def test_split_fasta_diff_num_seqs_per_file_alt(self):
"""split_fasta funcs always catches all seqs
"""
# start with 59 seqs (b/c it's prime, so should make more
# confusing splits)
in_seqs = LoadSeqs(data=[('seq%s' % k, 'AACCTTAA') for k in range(59)])
infile = in_seqs.toFasta().split('\n')
# test seqs_per_file from 1 to 1000
for i in range(1, 1000):
_, filename_prefix = mkstemp(dir=get_qiime_temp_dir(),
prefix='split_fasta_tests',
suffix='')
close(_)
actual = split_fasta(infile, i, filename_prefix)
actual_seqs = []
for fp in actual:
actual_seqs += list(open(fp))
# remove the files now, so if the test fails they still get
# cleaned up
remove_files(actual)
# building seq collections from infile and the split files result in
# equivalent seq collections
self.assertEqual(LoadSeqs(data=infile, aligned=False),
LoadSeqs(data=actual_seqs, aligned=False))
def test_alignadd(self):
"""testing adding one alignment to another."""
align1= LoadSeqs(data={'a': 'AAAA', 'b': 'TTTT', 'c': 'CCCC'})
align2 = LoadSeqs(data={'a': 'GGGG', 'b': '----', 'c': 'NNNN'})
align = align1 + align2
concatdict = align.todict()
self.assertEqual(concatdict, {'a': 'AAAAGGGG', 'b': 'TTTT----', 'c': 'CCCCNNNN'})
def get_paralinear_distances(gene, data_directory=None, third_position=False, **kw):
filenames = glob.glob(os.path.join(data_directory, gene+'.fasta*'))
assert len(filenames) == 1, 'Wrong number of alignment files for ' + gene
filename = filenames[0]
if filename.endswith('.fasta'):
with open(filename) as fastafile:
fastadata = fastafile.read()
elif filename.endswith('.fasta.gz'):
with GzipFile(filename) as fastafile:
fastadata = fastafile.read()
else:
raise RuntimeError(gene + ' file could not be read')
sequences = LoadSeqs(data=fastadata)
if third_position:
indices = [(i, i+1) for i in range(len(sequences))[2::3]]
pos3 = sequences.addFeature('pos3', 'pos3', indices)
sequences = pos3.getSlice()
sequences = sequences.filtered(lambda x: set(''.join(x)) <= set(DNA))
paralinear_calc = ParalinearPair(moltype=DNA, alignment=sequences)
paralinear_calc.run(show_progress=False)
dists = paralinear_calc.getPairwiseDistances()
return {frozenset(k):v for k, v in dists.items()}
def test_split_fasta_diff_num_seqs_per_file(self):
"""split_fasta funcs as expected when diff num seqs go to each file
"""
_, filename_prefix = mkstemp(dir=get_qiime_temp_dir(),
prefix='split_fasta_tests',
suffix='')
close(_)
infile = [
'>seq1', 'AACCTTAA', '>seq2', 'TTAACC', 'AATTAA', '>seq3',
'CCTT--AA'
]
actual = split_fasta(infile, 2, filename_prefix)
actual_seqs = []
for fp in actual:
actual_seqs += list(open(fp))
remove_files(actual)
expected = ['%s.%d.fasta' % (filename_prefix, i) for i in range(2)]
# list of file paths is as expected
self.assertEqual(actual, expected)
# building seq collections from infile and the split files result in
# equivalent seq collections
self.assertEqual(LoadSeqs(data=infile, aligned=False),
LoadSeqs(data=actual_seqs, aligned=False))
def pair_hmm_align_unaligned_seqs(seqs, moltype=DNA, params={}):
"""
Checks parameters for pairwise alignment, returns alignment.
Code from Greg Caporaso.
"""
seqs = LoadSeqs(data=seqs, moltype=moltype, aligned=False)
try:
s1, s2 = seqs.values()
except ValueError:
raise ValueError(
"Pairwise aligning of seqs requires exactly two seqs.")
try:
gap_open = params['gap_open']
except KeyError:
gap_open = 5
try:
gap_extend = params['gap_extend']
except KeyError:
gap_extend = 2
try:
score_matrix = params['score_matrix']
except KeyError:
score_matrix = make_dna_scoring_dict(
match=1, transition=-1, transversion=-1)
return local_pairwise(s1, s2, score_matrix, gap_open, gap_extend)
def rooted(doc, rooted_edges=None, gc=None, **kw):
aln = LoadSeqs(data=doc['aln'].encode('utf-8'), moltype=DNA)
tree = LoadTree(treestring=doc['tree'].encode('utf-8'))
code = get_genetic_code(gc)
aln = aln.withoutTerminalStopCodons(code)
aln = aln.filtered(lambda x: set(''.join(x)) <= set(DNA), motif_length=3)
sp_kw = dict(upper=20., lower=0.05, is_independent=False)
sm = MG94GTR(optimise_motif_probs=True)
init_lf = sm.makeLikelihoodFunction(tree)
init_lf.setAlignment(aln)
with init_lf.updatesPostponed():
for param in init_lf.getParamNames():
if '/' in param:
init_lf.setParamRule(param, **sp_kw)
init_lf.setParamRule('length', edges=rooted_edges, is_independent=False)
init_lf.optimise(local=True, show_progress=False, limit_action='raise')
init_lf = nest.deflate_likelihood_function(init_lf, save_jsd=False)
sm = GNC(optimise_motif_probs=True)
lf = sm.makeLikelihoodFunction(tree)
lf.setAlignment(aln)
_populate_parameters(lf, init_lf, **sp_kw)
for param in lf.getParamNames():
if '>' in param or param == 'omega':
lf.setParamRule(param, edges=rooted_edges, is_independent=False)
lf.optimise(local=True, show_progress=False, limit_action='raise')
flat_lf = nest.deflate_likelihood_function(lf)
flat_lf['hard_up'] = _is_hard_up(lf)
return {'lf': flat_lf, 'gc': code.Name, 'rooted_edges': rooted_edges}
def ml(doc,
model='NG',
gc=None,
omega_indep=True,
model_gaps=False,
indel_indep=True,
**kw):
aln = LoadSeqs(data=doc['aln'].encode('utf-8'), moltype=DNA)
tree = LoadTree(treestring=doc['tree'].encode('utf-8'))
code = get_genetic_code(gc)
if model != 'NG':
# Trim terminal stop codons
aln = aln.withoutTerminalStopCodons(code)
if model_gaps:
