def test_to_phylip_no_positions(self): d1 = DNASequence('', id="d1") d2 = DNASequence('', id="d2") a = Alignment([d1, d2]) with self.assertRaises(SequenceCollectionError): npt.assert_warns(UserWarning, a.to_phylip)
def setUp(self): """Initialize values to be used in tests """ self.d1 = DNASequence('GATTACA', id="d1") self.d2 = DNASequence('TTG', id="d2") self.d1_lower = DNASequence('gattaca', id="d1") self.d2_lower = DNASequence('ttg', id="d2") self.r1 = RNASequence('GAUUACA', id="r1") self.r2 = RNASequence('UUG', id="r2") self.r3 = RNASequence('U-----UGCC--', id="r3") self.i1 = DNASequence('GATXACA', id="i1") self.seqs1 = [self.d1, self.d2] self.seqs1_lower = [self.d1_lower, self.d2_lower] self.seqs2 = [self.r1, self.r2, self.r3] self.seqs3 = self.seqs1 + self.seqs2 self.seqs1_t = [('d1', 'GATTACA'), ('d2', 'TTG')] self.seqs2_t = [('r1', 'GAUUACA'), ('r2', 'UUG'), ('r3', 'U-----UGCC--')] self.seqs3_t = self.seqs1_t + self.seqs2_t self.s1 = SequenceCollection(self.seqs1) self.s1_lower = SequenceCollection(self.seqs1_lower) self.s2 = SequenceCollection(self.seqs2) self.s3 = SequenceCollection(self.seqs3) self.empty = SequenceCollection([]) self.invalid_s1 = SequenceCollection([self.i1])
def setUp(self): """Setup for Fasta tests.""" self.strings = ['AAAA', 'CCCC', 'gggg', 'uuuu'] self.fasta_no_label = '>0\nAAAA\n>1\nCCCC\n>2\ngggg\n>3\nuuuu' self.fasta_with_label =\ '>1st\nAAAA\n>2nd\nCCCC\n>3rd\nGGGG\n>4th\nUUUU' self.fasta_with_label_lw2 =\ '>1st\nAA\nAA\n>2nd\nCC\nCC\n>3rd\nGG\nGG\n>4th\nUU\nUU' self.alignment_dict = { '1st': 'AAAA', '2nd': 'CCCC', '3rd': 'GGGG', '4th': 'UUUU' } self.sequence_objects_a = [ DNASequence('ACTCGAGATC', 'seq1'), DNASequence('GGCCT', 'seq2') ] self.sequence_objects_b = [ BiologicalSequence('ACTCGAGATC', 'seq1'), BiologicalSequence('GGCCT', 'seq2') ] seqs = [ DNASequence("ACC--G-GGTA..", id="seq1"), DNASequence("TCC--G-GGCA..", id="seqs2") ] self.alignment = Alignment(seqs)
def setUp(self): self.d1 = DNASequence('..ACC-GTTGG..', id="d1") self.d2 = DNASequence('TTACCGGT-GGCC', id="d2") self.d3 = DNASequence('.-ACC-GTTGC--', id="d3") self.r1 = RNASequence('UUAU-', id="r1") self.r2 = RNASequence('ACGUU', id="r2") self.seqs1 = [self.d1, self.d2, self.d3] self.seqs2 = [self.r1, self.r2] self.seqs1_t = [('d1', '..ACC-GTTGG..'), ('d2', 'TTACCGGT-GGCC'), ('d3', '.-ACC-GTTGC--')] self.seqs2_t = [('r1', 'UUAU-'), ('r2', 'ACGUU')] self.a1 = Alignment(self.seqs1) self.a2 = Alignment(self.seqs2) self.a3 = Alignment(self.seqs2, score=42.0, start_end_positions=[(0, 3), (5, 9)]) self.a4 = Alignment(self.seqs2, score=-42.0, start_end_positions=[(1, 4), (6, 10)]) # no sequences self.empty = Alignment([]) # sequences, but no positions self.no_positions = Alignment([RNA('', id='a'), RNA('', id='b')])
