Reference
---------
.. [#] ftp://ftp.ebi.ac.uk/pub/databases/embl/doc/usrman.txt
'''
from skbio.io import create_format, FileFormatError
from skbio.sequence import Sequence, DNA, RNA, Protein
from skbio.io.format._base import (_line_generator, _get_nth_sequence,
_too_many_blanks)
class EMBLFormatError(FileFormatError):
pass
embl = create_format('embl')
# This list is ordered. From EMBL specification
_HEADERS = [
'ID', # identification (begins each entry; 1 per entry)
'AC', # accession number (>=1 per entry)
'PR', # project identifier (0 or 1 per entry)
'DT', # date (2 per entry)
'DE', # description (>=1 per entry)
'KW', # keyword (>=1 per entry)
'OS', # organism species (>=1 per entry)
'OC', # organism classification (>=1 per entry)
'OG', # organelle (0 or 1 per entry)
'RN', # reference number (>=1 per entry)
'RC', # reference comment (>=0 per entry)
'RP', # reference positions (>=1 per entry)
from __future__ import (absolute_import, division, print_function,
unicode_literals)
from future.builtins import zip, range
from skbio.io import create_format, QSeqFormatError
from skbio.io.format._base import _decode_qual_to_phred, _get_nth_sequence
from skbio.alignment import SequenceCollection
from skbio.sequence import Sequence, DNA, RNA, Protein
_default_phred_offset = None
_default_variant = None
_will_filter = True
qseq = create_format('qseq')
@qseq.sniffer()
def _qseq_sniffer(fh):
empty = True
try:
for _, line in zip(range(10), fh):
_record_parser(line)
empty = False
return not empty, {}
except QSeqFormatError:
return False, {}
@qseq.reader(None)
"""
# ----------------------------------------------------------------------------
# Copyright (c) 2013--, scikit-bio development team.
#
# Distributed under the terms of the Modified BSD License.
#
# The full license is in the file COPYING.txt, distributed with this software.
# ----------------------------------------------------------------------------
import pandas as pd
from skbio.io import create_format, BLAST7FormatError
from skbio.io.format._blast import _parse_blast_data
blast7 = create_format('blast+7')
column_converter = {
'query id': 'qseqid',
'query gi': 'qgi',
'query acc.': 'qacc',
'query acc.ver': 'qaccver',
'query length': 'qlen',
'subject id': 'sseqid',
'subject ids': 'sallseqid',
'subject gi': 'sgi',
'subject gis': 'sallgi',
'subject acc.': 'sacc',
'subject acc.ver': 'saccver',
'subject accs.': 'sallacc',
'subject length': 'slen',
#
# Distributed under the terms of the Modified BSD License.
#
# The full license is in the file COPYING.txt, distributed with this software.
# ----------------------------------------------------------------------------
from __future__ import (absolute_import, division, print_function,
unicode_literals)
import functools
import pandas as pd
from skbio.io import create_format
blast6 = create_format('blast+6')
_possible_columns = {'qseqid': str, 'qgi': float, 'qacc': str, 'qaccver': str,
'qlen': float, 'sseqid': str, 'sallseqid': str,
'sgi': float, 'sallgi': float, 'sacc': str,
'saccver': str, 'sallacc': str, 'slen': float,
'qstart': float, 'qend': float, 'sstart': float,
'send': float, 'qseq': str, 'sseq': str,
'evalue': float, 'bitscore': float, 'score': float,
'length': float, 'pident': float, 'nident': float,
'mismatch': float, 'positive': float, 'gapopen': float,
'gaps': float, 'ppos': float, 'frames': str,
'qframe': float, 'sframe': float, 'btop': float,
'staxids': str, 'sscinames': str, 'scomnames': str,
'sblastnames': str, 'sskingdoms': str, 'stitle': str,
'salltitles': str, 'sstrand': str, 'qcovs': float,
# ----------------------------------------------------------------------------
# Copyright (c) 2015--, micronota development team.
#
# Distributed under the terms of the Modified BSD License.
#
# The full license is in the file COPYING.txt, distributed with this software.
# ----------------------------------------------------------------------------
import re
from skbio.metadata import IntervalMetadata
from skbio.io import create_format
from ..util import split, split_head
transtermhp = create_format('transtermhp')
@transtermhp.reader(None)
def _generator(fh):
'''Parse the annotation and add it to interval metadata.