filt = lambda x: set(''.join(x)) <= set(DNA).union({'-'})
else:
filt = lambda x: set(''.join(x)) <= set(DNA)
aln = aln.filtered(filt, motif_length=3)
flat_lf, time = _fit(aln, tree, model, code, omega_indep, model_gaps,
indel_indep)
return {
'lf': flat_lf,
'time': time,
'model': model,
'gc': code.Name,
'omega_indep': omega_indep,
'model_gaps': model_gaps,
'indel_indep': indel_indep
}
def main():
new_dna_dict = dict()
new_aa_dict = dict()
dna_dict = SeqIO.to_dict(SeqIO.parse(infile, 'fasta'))
#unaligned_DNA = LoadSeqs(infile, moltype = DNA, aligned = False, format = 'fasta')
#help(unaligned_DNA)
#unaligned_DNA = unaligned_DNA.withoutTerminalStopCodons()
# help(unaligned_DNA)
for seqname, sequence in dna_dict.iteritems():
#help(seqitem)
new_aa_seq, new_dna_seq = findBestSeq(sequence)
new_aa_dict[seqname] = new_aa_seq
new_dna_dict[seqname] = new_dna_seq
unaligned_aa = LoadSeqs(data=new_aa_dict, moltype = PROTEIN, aligned = False)
new_unaligned_dna = LoadSeqs(data=new_dna_dict, moltype = DNA, aligned = False)
# print seqitem.getName()
# while seqitem.hasTerminalStop() == True:
# print "\nold last sic = "+str(seqitem[-6:])
# seqitem = seqitem.withoutTerminalStopCodon()
# print "\nnew last sic = "+str(seqitem[-6:])
# unaligned_DNA.writeToFile(outfile+".dna")
# unaligned_aa = myTranslate(unaligned_DNA)
aa_outstring = unaligned_aa.toFasta()
dna_outstring = new_unaligned_dna.toFasta()
dna_outfile_temp = outfile.split('.')[0]
dna_outfile = dna_outfile_temp+'_dna.fasta'
aa_outfile_handle = open(outfile, "w")
aa_outfile_handle.write(aa_outstring)
aa_outfile_handle.close()
dna_outfile_handle = open(dna_outfile, 'w')
dna_outfile_handle.write(dna_outstring)
dna_outfile_handle.close()
def test_split_fasta_diff_num_seqs_per_file_alt(self):
"""split_fasta funcs always catches all seqs
"""
# start with 59 seqs (b/c it's prime, so should make more
# confusing splits)
in_seqs = LoadSeqs(data=[('seq%s' % k, 'AACCTTAA') for k in range(59)])
infile = in_seqs.toFasta().split('\n')
# test seqs_per_file from 1 to 1000
for i in range(1, 1000):
_, filename_prefix = mkstemp(dir=get_qiime_temp_dir(),
prefix='split_fasta_tests',
suffix='')
close(_)
actual = split_fasta(infile, i, filename_prefix)
actual_seqs = []
for fp in actual:
actual_seqs += list(open(fp))
# remove the files now, so if the test fails they still get
# cleaned up
remove_files(actual)
# building seq collections from infile and the split files result in
# equivalent seq collections
self.assertEqual(
LoadSeqs(data=infile, aligned=False),
LoadSeqs(data=actual_seqs, aligned=False))
def pair_hmm_align_unaligned_seqs(seqs, moltype, params={}):
"""
This needs to be moved to cogent.align.align
"""
seqs = LoadSeqs(data=seqs, moltype=moltype, aligned=False)
try:
s1, s2 = seqs.values()
except ValueError:
raise ValueError,\
"Pairwise aligning of seqs requires exactly two seqs."
try:
gap_open = params['gap_open']
except KeyError:
gap_open = 5
try:
gap_extend = params['gap_extend']
except KeyError:
gap_extend = 2
try:
score_matrix = params['score_matrix']
except KeyError:
score_matrix = make_dna_scoring_dict(\
match=1,transition=-1,transversion=-1)
return global_pairwise(s1, s2, score_matrix, gap_open, gap_extend)
def test_paralinear_pair_aa(self):
"""paralinear shouldn't fail to produce distances for aa seqs"""
aln = LoadSeqs('data/brca1_5.paml', moltype=DNA)
aln = aln.getTranslation()
paralinear_calc = ParalinearPair(moltype=PROTEIN, alignment=aln)
paralinear_calc.run(show_progress=False)
dists = paralinear_calc.getPairwiseDistances()
def test_replaceSeqs(self):
"""synchronize gaps between protein seqs and codon seqs"""
pd = {
'FlyingFox': 'C-TNAH',
'DogFaced': 'CGTNT-',
'FreeTaile': '-GTDTH',
'LittleBro': 'C-TD-H',
'TombBat': 'C--STH'
}
pal = LoadSeqs(moltype=PROTEIN, data=pd)
cu = {
'TombBat': 'TGTAGTACTCAT',
'FreeTaile': 'GGCACAGATACTCAT',
'FlyingFox': 'TGTACAAATGCTCAT',
'LittleBro': 'TGTACAGATCAT',
'DogFaced': 'TGTGGCACAAATACT'
}
co = LoadSeqs(moltype=DNA, data=cu, aligned=False)
cal = pal.replaceSeqs(co)
result = cal.todict()
for taxon, expected_sequence in [('FlyingFox', 'TGT---ACAAATGCTCAT'),
('DogFaced', 'TGTGGCACAAATACT---'),
('FreeTaile', '---GGCACAGATACTCAT'),
('LittleBro', 'TGT---ACAGAT---CAT'),
('TombBat', 'TGT------AGTACTCAT')]:
self.assertEqual(result[taxon], expected_sequence)
def test_getBySequenceAnnotation(self):
aln = LoadSeqs(data={"a": "ATCGAAATCGAT", "b": "ATCGA--TCGAT"})
b = aln.getSeq("b")
b.addAnnotation(Feature, "test_type", "test_label", [(4, 6)])
answer = aln.getBySequenceAnnotation("b", "test_type")[0].todict()
self.assertEqual(answer, {"b": "A--T", "a": "AAAT"})
def pair_hmm_align_unaligned_seqs(seqs,moltype,params={}):
"""
This needs to be moved to cogent.align.align
"""
seqs = LoadSeqs(data=seqs,moltype=moltype,aligned=False)
try:
s1, s2 = seqs.values()
except ValueError:
raise ValueError,\
"Pairwise aligning of seqs requires exactly two seqs."
try:
gap_open = params['gap_open']
except KeyError:
gap_open = 5
try:
gap_extend = params['gap_extend']
except KeyError:
gap_extend = 2
try:
score_matrix = params['score_matrix']
except KeyError:
score_matrix = make_dna_scoring_dict(\
match=1,transition=-1,transversion=-1)
return global_pairwise(s1,s2,score_matrix,gap_open,gap_extend)
def test_reversecomplement(self):
"""test reverse complementing of Alignments and SequenceCollection."""
