• 设为首页
  • 点击收藏
  • 手机版
    手机扫一扫访问
    迪恩网络手机版
  • 关注官方公众号
    微信扫一扫关注
    迪恩网络公众号
登陆 注册
描述文字

Python skbio.SequenceCollection类代码示例

原作者: [db:作者] 来自: [db:来源] 收藏 邀请

本文整理汇总了Python中skbio.SequenceCollection类的典型用法代码示例。如果您正苦于以下问题：Python SequenceCollection类的具体用法？Python SequenceCollection怎么用？Python SequenceCollection使用的例子？那么恭喜您, 这里精选的类代码示例或许可以为您提供帮助。



在下文中一共展示了SequenceCollection类的18个代码示例，这些例子默认根据受欢迎程度排序。您可以为喜欢或者感觉有用的代码点赞，您的评价将有助于我们的系统推荐出更棒的Python代码示例。

示例1: test_k_word_frequencies

    def test_k_word_frequencies(self):
        expected1 = defaultdict(float)
        expected1['A'] = 3 / 7.
        expected1['C'] = 1 / 7.
        expected1['G'] = 1 / 7.
        expected1['T'] = 2 / 7.
        expected2 = defaultdict(float)
        expected2['G'] = 1 / 3.
        expected2['T'] = 2 / 3.
        self.assertEqual(self.s1.k_word_frequencies(k=1),
                         [expected1, expected2])

        expected1 = defaultdict(float)
        expected1['GAT'] = 1 / 2.
        expected1['TAC'] = 1 / 2.
        expected2 = defaultdict(float)
        expected2['TTG'] = 1 / 1.
        self.assertEqual(self.s1.k_word_frequencies(k=3, overlapping=False),
                         [expected1, expected2])

        self.assertEqual(self.empty.k_word_frequencies(k=1), [])

        # Test to ensure floating point precision bug isn't present. See the
        # tests for BiologicalSequence.k_word_frequencies for more details.
        sc = SequenceCollection([RNA('C' * 10, id='s1'),
                                 RNA('G' * 10, id='s2')])
        self.assertEqual(sc.k_word_frequencies(1),
                         [defaultdict(float, {'C': 1.0}),
                          defaultdict(float, {'G': 1.0})])
开发者ID:AndreaEdwards，项目名称:scikit-bio，代码行数:29，代码来源:test_alignment.py


示例2: extract_seq_ids

def extract_seq_ids(data, fmt='fasta', variant=None):
    """
    Given FASTQ-format data (string), parse out only the
    sequence IDs and return.
    """
    fh = StringIO(data)
    if fmt == 'fastq':
        sc = SequenceCollection.read(fh, format=fmt, variant=variant)
    else:
        sc = SequenceCollection.read(fh, format=fmt)
    return frozenset(entry.id for entry in sc)
开发者ID:3009420，项目名称:PyMGRAST，代码行数:11，代码来源:filter_failed_screening.py


示例3: test_degap

    def test_degap(self):
        """degap functions as expected
        """
        expected = [(id_, seq.replace(".", "").replace("-", "")) for id_, seq in self.seqs1_t]
        expected = SequenceCollection.from_fasta_records(expected, DNASequence)
        actual = self.a1.degap()
        self.assertEqual(actual, expected)

        expected = [(id_, seq.replace(".", "").replace("-", "")) for id_, seq in self.seqs2_t]
        expected = SequenceCollection.from_fasta_records(expected, RNASequence)
        actual = self.a2.degap()
        self.assertEqual(actual, expected)
开发者ID:cauyrd，项目名称:scikit-bio，代码行数:12，代码来源:test_alignment.py


示例4: test_distances

    def test_distances(self):
        s1 = SequenceCollection([DNA("ACGT", "d1"), DNA("ACGG", "d2")])
        expected = [[0, 0.25],
                    [0.25, 0]]
        expected = DistanceMatrix(expected, ['d1', 'd2'])
        actual = s1.distances(hamming)
        self.assertEqual(actual, expected)

        # alt distance function provided
        def dumb_distance(s1, s2):
            return 42.
        expected = [[0, 42.],
                    [42., 0]]
        expected = DistanceMatrix(expected, ['d1', 'd2'])
        actual = s1.distances(dumb_distance)
        self.assertEqual(actual, expected)
开发者ID:bctaylor，项目名称:scikit-bio，代码行数:16，代码来源:test_alignment.py


