def test_create_viterbi():
""" This test needs to be fixed, the HMM cannot be initialised in this way.
"""
assert 0, "Test not fixed"
my_hmm = HMM()
my_hmm.states = ['H', 'F']
# Initialisation
my_hmm.p_0 = {"H": 0.6, "F": 0.4}
# Feed Values to p_t
#my_hmm.p_t["START"] = {"H": 0.6, "F": 0.4}
my_hmm.p_t["H"] = {"H": 0.7, "F": 0.3}
my_hmm.p_t["F"] = {"H": 0.4, "F": 0.6}
# emissions
my_hmm.emissions = ["D", "C", "N"]
# emission probabilities
my_hmm.p_e['H'] = {"D": 0.1, "C": 0.4, "N": 0.5}
my_hmm.p_e['F'] = {"D": 0.6, "C": 0.3, "N": 0.1}
my_viterbi = Viterbi(my_hmm, "NCD")
if my_viterbi.viterbi() == "HHF":
print("Test SUCCESSFUL")
else:
print("Test FAILED")
def test_create_viterbi():
""" This test needs to be fixed, the HMM cannot be initialised in this way.
"""
assert 0, "Test not fixed"
my_hmm = HMM()
my_hmm.states = ['H', 'F']
# Initialisation
my_hmm.p_0 = {"H": 0.6, "F": 0.4}
# Feed Values to p_t
#my_hmm.p_t["START"] = {"H": 0.6, "F": 0.4}
my_hmm.p_t["H"] = {"H": 0.7, "F": 0.3}
my_hmm.p_t["F"] = {"H": 0.4, "F": 0.6}
# emissions
my_hmm.emissions = ["D", "C", "N"]
# emission probabilities
my_hmm.p_e['H'] = {"D":0.1, "C":0.4, "N":0.5}
my_hmm.p_e['F'] = {"D":0.6, "C":0.3, "N":0.1}
my_viterbi = Viterbi(my_hmm, "NCD")
if my_viterbi.viterbi() == "HHF":
print("Test SUCCESSFUL")
else:
print("Test FAILED")
def test_hmm_pickle():
test_repeat = repeat.Repeat(msa=TEST_REPEAT_MSA_DOUBLE)
test_hmm = HMM.create(input_format='repeat', repeat=test_repeat)
test_pickle = os.path.join(path(), "test.pickle")
test_hmm.write(test_pickle, 'pickle')
test_hmm_new = HMM.create(input_format='pickle', file=test_pickle)
assert test_hmm.hmmer == test_hmm_new.hmmer
assert test_hmm.alphabet == test_hmm_new.alphabet
if os.path.exists(test_pickle):
os.remove(test_pickle)
def test_hmm_pickle():
test_repeat = repeat.Repeat(msa = TEST_REPEAT_MSA_DOUBLE)
test_hmm = HMM.create(input_format = 'repeat', repeat = test_repeat)
test_pickle = os.path.join(path(), "test.pickle")
test_hmm.write(test_pickle, 'pickle')
test_hmm_new = HMM.create(input_format = 'pickle', file = test_pickle)
assert test_hmm.hmmer == test_hmm_new.hmmer
assert test_hmm.alphabet == test_hmm_new.alphabet
if os.path.exists(test_pickle):
os.remove(test_pickle)
def test_too_big_hmms():
test_repeat = repeat.Repeat(msa = TEST_RESULT_REPEAT_MSA_LONG)
test_hmm = HMM.create(input_format = 'repeat', repeat = test_repeat)
test_seq = sequence.Sequence(TEST_SEQUENCE_A)
test_optimized_repeat = test_seq.detect([test_hmm])
assert type(test_optimized_repeat) == repeat_list.RepeatList
assert len(test_optimized_repeat.repeats) == 0
test_repeat = repeat.Repeat(msa = TEST_RESULT_REPEAT_MSA_SUPER_LONG)
test_hmm = HMM.create(input_format = 'repeat', repeat = test_repeat)
test_seq = sequence.Sequence(TEST_SEQUENCE_SUPER_LONG_A)
test_optimized_repeat = test_seq.detect([test_hmm])
assert type(test_optimized_repeat) == repeat_list.RepeatList
assert len(test_optimized_repeat.repeats) == 0
def test_too_big_hmms():
test_repeat = repeat.Repeat(msa=TEST_RESULT_REPEAT_MSA_LONG)
test_hmm = HMM.create(input_format='repeat', repeat=test_repeat)
test_seq = sequence.Sequence(TEST_SEQUENCE_A)
test_optimized_repeat = test_seq.detect([test_hmm])
assert type(test_optimized_repeat) == repeat_list.RepeatList
assert len(test_optimized_repeat.repeats) == 0
test_repeat = repeat.Repeat(msa=TEST_RESULT_REPEAT_MSA_SUPER_LONG)
test_hmm = HMM.create(input_format='repeat', repeat=test_repeat)
test_seq = sequence.Sequence(TEST_SEQUENCE_SUPER_LONG_A)