dna = {
'seq1': '--ACGT--GT---',
'seq2': 'TTACGTA-GT---',
'seq3': '--ACGTA-GCC--'
}
dna_rc = {
'seq1': '---AC--ACGT--',
'seq2': '---AC-TACGTAA',
'seq3': '--GGC-TACGT--'
}
# alignment with gaps
aln = LoadSeqs(data=dna, moltype=DNA)
aln_rc = aln.rc()
self.assertEqual(aln_rc.todict(), dna_rc)
# check collection, with gaps
coll = LoadSeqs(data=dna, moltype=DNA, aligned=False)
coll_rc = coll.rc()
self.assertEqual(coll_rc.todict(), dna_rc)
self.assertEqual(coll_rc.todict(), coll.reversecomplement().todict())
# collection with no gaps
dna = {'seq1': 'ACGTGT', 'seq2': 'TTACGTAGT', 'seq3': 'ACGTAGCC'}
dna_rc = {'seq1': 'ACACGT', 'seq2': 'ACTACGTAA', 'seq3': 'GGCTACGT'}
coll = LoadSeqs(data=dna, moltype=DNA, aligned=False)
coll_rc = coll.rc()
self.assertEqual(coll_rc.todict(), dna_rc)
def test_getBySequenceAnnotation(self):
aln = LoadSeqs(data={'a': 'ATCGAAATCGAT', 'b': 'ATCGA--TCGAT'})
b = aln.getSeq('b')
b.addAnnotation(Feature, 'test_type', 'test_label', [(4, 6)])
answer = aln.getBySequenceAnnotation('b', 'test_type')[0].todict()
self.assertEqual(answer, {'b': 'A--T', 'a': 'AAAT'})
def test_paralinear_pair_aa(self):
"""paralinear shouldn't fail to produce distances for aa seqs"""
aln = LoadSeqs('data/brca1_5.paml', moltype=DNA)
aln = aln.getTranslation()
paralinear_calc = ParalinearPair(moltype=PROTEIN, alignment=aln)
paralinear_calc.run(show_progress=False)
dists = paralinear_calc.getPairwiseDistances()
def test_replaceSeqs(self):
"""synchronize gaps between protein seqs and codon seqs"""
pd={'FlyingFox': 'C-TNAH',
'DogFaced': 'CGTNT-',
'FreeTaile': '-GTDTH',
'LittleBro': 'C-TD-H',
'TombBat': 'C--STH'}
pal = LoadSeqs(moltype = PROTEIN, data = pd)
cu={'TombBat': 'TGTAGTACTCAT',
'FreeTaile': 'GGCACAGATACTCAT',
'FlyingFox': 'TGTACAAATGCTCAT',
'LittleBro': 'TGTACAGATCAT',
'DogFaced': 'TGTGGCACAAATACT'}
co = LoadSeqs(moltype = DNA, data = cu, aligned = False)
cal = pal.replaceSeqs(co)
result = cal.todict()
for taxon, expected_sequence in [
('FlyingFox', 'TGT---ACAAATGCTCAT'),
('DogFaced', 'TGTGGCACAAATACT---'),
('FreeTaile', '---GGCACAGATACTCAT'),
('LittleBro', 'TGT---ACAGAT---CAT'),
('TombBat', 'TGT------AGTACTCAT')]:
self.assertEqual(result[taxon], expected_sequence)
def est_logdet_pair_aa(self):
"""logdet shouldn't fail to produce distances for aa seqs"""
aln = LoadSeqs('data/brca1_5.paml', moltype=DNA)
aln = aln.getTranslation()
logdet_calc = LogDetPair(moltype=PROTEIN, alignment=aln)
logdet_calc.run(use_tk_adjustment=True, show_progress=False)
dists = logdet_calc.getPairwiseDistances()
def BestLogLikelihood(aln, alphabet=None, exclude_chars = None,
allowed_chars='ACGT', motif_length=None, return_length=False):
"""returns the best log-likelihood according to Goldman 1993.
Arguments:
- alphabet: a sequence alphabet object.
- motif_length: 1 for nucleotide, 2 for dinucleotide, etc ..
- exclude_chars: a series of characters used to exclude motifs
- allowed_chars: only motifs that contain a subset of these are
allowed
- return_length: whether to also return the number of alignment columns
"""
assert alphabet or motif_length, "Must provide either an alphabet or a"\
" motif_length"
# need to use the alphabet, so we can enforce character compliance
if alphabet:
kwargs = dict(moltype=alphabet.MolType)
motif_length = alphabet.getMotifLen()
else:
kwargs = {}
aln = LoadSeqs(data=aln.todict(), **kwargs)
columns = aligned_columns_to_rows(aln, motif_length, exclude_chars,
allowed_chars)
num_cols = len(columns)
log_likelihood = get_G93_lnL_from_array(columns)
if return_length:
return log_likelihood, num_cols
return log_likelihood
def BestLogLikelihood(aln,
alphabet=None,
exclude_chars=None,
allowed_chars='ACGT',
motif_length=None,
return_length=False):
"""returns the best log-likelihood according to Goldman 1993.
Arguments:
- alphabet: a sequence alphabet object.
- motif_length: 1 for nucleotide, 2 for dinucleotide, etc ..
- exclude_chars: a series of characters used to exclude motifs
- allowed_chars: only motifs that contain a subset of these are
allowed
- return_length: whether to also return the number of alignment columns
"""
assert alphabet or motif_length, "Must provide either an alphabet or a"\
" motif_length"
# need to use the alphabet, so we can enforce character compliance
if alphabet:
kwargs = dict(moltype=alphabet.MolType)
motif_length = alphabet.getMotifLen()
else:
kwargs = {}
aln = LoadSeqs(data=aln.todict(), **kwargs)
columns = aligned_columns_to_rows(aln, motif_length, exclude_chars,
allowed_chars)
num_cols = len(columns)
log_likelihood = get_G93_lnL_from_array(columns)
if return_length:
return log_likelihood, num_cols
return log_likelihood
def test_logdet_pair_aa(self):
"""logdet shouldn't fail to produce distances for aa seqs"""
aln = LoadSeqs('data/brca1_5.paml', moltype=DNA)
aln = aln.getTranslation()
logdet_calc = LogDetPair(moltype=PROTEIN, alignment=aln)
logdet_calc.run(use_tk_adjustment=True, show_progress=False)
dists = logdet_calc.getPairwiseDistances()
def pair_hmm_align_unaligned_seqs(seqs, moltype=DNA, params={}):
"""
Checks parameters for pairwise alignment, returns alignment.
Code from Greg Caporaso.