示例5: convert_phylip

def convert_phylip(infile, outfile, format):
    seqs = SequenceCollection.read(
        infile, format='phylip',
        data_parser=phylip.relaxed_ids
    )

    seqs.write(outfile, format=format)
开发者ID:sh4wn，项目名称:af-phylogeny，代码行数:7，代码来源:phylip-splitter.py


示例6: main

def main():
    args = handle_program_options()

    if osp.isfile(args.out_dir):
        print("--out_dir (-o) option must be a valid directory and not a file",
              file=sys.stderr)
        sys.exit(1)

    # will fail gracefully if dir exists
    skbu.create_dir(args.out_dir)

    metagenomes = []
    if args.metagenome_id is not None:
        metagenomes.append(args.metagenome_id)
    elif args.metagenome_file is not None:
        metagenomes.extend(parse_metagenome_file(args.metagenome_file))
        
    if args.verbose:
        msg = 'Processing requested for {} metagenome(s) found in: {}'
        print(msg.format(len(metagenomes), args.metagenome_file))

    # MG-RAST stage.file ids for downloading
    derep_passed = '150.1'
    screen_passed = '299.1'

    for mg_id in metagenomes:
        if args.verbose:
            print('Processing metagenome: {}'.format(mg_id))
            print('\tDownloading: Dereplication Passed...', end='')
            sys.stdout.flush()
        derepp_rsp = mgapi.mgrast_request('download', mg_id,
                                          {'file': derep_passed},
                                          auth_key=args.auth_key)
        derepp_sc = SequenceCollection.read(StringIO(derepp_rsp.text),
                                            format='fastq',
                                            variant='illumina1.8')
        if args.verbose:
            print('{} sequences'.format(len(derepp_sc)))
            print('\tDownloading: Screen Passed...', end='')
            sys.stdout.flush()
        screenp_rsp = mgapi.mgrast_request('download', mg_id,
                                           {'file': screen_passed},
                                           auth_key=args.auth_key)
        screenp_ids = extract_seq_ids(screenp_rsp.text, fmt='fastq',
                                      variant='illumina1.8')
        if args.verbose:
            print('{} sequences'.format(len(screenp_ids)))

        # filter dereplication passed with IDs from screen passed
        failed_screen = filter_seqs(derepp_sc, screenp_ids)
        if args.verbose:
            nsp = len(screenp_ids)
            print('\tRemoved {} sequences from Dereplication Passed'.format(nsp))
            print('\tleaving {} sequences'.format(len(failed_screen)))

        out_fp = osp.join(args.out_dir, mg_id + '_screen_failed.fastq')
        failed_screen.write(out_fp, format='fastq', variant='illumina1.8')
        if args.verbose:
            print('Sequence data written to: ' + out_fp)
开发者ID:3009420，项目名称:PyMGRAST，代码行数:59，代码来源:filter_failed_screening.py


示例7: test_make_mini_otu_files

 def test_make_mini_otu_files(self):
     os.system("mkdir tmp")
     self.extension_seqs = SequenceCollection.read(self.extension_seqs)
     result = _make_mini_otu_files(self.key_node,
                                   self.extension_genus_dic_few,
                                   self.extension_seqs)
     os.system("rm -r tmp")
     self.assertEqual(result, """>P1\nTTAAAAAA\n""")
开发者ID:wasade，项目名称:ghost-tree，代码行数:8，代码来源:test_hybridtree.py


示例8: setUp

    def setUp(self):
        self.d1 = DNA('GATTACA', metadata={'id': "d1"})
        self.d2 = DNA('TTG', metadata={'id': "d2"})
        self.d3 = DNA('GTATACA', metadata={'id': "d3"})
        self.r1 = RNA('GAUUACA', metadata={'id': "r1"})
        self.r2 = RNA('UUG', metadata={'id': "r2"})
        self.r3 = RNA('U-----UGCC--', metadata={'id': "r3"})

        self.seqs1 = [self.d1, self.d2]
        self.seqs2 = [self.r1, self.r2, self.r3]
        self.seqs3 = self.seqs1 + self.seqs2
        self.seqs4 = [self.d1, self.d3]

        self.s1 = SequenceCollection(self.seqs1)
        self.s2 = SequenceCollection(self.seqs2)
        self.s3 = SequenceCollection(self.seqs3)
        self.s4 = SequenceCollection(self.seqs4)
        self.empty = SequenceCollection([])
开发者ID:jhcepas，项目名称:scikit-bio，代码行数:18，代码来源:test_alignment.py