test_optimized_repeat = test_seq.detect([test_hmm])
assert type(test_optimized_repeat) == repeat_list.RepeatList
assert len(test_optimized_repeat.repeats) == 0
def test_viterbi():
# {Test_name: [Original_TR_MSA, Sequence, Viterbi_path, Refined_TR_MSA], ... }
TEST = {
"Single": [["A", "A", "A"], "AAAAAA",
["M1", "M1", "M1", "M1", "M1", "M1"],
["A", "A", "A", "A", "A", "A"]],
"Double": [["AA", "AA"], "AAAAAA",
["M1", "M2", "M1", "M2", "M1", "M2"], ["AA", "AA", "AA"]],
"Long": [["ADKL", "ADKL"], "GYRADKLADKLADKL",
[
"N", "N", "N", "M1", "M2", "M3", "M4", "M1", "M2", "M3",
"M4", "M1", "M2", "M3", "M4"
], ["ADKL", "ADKL", "ADKL"]]
}
for test, p in TEST.items():
test_repeat = repeat.Repeat(msa=p[0])
test_hmm = HMM.create(input_format="repeat", repeat=test_repeat)
for iHMM in [test_hmm]:
# Detect TRs on self.seq with hmm using the Viterbi algorithm.
most_likely_path = iHMM.viterbi(p[1])
assert type(most_likely_path) == list
assert most_likely_path == p[2]
unaligned_msa = hmm_path_to_non_aligned_tandem_repeat_units(
p[1], most_likely_path, iHMM.l_effective)
assert unaligned_msa == p[3]
aligned_msa = repeat_align.realign_repeat(unaligned_msa)
assert aligned_msa == p[3]
def test_create_HMM_from_Repeat():
test_repeat = repeat.Repeat(msa=TEST_REPEAT_MSA_DOUBLE)
test_hmm = HMM.create(input_format='repeat', repeat=test_repeat)
assert test_hmm.l_effective == 2
assert set(test_hmm.states) == set(TEST_HMM_STATES_DOUBLE)
assert test_hmm.p_0 == TEST_HMM_P0_DOUBLE
#assert test_hmm.p_t == TEST_HMM_P0_DOUBLE
test_repeat = repeat.Repeat(msa=TEST_REPEAT_MSA_SINGLE)
test_hmm = HMM.create(input_format='repeat', repeat=test_repeat)
assert test_hmm.l_effective == 1
assert test_hmm.states == TEST_HMM_STATES_SINGLE
assert test_hmm.p_0 == TEST_HMM_P0_SINGLE
def test_sequence_pickle():
test_seq = sequence.Sequence(TEST_SEQUENCE)
test_pickle = os.path.join(path(), "test.pickle")
test_seq.write(test_pickle, 'pickle')
test_seq_new = sequence.Sequence.create(test_pickle, 'pickle')
assert test_seq.seq == test_seq_new.seq
test_repeat = repeat.Repeat(msa=TEST_REPEAT_MSA_DOUBLE)
test_hmm = HMM.create(input_format='repeat', repeat=test_repeat)
test_optimized_repeat = test_seq.detect([test_hmm])
test_seq.set_repeatlist(test_optimized_repeat, TEST_SEQUENCE_TAG)
assert type(test_optimized_repeat) == repeat_list.RepeatList
assert list(test_seq.d_repeatlist.keys()) == [TEST_SEQUENCE_TAG]
assert type(
test_seq.d_repeatlist[TEST_SEQUENCE_TAG]) == repeat_list.RepeatList
assert test_seq.d_repeatlist[TEST_SEQUENCE_TAG].repeats
test_retrieved_repeatlist = test_seq.get_repeatlist(TEST_SEQUENCE_TAG)
assert test_retrieved_repeatlist == test_optimized_repeat
test_seq.write(test_pickle, 'pickle')
test_seq_new = sequence.Sequence.create(test_pickle, 'pickle')
assert test_seq.d_repeatlist.keys() == test_seq_new.d_repeatlist.keys()
assert test_seq.d_repeatlist[TEST_SEQUENCE_TAG].repeats[
0].msa == test_seq_new.d_repeatlist[TEST_SEQUENCE_TAG].repeats[0].msa
if os.path.exists(test_pickle):
os.remove(test_pickle)
def test_detect_repeats_with_repeat():
test_repeat = repeat.Repeat(msa = TEST_REPEAT_MSA_DOUBLE)
test_hmm = HMM.create(input_format = 'repeat', repeat = test_repeat)
test_seq = sequence.Sequence(TEST_SEQUENCE)
test_optimized_repeat = test_seq.detect([test_hmm])
assert type(test_optimized_repeat) == repeat_list.RepeatList
assert len(test_optimized_repeat.repeats) == 1
assert test_optimized_repeat.repeats[0].msa == TEST_RESULT_REPEAT_MSA_DOUBLE
test_repeat = repeat.Repeat(msa = TEST_REPEAT_MSA_SINGLE)