def test_reverse_complement(self): self.assertEqual(self.b1.reverse_complement(), DNASequence("TGTAATC")) self.assertEqual(self.b2.reverse_complement(), DNASequence("GGTACCGGT")) self.assertRaises(BiologicalSequenceError, self.b3.reverse_complement) self.assertEqual(self.b4.reverse_complement(), DNASequence("NVHDBMRSWYK"))
def test_to_phylip_unequal_sequence_lengths(self): d1 = DNASequence('A-CT', id="d1") d2 = DNASequence('TTA', id="d2") d3 = DNASequence('.-AC', id="d3") a = Alignment([d1, d2, d3]) with self.assertRaises(SequenceCollectionError): npt.assert_warns(UserWarning, a.to_phylip)
def test_nondegenerates_mixed_degens(self): exp = [ DNASequence('AGC'), DNASequence('AGT'), DNASequence('GGC'), DNASequence('GGT') ] obs = sorted(DNASequence('RGY').nondegenerates(), key=str) self.assertEqual(obs, exp)
def test_majority_consensus_constructor(self): d1 = DNASequence('TTT', id="d1") d2 = DNASequence('TT-', id="d2") d3 = DNASequence('TC-', id="d3") a1 = Alignment([d1, d2, d3]) obs = npt.assert_warns(UserWarning, a1.majority_consensus, constructor=str) self.assertEqual(obs, 'TT-')
def test_nondegenerates_gap_mixed_case(self): exp = [ DNASequence('-A.a'), DNASequence('-A.c'), DNASequence('-C.a'), DNASequence('-C.c') ] obs = sorted(DNASequence('-M.m').nondegenerates(), key=str) self.assertEqual(obs, exp)
def test_validate_lengths(self): self.assertTrue(self.a1._validate_lengths()) self.assertTrue(self.a2._validate_lengths()) self.assertTrue(self.empty._validate_lengths()) self.assertTrue(Alignment([ DNASequence('TTT', id="d1")])._validate_lengths()) self.assertFalse(Alignment([ DNASequence('TTT', id="d1"), DNASequence('TT', id="d2")])._validate_lengths())
def test_subalignment(self): """subalignment functions as expected """ # keep seqs by ids actual = self.a1.subalignment(seqs_to_keep=['d1', 'd3']) expected = Alignment([self.d1, self.d3]) self.assertEqual(actual, expected) # keep seqs by indices actual = self.a1.subalignment(seqs_to_keep=[0, 2]) expected = Alignment([self.d1, self.d3]) self.assertEqual(actual, expected) # keep seqs by ids (invert) actual = self.a1.subalignment(seqs_to_keep=['d1', 'd3'], invert_seqs_to_keep=True) expected = Alignment([self.d2]) self.assertEqual(actual, expected) # keep seqs by indices (invert) actual = self.a1.subalignment(seqs_to_keep=[0, 2], invert_seqs_to_keep=True) expected = Alignment([self.d2]) self.assertEqual(actual, expected) # keep positions actual = self.a1.subalignment(positions_to_keep=[0, 2, 3]) d1 = DNASequence('.AC', id="d1") d2 = DNASequence('TAC', id="d2") d3 = DNASequence('.AC', id="d3") expected = Alignment([d1, d2, d3]) self.assertEqual(actual, expected) # keep positions (invert) actual = self.a1.subalignment(positions_to_keep=[0, 2, 3], invert_positions_to_keep=True) d1 = DNASequence('.C-GTTGG..', id="d1") d2 = DNASequence('TCGGT-GGCC', id="d2") d3 = DNASequence('-C-GTTGC--', id="d3") expected = Alignment([d1, d2, d3]) self.assertEqual(actual, expected) # keep seqs and positions actual = self.a1.subalignment(seqs_to_keep=[0, 2], positions_to_keep=[0, 2, 3]) d1 = DNASequence('.AC', id="d1") d3 = DNASequence('.AC', id="d3") expected = Alignment([d1, d3]) self.assertEqual(actual, expected) # keep seqs and positions (invert) actual = self.a1.subalignment(seqs_to_keep=[0, 2], positions_to_keep=[0, 2, 3], invert_seqs_to_keep=True, invert_positions_to_keep=True) d2 = DNASequence('TCGGT-GGCC', id="d2") expected = Alignment([d2]) self.assertEqual(actual, expected)
def test_to_phylip(self): d1 = DNASequence('..ACC-GTTGG..', id="d1") d2 = DNASequence('TTACCGGT-GGCC', id="d2") d3 = DNASequence('.-ACC-GTTGC--', id="d3") a = Alignment([d1, d2, d3]) phylip_str, id_map = npt.assert_warns(DeprecationWarning, a.to_phylip, map_labels=False) self.assertEqual(id_map, {'d1': 'd1', 'd3': 'd3', 'd2': 'd2'}) expected = "\n".join([ "3 13", "d1 ..ACC-GTTGG..", "d2 TTACCGGT-GGCC", "d3 .-ACC-GTTGC--" ]) self.assertEqual(phylip_str, expected)
def test_to_phylip_map_labels(self): """to_phylip functions as expected with label mapping """ d1 = DNASequence('..ACC-GTTGG..', id="d1") d2 = DNASequence('TTACCGGT-GGCC', id="d2") d3 = DNASequence('.-ACC-GTTGC--', id="d3") a = Alignment([d1, d2, d3]) phylip_str, id_map = a.to_phylip(map_labels=True, label_prefix="s") self.assertEqual(id_map, {'s1': 'd1', 's3': 'd3', 's2': 'd2'}) expected = "\n".join([ "3 13", "s1 ..ACC-GTTGG..", "s2 TTACCGGT-GGCC", "s3 .-ACC-GTTGC--" ]) self.assertEqual(phylip_str, expected)
def test_is_valid(self): """is_valid functions as expected """ self.assertTrue(self.a1.is_valid()) self.assertTrue(self.a2.is_valid()) self.assertTrue(self.empty.is_valid()) # invalid because of length mismatch d1 = DNASequence('..ACC-GTTGG..', id="d1") d2 = DNASequence('TTACCGGT-GGC', id="d2") self.assertFalse(Alignment([d1, d2]).is_valid()) # invalid because of invalid charaters d1 = DNASequence('..ACC-GTXGG..', id="d1") d2 = DNASequence('TTACCGGT-GGCC', id="d2") self.assertFalse(Alignment([d1, d2]).is_valid())
def test_init_validate(self): """initialization with validation functions as expected """ Alignment(self.seqs1, validate=True) # invalid DNA character invalid_seqs1 = [self.d1, self.d2, self.d3, DNASequence('.-ACC-GTXGC--', id="i1")] self.assertRaises(SequenceCollectionError, Alignment, invalid_seqs1, validate=True) # invalid lengths (they're not all equal) invalid_seqs2 = [self.d1, self.d2, self.d3, DNASequence('.-ACC-GTGC--', id="i2")] self.assertRaises(SequenceCollectionError, Alignment, invalid_seqs2, validate=True)
def test_iupac_degenerate_characters(self): exp = set([ 'B', 'D', 'H', 'K', 'M', 'N', 'S', 'R', 'W', 'V', 'Y', 'b', 'd', 'h', 'k', 'm', 'n', 's', 'r', 'w', 'v', 'y' ]) self.assertEqual(self.b1.iupac_degenerate_characters(), exp) self.assertEqual(DNASequence.iupac_degenerate_characters(), exp)