示例9: test_distances

    def test_distances(self):
        s1 = SequenceCollection([DNA("ACGT", metadata={'id': "d1"}),
                                 DNA("ACGG", metadata={'id': "d2"})])
        expected = [[0, 0.25],
                    [0.25, 0]]
        expected = DistanceMatrix(expected, ['d1', 'd2'])

        def h(s1, s2):
            return hamming(s1.values, s2.values)
        actual = s1.distances(h)
        self.assertEqual(actual, expected)

        # alt distance function provided
        def dumb_distance(s1, s2):
            return 42.
        expected = [[0, 42.],
                    [42., 0]]
        expected = DistanceMatrix(expected, ['d1', 'd2'])
        actual = s1.distances(dumb_distance)
        self.assertEqual(actual, expected)
开发者ID:jhcepas，项目名称:scikit-bio，代码行数:20，代码来源:test_alignment.py


示例10: setUp

    def setUp(self):
        self.d1 = DNASequence('GATTACA', id="d1")
        self.d2 = DNASequence('TTG', id="d2")
        self.d3 = DNASequence('GTATACA', id="d3")
        self.d1_lower = DNASequence('gattaca', id="d1")
        self.d2_lower = DNASequence('ttg', id="d2")
        self.d3_lower = DNASequence('gtataca', id="d3")
        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.seqs4 = [self.d1, self.d3]

        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.s4 = SequenceCollection(self.seqs4)
        self.empty = SequenceCollection([])

        self.invalid_s1 = SequenceCollection([self.i1])
开发者ID:AndreaEdwards，项目名称:scikit-bio，代码行数:32，代码来源:test_alignment.py


示例11: setUp

    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])
开发者ID:cauyrd，项目名称:scikit-bio，代码行数:29，代码来源:test_alignment.py


示例12: test_kmer_frequencies

    def test_kmer_frequencies(self):
        expected1 = Counter({'GAT': 1, 'TAC': 1})
        expected2 = Counter({'TTG': 1})
        self.assertEqual(
            self.s1.kmer_frequencies(k=3, overlap=False, relative=False),
            [expected1, expected2])

        expected1 = defaultdict(float)
        expected1['A'] = 3 / 7.
        expected1['C'] = 1 / 7.
        expected1['G'] = 1 / 7.
        expected1['T'] = 2 / 7.
        expected2 = defaultdict(float)
        expected2['G'] = 1 / 3.
        expected2['T'] = 2 / 3.
        self.assertEqual(self.s1.kmer_frequencies(k=1, relative=True),
                         [expected1, expected2])

        expected1 = defaultdict(float)
        expected1['GAT'] = 1 / 2.
        expected1['TAC'] = 1 / 2.
        expected2 = defaultdict(float)
        expected2['TTG'] = 1 / 1.
        self.assertEqual(
            self.s1.kmer_frequencies(k=3, overlap=False, relative=True),
            [expected1, expected2])

        self.assertEqual(self.empty.kmer_frequencies(k=1, relative=True), [])

        # Test to ensure floating point precision bug isn't present. See the
        # tests for Sequence.kmer_frequencies for more details.
        sc = SequenceCollection([RNA('C' * 10, metadata={'id': 's1'}),
                                 RNA('G' * 10, metadata={'id': 's2'})])
        self.assertEqual(sc.kmer_frequencies(1, relative=True),
                         [defaultdict(float, {'C': 1.0}),
                          defaultdict(float, {'G': 1.0})])
开发者ID:jhcepas，项目名称:scikit-bio，代码行数:36，代码来源:test_alignment.py


示例13: str

from qiime_default_reference import get_template_alignment, get_reference_sequences

from skbio import SequenceCollection

gapped_sequences = [(s.id, str(s)) for s in SequenceCollection.read(get_template_alignment())][:500]

sequences = [(s.id, str(s)) for s in SequenceCollection.read(get_reference_sequences())][:500]

motif_1 = "GGTGCAAGCCGGTGGAAACA"
开发者ID:bctaylor，项目名称:sequence-benchmarks，代码行数:9，代码来源:test_data.py


