def test_subpangraph_construction_full_graph(self):
nodes = [
pNode.Node(node_id=nid(0), base=b('A'), aligned_to=None),
pNode.Node(node_id=nid(1), base=b('A'), aligned_to=None),
pNode.Node(node_id=nid(2), base=b('C'), aligned_to=None),
pNode.Node(node_id=nid(3), base=b('A'), aligned_to=None),
pNode.Node(node_id=nid(4), base=b('T'), aligned_to=None)
]
sequences = {
pSeq.SequenceID('seq0'):
pSeq.Sequence(pSeq.SequenceID('seq0'),
[pSeq.SequencePath([*map(nid, [0, 1, 2, 3, 4])])],
pSeq.SequenceMetadata({'group': '1'}))
}
poagraph = pPoagraph.Poagraph(nodes, sequences)
translator = poa.PoagraphPOTranslator(poagraph,
[pSeq.SequenceID('seq0')])
actual_po_content = translator.get_input_po_content()
expected_po_content = "VERSION=pangenome\n" \
"NAME=pangenome\n" \
"TITLE=pangenome\n" \
"LENGTH=5\n" \
"SOURCECOUNT=1\n" \
"SOURCENAME=seq0\n" \
"SOURCEINFO=5 0 100 -1 seq0\n" \
"a:S0\n" \
"a:L0S0\n" \
"c:L1S0\n" \
"a:L2S0\n" \
"t:L3S0"
self.assertEqual(expected_po_content, actual_po_content)
def test_subpangraph_should_omit_edges_2(self):
nodes = [
pNode.Node(node_id=nid(0), base=b('A'), aligned_to=None),
pNode.Node(node_id=nid(1), base=b('C'), aligned_to=None),
pNode.Node(node_id=nid(2), base=b('C'), aligned_to=None)
]
sequences = {
pSeq.SequenceID('seq1'):
pSeq.Sequence(pSeq.SequenceID('seq1'),
[pSeq.SequencePath([*map(nid, [0, 2])])],
pSeq.SequenceMetadata({'group': '1'})),
pSeq.SequenceID('seq2'):
pSeq.Sequence(pSeq.SequenceID('seq2'),
[pSeq.SequencePath([*map(nid, [0, 1, 2])])],
pSeq.SequenceMetadata({'group': '1'}))
}
poagraph = pPoagraph.Poagraph(nodes, sequences)
translator = poa.PoagraphPOTranslator(poagraph,
[pSeq.SequenceID('seq1')])
actual_po_content = translator.get_input_po_content()
expected_po_content = "VERSION=pangenome\n" \
"NAME=pangenome\n" \
"TITLE=pangenome\n" \
"LENGTH=2\n" \
"SOURCECOUNT=1\n" \
"SOURCENAME=seq1\n" \
"SOURCEINFO=2 0 100 -1 seq1\n" \
"a:S0\n" \
"c:L0S0"
self.assertEqual(expected_po_content, actual_po_content)
def test_2_three_sequences(self):
fasta_path = self.fasta_dir + "test_2_three_sequences.fasta"
fasta_provider = FromFile(Path(fasta_path))
sequence_id_1 = pSeq.SequenceID("seq1")
self.raise_error_if_unequal(sequence_id_1, "ACTGGGTGGGA", fasta_provider)
sequence_id_2 = pSeq.SequenceID("seq2")
self.raise_error_if_unequal(sequence_id_2, "AA", fasta_provider)
sequence_id_3 = pSeq.SequenceID("seq3")
self.raise_error_if_unequal(sequence_id_3, "GT", fasta_provider)
class FromNCBITests(unittest.TestCase):
def setUp(self) -> None:
self.fasta_provider = FromNCBI(EmailAddress('*****@*****.**'),
use_cache=False)
@unittest.skip("slow test - internet connection required")
def test_0_get_10th_symbol_of_AB050936v1(self):
sequence_id = pSeq.SequenceID("AB050936.1", skip_part_before_dot=False)