"""
seqs = LoadSeqs(data=seqs, moltype=moltype, aligned=False)
try:
s1, s2 = seqs.values()
except ValueError:
raise ValueError(
"Pairwise aligning of seqs requires exactly two seqs.")
try:
gap_open = params['gap_open']
except KeyError:
gap_open = 5
try:
gap_extend = params['gap_extend']
except KeyError:
gap_extend = 2
try:
score_matrix = params['score_matrix']
except KeyError:
score_matrix = make_dna_scoring_dict(match=1,
transition=-1,
transversion=-1)
return local_pairwise(s1, s2, score_matrix, gap_open, gap_extend)
def setUp(self):
self.pynast_test1_input_fp = get_tmp_filename(
prefix='PyNastAlignerTests_', suffix='.fasta')
open(self.pynast_test1_input_fp, 'w').write(pynast_test1_input_fasta)
self.pynast_test1_template_fp = get_tmp_filename(
prefix='PyNastAlignerTests_', suffix='template.fasta')
open(self.pynast_test1_template_fp, 'w').\
write(pynast_test1_template_fasta)
self.pynast_test_template_w_dots_fp = get_tmp_filename(
prefix='PyNastAlignerTests_', suffix='template.fasta')
open(self.pynast_test_template_w_dots_fp, 'w').\
write(pynast_test1_template_fasta.replace('-', '.'))
self.pynast_test_template_w_u_fp = get_tmp_filename(
prefix='PyNastAlignerTests_', suffix='template.fasta')
open(self.pynast_test_template_w_u_fp, 'w').\
write(pynast_test1_template_fasta.replace('T', 'U'))
self.pynast_test_template_w_lower_fp = get_tmp_filename(
prefix='PyNastAlignerTests_', suffix='template.fasta')
open(self.pynast_test_template_w_lower_fp, 'w').\
write(pynast_test1_template_fasta.lower())
# create temp file names (and touch them so we can reliably
# clean them up)
self.result_fp = get_tmp_filename(
prefix='PyNastAlignerTests_', suffix='.fasta')
open(self.result_fp, 'w').close()
self.failure_fp = get_tmp_filename(
prefix='PyNastAlignerTests_', suffix='.fasta')
open(self.failure_fp, 'w').close()
self.log_fp = get_tmp_filename(
prefix='PyNastAlignerTests_', suffix='.log')
open(self.log_fp, 'w').close()
self._paths_to_clean_up = [
self.pynast_test1_input_fp,
self.result_fp,
self.failure_fp,
self.log_fp,
self.pynast_test1_template_fp,
self.pynast_test_template_w_dots_fp,
self.pynast_test_template_w_u_fp,
self.pynast_test_template_w_lower_fp
]
self.pynast_test1_aligner = PyNastAligner({
'template_filepath': self.pynast_test1_template_fp,
'min_len': 15,
})
self.pynast_test1_expected_aln = \
LoadSeqs(
data=pynast_test1_expected_alignment,
aligned=DenseAlignment)
self.pynast_test1_expected_fail = \
LoadSeqs(data=pynast_test1_expected_failure, aligned=False)
class TestCigar(unittest.TestCase):
def setUp(self):
self.cigar_text = '3D2M3D6MDM2D3MD'
self.aln_seq = DNA.makeSequence('---AA---GCTTAG-A--CCT-')
self.aln_seq1 = DNA.makeSequence('CCAAAAAA---TAGT-GGC--G')
self.map, self.seq = self.aln_seq.parseOutGaps()
self.map1, self.seq1 = self.aln_seq1.parseOutGaps()
self.slices = [(1, 4), (0, 8), (7, 12), (0, 1), (3, 5)]
self.aln = LoadSeqs(data = {"FAKE01": self.aln_seq, "FAKE02": self.aln_seq1})
self.cigars = {"FAKE01": self.cigar_text, "FAKE02": map_to_cigar(self.map1)}
self.seqs = {"FAKE01": str(self.seq), "FAKE02": str(self.seq1)}
def test_map_to_cigar(self):
"""convert a Map to cigar string"""
assert map_to_cigar(self.map) == self.cigar_text
def test_cigar_to_map(self):
"""test generating a Map from cigar"""
map = cigar_to_map(self.cigar_text)
assert str(map) == str(self.map)
def test_aligned_from_cigar(self):
"""test generating aligned seq from cigar"""
aligned_seq = aligned_from_cigar(self.cigar_text, self.seq)
assert aligned_seq == self.aln_seq
def test_slice_cigar(self):
"""test slicing cigars"""
for start, end in self.slices:
# test by_align = True
map1, loc1 = slice_cigar(self.cigar_text, start, end)
ori1 = self.aln_seq[start:end]
if loc1:
slicealn1 = self.seq[loc1[0]:loc1[1]].gappedByMap(map1)
assert ori1 == slicealn1
else:
assert map1.length == len(ori1)
# test by_align = False
map2, loc2 = slice_cigar(self.cigar_text, start, end, by_align = False)
slicealn2 = self.seq[start:end].gappedByMap(map2)
ori2 = self.aln_seq[loc2[0]:loc2[1]]
assert slicealn2 == ori2
def test_CigarParser(self):
"""test without slice"""
aln = CigarParser(self.seqs, self.cigars)
assert aln == self.aln
# test slice
i = 1
for start, end in self.slices:
self.aln.getSeq("FAKE01").addFeature("annot%d"%i, "annot", [(start, end)])
annot = self.aln.getAnnotationsFromAnySequence("annot%d"%i)
slice_aln = aln.getRegionCoveringAll(annot).asOneSpan().getSlice()
i += 1
cmp_aln = CigarParser(self.seqs, self.cigars, sliced = True,
ref_seqname = "FAKE01", start = start, end = end)
assert cmp_aln == slice_aln
class TestCigar(unittest.TestCase):
def setUp(self):
self.cigar_text = '3D2M3D6MDM2D3MD'
self.aln_seq = DNA.makeSequence('---AA---GCTTAG-A--CCT-')
self.aln_seq1 = DNA.makeSequence('CCAAAAAA---TAGT-GGC--G')
self.map, self.seq = self.aln_seq.parseOutGaps()
self.map1, self.seq1 = self.aln_seq1.parseOutGaps()
self.slices = [(1, 4), (0, 8), (7, 12), (0, 1), (3, 5)]
self.aln = LoadSeqs(data = {"FAKE01": self.aln_seq, "FAKE02": self.aln_seq1})