示例14: test_from_fasta_records

 def test_from_fasta_records(self):
     """Initialization from list of tuples functions as expected
     """
     SequenceCollection.from_fasta_records(self.seqs1_t, DNASequence)
     SequenceCollection.from_fasta_records(self.seqs2_t, RNASequence)
     SequenceCollection.from_fasta_records(self.seqs3_t, NucleotideSequence)
开发者ID:nbresnick，项目名称:scikit-bio，代码行数:6，代码来源:test_alignment.py


示例15: SequenceCollectionTests

class SequenceCollectionTests(TestCase):

    """Tests of the SequenceCollection class """

    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 test_init(self):
        """Initialization functions as expected with varied input types
        """
        SequenceCollection(self.seqs1)
        SequenceCollection(self.seqs2)
        SequenceCollection(self.seqs3)
        SequenceCollection([])

    def test_init_fail(self):
        """initialization with sequences with overlapping ids fails
        """
        s1 = [self.d1, self.d1]
        self.assertRaises(SequenceCollectionError, SequenceCollection, s1)

    def test_init_validate(self):
        """initialization with validation functions as expected
        """
        SequenceCollection(self.seqs1, validate=True)
        SequenceCollection(self.seqs1, validate=True)
        # can't validate self.seqs2 as a DNASequence
        self.assertRaises(SequenceCollectionError, SequenceCollection,
                          self.invalid_s1, validate=True)

    def test_from_fasta_records(self):
        """Initialization from list of tuples functions as expected
        """
        SequenceCollection.from_fasta_records(self.seqs1_t, DNASequence)
        SequenceCollection.from_fasta_records(self.seqs2_t, RNASequence)
        SequenceCollection.from_fasta_records(self.seqs3_t, NucleotideSequence)

    def test_contains(self):
        """in operator functions as expected
        """
        self.assertTrue('d1' in self.s1)
        self.assertTrue('r2' in self.s2)
        self.assertFalse('r2' in self.s1)

    def test_eq(self):
        """equality operator functions as expected
        """
        self.assertTrue(self.s1 == self.s1)
        self.assertFalse(self.s1 == self.s2)

        # different objects can be equal
        self.assertTrue(self.s1 == SequenceCollection([self.d1, self.d2]))
        self.assertTrue(SequenceCollection([self.d1, self.d2]) == self.s1)

        # SequenceCollections with different number of sequences are not equal
        self.assertFalse(self.s1 == SequenceCollection([self.d1]))

        class FakeSequenceCollection(SequenceCollection):
            pass
        # SequenceCollections of different types are not equal
        self.assertFalse(self.s1 == FakeSequenceCollection([self.d1, self.d2]))
        self.assertFalse(self.s1 == Alignment([self.d1, self.d2]))

        # SequenceCollections with different sequences are not equal
        self.assertFalse(self.s1 == SequenceCollection([self.d1, self.r1]))

    def test_getitem(self):
        """getitem functions as expected
        """
        self.assertEqual(self.s1[0], self.d1)
        self.assertEqual(self.s1[1], self.d2)
        self.assertEqual(self.s2[0], self.r1)
#.........这里部分代码省略.........
开发者ID:nbresnick，项目名称:scikit-bio，代码行数:101，代码来源:test_alignment.py


示例16: SequenceCollectionTests

class SequenceCollectionTests(TestCase):
    def setUp(self):
        self.d1 = DNA('GATTACA', metadata={'id': "d1"})
        self.d2 = DNA('TTG', metadata={'id': "d2"})
        self.d3 = DNA('GTATACA', metadata={'id': "d3"})
        self.r1 = RNA('GAUUACA', metadata={'id': "r1"})
        self.r2 = RNA('UUG', metadata={'id': "r2"})
        self.r3 = RNA('U-----UGCC--', metadata={'id': "r3"})

        self.seqs1 = [self.d1, self.d2]
        self.seqs2 = [self.r1, self.r2, self.r3]
        self.seqs3 = self.seqs1 + self.seqs2
        self.seqs4 = [self.d1, self.d3]

        self.s1 = SequenceCollection(self.seqs1)
        self.s2 = SequenceCollection(self.seqs2)
        self.s3 = SequenceCollection(self.seqs3)
        self.s4 = SequenceCollection(self.seqs4)
        self.empty = SequenceCollection([])

    def test_init(self):
        SequenceCollection(self.seqs1)
        SequenceCollection(self.seqs2)
        SequenceCollection(self.seqs3)
        SequenceCollection([])