actual_base = self.fasta_provider.get_base(sequence_id, 10)
path = Path('tests/data/fasta_providers/fasta_files/AB050936.1.fasta')
expected_base = self.read_sequence(path)[10]
self.assertEqual(expected_base, actual_base)
@unittest.skip("slow test - internet connection required")
def test_1_download_AB050936v1(self):
fasta_provider = FromNCBI(EmailAddress('*****@*****.**'), use_cache=False)
sequence_id = pSeq.SequenceID("AB050936.1", skip_part_before_dot=False)
actual_sequence = fasta_provider._download_from_ncbi(sequence_id)
p = Path('tests/data/fasta_providers/fasta_files/AB050936.1.fasta')
expected_sequence = self.read_sequence(p)
self.assertEqual(expected_sequence, actual_sequence)
@unittest.skip("slow test - internet connection required")
def test_2_failed_download(self):
fasta_provider = FromNCBI(EmailAddress('*****@*****.**'), use_cache=False)
sequence_id = ""
with self.assertRaises(Exception) as err:
_ = fasta_provider._download_from_ncbi(sequence_id)
self.assertEqual(
str(err),
f"Cannot download from Entrez sequence of ID: {sequence_id}")
@data((pSeq.SequenceID("plain", False), "plain"),
(pSeq.SequenceID("with.dot", False), "with.dot"),
(pSeq.SequenceID("with.two.dots", False), "with.two.dots"),
(pSeq.SequenceID("withv1", False), "with.1"))
@unpack
def test_3_guess_entrez_id(self, sequenceID: pSeq.SequenceID,
expected_guessed_entrez_id: str):
fasta_provider = FromNCBI(EmailAddress('*****@*****.**'), use_cache=False)
actual_guessed_entrez_id = fasta_provider._guess_ncbi_sequence_id(
sequenceID)
self.assertEqual(expected_guessed_entrez_id, actual_guessed_entrez_id)
def read_sequence(self, path: Path):
with open(path) as fasta_file_hanlder:
_ = fasta_file_hanlder.readline()
return fasta_file_hanlder.read().upper().replace("\n", "")
def test_1_download_sequence_and_save_to_cache(self):
fasta_provider = FromNCBI(EmailAddress('*****@*****.**'), use_cache=True)
cache_dir_path = pathtools.get_child_path(Path.cwd(), ".fastacache")
if cache_dir_path.exists():
shutil.rmtree(cache_dir_path)
sequence_id = pSeq.SequenceID("AB050936.1", skip_part_before_dot=False)
actual_sequence = fasta_provider.get_base(sequence_id, 15)
# cache directory creation
cache_directory_created = cache_dir_path.exists()
self.assertTrue(cache_directory_created)
# file creation
files_in_cache_dircetory = [*cache_dir_path.glob("*")]
expected_filepath = pathtools.get_child_path(cache_dir_path,
f"{sequence_id}.fasta")
file_created_in_cache = expected_filepath in files_in_cache_dircetory
self.assertTrue(file_created_in_cache)
# file content
control_fasta_path = Path(
'tests/data/fasta_providers/fasta_ncbi/AB050936.1.fasta')
with open(control_fasta_path) as fasta_file_hanlder:
expected_content = fasta_file_hanlder.read()
with open(expected_filepath) as fasta_file_handler:
