), "r")
self.x.options.outdir = tempfile.mkdtemp()
suff_bit = "-64" if sys.maxsize > 2**32 else "-32"
if platform.system() == 'Darwin':
suff_bit = ""
for prog in ['hmmalign', 'hmmbuild', 'hmmsearch', 'pplacer']:
setattr(
self.x.options, prog,
Namespace(
path=get_data_path("../../../tools/bundled/%s/%s%s" %
(platform.system(), prog, suff_bit))))
def testMainConfigFile(self):
# Just to make different test cases independent of each other.
config._options_singelton = None
sys.argv = [sys.argv[0], "-c", get_data_path("configs/test2.config")]
# set pplacer filepath to a file shipped with the code base
options().pplacer.path = get_data_path(
"../../../tools/bundled/Darwin/pplacer")
assert (options().pplacer is not None and os.path.exists(
options().pplacer.path)), \
("main config file options not read properly,"
"or nonexistent binaries: pplacer = %s" %
options().pplacer.path)
options().hmmalign.path = get_data_path(
"../../../tools/bundled/Darwin/hmmalign")
assert (options().hmmalign is not None and os.path.exists(
options().hmmalign.path)), \
("main config file options not read properly, or nonexistent "
"binaries: hmmalign = %s" % options().hmmalign.path)
options().hmmsearch.path = get_data_path(
"../../../tools/bundled/Darwin/hmmsearch")
assert (options().hmmsearch is not None and os.path.exists(
options().hmmsearch.path)), \
("main config file options not read properly, or nonexistent "
"binaries: hmmsearch = %s" % options().hmmsearch.path)
def testMerge(self):
sys.argv = [sys.argv[0]]
stdindata = open(get_data_path("tmp/tempmerge")).read()
# write path of seppJsonMerger.jar into configuration
setattr(sepp.config.options(), 'jsonmerger', Namespace(
path=get_data_path("../../../tools/merge/seppJsonMerger.jar")))
mergeJsonJob = MergeJsonJob()
mergeJsonJob.setup(stdindata.replace(
'data/tmp/pplacer.extended',
os.path.dirname(get_data_path("tmp/tempmerge")) +
'/pplacer.extended'), get_data_path("tmp/mergedfile"))
mergeJsonJob.run()
def testAlignmentReadFasta(self):
alg = MutableAlignment()
alg.read_filepath(get_data_path("mock/pyrg/sate.fasta"))
assert len(alg) == 65, "MutableAlignment length is %s" % len(alg)
assert all([not alg.is_all_gap(i) for i in range(0, alg.get_length())])
def test_notpiped_jobs(self):
sepp.config.options().hmmsearch.piped = "False"
self.x.options.fragment_file = open(
get_data_path(
"q2-fragment-insertion/input_fragments_tiny.fasta"), "r")
self.x.run()
self.assertTrue(self.x.results is not None)
def testConfigFile(self):
# Just to make different test cases independent of each other.
config._options_singelton = None
# Diasable main config path for this test
config.main_config_path = self.fp_config
sys.argv = [
sys.argv[0], "-A", "2", "-c",
get_data_path("configs/test.config"), "--outdir",
"dir_form_commandline"
]
assert options().alignment_size == 2, \
"Commandline option -A not read properly"
assert isinstance(options().config_file, filetypes) and \
options().config_file.name.endswith("data/configs/test.config"), \
"Commandline option -c not read properly"
assert (options().pplacer is not None and
options().pplacer.path == "pplacer"), \
"config file options not read properly"
assert options().placement_size == 10, \
"Config file option placementSize not read properly"
assert options().outdir.endswith("dir_form_commandline"), \
"Config file value outdir is not properly overwritten:%s " % \
options().outdir
assert options().tempdir is not None, \
"Default value not properly set for tempfile attribute"
def testAlignmentReadFasta(self):
alg = MutableAlignment()
alg.read_filepath(get_data_path("mock/pyrg/sate.fasta"))
assert len(alg) == 65, "MutableAlignment length is %s" % len(alg)
assert all([not alg.is_all_gap(i) for i in range(0, alg.get_length())])
def testConfigFile(self):