def test_iupac_degeneracies(self): exp = { 'B': set(['C', 'T', 'G']), 'D': set(['A', 'T', 'G']), 'H': set(['A', 'C', 'T']), 'K': set(['T', 'G']), 'M': set(['A', 'C']), 'N': set(['A', 'C', 'T', 'G']), 'S': set(['C', 'G']), 'R': set(['A', 'G']), 'W': set(['A', 'T']), 'V': set(['A', 'C', 'G']), 'Y': set(['C', 'T']), 'b': set(['c', 't', 'g']), 'd': set(['a', 't', 'g']), 'h': set(['a', 'c', 't']), 'k': set(['t', 'g']), 'm': set(['a', 'c']), 'n': set(['a', 'c', 't', 'g']), 's': set(['c', 'g']), 'r': set(['a', 'g']), 'w': set(['a', 't']), 'v': set(['a', 'c', 'g']), 'y': set(['c', 't']) } self.assertEqual(self.b1.iupac_degeneracies(), exp) self.assertEqual(DNASequence.iupac_degeneracies(), exp)
def test_iupac_characters(self): exp = { 'A', 'C', 'B', 'D', 'G', 'H', 'K', 'M', 'N', 'S', 'R', 'T', 'W', 'V', 'Y', 'a', 'c', 'b', 'd', 'g', 'h', 'k', 'm', 'n', 's', 'r', 't', 'w', 'v', 'y' } self.assertEqual(self.b1.iupac_characters(), exp) self.assertEqual(DNASequence.iupac_characters(), exp)
def test_to_phylip_map_labels(self): d1 = DNASequence('..ACC-GTTGG..', id="d1") d2 = DNASequence('TTACCGGT-GGCC', id="d2") d3 = DNASequence('.-ACC-GTTGC--', id="d3") a = Alignment([d1, d2, d3]) phylip_str, id_map = npt.assert_warns(UserWarning, a.to_phylip, map_labels=True, label_prefix="s") self.assertEqual(id_map, {'s1': 'd1', 's3': 'd3', 's2': 'd2'}) expected = "\n".join(["3 13", "s1 ..ACC-GTTGG..", "s2 TTACCGGT-GGCC", "s3 .-ACC-GTTGC--"]) self.assertEqual(phylip_str, expected)
def generator(): yield BiologicalSequence('ACGT', id='', description='', quality=range(4)) yield RNASequence('GAU', id=' foo \t\t bar ', description='') yield DNASequence('TAG', id='', description='foo\n\n bar\n') yield BiologicalSequence('A', id='foo', description='bar baz', quality=[42])
def test_complement_map(self): exp = { '-': '-', '.': '.', 'A': 'T', 'C': 'G', 'B': 'V', 'D': 'H', 'G': 'C', 'H': 'D', 'K': 'M', 'M': 'K', 'N': 'N', 'S': 'S', 'R': 'Y', 'T': 'A', 'W': 'W', 'V': 'B', 'Y': 'R', 'a': 't', 'c': 'g', 'b': 'v', 'd': 'h', 'g': 'c', 'h': 'd', 'k': 'm', 'm': 'k', 'n': 'n', 's': 's', 'r': 'y', 't': 'a', 'w': 'w', 'v': 'b', 'y': 'r' } self.assertEqual(self.b1.complement_map(), exp) self.assertEqual(DNASequence.complement_map(), exp)
def test_init_validate(self): Alignment(self.seqs1, validate=True) # invalid DNA character invalid_seqs1 = [ self.d1, self.d2, self.d3, DNASequence('.-ACC-GTXGC--', id="i1") ] self.assertRaises(SequenceCollectionError, Alignment, invalid_seqs1, validate=True)
def test_majority_consensus(self): d1 = DNASequence('TTT', id="d1") d2 = DNASequence('TT-', id="d2") d3 = DNASequence('TC-', id="d3") a1 = Alignment([d1, d2, d3]) self.assertTrue(a1.majority_consensus().equals(DNASequence('TT-'))) d1 = DNASequence('T', id="d1") d2 = DNASequence('A', id="d2") a1 = Alignment([d1, d2]) self.assertTrue(a1.majority_consensus() in [DNASequence('T'), DNASequence('A')]) self.assertEqual(self.empty.majority_consensus(), '')