actual_content = fasta_file_handler.read()
self.assertEqual(expected_content, actual_content)
def test_1_download_AB050936v1(self):
fasta_provider = FromNCBI(EmailAddress('*****@*****.**'), use_cache=False)
sequence_id = pSeq.SequenceID("AB050936.1", skip_part_before_dot=False)
actual_sequence = fasta_provider._download_from_ncbi(sequence_id)
p = Path('tests/data/fasta_providers/fasta_files/AB050936.1.fasta')
expected_sequence = self.read_sequence(p)
self.assertEqual(expected_sequence, actual_sequence)
def test_1_one_sequence(self):
fasta_path = self.fasta_dir + "test_1_one_sequence.fasta"
fasta_provider = FromFile(Path(fasta_path))
sequence_id = pSeq.SequenceID("seq1")
expected_sequence = self.read_sequence(fasta_path)
self.raise_error_if_unequal(sequence_id, expected_sequence, fasta_provider)
def test_1_one_sequence_one_file_in_zip(self):
fasta_path = self.fasta_dir + "test_1_one_sequence_one_file_in_zip.zip"
fasta_provider = FromFile(Path(fasta_path))
sequence_id = pSeq.SequenceID("seq1")
expected_sequence = "ACTGGGTGGGA"
self.raise_error_if_unequal(sequence_id, expected_sequence,
fasta_provider)
def test_1_typical_pangraph(self):
expected_po_content_path = Path(self.po_files_dir + "test_1.po")
poagraph_nodes = [
pNode.Node(node_id=nid(0), base=bid('A'), aligned_to=nid(1)),
pNode.Node(node_id=nid(1), base=bid('G'), aligned_to=nid(0)),
pNode.Node(node_id=nid(2), base=bid('C'), aligned_to=nid(3)),
pNode.Node(node_id=nid(3), base=bid('G'), aligned_to=nid(2)),
pNode.Node(node_id=nid(4), base=bid('A'), aligned_to=nid(5)),
pNode.Node(node_id=nid(5), base=bid('T'), aligned_to=nid(4)),
pNode.Node(node_id=nid(6), base=bid('G'), aligned_to=None),
pNode.Node(node_id=nid(7), base=bid('G'), aligned_to=None),
pNode.Node(node_id=nid(8), base=bid('A'), aligned_to=nid(9)),
pNode.Node(node_id=nid(9), base=bid('C'), aligned_to=nid(10)),
pNode.Node(node_id=nid(10), base=bid('G'), aligned_to=nid(11)),
pNode.Node(node_id=nid(11), base=bid('T'), aligned_to=nid(8)),
pNode.Node(node_id=nid(12), base=bid('A'), aligned_to=nid(13)),
pNode.Node(node_id=nid(13), base=bid('C'), aligned_to=nid(12)),
pNode.Node(node_id=nid(14), base=bid('T'), aligned_to=None),
pNode.Node(node_id=nid(15), base=bid('A'), aligned_to=nid(16)),
pNode.Node(node_id=nid(16), base=bid('C'), aligned_to=nid(17)),
pNode.Node(node_id=nid(17), base=bid('G'), aligned_to=nid(15))
]
poagraph_sequences = {
pSeq.SequenceID('seq0'):
pSeq.Sequence(pSeq.SequenceID('seq0'), [
pSeq.SequencePath([*map(nid, [0, 2, 4, 6, 7, 8, 12, 14, 16])])
], pSeq.SequenceMetadata({'group': '1'})),
pSeq.SequenceID('seq1'):
pSeq.Sequence(pSeq.SequenceID('seq1'),
[pSeq.SequencePath([*map(nid, [1, 2, 5, 6, 7, 9])])],
pSeq.SequenceMetadata({'group': '1'})),
pSeq.SequenceID('seq2'):
pSeq.Sequence(