# Just to make different test cases independent of each other.
config._options_singelton = None
# Diasable main config path for this test
config.main_config_path = self.fp_config
sys.argv = [
sys.argv[0], "-A", "2",
"-c", get_data_path("configs/test.config"),
"--outdir", "dir_form_commandline"]
assert options().alignment_size == 2, \
"Commandline option -A not read properly"
assert isinstance(options().config_file, filetypes) and \
options().config_file.name.endswith("data/configs/test.config"), \
"Commandline option -c not read properly"
assert (options().pplacer is not None and
options().pplacer.path == "pplacer"), \
"config file options not read properly"
assert options().placement_size == 10, \
"Config file option placementSize not read properly"
assert options().outdir.endswith("dir_form_commandline"), \
"Config file value outdir is not properly overwritten:%s " % \
options().outdir
assert options().tempdir is not None, \
"Default value not properly set for tempfile attribute"
def test_diamCent(self):
self.x.options.fragment_file = open(
get_data_path("q2-fragment-insertion/input_fragments.fasta"), "r")
self.x.options.maxDiam = 0.1
self.x.options.fragmentChunkSize = 1
self.x.options.decomp_strategy = "centroid"
self.x.run()
self.assertTrue(self.x.results is not None)
def test_seqnames_whitespaces(self):
self.x.options.fragment_file = open(
get_data_path(
"q2-fragment-insertion/input_fragments_spaces.fasta"), "r")
with self.assertRaisesRegex(ValueError,
"contain either whitespaces: "):
self.x.run()
self.assertTrue(self.x.results is None)
def test_id_collision_collision(self):
self.x.options.fragment_file = open(
get_data_path(
"q2-fragment-insertion/input_fragments_collide.fasta"), "r")
with self.assertRaisesRegex(
ValueError,
' whose names overlap with names in your reference'):
self.x.run()
self.assertTrue(self.x.results is None)
def test_seqnames_whitespaces(self):
self.x.options.fragment_file = open(
get_data_path(
"q2-fragment-insertion/input_fragments_spaces.fasta"), "r")
with self.assertRaisesRegex(
ValueError,
"contain either whitespaces: "):
self.x.run()
self.assertTrue(self.x.results is None)
def test_id_collision_collision(self):
self.x.options.fragment_file = open(
get_data_path(
"q2-fragment-insertion/input_fragments_collide.fasta"), "r")
with self.assertRaisesRegex(
ValueError,
' whose names overlap with names in your reference'):
self.x.run()
self.assertTrue(self.x.results is None)
def test_diamCent(self):
self.x.options.fragment_file = open(
get_data_path(
"q2-fragment-insertion/input_fragments.fasta"), "r")
self.x.options.maxDiam = 0.1
self.x.options.fragmentChunkSize = 1
self.x.options.decomp_strategy = "centroid"
self.x.run()
self.assertTrue(self.x.results is not None)
def resetSepp(self):
# ensure necessary settings are made
sepp.scheduler._jobPool = None
sepp.scheduler._parser = None
self.x = ExhaustiveAlgorithm()
self.x.options.alignment_file = open(
get_data_path(
"q2-fragment-insertion/reference_alignment_tiny.fasta"), "r")
self.x.options.info_file = open(
get_data_path(
"q2-fragment-insertion/RAxML_info-reference-gg-raxml-bl.info"),
"r")
self.x.options.tree_file = open(
get_data_path(
"q2-fragment-insertion/reference_phylogeny_tiny.nwk"), "r")
self.x.options.fragment_file = open(
get_data_path(
"q2-fragment-insertion/input_fragments.fasta"), "r")
self.x.options.outdir = tempfile.mkdtemp()
self.x.options.placement_size = 20
def resetSepp(self):
sepp.scheduler._jobPool = None
self.x = ExhaustiveAlgorithm()
self.x.options.alignment_file = open(