def setUp(self): """Setup for stockholm tests.""" self.seqs = [DNASequence("ACC-G-GGTA", id="seq1"), DNASequence("TCC-G-GGCA", id="seq2")] self.GF = OrderedDict([ ("AC", "RF00360"), ("BM", ["cmbuild -F CM SEED", "cmsearch -Z 274931 -E 1000000"]), ("SQ", "9"), ("RT", ["TITLE1", "TITLE2"]), ("RN", ["[1]", "[2]"]), ("RA", ["Auth1;", "Auth2;"]), ("RL", ["J Mol Biol", "Cell"]), ("RM", ["11469857", "12007400"]), ('RN', ['[1]', '[2]']) ]) self.GS = {"AC": OrderedDict([("seq1", "111"), ("seq2", "222")])} self.GR = {"SS": OrderedDict([("seq1", "1110101111"), ("seq2", "0110101110")])} self.GC = {"SS_cons": "(((....)))"} self.st = StockholmAlignment(self.seqs, gc=self.GC, gf=self.GF, gs=self.GS, gr=self.GR)
def setUp(self): self.empty = DNASequence('') self.b1 = DNASequence('GATTACA') self.b2 = DNASequence('ACCGGTACC', id="test-seq-2", description="A test sequence", quality=range(9)) self.b3 = DNASequence( 'ACCGGUACC', id="bad-seq-1", description="Not a DNA sequence") self.b4 = DNASequence( 'MRWSYKVHDBN', id="degen", description="All of the degenerate bases") self.b5 = DNASequence('.G--ATTAC-A...')
def test_iupac_degenerate_characters(self): exp = set(['B', 'D', 'H', 'K', 'M', 'N', 'S', 'R', 'W', 'V', 'Y', 'b', 'd', 'h', 'k', 'm', 'n', 's', 'r', 'w', 'v', 'y']) self.assertEqual(self.b1.iupac_degenerate_characters(), exp) self.assertEqual(DNASequence.iupac_degenerate_characters(), exp)
def test_iupac_standard_characters(self): exp = set("ACGTacgt") self.assertEqual(self.b1.iupac_standard_characters(), exp) self.assertEqual(DNASequence.iupac_standard_characters(), exp)
class DNASequenceTests(TestCase): def setUp(self): self.empty = DNASequence('') self.b1 = DNASequence('GATTACA') self.b2 = DNASequence( 'ACCGGTACC', id="test-seq-2", description="A test sequence") self.b3 = DNASequence( 'ACCGGUACC', id="bad-seq-1", description="Not a DNA sequence") self.b4 = DNASequence( 'MRWSYKVHDBN', id="degen", description="All of the degenerate bases") self.b5 = DNASequence('.G--ATTAC-A...') def test_alphabet(self): exp = { 'A', 'C', 'B', 'D', 'G', 'H', 'K', 'M', 'N', 'S', 'R', 'T', 'W', 'V', 'Y', 'a', 'c', 'b', 'd', 'g', 'h', 'k', 'm', 'n', 's', 'r', 't', 'w', 'v', 'y' } self.assertEqual(self.b1.alphabet(), exp) self.assertEqual(DNASequence.alphabet(), exp) def test_gap_alphabet(self): self.assertEqual(self.b1.gap_alphabet(), set('-.')) def test_complement_map(self): exp = { '-': '-', '.': '.', 'A': 'T', 'C': 'G', 'B': 'V', 'D': 'H', 'G': 'C', 'H': 'D', 'K': 'M', 'M': 'K', 'N': 'N', 'S': 'S', 'R': 'Y', 'T': 'A', 'W': 'W', 'V': 'B', 'Y': 'R', 'a': 't', 'c': 'g', 'b': 'v', 'd': 'h', 'g': 'c', 'h': 'd', 'k': 'm', 'm': 'k', 'n': 'n', 's': 's', 'r': 'y', 't': 'a', 'w': 'w', 'v': 'b', 'y': 'r' } self.assertEqual(self.b1.complement_map(), exp) self.assertEqual(DNASequence.complement_map(), exp) def test_iupac_standard_characters(self): exp = set("ACGTacgt") self.assertEqual(self.b1.iupac_standard_characters(), exp) self.assertEqual(DNASequence.iupac_standard_characters(), exp) def test_iupac_degeneracies(self): exp = { 'B': set(['C', 'T', 'G']), 'D': set(['A', 'T', 'G']), 'H': set(['A', 'C', 'T']), 'K': set(['T', 'G']), 'M': set(['A', 'C']), 'N': set(['A', 'C', 'T', 'G']), 'S': set(['C', 'G']), 'R': set(['A', 'G']), 'W': set(['A', 'T']), 'V': set(['A', 'C', 'G']), 'Y': set(['C', 'T']), 'b': set(['c', 't', 'g']), 'd': set(['a', 't', 'g']), 'h': set(['a', 'c', 't']), 'k': set(['t', 'g']), 'm': set(['a', 'c']), 'n': set(['a', 'c', 't', 'g']), 's': set(['c', 'g']), 'r': set(['a', 'g']), 'w': set(['a', 't']), 'v': set(['a', 'c', 'g']), 'y': set(['c', 't']) } self.assertEqual(self.b1.iupac_degeneracies(), exp) self.assertEqual(DNASequence.iupac_degeneracies(), exp) def test_iupac_degenerate_characters(self): exp = set(['B', 'D', 'H', 'K', 'M', 'N', 'S', 'R', 'W', 'V', 'Y', 'b', 'd', 'h', 'k', 'm', 'n', 's', 'r', 'w', 'v', 'y']) self.assertEqual(self.b1.iupac_degenerate_characters(), exp) self.assertEqual(DNASequence.iupac_degenerate_characters(), exp) def test_iupac_characters(self): exp = { 'A', 'C', 'B', 'D', 'G', 'H', 'K', 'M', 'N', 'S', 'R', 'T', 'W', 'V', 'Y', 'a', 'c', 'b', 'd', 'g', 'h', 'k', 'm', 'n', 's', 'r', 't', 'w', 'v', 'y' } self.assertEqual(self.b1.iupac_characters(), exp) self.assertEqual(DNASequence.iupac_characters(), exp) def test_complement(self): self.assertEqual(self.b1.complement(), DNASequence("CTAATGT")) self.assertEqual(self.b2.complement(), DNASequence("TGGCCATGG")) self.assertRaises(BiologicalSequenceError, self.b3.complement) self.assertEqual(self.b4.complement(), DNASequence("KYWSRMBDHVN")) self.assertEqual(self.b5.complement(), DNASequence(".C--TAATG-T...")) def test_reverse_complement(self): self.assertEqual(self.b1.reverse_complement(), DNASequence("TGTAATC")) self.assertEqual(self.b2.reverse_complement(), DNASequence("GGTACCGGT")) self.assertRaises(BiologicalSequenceError, self.b3.reverse_complement) self.assertEqual(self.b4.reverse_complement(), DNASequence("NVHDBMRSWYK")) def test_unsupported_characters(self): self.assertEqual(self.b1.unsupported_characters(), set()) self.assertEqual(self.b2.unsupported_characters(), set()) self.assertEqual(self.b3.unsupported_characters(), set('U')) self.assertEqual(self.b4.unsupported_characters(), set()) def test_has_unsupported_characters(self): self.assertFalse(self.b1.has_unsupported_characters()) self.assertFalse(self.b2.has_unsupported_characters()) self.assertTrue(self.b3.has_unsupported_characters()) self.assertFalse(self.b4.has_unsupported_characters()) def test_is_reverse_complement(self): self.assertFalse(self.b1.is_reverse_complement(self.b1)) self.assertTrue( self.b1.is_reverse_complement(DNASequence('TGTAATC'))) self.assertTrue( self.b4.is_reverse_complement(DNASequence('NVHDBMRSWYK'))) def test_nondegenerates_invalid(self): with