pSeq.SequenceID('seq2'),
[pSeq.SequencePath([*map(nid, [3, 4, 6, 7, 10, 12, 14, 17])])],
pSeq.SequenceMetadata({'group': '1'})),
pSeq.SequenceID('seq3'):
pSeq.Sequence(pSeq.SequenceID('seq3'),
[pSeq.SequencePath([*map(nid, [11, 13, 14, 15])])],
pSeq.SequenceMetadata({'group': '1'})),
}
poagraph = pPoagraph.Poagraph(poagraph_nodes, poagraph_sequences)
actual_po_content = PangenomePO.poagraph_to_PangenomePO(poagraph)
expected_po_content = pathtools.get_file_content(
expected_po_content_path)
self.assertEqual(expected_po_content, actual_po_content)
def test_subpangraph_construction_from_pangraph_keep_seq_0_1(self):
translator = poa.PoagraphPOTranslator(
self.poagraph, [pSeq.SequenceID('seq0'),
pSeq.SequenceID('seq1')])
actual_po_content = translator.get_input_po_content()
expected_po_content = "VERSION=pangenome\n"\
"NAME=pangenome\n"\
"TITLE=pangenome\n"\
"LENGTH=9\n"\
"SOURCECOUNT=2\n"\
"SOURCENAME=seq0\n"\
"SOURCEINFO=7 0 0 -1 seq0\n"\
"SOURCENAME=seq1\n"\
"SOURCEINFO=5 1 100 -1 seq1\n"\
"t:S0\n"\
"a:L0S0S1\n"\
"a:L1S0S1\n"\
"a:L2S0A4\n"\
"c:L2S1A3\n"\
"a:L3L4S0S1\n"\
"c:L5S0A7\n"\
"t:L5S1A6\n"\
"a:L6S0"
self.assertEqual(expected_po_content, actual_po_content)
def setUp(self):
nodes = [
pNode.Node(
node_id=nid(0),
base=b('T'),
aligned_to=None,
),
pNode.Node(node_id=nid(1), base=b('A'), aligned_to=nid(2)),
pNode.Node(node_id=nid(2), base=b('G'), aligned_to=nid(1)),
pNode.Node(node_id=nid(3), base=b('A'), aligned_to=nid(4)),
pNode.Node(node_id=nid(4), base=b('C'), aligned_to=nid(3)),
pNode.Node(node_id=nid(5), base=b('A'), aligned_to=nid(6)),
pNode.Node(node_id=nid(6), base=b('C'), aligned_to=nid(7)),
pNode.Node(node_id=nid(7), base=b('G'), aligned_to=nid(8)),
pNode.Node(node_id=nid(8), base=b('T'), aligned_to=nid(5)),
pNode.Node(node_id=nid(9), base=b('A'), aligned_to=None),
pNode.Node(node_id=nid(10), base=b('C'), aligned_to=nid(11)),
pNode.Node(node_id=nid(11), base=b('T'), aligned_to=nid(10)),
pNode.Node(node_id=nid(12), base=b('G'), aligned_to=None),
pNode.Node(node_id=nid(13), base=b('A'), aligned_to=nid(14)),
pNode.Node(node_id=nid(14), base=b('C'), aligned_to=nid(13))
]
sequences = {
pSeq.SequenceID('seq0'):
pSeq.Sequence(
pSeq.SequenceID('seq0'),
[pSeq.SequencePath([*map(nid, [0, 1, 3, 5, 9, 10, 13])])],
pSeq.SequenceMetadata({'group': '1'})),
pSeq.SequenceID('seq1'):
pSeq.Sequence(pSeq.SequenceID('seq1'),
[pSeq.SequencePath([*map(nid, [1, 3, 6, 9, 11])])],
pSeq.SequenceMetadata({'group': '1'})),
pSeq.SequenceID('seq2'):
pSeq.Sequence(
pSeq.SequenceID('seq2'),
[pSeq.SequencePath([*map(nid, [2, 4, 7, 9, 11, 12])])],
pSeq.SequenceMetadata({'group': '1'})),
pSeq.SequenceID('seq3'):
pSeq.Sequence(
pSeq.SequenceID('seq3'),
[pSeq.SequencePath([*map(nid, [2, 4, 8, 9, 11, 12, 14])])],
pSeq.SequenceMetadata({'group': '1'})),