test_hmm = HMM.create(input_format = 'repeat', repeat = test_repeat)
test_optimized_repeat = test_seq.detect([test_hmm])
assert type(test_optimized_repeat) == repeat_list.RepeatList
assert len(test_optimized_repeat.repeats) == 1
assert test_optimized_repeat.repeats[0].msa == TEST_RESULT_REPEAT_MSA_SINGLE
def test_sequence_pickle():
test_seq = sequence.Sequence(TEST_SEQUENCE)
test_pickle = os.path.join(path(), "test.pickle")
test_seq.write(test_pickle, 'pickle')
test_seq_new = sequence.Sequence.create(test_pickle, 'pickle')
assert test_seq.seq == test_seq_new.seq
test_repeat = repeat.Repeat(msa = TEST_REPEAT_MSA_DOUBLE)
test_hmm = HMM.create(input_format = 'repeat', repeat = test_repeat)
test_optimized_repeat = test_seq.detect([test_hmm])
test_seq.set_repeatlist(test_optimized_repeat, TEST_SEQUENCE_TAG)
assert type(test_optimized_repeat) == repeat_list.RepeatList
assert list(test_seq.d_repeatlist.keys()) == [TEST_SEQUENCE_TAG]
assert type(test_seq.d_repeatlist[TEST_SEQUENCE_TAG]) == repeat_list.RepeatList
assert test_seq.d_repeatlist[TEST_SEQUENCE_TAG].repeats
test_retrieved_repeatlist = test_seq.get_repeatlist(TEST_SEQUENCE_TAG)
assert test_retrieved_repeatlist == test_optimized_repeat
test_seq.write(test_pickle, 'pickle')
test_seq_new = sequence.Sequence.create(test_pickle, 'pickle')
assert test_seq.d_repeatlist.keys() == test_seq_new.d_repeatlist.keys()
assert test_seq.d_repeatlist[TEST_SEQUENCE_TAG].repeats[0].msa == test_seq_new.d_repeatlist[TEST_SEQUENCE_TAG].repeats[0].msa
if os.path.exists(test_pickle):
os.remove(test_pickle)
def test_single_hmm_without_id_read(path):
test_dict_list = list(HMM.read(os.path.join(path, TEST_FILE_WITHOUT_ID)))
assert len(test_dict_list) == 1
test_dict = test_dict_list[0]
compare_carcinustatin(test_dict)
assert test_dict[ID_KEY_NAME] is None
def test_create_HMM_from_Repeat():
test_repeat = repeat.Repeat(msa = TEST_REPEAT_MSA_DOUBLE)
test_hmm = HMM.create(input_format = 'repeat', repeat = test_repeat)
assert test_hmm.l_effective == 2
assert set(test_hmm.states) == set(TEST_HMM_STATES_DOUBLE)
assert test_hmm.p_0 == TEST_HMM_P0_DOUBLE
#assert test_hmm.p_t == TEST_HMM_P0_DOUBLE
test_repeat = repeat.Repeat(msa = TEST_REPEAT_MSA_SINGLE)
test_hmm = HMM.create(input_format = 'repeat', repeat = test_repeat)
assert test_hmm.l_effective == 1
assert test_hmm.states == TEST_HMM_STATES_SINGLE
assert test_hmm.p_0 == TEST_HMM_P0_SINGLE
def test_single_hmm_without_id_read(path):
test_dict_list = list(HMM.read(os.path.join(path, TEST_FILE_WITHOUT_ID)))
assert len(test_dict_list) == 1
test_dict = test_dict_list[0]
compare_carcinustatin(test_dict)
assert test_dict[ID_KEY_NAME] is None
def test_detect_repeats_with_repeat():
test_repeat = repeat.Repeat(msa=TEST_REPEAT_MSA_DOUBLE)
test_hmm = HMM.create(input_format='repeat', repeat=test_repeat)
test_seq = sequence.Sequence(TEST_SEQUENCE)
test_optimized_repeat = test_seq.detect([test_hmm])
assert type(test_optimized_repeat) == repeat_list.RepeatList
assert len(test_optimized_repeat.repeats) == 1
assert test_optimized_repeat.repeats[
0].msa == TEST_RESULT_REPEAT_MSA_DOUBLE
test_repeat = repeat.Repeat(msa=TEST_REPEAT_MSA_SINGLE)
test_hmm = HMM.create(input_format='repeat', repeat=test_repeat)
test_optimized_repeat = test_seq.detect([test_hmm])
assert type(test_optimized_repeat) == repeat_list.RepeatList
assert len(test_optimized_repeat.repeats) == 1
assert test_optimized_repeat.repeats[
0].msa == TEST_RESULT_REPEAT_MSA_SINGLE
def test_init_with_repeat():
""" This test needs to be fixed.