get_data_path(
"q2-fragment-insertion/reference_alignment_tiny.fasta"), "r")
self.x.options.info_file = open(
get_data_path(
"q2-fragment-insertion/RAxML_info-reference-gg-raxml-bl.info"),
"r")
self.x.options.tree_file = open(
get_data_path(
"q2-fragment-insertion/reference_phylogeny_tiny.nwk"), "r")
self.x.options.outdir = tempfile.mkdtemp()
suff_bit = "-64" if sys.maxsize > 2**32 else "-32"
if platform.system() == 'Darwin':
suff_bit = ""
for prog in ['hmmalign', 'hmmbuild', 'hmmsearch', 'pplacer']:
setattr(self.x.options, prog, Namespace(
path=get_data_path("../../../tools/bundled/%s/%s%s" % (
platform.system(), prog, suff_bit))))
def testReadOnlySubAlignment(self):
alg = MutableAlignment()
alg.read_filepath(get_data_path("mock/pyrg/sate.fasta"))
subset = [
'NC_008701_720717_722309', 'NC_013156_149033_150643',
'NC_013887_802739_801129'
]
readonly_subalignment = ReadonlySubalignment(subset, alg)
assert len(readonly_subalignment) == 3, len(readonly_subalignment)
assert set(readonly_subalignment.keys()) == set(
readonly_subalignment.get_sequence_names()) == set(subset), \
"Subalignment keys not matching given keys %s vs %s" % (
list(readonly_subalignment.keys()), subset)
for (k, s) in list(readonly_subalignment.items()):
assert k in subset, \
"%s not found in subset but returned by subalignment" % k
assert s == alg[k], \
"sequence associated with %s not matching parent alignment" % k
try:
readonly_subalignment[2] = "ACGT"
assert False, "Readony alignment is successfully modified. "
except TypeError:
pass
assert readonly_subalignment.get_length() == alg.get_length(), \
"alignment length should not change"
assert readonly_subalignment.is_aligned() is True
assert readonly_subalignment.is_all_gap(2) is True, \
"Site 2 should be all gaps"
assert readonly_subalignment.is_all_gap(150) is False, \
"Site 100 should not be all gaps"
readonly_subalignment.write_to_path(
self.fp_dummy1) # "mock/pyrg/sate.sub.fasta"
mutable_subalignment = readonly_subalignment.get_mutable_alignment()
mutable_subalignment.delete_all_gap()
assert all([
not mutable_subalignment.is_all_gap(i)
for i in range(0, mutable_subalignment.get_length())
])
def testConfigFileMissingFile(self):
# Just to make different test cases independent of each other.
config._options_singelton = None
# Diasable main config path for this test
config.main_config_path = self.fp_config
sys.argv = [sys.argv[0],
"-c", get_data_path("configs/test2.config"),
"-f", get_data_path("simulated/test.fas"),
"-a", get_data_path("simulated/test.small.fas")]
assert isinstance(options().config_file, filetypes) and \
options().config_file.name.endswith(
"data/configs/test2.config"), \
"Commandline option -c not read properly"
assert isinstance(options().alignment_file, filetypes) and\
options().alignment_file.name.endswith(
"data/simulated/test.small.fas"), \
"Config file option alignment not read properly"
assert isinstance(options().fragment_file, filetypes) and\
options().fragment_file.name.endswith(
"data/simulated/test.fas"), \
"Command-line option -f alignment not read properly"
def testReadOnlySubAlignment(self):
alg = MutableAlignment()
alg.read_filepath(get_data_path("mock/pyrg/sate.fasta"))
subset = ['NC_008701_720717_722309', 'NC_013156_149033_150643',
'NC_013887_802739_801129']
readonly_subalignment = ReadonlySubalignment(subset, alg)
assert len(readonly_subalignment) == 3, len(readonly_subalignment)
assert set(readonly_subalignment.keys()) == set(
readonly_subalignment.get_sequence_names()) == set(subset), \