}
self.poagraph = pPoagraph.Poagraph(nodes, sequences)
def setUp(self):
self.fasta_dir = 'tests/output/fasta_files/'
poagraph_nodes = [
pNode.Node(node_id=nid(0), base=bid('A'), aligned_to=nid(1)),
pNode.Node(node_id=nid(1), base=bid('G'), aligned_to=nid(0)),
pNode.Node(node_id=nid(2), base=bid('C'), aligned_to=nid(3)),
pNode.Node(node_id=nid(3), base=bid('G'), aligned_to=nid(2)),
pNode.Node(node_id=nid(4), base=bid('A'), aligned_to=nid(5)),
pNode.Node(node_id=nid(5), base=bid('T'), aligned_to=nid(4)),
pNode.Node(node_id=nid(6), base=bid('G'), aligned_to=None),
pNode.Node(node_id=nid(7), base=bid('G'), aligned_to=None),
pNode.Node(node_id=nid(8), base=bid('A'), aligned_to=nid(9)),
pNode.Node(node_id=nid(9), base=bid('C'), aligned_to=nid(10)),
pNode.Node(node_id=nid(10), base=bid('G'), aligned_to=nid(11)),
pNode.Node(node_id=nid(11), base=bid('T'), aligned_to=nid(8)),
pNode.Node(node_id=nid(12), base=bid('A'), aligned_to=nid(13)),
pNode.Node(node_id=nid(13), base=bid('C'), aligned_to=nid(12)),
pNode.Node(node_id=nid(14), base=bid('T'), aligned_to=None),
pNode.Node(node_id=nid(15), base=bid('A'), aligned_to=nid(16)),
pNode.Node(node_id=nid(16), base=bid('C'), aligned_to=nid(17)),
pNode.Node(node_id=nid(17), base=bid('G'), aligned_to=nid(15))
]
poagraph_sequences = {
pSeq.SequenceID('seq0'):
pSeq.Sequence(pSeq.SequenceID('seq0'), [
pSeq.SequencePath([*map(nid, [0, 2, 4, 6, 7, 8, 12, 14, 16])])
], pSeq.SequenceMetadata({'group': '1'})),
pSeq.SequenceID('seq1'):
pSeq.Sequence(pSeq.SequenceID('seq1'), [],
pSeq.SequenceMetadata({'group': '1'})),
pSeq.SequenceID('seq2'):
pSeq.Sequence(pSeq.SequenceID('seq2'), [
pSeq.SequencePath([*map(nid, [3, 4, 6, 7, 10, 12])]),
pSeq.SequencePath([*map(nid, [14, 17])])
], pSeq.SequenceMetadata({'group': '1'})),
pSeq.SequenceID('seq3'):
pSeq.Sequence(pSeq.SequenceID('seq3'), [
pSeq.SequencePath([*map(nid, [11])]),
pSeq.SequencePath([*map(nid, [13, 14, 15])])
], pSeq.SequenceMetadata({'group': '1'})),
}
self.poagraph = pPoagraph.Poagraph(poagraph_nodes, poagraph_sequences)
def test_read_consensus_path_seq1_only_in_input(self):
translator = poa.PoagraphPOTranslator(self.poagraph,
[pSeq.SequenceID('seq1')])
_ = translator.get_input_po_content()
poa_lines = [
"VERSION=pangenome\n", "NAME=pangenome\n", "TITLE=pangenome\n",
"LENGTH=5\n", "SOURCECOUNT=2\n", "SOURCENAME=seq1\n",
"SOURCEINFO=5 0 100 0 seq1\n", "SOURCENAME=CONSENS0\n",
"SOURCEINFO=5 0 100 0 CONSENS0\n", "a:S0S1\n", "a:L0S0S1\n",
"c:L1S0S1\n", "a:L2S0S1\n", "t:L2S0S1"
]
actual_consensus_path = translator.read_consensus_paths(poa_lines, [0])
expected_consensus_path = [1, 3, 6, 9, 11]
self.assertEqual(expected_consensus_path,
actual_consensus_path[0].path)
def test_subpangraph_unfilled_nodes(self):
symbol_for_uknown = '?'