    def test_init_fail(self):
        # sequences with overlapping ids
        s1 = [self.d1, self.d1]
        self.assertRaises(SequenceCollectionError, SequenceCollection, s1)

    def test_init_fail_no_id(self):
        seq = Sequence('ACGTACGT')
        with six.assertRaisesRegex(self, SequenceCollectionError,
                                   "'id' must be included in the sequence "
                                   "metadata"):
            SequenceCollection([seq])

    def test_contains(self):
        self.assertTrue('d1' in self.s1)
        self.assertTrue('r2' in self.s2)
        self.assertFalse('r2' in self.s1)

    def test_eq(self):
        self.assertTrue(self.s1 == self.s1)
        self.assertFalse(self.s1 == self.s2)

        # different objects can be equal
        self.assertTrue(self.s1 == SequenceCollection([self.d1, self.d2]))
        self.assertTrue(SequenceCollection([self.d1, self.d2]) == self.s1)

        # SequenceCollections with different number of sequences are not equal
        self.assertFalse(self.s1 == SequenceCollection([self.d1]))

        class FakeSequenceCollection(SequenceCollection):
            pass
        # SequenceCollections of different types are not equal
        self.assertFalse(self.s4 == FakeSequenceCollection([self.d1, self.d3]))
        self.assertFalse(self.s4 == Alignment([self.d1, self.d3]))

        # SequenceCollections with different sequences are not equal
        self.assertFalse(self.s1 == SequenceCollection([self.d1, self.r1]))

    def test_getitem(self):
        self.assertEqual(self.s1[0], self.d1)
        self.assertEqual(self.s1[1], self.d2)
        self.assertEqual(self.s2[0], self.r1)
        self.assertEqual(self.s2[1], self.r2)

        self.assertRaises(IndexError, self.empty.__getitem__, 0)
        self.assertRaises(KeyError, self.empty.__getitem__, '0')

    def test_iter(self):
        s1_iter = iter(self.s1)
        count = 0
        for actual, expected in zip(s1_iter, self.seqs1):
            count += 1
            self.assertEqual(actual, expected)
        self.assertEqual(count, len(self.seqs1))
        self.assertRaises(StopIteration, lambda: next(s1_iter))

    def test_len(self):
        self.assertEqual(len(self.s1), 2)
        self.assertEqual(len(self.s2), 3)
        self.assertEqual(len(self.s3), 5)
        self.assertEqual(len(self.empty), 0)

    def test_ne(self):
        self.assertFalse(self.s1 != self.s1)
        self.assertTrue(self.s1 != self.s2)

        # SequenceCollections with different number of sequences are not equal
        self.assertTrue(self.s1 != SequenceCollection([self.d1]))

        class FakeSequenceCollection(SequenceCollection):
            pass
        # SequenceCollections of different types are not equal
        self.assertTrue(self.s4 != FakeSequenceCollection([self.d1, self.d3]))
        self.assertTrue(self.s4 != Alignment([self.d1, self.d3]))

#.........这里部分代码省略.........
开发者ID:jhcepas，项目名称:scikit-bio，代码行数:101，代码来源:test_alignment.py


示例17: SequenceCollectionTests

class SequenceCollectionTests(TestCase):
    def setUp(self):
        self.d1 = DNASequence('GATTACA', id="d1")
        self.d2 = DNASequence('TTG', id="d2")
        self.d3 = DNASequence('GTATACA', id="d3")
        self.d1_lower = DNASequence('gattaca', id="d1")
        self.d2_lower = DNASequence('ttg', id="d2")
        self.d3_lower = DNASequence('gtataca', id="d3")
        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.seqs4 = [self.d1, self.d3]

        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.s4 = SequenceCollection(self.seqs4)
        self.empty = SequenceCollection([])

        self.invalid_s1 = SequenceCollection([self.i1])

    def test_init(self):
        SequenceCollection(self.seqs1)
        SequenceCollection(self.seqs2)
        SequenceCollection(self.seqs3)
        SequenceCollection([])

    def test_init_fail(self):
        # sequences with overlapping ids
        s1 = [self.d1, self.d1]
        self.assertRaises(SequenceCollectionError, SequenceCollection, s1)

    def test_init_validate(self):
        SequenceCollection(self.seqs1, validate=True)
        SequenceCollection(self.seqs1, validate=True)
        # can't validate self.seqs2 as a DNASequence
        self.assertRaises(SequenceCollectionError, SequenceCollection,
                          self.invalid_s1, validate=True)

    def test_contains(self):
        self.assertTrue('d1' in self.s1)
        self.assertTrue('r2' in self.s2)
        self.assertFalse('r2' in self.s1)

    def test_eq(self):
        self.assertTrue(self.s1 == self.s1)
        self.assertFalse(self.s1 == self.s2)