"Subalignment keys not matching given keys %s vs %s" % (
list(readonly_subalignment.keys()), subset)
for (k, s) in list(readonly_subalignment.items()):
assert k in subset, \
"%s not found in subset but returned by subalignment" % k
assert s == alg[k], \
"sequence associated with %k not matching parent alignment" % k
try:
readonly_subalignment[2] = "ACGT"
assert False, "Readony alignment is successfully modified. "
except TypeError:
pass
assert readonly_subalignment.get_length() == alg.get_length(), \
"alignment length should not change"
assert readonly_subalignment.is_aligned() is True
assert readonly_subalignment.is_all_gap(2) is True, \
"Site 2 should be all gaps"
assert readonly_subalignment.is_all_gap(150) is False, \
"Site 100 should not be all gaps"
readonly_subalignment.write_to_path(
self.fp_dummy1) # "mock/pyrg/sate.sub.fasta"
mutable_subalignment = readonly_subalignment.get_mutable_alignment()
mutable_subalignment.delete_all_gap()
assert all([not mutable_subalignment.is_all_gap(i)
for i in range(0, mutable_subalignment.get_length())])
def test_id_collision_working(self):
self.x.options.fragment_file = open(
get_data_path("q2-fragment-insertion/input_fragments.fasta"), "r")
self.x.run()
self.assertTrue(self.x.results is not None)
def test_id_collision_working(self):
self.x.options.fragment_file = open(
get_data_path(
"q2-fragment-insertion/input_fragments.fasta"), "r")
self.x.run()
self.assertTrue(self.x.results is not None)
def testExtendedAlignment(self):
subset = [
"SFIF", "SFII", "SCFC", "SGHD", "SDCC", "SBGE", "SFBB", "SDI",
"SCGB", "SJGF", "SGBI", "SCJA", "SGAD", "SHEB", "SFHB", "SDJI",
"SHED", "SJJJ", "SBBE", "SCCH", "SDJB", "SDAC", "SHEH", "SFDC",
"SFEI", "SHHB", "SC", "SIAB", "SDDI", "SBCB", "SJB", "SEBD",
"SFGD", "SHA", "SIDA", "SGHI", "SGIB", "SBFJ", "SFIE", "SCJF",
"SJHJ", "SJBG", "SEJI", "SFFF", "SJ", "SIII", "SJHH", "SEIH",
"SBDC", "SHDJ", "SJDD", "SGDB", "SIHA", "SIBB", "SECC", "SCAD",
"SGBB", "SGIF", "SJHC", "SFCD", "SEAA", "SEFF", "SDFG", "SDJE",
"SCFG", "SFH", "SCJ", "SDDD", "SEGD", "SCIH", "SDAG", "SCJE",
"SFAJ", "SIDJ", "SE", "SHBC", "SJFF", "SCHD", "SBHA", "SEDF",
"SFAF", "SEDD", "SDHD", "SGJD", "SIBH", "SGDF", "SIFA", "SJGA",
"SIJB", "SFI", "SGA", "SBFC", "SBJA", "SFFC", "SFDH", "SFEE",
"SBDF", "SGBJ", "SDHE", "SJIB", "SHHI", "SIDE", "SJII"]
alg = MutableAlignment()
alg.read_filepath(get_data_path("simulated/test.fasta"))
alg.delete_all_gap()
tlen = alg.get_length()
frg = MutableAlignment()
frg.read_filepath(get_data_path("simulated/test.fas"))
# print frg.get_num_taxa()
pp = SeppProblem(list(alg.keys()))
pp.fragments = frg
pp.subalignment = alg
cp1 = SeppProblem(subset, pp)
cp2 = SeppProblem(list(set(alg.keys()) - set(subset)), pp)
cp1.fragments = ReadonlySubalignment(
[k for k in list(frg.keys()) if int(k[-1]) >= 9], frg)
cp2.fragments = ReadonlySubalignment(
[k for k in list(frg.keys()) if int(k[-1]) <= 1], frg)
cp1labels = cp1.write_subalignment_without_allgap_columns(
self.fp_dummy1) # tmp/cp1.fasta
cp2labels = cp2.write_subalignment_without_allgap_columns(
self.fp_dummy2) # tmp/cp2.fasta
tmp = MutableAlignment().read_filepath(self.fp_dummy1)
assert all([not tmp.is_all_gap(pos)
for pos in range(0, tmp.get_length())])
tmp = MutableAlignment().read_filepath(self.fp_dummy2)
assert all([not tmp.is_all_gap(pos)
for pos in range(0, tmp.get_length())])
cp1.fragments.write_to_path(self.fp_dummy3) # tmp/cp1.frags.fas
cp2.fragments.write_to_path(self.fp_dummy4) # tmp/cp2.frags.fas
'''We have done the hmmalign before.