nodes = [
pNode.Node(node_id=nid(0), base=b('A'), aligned_to=nid(1)),
pNode.Node(node_id=nid(1), base=b('C'), aligned_to=nid(0)),
pNode.Node(node_id=nid(2), base=b('G'), aligned_to=None),
pNode.Node(node_id=nid(3),
base=b(symbol_for_uknown),
aligned_to=None),
pNode.Node(node_id=nid(4),
base=b(symbol_for_uknown),
aligned_to=None),
pNode.Node(node_id=nid(5), base=b('G'), aligned_to=None),
pNode.Node(node_id=nid(6), base=b('C'), aligned_to=None),
pNode.Node(node_id=nid(7), base=b('A'), aligned_to=None),
pNode.Node(node_id=nid(5), base=b('T'), aligned_to=None)
]
sequences = {
pSeq.SequenceID('seq1'):
pSeq.Sequence(pSeq.SequenceID('seq1'),
[pSeq.SequencePath([*map(nid, [0, 2, 3, 4, 7, 8])])],
pSeq.SequenceMetadata({'group': '1'})),
pSeq.SequenceID('seq2'):
pSeq.Sequence(pSeq.SequenceID('seq2'),
[pSeq.SequencePath([*map(nid, [1, 2, 5, 6, 7, 8])])],
pSeq.SequenceMetadata({'group': '1'}))
}
poagraph = pPoagraph.Poagraph(nodes, sequences)
translator = poa.PoagraphPOTranslator(
poagraph, [pSeq.SequenceID('seq1'),
pSeq.SequenceID('seq2')])
actual_po_content = translator.get_input_po_content()
expected_po_content = "VERSION=pangenome\n" \
"NAME=pangenome\n" \
"TITLE=pangenome\n" \
"LENGTH=9\n" \
"SOURCECOUNT=2\n" \
"SOURCENAME=seq1\n" \
"SOURCEINFO=6 0 100 -1 seq1\n" \
"SOURCENAME=seq2\n" \
"SOURCEINFO=6 1 100 -1 seq2\n" \
"a:S0A1\n" \
"c:S1A0\n" \
"g:L0L1S0S1\n" \
f"{symbol_for_uknown}:L2S0\n" \
f"{symbol_for_uknown}:L3S0\n" \
"g:L2S1\n" \
"c:L5S1\n" \
"a:L4L6S0S1\n" \
"t:L7S0S1"
self.assertEqual(expected_po_content, actual_po_content)
def test_2_read_seqeunce_from_cache_instead_downloading(self):
fasta_provider = FromNCBI(EmailAddress('*****@*****.**'), use_cache=True)
cache_dir_path = pathtools.get_child_path(Path.cwd(), ".fastacache")
if cache_dir_path.exists():
shutil.rmtree(cache_dir_path)
cache_dir_path.mkdir()
sequence_id = pSeq.SequenceID("seq1")
fake_sequence = "foo"
expected_base = pNode.Base("o")
fake_fasta_path = pathtools.get_child_path(cache_dir_path,
f"{sequence_id}.fasta")
with open(fake_fasta_path, 'w') as fake_fasta_handler:
fake_fasta_handler.write(f">{sequence_id} cached\n{fake_sequence}")
actual_base = fasta_provider.get_base(sequence_id, 2)
self.assertEqual(expected_base, actual_base)
def test_subpangraph_construction_from_pangraph_keep_seq3(self):
translator = poa.PoagraphPOTranslator(self.poagraph,
[pSeq.SequenceID('seq3')])
actual_po_content = translator.get_input_po_content()
expected_po_content = "VERSION=pangenome\n" \
"NAME=pangenome\n" \
"TITLE=pangenome\n" \
"LENGTH=7\n" \
"SOURCECOUNT=1\n" \
"SOURCENAME=seq3\n" \
"SOURCEINFO=7 0 100 -1 seq3\n" \
"g:S0\n" \
"c:L0S0\n" \
"t:L1S0\n" \
"a:L2S0\n" \
"t:L3S0\n" \
"g:L4S0\n" \
"c:L5S0"
self.assertEqual(expected_po_content, actual_po_content)
def test_0_get_10th_symbol_of_AB050936v1(self):
sequence_id = pSeq.SequenceID("AB050936.1", skip_part_before_dot=False)
actual_base = self.fasta_provider.get_base(sequence_id, 10)
path = Path('tests/data/fasta_providers/fasta_files/AB050936.1.fasta')
expected_base = self.read_sequence(path)[10]
self.assertEqual(expected_base, actual_base)
def test_2_consensuses_tree_fasta(self):
expected_consensuses_fasta_path = Path(self.fasta_dir +