Parameters
----------
f : str
the file path from prediction
Yield
-----
tuple of str and IntervalMetadata
seq_id and interval metadata
#
# Distributed under the terms of the Modified BSD License.
#
# The full license is in the file COPYING.txt, distributed with this software.
# ----------------------------------------------------------------------------
from __future__ import (absolute_import, division, print_function,
unicode_literals)
from skbio.alignment import Alignment
from skbio.sequence import Sequence
from skbio.io import create_format, PhylipFormatError
from skbio.util._misc import chunk_str
phylip = create_format('phylip')
@phylip.sniffer()
def _phylip_sniffer(fh):
# Strategy:
# Read the header and a single sequence; verify that the sequence length
# matches the header information. Do not verify that the total number of
# lines matches the header information, since that would require reading
# the whole file.
try:
header = next(_line_generator(fh))
_, seq_len = _validate_header(header)
line = next(_line_generator(fh))
_validate_line(line, seq_len)
except (StopIteration, PhylipFormatError):
# ----------------------------------------------------------------------------
# Copyright (c) 2015--, micronota development team.
#
# Distributed under the terms of the Modified BSD License.
#
# The full license is in the file COPYING.txt, distributed with this software.
# ----------------------------------------------------------------------------
from skbio.metadata import IntervalMetadata
from skbio.io import create_format
from ..util import split, split_head
tandem_repeats_finder = create_format('tandem_repeats_finder')
@tandem_repeats_finder.reader(None)
def _generator(fh):
'''Parse the annotation and add it to interval metadata.
Parameters
----------
fp : str
the file path from Tandem Repeat Finder prediction
Yield
-----
tuple of str and IntervalMetadata
seq_id and interval metadata
'''
splitter = split(split_head, is_head=lambda line: line.startswith('@'))
# Copyright (c) 2013--, scikit-bio development team.
#
# Distributed under the terms of the Modified BSD License.
#
# The full license is in the file COPYING.txt, distributed with this software.
# ----------------------------------------------------------------------------
from __future__ import (absolute_import, division, print_function,
unicode_literals)
import pandas as pd
from skbio.io import create_format
from skbio.io.format._blast import _parse_blast_data, _possible_columns
blast6 = create_format('blast+6')
_default_columns = [
'qseqid', 'sseqid', 'pident', 'length', 'mismatch', 'gapopen', 'qstart',
'qend', 'sstart', 'send', 'evalue', 'bitscore'
]
@blast6.reader(pd.DataFrame, monkey_patch=False)
def _blast6_to_data_frame(fh, columns=None, default_columns=False):
if default_columns and columns is not None:
raise ValueError("`columns` and `default_columns` cannot both be"
" provided.")
if not default_columns and columns is None:
raise ValueError("Either `columns` or `default_columns` must be"
" provided.")
import re
from skbio.io import create_format
from skbio.metadata import IntervalMetadata
from ..util import split, split_head
aragorn = create_format('aragorn')
@aragorn.reader(None)
def _generator(fh):
# aragorn output has a final summary line like this:
# >end 5 sequences 97 tRNA genes 1 tmRNA genes
# This line should be skipped and not parsed
p = re.compile(r'>end\s+\d+ sequences \d+ tRNA genes \d+ tmRNA genes')
splitter = split(split_head)
for lines in splitter(fh):
headline = lines[0]
if p.match(headline):
return
sid = headline.split(None, 1)[0][1:]
yield sid, _parse_record(lines[2:])
def _parse_record(lines):
'''Return interval metadata.'''
imd = IntervalMetadata(None)
for line in lines:
bounds, md = _parse_line(line)
imd.add(bounds, metadata=md)
# Distributed under the terms of the Modified BSD License.
#
# The full license is in the file COPYING.txt, distributed with this software.
# ----------------------------------------------------------------------------
from __future__ import (absolute_import, division, print_function,
unicode_literals)
from future.builtins import zip
import numpy as np
import pandas as pd
from skbio._base import OrdinationResults
from skbio.io import create_format, OrdinationFormatError
ordination = create_format('ordination')
@ordination.sniffer()
def _ordination_sniffer(fh):
# Smells an ordination file if *all* of the following lines are present
# *from the beginning* of the file:
# - eigvals header (minimally parsed)
# - another line (contents ignored)
# - a whitespace-only line
# - proportion explained header (minimally parsed)
try:
_parse_header(fh, 'Eigvals', 1)
next_line = next(fh, None)
if next_line is not None:
# The full license is in the file COPYING.txt, distributed with this software.
# ----------------------------------------------------------------------------
from __future__ import absolute_import, division, print_function, unicode_literals
from future.builtins import zip, range
from skbio.io import create_format, QSeqFormatError
from skbio.io.format._base import _decode_qual_to_phred, _get_nth_sequence
from skbio.sequence import Sequence, DNA, RNA, Protein
_default_phred_offset = None
_default_variant = None
_will_filter = True
qseq = create_format("qseq")
@qseq.sniffer()
def _qseq_sniffer(fh):
empty = True
try:
for _, line in zip(range(10), fh):
_record_parser(line)
empty = False
return not empty, {}
except QSeqFormatError:
return False, {}
@qseq.reader(None)
# ----------------------------------------------------------------------------
# Copyright (c) 2013--, scikit-bio development team.
#
# Distributed under the terms of the Modified BSD License.
#
# The full license is in the file COPYING.txt, distributed with this software.
# ----------------------------------------------------------------------------
from __future__ import absolute_import, division, print_function, unicode_literals
from skbio.alignment import Alignment
from skbio.io import create_format, PhylipFormatError
from skbio.util._misc import chunk_str
phylip = create_format("phylip")
@phylip.writer(Alignment)
def _alignment_to_phylip(obj, fh):
if obj.is_empty():
raise PhylipFormatError(
"Alignment can only be written in PHYLIP format if there is at " "least one sequence in the alignment."