self.cigars = {"FAKE01": self.cigar_text, "FAKE02": map_to_cigar(self.map1)}
self.seqs = {"FAKE01": str(self.seq), "FAKE02": str(self.seq1)}
def test_map_to_cigar(self):
"""convert a Map to cigar string"""
assert map_to_cigar(self.map) == self.cigar_text
def test_cigar_to_map(self):
"""test generating a Map from cigar"""
map = cigar_to_map(self.cigar_text)
assert str(map) == str(self.map)
def test_aligned_from_cigar(self):
"""test generating aligned seq from cigar"""
aligned_seq = aligned_from_cigar(self.cigar_text, self.seq)
assert aligned_seq == self.aln_seq
def test_slice_cigar(self):
"""test slicing cigars"""
for start, end in self.slices:
# test by_align = True
map1, loc1 = slice_cigar(self.cigar_text, start, end)
ori1 = self.aln_seq[start:end]
if loc1:
slicealn1 = self.seq[loc1[0]:loc1[1]].gappedByMap(map1)
assert ori1 == slicealn1
else:
assert map1.length == len(ori1)
# test by_align = False
map2, loc2 = slice_cigar(self.cigar_text, start, end, by_align = False)
slicealn2 = self.seq[start:end].gappedByMap(map2)
ori2 = self.aln_seq[loc2[0]:loc2[1]]
assert slicealn2 == ori2
def test_CigarParser(self):
"""test without slice"""
aln = CigarParser(self.seqs, self.cigars)
assert aln == self.aln
# test slice
i = 1
for start, end in self.slices:
self.aln.getSeq("FAKE01").addFeature("annot%d"%i, "annot", [(start, end)])
annot = self.aln.getAnnotationsFromAnySequence("annot%d"%i)
slice_aln = aln.getRegionCoveringAll(annot).asOneSpan().getSlice()
i += 1
cmp_aln = CigarParser(self.seqs, self.cigars, sliced = True,
ref_seqname = "FAKE01", start = start, end = end)
assert cmp_aln == slice_aln
def _loadfromfile(self, filename, test_write=True, **kw):
filename = os.path.join(data_path, filename)
aln = LoadSeqs(filename=filename, **kw)
if test_write:
suffix = filename.split('.')[-1]
fn = tempfile.mktemp(suffix='.'+suffix)
aln.writeToFile(filename=fn)
os.remove(fn)
def _loadfromfile(self, filename, test_write=True, **kw):
filename = os.path.join(data_path, filename)
aln = LoadSeqs(filename=filename, **kw)
if test_write:
suffix = filename.split('.')[-1]
fn = tempfile.mktemp(suffix='.' + suffix)
aln.writeToFile(filename=fn)
os.remove(fn)
def test_partimatrix(self):
aln = LoadSeqs(filename='data/brca1.fasta', moltype=DNA)
species5 = ['Human','HowlerMon','Mouse','NineBande','DogFaced']
aln = aln.takeSeqs(species5)
aln = aln[:500]
fig = partimatrix(aln, samples=0, display=True, print_stats=False,
s_limit=10, title="brca1")
test_figure('compatibility', fig)
def setUp(self):
self.al = LoadSeqs(data = {'a':'GTACGTACGATC',
'b':'GTACGTACGTAC',
'c':'GTACGTACGTTC',
'e':'GTACGTACTGGT'})
self.collection = LoadSeqs(data = {'a':'GTACGTACGATC',
'b':'GTACGTACGTAC',
'c':'GTACGTACGTTC',
'e':'GTACGTACTGGT'}, aligned=False)
def test_withoutAnyGaps(self):
"""test removal of all gaps (any entries in alignment column are gaps)"""
alignment = LoadSeqs(data={'seq1': '--ACGT--GT---', 'seq2': '--ACGTA-GT---', 'seq3': '--ACGTA-GT---'})
align_dict = alignment.omitGapPositions(allowed_gap_frac=0).todict()
self.assertEqual(align_dict, {'seq1':'ACGTGT', 'seq2':'ACGTGT', 'seq3':'ACGTGT'})
alignment = LoadSeqs(data={'seq1': 'ACGT', 'seq2': '----', 'seq3': '----'})
align_dict = alignment.omitGapPositions(allowed_gap_frac=0).todict()
self.assertEqual(align_dict, {'seq1':'', 'seq2':'', 'seq3':''})
def test_getBySequenceAnnotation(self):
aln = LoadSeqs(data={
'a': 'ATCGAAATCGAT',
'b': 'ATCGA--TCGAT'})
b = aln.getSeq('b')
b.addAnnotation(Feature, 'test_type', 'test_label', [(4,6)])
answer = aln.getBySequenceAnnotation('b', 'test_type')[0].todict()
self.assertEqual(answer, {'b':'A--T', 'a':'AAAT'})
def __call__(self, seq_path, result_path=None, log_path=None,
failure_path=None):
# load candidate sequences
seq_file = open(seq_path, 'U')
candidate_sequences = parse_fasta(seq_file)
# load template sequences
template_alignment = []
template_alignment_fp = self.Params['template_filepath']
for seq_id, seq in parse_fasta(open(template_alignment_fp)):
# replace '.' characters with '-' characters
template_alignment.append((seq_id, seq.replace('.', '-').upper()))
try:
template_alignment = LoadSeqs(data=template_alignment, moltype=DNA,
aligned=DenseAlignment)
except KeyError as e:
raise KeyError('Only ACGT-. characters can be contained in template alignments.' +
' The offending character was: %s' % e)
# initialize_logger
logger = NastLogger(log_path)
# get function for pairwise alignment method
pairwise_alignment_f = pairwise_alignment_methods[
self.Params['pairwise_alignment_method']]
pynast_aligned, pynast_failed = pynast_seqs(
candidate_sequences,
template_alignment,
min_pct=self.Params['min_pct'],
min_len=self.Params['min_len'],
align_unaligned_seqs_f=pairwise_alignment_f,
logger=logger,
temp_dir=get_qiime_temp_dir())
logger.record(str(self))
if failure_path is not None:
fail_file = open(failure_path, 'w')
for seq in pynast_failed:
fail_file.write(seq.toFasta())
fail_file.write('\n')
fail_file.close()
if result_path is not None:
result_file = open(result_path, 'w')
for seq in pynast_aligned:
result_file.write(seq.toFasta())