"""
assert 0, "Test not fixed"
my_TR = Repeat(begin = 0, msa = ['A-G', 'ACG', 'ACG'], sequence_type = 'DNA')
my_hmm = HMM.create(repeat=my_TR)
from . import sequence
my_sequence = sequence.Sequence()
my_viterbi = Viterbi(my_hmm, my_sequence.sequence)
v = my_viterbi.viterbi()
"".join(v)
def test_init_with_repeat():
""" This test needs to be fixed.
"""
assert 0, "Test not fixed"
my_TR = Repeat(begin=0, msa=['A-G', 'ACG', 'ACG'], sequence_type='DNA')
my_hmm = HMM.create(repeat=my_TR)
from . import sequence
my_sequence = sequence.Sequence()
my_viterbi = Viterbi(my_hmm, my_sequence.sequence)
v = my_viterbi.viterbi()
"".join(v)
def test_viterbi():
# {Test_name: [Original_TR_MSA, Sequence, Viterbi_path, Refined_TR_MSA], ... }
TEST = {"Single": [["A","A","A"], "AAAAAA", ["M1","M1","M1","M1","M1","M1"], ["A","A","A","A","A","A"]],
"Double": [["AA","AA"], "AAAAAA", ["M1","M2","M1","M2","M1","M2"], ["AA","AA","AA"]],
"Long": [["ADKL","ADKL"], "GYRADKLADKLADKL", ["N","N","N","M1","M2","M3","M4","M1","M2","M3","M4","M1","M2","M3","M4"], ["ADKL","ADKL","ADKL"]]
}
for test, p in TEST.items():
test_repeat = repeat.Repeat(msa = p[0])
test_hmm = HMM.create(input_format = "repeat", repeat = test_repeat)
for iHMM in [test_hmm]:
# Detect TRs on self.seq with hmm using the Viterbi algorithm.
most_likely_path = iHMM.viterbi(p[1])
assert type(most_likely_path) == list
assert most_likely_path == p[2]
unaligned_msa = hmm_path_to_non_aligned_tandem_repeat_units(p[1], most_likely_path, iHMM.l_effective)
assert unaligned_msa == p[3]
aligned_msa = repeat_align.realign_repeat(unaligned_msa)
assert aligned_msa == p[3]
def test_detect_repeats_with_hmm():
test_hmm = HMM.create(input_format='hmmer',
file=os.path.join(path(), TEST_FILE_WITH_ID))
test_seq = sequence.Sequence(TEST_SEQUENCE)
test_optimized_repeat = test_seq.detect([test_hmm])
def test_single_hmm_no_id_with_query_read(path):
test_dict_list = list(HMM.read(os.path.join(path, TEST_FILE_WITHOUT_ID),
id=CARCINUSTATIN_ID))
assert len(test_dict_list) == 0
def test_detect_repeats_with_hmm():
test_hmm = HMM.create(input_format = 'hmmer', file = os.path.join(path(), TEST_FILE_WITH_ID))
test_seq = sequence.Sequence(TEST_SEQUENCE)
test_optimized_repeat = test_seq.detect([test_hmm])
def test_single_hmm_with_wrong_query_read(path):
test_dict_list = list(HMM.read(os.path.join(path, TEST_FILE_WITH_ID),
id=WRONG_CARCINUSTATIN_ID))
assert len(test_dict_list) == 0
def test_single_hmm_with_wrong_query_read(path):
test_dict_list = list(
HMM.read(os.path.join(path, TEST_FILE_WITH_ID),
id=WRONG_CARCINUSTATIN_ID))
assert len(test_dict_list) == 0
def test_single_hmm_no_id_with_query_read(path):
test_dict_list = list(
HMM.read(os.path.join(path, TEST_FILE_WITHOUT_ID),
id=CARCINUSTATIN_ID))
assert len(test_dict_list) == 0