don't worry about that right now'''
ext1 = ExtendedAlignment(cp1.fragments)
ext1.build_extended_alignment(
self.fp_dummy1,
get_data_path("tmp/cp1.extended.sto"))
ext1.relabel_original_columns(cp1labels)
ext2 = ExtendedAlignment(cp2.fragments)
ext2.build_extended_alignment(
self.fp_dummy2,
get_data_path("tmp/cp2.extended.sto"))
ext2.relabel_original_columns(cp2labels)
extmerger = ExtendedAlignment([])
extmerger.merge_in(ext1)
mixed = extmerger.merge_in(ext2)
extmerger.write_to_path(self.fp_dummy5) # tmp/extended.merged.fasta
assert extmerger.is_aligned(), "Merged alignment is not aligned"
in1 = len([x for x in ext1._col_labels if x < 0])
in2 = len([x for x in ext2._col_labels if x < 0])
assert (in1 + in2 + tlen - mixed) == extmerger.get_length(), \
("Lengths don't match up after merging. Merged:%d. Insertion1:%d "
"Insertion2:%d BaseLen:%d Mixed-insertion: %d") % (
extmerger.get_length(), in1, in2, tlen, mixed)
assert (in1 + in2 - mixed) == len(extmerger.get_insertion_columns()), \
("Columns are not correctly labeled after merging. Merged "
"insertion count:%d. Insertion1:%d Insertion2:%d Mixed-insertion:"
" %d") % (
len(list(extmerger.iter_insertion_columns())), in1, in1, mixed)
tmp = extmerger.get_base_readonly_alignment().get_mutable_alignment()
tmp.delete_all_gap()
assert tmp.is_aligned(), "merged alignment should be aligned!"
assert tmp.get_length() == tlen, "merged alignment has wrong length"
assert all([alg[k] == s for (k, s) in list(tmp.items())]), \
"merged alignment should match original alignment"
def test_fake_jobs(self):
self.x.options.fragment_file = open(
get_data_path(
"q2-fragment-insertion/input_fragments_tiny.fasta"), "r")
self.x.run()
self.assertTrue(self.x.results is not None)
def setUp(self):
# ensure necessary settings are made
sys.argv = [sys.argv[0], "-c", get_data_path("configs/test2.config")]
self.resetSepp()
def testExtendedAlignment(self):
subset = [
"SFIF", "SFII", "SCFC", "SGHD", "SDCC", "SBGE", "SFBB", "SDI",
"SCGB", "SJGF", "SGBI", "SCJA", "SGAD", "SHEB", "SFHB", "SDJI",
"SHED", "SJJJ", "SBBE", "SCCH", "SDJB", "SDAC", "SHEH", "SFDC",
"SFEI", "SHHB", "SC", "SIAB", "SDDI", "SBCB", "SJB", "SEBD",
"SFGD", "SHA", "SIDA", "SGHI", "SGIB", "SBFJ", "SFIE", "SCJF",
"SJHJ", "SJBG", "SEJI", "SFFF", "SJ", "SIII", "SJHH", "SEIH",
"SBDC", "SHDJ", "SJDD", "SGDB", "SIHA", "SIBB", "SECC", "SCAD",
"SGBB", "SGIF", "SJHC", "SFCD", "SEAA", "SEFF", "SDFG", "SDJE",
"SCFG", "SFH", "SCJ", "SDDD", "SEGD", "SCIH", "SDAG", "SCJE",
"SFAJ", "SIDJ", "SE", "SHBC", "SJFF", "SCHD", "SBHA", "SEDF",
"SFAF", "SEDD", "SDHD", "SGJD", "SIBH", "SGDF", "SIFA", "SJGA",
"SIJB", "SFI", "SGA", "SBFC", "SBJA", "SFFC", "SFDH", "SFEE",
"SBDF", "SGBJ", "SDHE", "SJIB", "SHHI", "SIDE", "SJII"
]
alg = MutableAlignment()
alg.read_filepath(get_data_path("simulated/test.fasta"))