result_file.write('\n')
result_file.close()
return None
else:
try:
return LoadSeqs(data=pynast_aligned, aligned=DenseAlignment)
except ValueError:
return {}
def makeSampleAlignment():
seq1 = makeSampleSequence()
seq2 = makeSampleSequence(mid_gaps=True)
seqs = {'FAKE01': seq1, 'FAKE02': seq2}
aln = LoadSeqs(data = seqs)
aln.addAnnotation(Feature, 'misc_feature', 'misc', [(12,25)])
aln.addAnnotation(Feature, 'CDS', 'blue', [(15, 25)])
aln.addAnnotation(Feature, "5'UTR", 'red', [(2, 4)])
aln.addAnnotation(Feature, "LTR", "fake", [(2,15)])
return aln
def setUp(self):
self.submodel = Nucleotide(do_scaling=True,
model_gaps=False,
equal_motif_probs=True,
predicates={'beta': 'transition'})
self.data = LoadSeqs(filename=os.path.join(data_path, 'brca1_5.paml'),
moltype=self.submodel.MolType)
self.tree = LoadTree(filename=os.path.join(data_path, 'brca1_5.tree'))
def setUp(self):
"""Sets up environment for tests
"""
self.random_seq = LoadSeqs(data=\
'>seq0\nACUGCGCGGAUCGAUCGAUCGAUCGAUGCAUUUUACGAUCGCCA\n', aligned=False)
self.rrna = LoadSeqs(data=RRNA, aligned=False)
self.rrna_aln = LoadSeqs(data=REF_ALN)
self.seq_db_path = os.path.join(ABSPATH, 'test_data',
'Rfam10_part.fasta')
def setUp(self):
self.cigar_text = '3D2M3D6MDM2D3MD'
self.aln_seq = DNA.makeSequence('---AA---GCTTAG-A--CCT-')
self.aln_seq1 = DNA.makeSequence('CCAAAAAA---TAGT-GGC--G')
self.map, self.seq = self.aln_seq.parseOutGaps()
self.map1, self.seq1 = self.aln_seq1.parseOutGaps()
self.slices = [(1, 4), (0, 8), (7, 12), (0, 1), (3, 5)]
self.aln = LoadSeqs(data = {"FAKE01": self.aln_seq, "FAKE02": self.aln_seq1})
self.cigars = {"FAKE01": self.cigar_text, "FAKE02": map_to_cigar(self.map1)}
self.seqs = {"FAKE01": str(self.seq), "FAKE02": str(self.seq1)}
def test_call_write_to_file(self):
"""ReferenceRepSetPicker.__call__ otu map correctly written to file"""
app = ReferenceRepSetPicker(params={'Algorithm':'first',
'ChoiceF':first_id})
app(self.tmp_seq_filepath,
self.tmp_otu_filepath,
self.ref_seq_filepath,
result_path=self.result_filepath)
exp = rep_seqs_reference_result_file_exp
self.assertEqual(LoadSeqs(self.result_filepath,aligned=False),
LoadSeqs(data=exp,aligned=False))
def test_partimatrix(self):
aln = LoadSeqs(filename='data/brca1.fasta', moltype=DNA)
species5 = ['Human', 'HowlerMon', 'Mouse', 'NineBande', 'DogFaced']
aln = aln.takeSeqs(species5)
aln = aln[:500]
fig = partimatrix(aln,
samples=0,
display=True,
print_stats=False,
s_limit=10,
title="brca1")
test_figure('compatibility', fig)
def test_translate(self):
for seqs in [
{'seq1': 'GATTTT', 'seq2': 'GATC??'},
{'seq1': 'GAT---', 'seq2': '?GATCT'}]:
alignment = LoadSeqs(data=seqs, moltype=DNA)
self.assertEqual(len(alignment.getTranslation()), 2)
# check for a failure when no moltype specified
alignment = LoadSeqs(data=seqs)
try:
peps = alignment.getTranslation()
except AttributeError:
pass
def ml(doc, model='GNC', gc=None, outgroup=None, neutral=None, **kw):
aln = LoadSeqs(data=doc['aln'].encode('utf-8'), moltype=DNA)
tree = LoadTree(treestring=doc['tree'].encode('utf-8'))
code = get_genetic_code(gc)
# Trim terminal stop codons
aln = aln.withoutTerminalStopCodons(code)
aln = aln.filtered(lambda x: set(''.join(x)) <= set(DNA), motif_length=3)
flat_lf, time = _fit(aln, tree, model, code, outgroup, neutral)
return {'lf': flat_lf, 'time': time, 'model': model, 'gc': code.Name}
def optimization(result, aln, tree1, tree2):
# get the sites for each tree according to the assignments
aln1 = LoadSeqs(data=[('a', ''), ('c', ''), ('b', ''), ('d', '')],
moltype=DNA)
aln2 = LoadSeqs(data=[('a', ''), ('c', ''), ('b', ''), ('d', '')],
moltype=DNA)
for i in range(len(aln)):
if (result[i] == 1):
aln1 = aln1 + aln[i]
if (result[i] == 2):
aln2 = aln2 + aln[i]
if (result[i] == 0):
aln1 = aln1 + aln[i]
aln2 = aln2 + aln[i]
tree_parameter = [[], []]
modle = JC69()
# calculate the likelihood and do optimization. optimise will generates
# new tree parameters
lf1 = modle.makeLikelihoodFunction(tree1)
lf1.setAlignment(aln1)
lf1.optimise(local=True)
likelihood1 = lf1.getLogLikelihood()
# new tree parameters generates by optimise. As tree1/2 is symmetric, get
# p,q,r from 6 branch lengths
p1 = (lf1.getParamValue('length', 'a') +
lf1.getParamValue('length', 'c')) / 2.0
q1 = (lf1.getParamValue('length', 'b') +
lf1.getParamValue('length', 'd')) / 2.0
r1 = lf1.getParamValue('length', 'edge.1') + \
lf1.getParamValue('length', 'edge.0')
lf2 = modle.makeLikelihoodFunction(tree2)
lf2.setAlignment(aln2)
lf2.optimise(local=True)
likelihood2 = lf2.getLogLikelihood()
p2 = (lf2.getParamValue('length', 'a') +
lf2.getParamValue('length', 'c')) / 2.0
q2 = (lf2.getParamValue('length', 'b') +
lf2.getParamValue('length', 'd')) / 2.0
r2 = lf2.getParamValue('length', 'edge.1') + \
lf2.getParamValue('length', 'edge.0')
# return the new tree_parameter. As likelihood is in log, so plus together
# get the total likelihood for the whole sites
tree_parameter[0] = [p1, q1, r1]
tree_parameter[1] = [p2, q2, r2]
likelihood = likelihood1 + likelihood2
return tree_parameter, likelihood