"consensuses.fasta")
consensuses_tree = CT.ConsensusTree()
consensuses_tree.nodes = [
# all members set
CT.ConsensusNode(consensus_id=CT.ConsensusNodeID(0),
parent_node_id=CT.ConsensusNodeID(-1),
children_nodes_ids=[
CT.ConsensusNodeID(1),
CT.ConsensusNodeID(2)
],
sequences_ids=[
pSeq.SequenceID('seq0'),
pSeq.SequenceID('seq1'),
pSeq.SequenceID('seq2'),
pSeq.SequenceID('seq3')
],
mincomp=CT.CompatibilityToPath(0.5, P(1)),
compatibilities_to_all={
pSeq.SequenceID('seq0'):
CT.CompatibilityToPath(1.0, P(1)),
pSeq.SequenceID('seq1'):
CT.CompatibilityToPath(0.9, P(1)),
pSeq.SequenceID('seq2'):
CT.CompatibilityToPath(0.95, P(1)),
pSeq.SequenceID('seq3'):
CT.CompatibilityToPath(0.6, P(1))
},
consensus_path=pSeq.SequencePath([
nid(0),
nid(2),
nid(5),
nid(6),
nid(10),
nid(12),
nid(13),
nid(16)
])),
# no compatibilities to all, no mincomp
CT.ConsensusNode(consensus_id=CT.ConsensusNodeID(1),
parent_node_id=CT.ConsensusNodeID(0),
sequences_ids=[
pSeq.SequenceID('seq0'),
pSeq.SequenceID('seq1'),
pSeq.SequenceID('seq2')
],
consensus_path=pSeq.SequencePath([
nid(0),
nid(2),
nid(3),
nid(6),
nid(10),
nid(11),
nid(13),
nid(17)
]))
]
actual_consensuses_fasta_content = PangenomeFASTA.consensuses_tree_to_fasta(
self.poagraph, consensuses_tree)
expected_consensuses_fasta_content = pathtools.get_file_content(
expected_consensuses_fasta_path)
self.assertEqual(expected_consensuses_fasta_content,
actual_consensuses_fasta_content)
def test_2_consensuses_and_empty_sequences(self):
expected_po_content_path = Path(self.po_files_dir + "test_2.po")
poagraph_nodes = [
pNode.Node(node_id=nid(0), base=bid('C'), aligned_to=nid(1)),
pNode.Node(node_id=nid(1), base=bid('T'), aligned_to=nid(0)),
pNode.Node(node_id=nid(2), base=bid('A'), aligned_to=nid(3)),
pNode.Node(node_id=nid(3), base=bid('G'), aligned_to=nid(2)),
pNode.Node(node_id=nid(4), base=bid('C'), aligned_to=None),
pNode.Node(node_id=nid(5), base=bid('T'), aligned_to=None),
pNode.Node(node_id=nid(6), base=bid('A'), aligned_to=nid(7)),
pNode.Node(node_id=nid(7), base=bid('T'), aligned_to=nid(6)),
pNode.Node(node_id=nid(8), base=bid('G'), aligned_to=None)
]
poagraph_sequences = {
pSeq.SequenceID('seq0'):
pSeq.Sequence(pSeq.SequenceID('seq0'),
[pSeq.SequencePath([*map(nid, [0, 3, 4, 5, 6, 8])])],
pSeq.SequenceMetadata({'group': '1'})),
pSeq.SequenceID('seq1'):
pSeq.Sequence(pSeq.SequenceID('seq1'),
[pSeq.SequencePath([*map(nid, [1, 2, 4, 5, 7, 8])])],
pSeq.SequenceMetadata({'group': '1'})),
pSeq.SequenceID('seq2'):
pSeq.Sequence(pSeq.SequenceID('seq2'), [],
pSeq.SequenceMetadata({'group': '1'})),
pSeq.SequenceID('seq3'):
pSeq.Sequence(pSeq.SequenceID('seq3'), [],
pSeq.SequenceMetadata({'group': '1'})),
pSeq.SequenceID('CONSENS0'):
pSeq.Sequence(pSeq.SequenceID('CONSENS0'),
[pSeq.SequencePath([*map(nid, [0, 3, 4, 5, 7, 8])])],
None),
pSeq.SequenceID('CONSENS1'):
pSeq.Sequence(pSeq.SequenceID('CONSENS1'),
[pSeq.SequencePath([*map(nid, [1, 2, 4, 5, 6, 8])])],
None),
}
poagraph = pPoagraph.Poagraph(poagraph_nodes, poagraph_sequences)
actual_po_content = PangenomePO.poagraph_to_PangenomePO(poagraph)
expected_po_content = pathtools.get_file_content(
expected_po_content_path)
self.assertEqual(expected_po_content, actual_po_content)