def test_too_big_hmms():
test_repeat = repeat.Repeat(msa=TEST_RESULT_REPEAT_MSA_LONG)
test_hmm = HMM.create(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.Repeat_list
assert len(test_optimized_repeat.repeats) == 0
test_repeat = repeat.Repeat(msa=TEST_RESULT_REPEAT_MSA_SUPER_LONG)
test_hmm = HMM.create(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.Repeat_list
assert len(test_optimized_repeat.repeats) == 0
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(format='repeat', repeat=test_repeat)
test_optimized_repeat = test_seq.detect([test_hmm])
test_seq.set_repeat_list(test_optimized_repeat, TEST_SEQUENCE_TAG)
assert type(test_optimized_repeat) == repeat_list.Repeat_list
assert list(test_seq.dRepeat_list.keys()) == [TEST_SEQUENCE_TAG]
assert type(
test_seq.dRepeat_list[TEST_SEQUENCE_TAG]) == repeat_list.Repeat_list
assert test_seq.dRepeat_list[TEST_SEQUENCE_TAG].repeats
test_seq.write(test_pickle, 'pickle')
test_seq_new = sequence.Sequence.create(test_pickle, 'pickle')
assert test_seq.dRepeat_list.keys() == test_seq_new.dRepeat_list.keys()
assert test_seq.dRepeat_list[TEST_SEQUENCE_TAG].repeats[
0].msa == test_seq_new.dRepeat_list[TEST_SEQUENCE_TAG].repeats[0].msa
if os.path.exists(test_pickle):
os.remove(test_pickle)
def test_detect_repeats_denovo():
test_parameters = {"detection": {"lFinders": ["TRUST"]}}
test_seq = sequence.Sequence(TEST_SEQUENCE_Q9BRR0)
test_optimized_repeat = test_seq.detect(denovo=True, **test_parameters)
assert type(test_optimized_repeat) == repeat_list.Repeat_list
assert len(test_optimized_repeat.repeats) == 3
def test_detect_XSTREAM():
test_seq = sequence.Sequence(TEST_SEQUENCE_Q9BRR0)
predicted_repeats = repeat_detection_run.run_TRD(seq_records=[test_seq],
lFinders=["XSTREAM"
])[0]['XSTREAM']
assert len(predicted_repeats) == 1
assert predicted_repeats[0].msa == [
'ECGKSFAQS-SGLSK-HRRIHTGEKPYECE', 'ECGKAFIGS-SALVI-HQRVHTGEKPYECE',
'ECGKAFSHS-SDL-IKHQRTHTGEKPYECD', 'DCGKTFSQSCSLLEH-H-RIHTGEKPY'
]
def test_serialize_repeat_list_tsv():
test_repeats = [repeat.Repeat(msa=i) for i in TEST_REPEATS]
test_seq = sequence.Sequence(TEST_SEQUENCE)
for i in test_repeats:
test_seq.repeat_in_sequence(i)
test_repeat_list = rl.Repeat_list(repeats=test_repeats)
tsv = rl_io.serialize_repeat_list_tsv(test_repeat_list)
assert type(tsv) == str
def test_serialize_repeat_list_tsv():
test_repeats = [repeat.Repeat(msa=i) for i in TEST_REPEATS[:2]]
test_seq = sequence.Sequence(TEST_SEQUENCE)
for i in test_repeats:
test_seq.repeat_in_sequence(i)
test_repeat_list = rl.Repeat_list(repeats=test_repeats)
tsv = test_repeat_list.write("tsv", str=True)
assert type(tsv) == str
def test_detect_HHrepID():
test_seq = sequence.Sequence(TEST_SEQUENCE_Q9BRR0)
predicted_repeats = repeat_detection_run.run_TRD(seq_records=[test_seq],
lFinders=["HHrepID"
])[0]['HHrepID']
assert len(predicted_repeats) == 1
assert predicted_repeats[0].msa == [
'------------------IPTCAEAGEQ----', 'EGRLQRKQKNATGGRRHICHECGKSFAQ----',
'SSGLSKHRRIHTGEKPYECEECGKAFIG----', 'SSALVIHQRVHTGEKPYECEECGKAFSH----',
'SSDLIKHQRTHTGEKPYECDDCGKTFSQ----', 'SCSLLEHHRIHTGEKPYQCSMCGKAFRR----',
'SSHLLRHQRIHTGDKNVQEPEQGEAWKSRMES', '------QLENVETPMSYKCNECERSFTQ----',
'NTGLIEHQKIHTGEKPYQCNACGKGFTR----', 'ISYLVQHQRSHVG-------------------'
]
def test_detect_TRUST():
# Warning: TRUST finds these results ONLY with the BLOSUM50 substitution matrix.
test_seq = sequence.Sequence(TEST_SEQUENCE_Q9BRR0)
predicted_repeats = repeat_detection_run.run_TRD(seq_records=[test_seq],
lFinders=["TRUST"
])[0]['TRUST']
assert len(predicted_repeats) == 3
assert predicted_repeats[0].msa == [
'HLREDIAQIP---TCAEAGE---QEGRLQR', 'KQKNATGGRR--HICHECGKSFAQSSGLSK',
'HRRIHTGEKP--YECEECGKAFIGSSALVI', 'HQRVHTGEKP--YECEECGKAFSHSSDLIK',
'HQRTHTGEKP--YECDDCGKTFSQSCSLLE', 'HHRIHTGEKP--YQCSMCGKAFRRSSHLLR',
'HQRIHTGDKN--VQEPEQGEAW--KSRM--', 'ESQLENVETPmsYKCNECERSFTQNTGLIE',
'HQKIHTGEKP--YQCNACGKGFTRISYLVQ'
]
def test_detect_TREKS():
test_seq = sequence.Sequence(TEST_SEQUENCE_Q9BRR0)
predicted_repeats = repeat_detection_run.run_TRD(seq_records=[test_seq],
lFinders=["T-REKS"
])[0]['T-REKS']
assert len(predicted_repeats) == 1
assert predicted_repeats[0].msa == [
'C---G---KSFAQSSGLSKHRRIHTGEKPYECE-E',
'C---G---KAFIGSSALVIHQRVHTGEKPYECE-E',
'C---G---KAFSHSSDLIKHQRTHTGEKPYECD-D',
'C---G---KTFSQSCSLLEHHRIHTGEKPYQCS-M',
'C---G---KAFRRSSHLLRHQRIHTGDKNVQ-EPE',
'Q---G---EAW--KSRME-SQ-LENVETPMSYK--',
'C---NECERSFTQNTGLIEHQKIHTGEKPYQ----',
'CNACG---KGFTRISYLVQHQRSHVG-KNI-LS--'
]
def test_detect_repeats_with_repeat():
test_repeat = repeat.Repeat(msa=TEST_REPEAT_MSA_DOUBLE)
test_hmm = HMM.create(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.Repeat_list
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(format='repeat', repeat=test_repeat)
test_optimized_repeat = test_seq.detect([test_hmm])
assert type(test_optimized_repeat) == repeat_list.Repeat_list
assert len(test_optimized_repeat.repeats) == 1
assert test_optimized_repeat.repeats[
0].msa == TEST_RESULT_REPEAT_MSA_SINGLE
def test_detect_repeats_with_hmm():
test_hmm = HMM.create(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_initialise_sequence():
test_seq = sequence.Sequence(TEST_SEQUENCE)
assert test_seq.seq == TEST_SEQUENCE