        # different objects can be equal
        self.assertTrue(self.s1 == SequenceCollection([self.d1, self.d2]))
        self.assertTrue(SequenceCollection([self.d1, self.d2]) == self.s1)

        # SequenceCollections with different number of sequences are not equal
        self.assertFalse(self.s1 == SequenceCollection([self.d1]))

        class FakeSequenceCollection(SequenceCollection):
            pass
        # SequenceCollections of different types are not equal
        self.assertFalse(self.s4 == FakeSequenceCollection([self.d1, self.d3]))
        self.assertFalse(self.s4 == Alignment([self.d1, self.d3]))

        # SequenceCollections with different sequences are not equal
        self.assertFalse(self.s1 == SequenceCollection([self.d1, self.r1]))

    def test_getitem(self):
        self.assertEqual(self.s1[0], self.d1)
        self.assertEqual(self.s1[1], self.d2)
        self.assertEqual(self.s2[0], self.r1)
        self.assertEqual(self.s2[1], self.r2)

        self.assertRaises(IndexError, self.empty.__getitem__, 0)
        self.assertRaises(KeyError, self.empty.__getitem__, '0')

    def test_iter(self):
        s1_iter = iter(self.s1)
        count = 0
        for actual, expected in zip(s1_iter, self.seqs1):
            count += 1
            self.assertEqual(actual, expected)
        self.assertEqual(count, len(self.seqs1))
        self.assertRaises(StopIteration, lambda: next(s1_iter))

    def test_len(self):
        self.assertEqual(len(self.s1), 2)
        self.assertEqual(len(self.s2), 3)
        self.assertEqual(len(self.s3), 5)
        self.assertEqual(len(self.empty), 0)
#.........这里部分代码省略.........
开发者ID:AndreaEdwards，项目名称:scikit-bio，代码行数:101，代码来源:test_alignment.py


示例18: get_argument_parser

    log_choices = ["DEBUG", "INFO", "WARNING", "ERROR", "CRITICAL"]
    parser.add_argument(
        '--log-level', '-l', default="INFO", choices=log_choices,
        help="Set logging level. Default is info."
    )

    return parser

if __name__ == '__main__':
    parser = get_argument_parser()
    args = parser.parse_args()

    level = getattr(logging, args.log_level.upper(), logging.INFO)
    logging.basicConfig(level=level)

    sequences = SequenceCollection.read(args.infile, format=args.format)

    if args.parallel == 0 and len(sequences) > 16:
        pool_size = multiprocessing.cpu_count()
    else:
        pool_size = 1

    dmatrix = create_distance_matrix(sequences, d2.distance, pool_size,
                                     statistic=d2.d2_neighbourhood_dna)

    print(dmatrix)
    phylo_tree = nj(dmatrix)
    print(phylo_tree.ascii_art())
    phylo_tree.write(args.outfile, format=args.target)
开发者ID:sh4wn，项目名称:af-phylogeny，代码行数:29，代码来源:af-phylogeny.py



注：本文中的skbio.SequenceCollection类示例由纯净天空整理自Github/MSDocs等源码及文档管理平台，相关代码片段筛选自各路编程大神贡献的开源项目，源码版权归原作者所有，传播和使用请参考对应项目的License；未经允许，请勿转载。

鲜花
握手
雷人
路过
鸡蛋
该文章已有0人参与评论

请发表评论

全部评论

专题导读
More+
上一篇：
Python skbio.TabularMSA类代码示例发布时间：2022-05-27
下一篇：
Python skbio.DistanceMatrix类代码示例发布时间：2022-05-27
热门推荐
More+
热门话题
More+
阅读排行榜

扫描微信二维码

查看手机版网站

随时了解更新最新资讯

139-2527-9053

在线客服（服务时间 9:00～18:00）

在线QQ客服
地址：深圳市南山区西丽大学城创智工业园
电邮：jeky_zhao#qq.com
移动电话：139-2527-9053

Powered by 互联科技 X3.4© 2001-2213 极客世界.|Sitemap