def test_degap(self):
"""test stripping gaps from collections and alignments"""
aln = LoadSeqs(data={'seq1': '--ACGT--GT---', 'seq2': '--ACGTA-GT---',
'seq3': '--ACGTA-GT---'})
observed = aln.degap()
expect = {'seq1': 'ACGTGT', 'seq2': 'ACGTAGT', 'seq3': 'ACGTAGT'}
self.assertEqual(observed.todict(), expect)
collection = LoadSeqs(data={'seq1': '--ACGT--GT---',
'seq2': '--ACGTA-GT---', 'seq3': '--ACGTA-GT---'},
aligned=False, moltype=DNA)
observed = collection.degap()
self.assertEqual(observed.todict(), expect)
self.assertEqual(observed.MolType, DNA)
def makeSampleAlignment():
seq1 = makeSampleSequence()
seq2 = makeSampleSequence(with_gaps=True)
seqs = {'FAKE01': seq1, 'FAKE02': seq2}
aln = LoadSeqs(data = seqs)
aln.addAnnotation(Feature, 'misc_feature', 'misc', [(12,25)])
aln.addAnnotation(Feature, 'CDS', 'blue', [(15, 25)])
aln.addAnnotation(Feature, "5'UTR", 'red', [(2, 4)])
aln.addAnnotation(Feature, "LTR", "fake", [(2,15)])
return aln
def test_sample_tuples(self):
##### test with motif size != 1 #####
alignment = LoadSeqs(data={'seq1': 'AABBCCDDEEFFGGHHIIJJKKLLMMNNOOPP',
'seq2': 'AABBCCDDEEFFGGHHIIJJKKLLMMNNOOPP'})
shuffled = alignment.sample(motif_length=2)
# ensure length correct
sample = alignment.sample(10,motif_length=2)
self.assertEqual(len(sample), 20)
# test columns alignment preserved
seqs = sample.todict().values()
self.assertEqual(seqs[0], seqs[1])
# ensure each char occurs twice as sampling dinucs without replacement
for char in seqs[0]:
self.assertEqual(seqs[0].count(char), 2)
def test_sample_tuples(self):
##### test with motif size != 1 #####
alignment = LoadSeqs(data={'seq1': 'AABBCCDDEEFFGGHHIIJJKKLLMMNNOOPP',
'seq2': 'AABBCCDDEEFFGGHHIIJJKKLLMMNNOOPP'})
shuffled = alignment.sample(motif_length=2)
# ensure length correct
sample = alignment.sample(10,motif_length=2)
self.assertEqual(len(sample), 20)
# test columns alignment preserved
seqs = sample.todict().values()
self.assertEqual(seqs[0], seqs[1])
# ensure each char occurs twice as sampling dinucs without replacement
for char in seqs[0]:
self.assertEqual(seqs[0].count(char), 2)
def ml(doc, model='GNCClock', gc=None, outgroup=None, omega_indep=True, **kw):
aln = LoadSeqs(data=doc['aln'].encode('utf-8'), moltype=DNA)
tree = LoadTree(treestring=doc['tree'].encode('utf-8'))
code = get_genetic_code(gc)
if model != 'NGClock':
# Trim terminal stop codons
aln = aln.withoutTerminalStopCodons(code)
aln = aln.filtered(lambda x: set(''.join(x)) <= set(DNA),
motif_length=3)
ingroup = [t for t in aln.Names if t != outgroup]
flat_lf, time = _fit(aln, tree, model, code, ingroup, omega_indep)
return {'lf': flat_lf, 'time': time, 'model': model, 'gc': code.Name}
def test_withoutRedundantGaps(self):
"""test removal of redundant gaps (all entries in alignment column are gaps)"""
alignment = LoadSeqs(
data={
'seq1': '--ACGT--GT---',
'seq2': '--ACGTA-GT---',
'seq3': '--ACGTA-GT---'
})
align_dict = alignment.omitGapPositions().todict()
self.assertEqual(align_dict, {
'seq1': 'ACGT-GT',
'seq2': 'ACGTAGT',
'seq3': 'ACGTAGT'
})
def test_sample(self):
"""Test sample generation"""
alignment = LoadSeqs(data={'seq1': 'ABCDEFGHIJKLMNOP',
'seq2': 'ABCDEFGHIJKLMNOP'})
# effectively permute columns, preserving length
shuffled = alignment.sample()
# ensure length correct
sample = alignment.sample(10)
self.assertEqual(len(sample), 10)
# test columns alignment preserved
seqs = sample.todict().values()
self.assertEqual(seqs[0], seqs[1])
# ensure each char occurs once as sampling without replacement
for char in seqs[0]:
self.assertEqual(seqs[0].count(char), 1)
def filter_samples(prefs, data, dir_path='', filename=None):
"""processes the filtering of the otus file and representative seq set, then
writes filtered otus and filtered representative seq set files"""
aln = data['aln']
otus = data['otus']
# filter the otus file based on which samples to remove
new_otus_list = filter_otus(otus, prefs)
filtered_otus_output_filepath = '%s/%s_sfiltered_otus.txt' \
% (dir_path, filename)
filtered_otus_output_filepath = open(filtered_otus_output_filepath, 'w')
# Write out a new otus file
for key in (new_otus_list):
filtered_otus_output_filepath.write(key[0])
for j in key[1]:
filtered_otus_output_filepath.write('\t' + str(j))
filtered_otus_output_filepath.write('\n')
filtered_otus_output_filepath.close()
# filter seq set
filtered_seqs, removed_seqs = filter_aln_by_otus(aln, prefs)
# write a fasta containing list of sequences removed from
# representative set
try:
removed_seqs = LoadSeqs(data=removed_seqs, aligned=False)
except:
raise ValueError(
'No sequences were removed. Did you specify the correct Sample ID?')
output_filepath2 = '%s/%s_sremoved.fasta' % (dir_path, filename)
output_file2 = open(output_filepath2, 'w')
output_file2.write(removed_seqs.toFasta())
output_file2.close()
# write a fasta containing the filtered representative seqs
try:
filtered_seqs = LoadSeqs(data=filtered_seqs, aligned=False)
except:
raise ValueError(
'No sequences were remaining in the fasta file. Did you remove all Sample ID\'s?')