self.assertRaises(BiologicalSequenceError): list(DNASequence('AZA').nondegenerates()) def test_nondegenerates_empty(self): self.assertEqual(list(self.empty.nondegenerates()), [self.empty]) def test_nondegenerates_no_degens(self): self.assertEqual(list(self.b1.nondegenerates()), [self.b1]) def test_nondegenerates_all_degens(self): # Same chars. exp = [DNASequence('CC'), DNASequence('CG'), DNASequence('GC'), DNASequence('GG')] # Sort based on sequence string, as order is not guaranteed. obs = sorted(DNASequence('SS').nondegenerates(), key=str) self.assertEqual(obs, exp) # Different chars. exp = [DNASequence('AC'), DNASequence('AG'), DNASequence('GC'), DNASequence('GG')] obs = sorted(DNASequence('RS').nondegenerates(), key=str) self.assertEqual(obs, exp) # Odd number of chars. obs = list(DNASequence('NNN').nondegenerates()) self.assertEqual(len(obs), 4**3) def test_nondegenerates_mixed_degens(self): exp = [DNASequence('AGC'), DNASequence('AGT'), DNASequence('GGC'), DNASequence('GGT')] obs = sorted(DNASequence('RGY').nondegenerates(), key=str) self.assertEqual(obs, exp) def test_nondegenerates_gap_mixed_case(self): exp = [DNASequence('-A.a'), DNASequence('-A.c'), DNASequence('-C.a'), DNASequence('-C.c')] obs = sorted(DNASequence('-M.m').nondegenerates(), key=str) self.assertEqual(obs, exp)
def test_complement(self): self.assertEqual(self.b1.complement(), DNASequence("CTAATGT")) self.assertEqual(self.b2.complement(), DNASequence("TGGCCATGG")) self.assertRaises(BiologicalSequenceError, self.b3.complement) self.assertEqual(self.b4.complement(), DNASequence("KYWSRMBDHVN")) self.assertEqual(self.b5.complement(), DNASequence(".C--TAATG-T..."))
def missing_qual_gen(): for seq in (RNASequence('A', quality=[42]), BiologicalSequence('AG'), DNASequence('GG', quality=[41, 40])): yield seq
def blank_seq_gen(): for seq in (DNASequence('A'), BiologicalSequence(''), RNASequence('GG')): yield seq
def test_is_reverse_complement(self): self.assertFalse(self.b1.is_reverse_complement(self.b1)) self.assertTrue(self.b1.is_reverse_complement(DNASequence('TGTAATC'))) self.assertTrue( self.b4.is_reverse_complement(DNASequence('NVHDBMRSWYK')))
def test_nondegenerates_invalid(self): with self.assertRaises(BiologicalSequenceError): list(DNASequence('AZA').nondegenerates())
def test_nondegenerates_all_degens(self): # Same chars. exp = [ DNASequence('CC'), DNASequence('CG'), DNASequence('GC'), DNASequence('GG') ] # Sort based on sequence string, as order is not guaranteed. obs = sorted(DNASequence('SS').nondegenerates(), key=str) self.assertEqual(obs, exp) # Different chars. exp = [ DNASequence('AC'), DNASequence('AG'), DNASequence('GC'), DNASequence('GG') ] obs = sorted(DNASequence('RS').nondegenerates(), key=str) self.assertEqual(obs, exp) # Odd number of chars. obs = list(DNASequence('NNN').nondegenerates()) self.assertEqual(len(obs), 4**3)