alg.delete_all_gap()
tlen = alg.get_length()
frg = MutableAlignment()
frg.read_filepath(get_data_path("simulated/test.fas"))
# print frg.get_num_taxa()
pp = SeppProblem(list(alg.keys()))
pp.fragments = frg
pp.subalignment = alg
cp1 = SeppProblem(subset, pp)
cp2 = SeppProblem(list(set(alg.keys()) - set(subset)), pp)
cp1.fragments = ReadonlySubalignment(
[k for k in list(frg.keys()) if int(k[-1]) >= 9], frg)
cp2.fragments = ReadonlySubalignment(
[k for k in list(frg.keys()) if int(k[-1]) <= 1], frg)
cp1labels = cp1.write_subalignment_without_allgap_columns(
self.fp_dummy1) # tmp/cp1.fasta
cp2labels = cp2.write_subalignment_without_allgap_columns(
self.fp_dummy2) # tmp/cp2.fasta
tmp = MutableAlignment().read_filepath(self.fp_dummy1)
assert all(
[not tmp.is_all_gap(pos) for pos in range(0, tmp.get_length())])
tmp = MutableAlignment().read_filepath(self.fp_dummy2)
assert all(
[not tmp.is_all_gap(pos) for pos in range(0, tmp.get_length())])
cp1.fragments.write_to_path(self.fp_dummy3) # tmp/cp1.frags.fas
cp2.fragments.write_to_path(self.fp_dummy4) # tmp/cp2.frags.fas
'''We have done the hmmalign before.
don't worry about that right now'''
ext1 = ExtendedAlignment(cp1.fragments)
ext1.build_extended_alignment(self.fp_dummy1,
get_data_path("tmp/cp1.extended.sto"))
ext1.relabel_original_columns(cp1labels)
ext2 = ExtendedAlignment(cp2.fragments)
ext2.build_extended_alignment(self.fp_dummy2,
get_data_path("tmp/cp2.extended.sto"))
ext2.relabel_original_columns(cp2labels)
extmerger = ExtendedAlignment([])
extmerger.merge_in(ext1)
mixed = extmerger.merge_in(ext2)
extmerger.write_to_path(self.fp_dummy5) # tmp/extended.merged.fasta
assert extmerger.is_aligned(), "Merged alignment is not aligned"
in1 = len([x for x in ext1._col_labels if x < 0])
in2 = len([x for x in ext2._col_labels if x < 0])
assert (in1 + in2 + tlen - mixed) == extmerger.get_length(), \
("Lengths don't match up after merging. Merged:%d. Insertion1:%d "
"Insertion2:%d BaseLen:%d Mixed-insertion: %d") % (
extmerger.get_length(), in1, in2, tlen, mixed)
assert (in1 + in2 - mixed) == len(extmerger.get_insertion_columns()), \
("Columns are not correctly labeled after merging. Merged "
"insertion count:%d. Insertion1:%d Insertion2:%d Mixed-insertion:"
" %d") % (
len(list(extmerger.iter_insertion_columns())), in1, in1, mixed)
tmp = extmerger.get_base_readonly_alignment().get_mutable_alignment()
tmp.delete_all_gap()
assert tmp.is_aligned(), "merged alignment should be aligned!"
assert tmp.get_length() == tlen, "merged alignment has wrong length"
assert all([alg[k] == s for (k, s) in list(tmp.items())]), \
"merged alignment should match original alignment"
def setUp(self):
# ensure necessary settings are made
sys.argv = [sys.argv[0], "-c", get_data_path("configs/test2.config")]
self.resetSepp()