output_filepath = '%s/%s_sfiltered.fasta' % (dir_path, filename)
output_file = open(output_filepath, 'w')
output_file.write(filtered_seqs.toFasta())
output_file.close()
def fileToFrequency(filePath):
aln = LoadSeqs(filePath,moltype = PROTEIN)
pf = aln.getPosFreqs()
pf.normalizePositions()
lines = pf.prettyPrint(include_header = True,col_sep=',').split('\n')#每行数据的列表
header_line = lines[0].split(',')#头行数据列表
str_tmp = ''
for line in lines[1::]:
line_content = line.split(',')
for i in range(len(line_content)):
if (float(line_content[i].strip()) > 0.01 and header_line[i].strip() != '-' and header_line[i].strip() != 'X'):#1是突变率的阈值，2是是否为-，3是是否为X
str_tmp = str_tmp+line_content[i]+','+header_line[i].strip()+'\t'
str_tmp = str_tmp +'\n'
return str_tmp
def remove_duplicates(seqsin):
'''Takes in LoadSeqs loadable sequences, removes duplicate sequences
and returns a list of unique sequence tuples, formated (sequence, count)
sorted most abundant to least abundant'''
parsable_seqs = LoadSeqs(data=seqsin, aligned=False)
uniques = {}
for header, seq in parsable_seqs.items():
seq = str(seq)
if seq in uniques:
uniques[seq] += 1
else:
uniques[seq] = 1
uniques = uniques.items()
uniques.sort(key=lambda x: x[1], reverse=True)
return uniques
def test_slidingWindows(self):
"""test slicing of sequences"""
alignment = LoadSeqs(data = {'seq1': 'ACGTACGT', 'seq2': 'ACGTACGT', 'seq3': 'ACGTACGT'})
result = []
for bit in alignment.slidingWindows(5,2):
result+=[bit]
self.assertEqual(result[0].todict(), {'seq3': 'ACGTA', 'seq2': 'ACGTA', 'seq1': 'ACGTA'})
self.assertEqual(result[1].todict(), {'seq3': 'GTACG', 'seq2': 'GTACG', 'seq1': 'GTACG'})
result = []
for bit in alignment.slidingWindows(5,1):
result+=[bit]
self.assertEqual(result[0].todict(), {'seq3': 'ACGTA', 'seq2': 'ACGTA', 'seq1': 'ACGTA'})
self.assertEqual(result[1].todict(), {'seq3': 'CGTAC', 'seq2': 'CGTAC', 'seq1': 'CGTAC'})
self.assertEqual(result[2].todict(), {'seq3': 'GTACG', 'seq2': 'GTACG', 'seq1': 'GTACG'})
self.assertEqual(result[3].todict(), {'seq3': 'TACGT', 'seq2': 'TACGT', 'seq1': 'TACGT'})
def test_call_pynast_test1_file_output(self):
"""PyNastAligner writes correct output files for pynast_test1 seqs
"""
# do not collect results; check output files instead
actual = self.pynast_test1_aligner(
self.pynast_test1_input_fp, result_path=self.result_fp,
log_path=self.log_fp, failure_path=self.failure_fp)
self.assertTrue(actual is None,
"Result should be None when result path provided.")
expected_aln = self.pynast_test1_expected_aln
actual_aln = LoadSeqs(self.result_fp, aligned=DenseAlignment)
self.assertEqual(actual_aln, expected_aln)
actual_fail = LoadSeqs(self.failure_fp, aligned=False)
self.assertEqual(actual_fail.toFasta(),
self.pynast_test1_expected_fail.toFasta())
def test_hasTerminalStops(self):
"""test truth values for terminal stops"""
# seq collections
seq_coll = LoadSeqs(data = {'seq1': 'ACGTAA', 'seq2': 'ACG',
'seq3': 'ACGCGT'}, moltype = DNA, aligned=False)
assert seq_coll.hasTerminalStops() == True
seq_coll = LoadSeqs(data = {'seq1': 'ACGTAC', 'seq2': 'ACGACG',
'seq3': 'ACGCGT'}, moltype = DNA, aligned=False)
assert seq_coll.hasTerminalStops() == False
# alignments
aln = LoadSeqs(data = {'seq1': 'ACGTAA', 'seq2': 'ACGCAA',
'seq3': 'ACGCGT'}, moltype = DNA)
assert aln.hasTerminalStops() == True
aln = LoadSeqs(data = {'seq1': 'ACGTAA', 'seq2': 'ACGTAG',
'seq3': 'ACGTGA'}, moltype = DNA)
assert aln.hasTerminalStops() == True
aln = LoadSeqs(data = {'seq1': 'ACGCAA', 'seq2': 'ACGCAA',
'seq3': 'ACGCGT'}, moltype = DNA)
assert aln.hasTerminalStops() == False
def setUp(self):
self.cigar_text = '3D2M3D6MDM2D3MD'
self.aln_seq = DNA.makeSequence('---AA---GCTTAG-A--CCT-')
self.aln_seq1 = DNA.makeSequence('CCAAAAAA---TAGT-GGC--G')
self.map, self.seq = self.aln_seq.parseOutGaps()
self.map1, self.seq1 = self.aln_seq1.parseOutGaps()
self.slices = [(1, 4), (0, 8), (7, 12), (0, 1), (3, 5)]
self.aln = LoadSeqs(data = {"FAKE01": self.aln_seq, "FAKE02": self.aln_seq1})
self.cigars = {"FAKE01": self.cigar_text, "FAKE02": map_to_cigar(self.map1)}
self.seqs = {"FAKE01": str(self.seq), "FAKE02": str(self.seq1)}
def setUp(self):
self.submodel = Nucleotide(
do_scaling=True, model_gaps=False, equal_motif_probs=True,
predicates = {'beta': 'transition'})
self.data = LoadSeqs(
filename = os.path.join(data_path, 'brca1_5.paml'),
moltype = self.submodel.MolType)
self.tree = LoadTree(
filename = os.path.join(data_path, 'brca1_5.tree'))
def test_call_pynast_test1_file_output_alt_params(self):
"""PyNastAligner writes correct output files when no seqs align
"""
aligner = PyNastAligner({
'template_filepath': self.pynast_test1_template_fp,
'min_len': 1000})
actual = aligner(
self.pynast_test1_input_fp, result_path=self.result_fp,
log_path=self.log_fp, failure_path=self.failure_fp)
self.assertTrue(actual is None,
"Result should be None when result path provided.")
self.assertEqual(getsize(self.result_fp), 0,
"No alignable seqs should result in an empty file.")
# all seqs reported to fail
actual_fail = LoadSeqs(self.failure_fp, aligned=False)
self.assertEqual(actual_fail.getNumSeqs(), 3)
def cluster_seqs(seqspath, simm, folderout='/tmp', gapopen=None, gapext=None):
if folderout[-1] != "/":
folderout += "/"
params = {
'--usersort': True,
'--id': float(simm),
'--maxaccepts': 20,
'--maxrejects': 500,
'--stepwords': 20,
'--hsp': 0,
'--match': 1,
'--mismatch': -1
}
if gapopen is not None:
params['--gapopen'] = gapopen
if gapext is not None:
params['--gapext'] = gapext
uclust = Uclust(params, WorkingDir='/tmp')
input_data = {
'--input': seqspath,
'--uc': folderout + "clusters.uc",
'--log': folderout + "clusters.log"
}
result = uclust(input_data)
clusters, failures, newseeds = clusters_from_uc_file(result['ClusterFile'])
seqs = LoadSeqs(seqspath, aligned=False)
convheader = {}
clusterseqs = {}
#create dictinary to convert shortened headers to full headers
for header in seqs.getSeqNames():
convheader[header.split()[0]] = header
#match headers in each cluster to seqs to create cluster tuples list
for num, cluster in enumerate(clusters):
clusterseqs["cluster_" + str(num)] = []
for header in clusters[cluster]:
clusterseqs["cluster_" + str(num)].append((convheader[header],
seqs.getSeq(convheader[header])))
return clusterseqs