)
sequence_length = obj.sequence_length()
if sequence_length == 0:
raise PhylipFormatError(
"Alignment can only be written in PHYLIP format if there is at " "least one position in the alignment."
)
|Yes |No |generator of :mod:`skbio.sequence.Sequence` objects |
+------+------+---------------------------------------------------------------+
Reference
---------
.. [#] https://samtools.github.io/hts-specs/SAMv1.pdf
'''
from skbio.io import create_format
from skbio.sequence import Sequence, DNA, RNA, Protein
from skbio.io.format._base import (
_line_generator, _get_nth_sequence, _too_many_blanks)
sam = create_format('sam')
# Alignment headers
_REQUIRED_FIELDS = [
'QNAME', # Query template NAME.
'FLAG', # Combination of bitwise FLAGs
'RNAME', # Reference sequence NAME of the alignment
'POS', # 1-based leftmost mapping position of the first base
'MAPQ', # Mapping quality. -10log10(P_err).
'CIGAR', # CIGAR string
'RNEXT', # Reference sequence name of the primary alignment of NEXT
'PNEXT', # Position of the primary alignment of the NEXT read
'TLEN', # signed observed template length
'SEQ', # segment sequence
'QUAL', # ASCII of base quality
]
# The full license is in the file COPYING.txt, distributed with this software.
# ----------------------------------------------------------------------------
import re
from functools import partial
from skbio.io import create_format, GenBankFormatError
from skbio.io.format._base import (_get_nth_sequence, _line_generator,
_too_many_blanks)
from skbio.util._misc import chunk_str
from skbio.sequence import Sequence, DNA, RNA, Protein
from skbio.io.format._sequence_feature_vocabulary import (
_yield_section, _parse_section_default, _serialize_section_default,
_parse_feature_table, _serialize_feature_table)
genbank = create_format('genbank')
# This list is ordered
# used to read and write genbank file.
_HEADERS = [
'LOCUS', 'DEFINITION', 'ACCESSION', 'VERSION', 'DBSOURCE', 'DBLINK',
'KEYWORDS', 'SOURCE', 'REFERENCE', 'COMMENT', 'FEATURES', 'ORIGIN'
]
@genbank.sniffer()
def _genbank_sniffer(fh):
# check the 1st real line is a valid LOCUS line
if _too_many_blanks(fh, 5):
return False, {}
try:
# ----------------------------------------------------------------------------
# Copyright (c) 2013--, scikit-bio development team.
#
# Distributed under the terms of the Modified BSD License.
#
# The full license is in the file COPYING.txt, distributed with this software.
# ----------------------------------------------------------------------------
import numpy as np
import pandas as pd
from skbio._base import OrdinationResults
from skbio.io import create_format, OrdinationFormatError
ordination = create_format('ordination')
@ordination.sniffer()
def _ordination_sniffer(fh):
# Smells an ordination file if *all* of the following lines are present
# *from the beginning* of the file:
# - eigvals header (minimally parsed)
# - another line (contents ignored)
# - a whitespace-only line
# - proportion explained header (minimally parsed)
try:
_parse_header(fh, 'Eigvals', 1)
next_line = next(fh, None)
if next_line is not None:
.. [2] http://evolution.genetics.washington.edu/phylip/newicktree.html
"""
# ----------------------------------------------------------------------------
# Copyright (c) 2013--, scikit-bio development team.
#
# Distributed under the terms of the Modified BSD License.
#
# The full license is in the file COPYING.txt, distributed with this software.
# ----------------------------------------------------------------------------
from skbio.io import create_format, NewickFormatError
from skbio.tree import TreeNode
newick = create_format('newick')
@newick.sniffer()
def _newick_sniffer(fh):
# Strategy:
# The following conditions preclude a file from being newick:
# * It is an empty file.
# * There is whitespace inside of a label (handled by tokenizer)
# * : is followed by anything that is an operator
# * ( is not preceded immediately by , or another (
# * The parens are unablanced when ; is found.
# If 100 tokens (or less if EOF occurs earlier) then it is probably
# newick, or at least we can't prove it isn't.
operators = set(",;:()")
empty = True
# ----------------------------------------------------------------------------
import re
from collections import Iterable
from skbio.sequence import DNA, Sequence
from skbio.io import create_format, GFF3FormatError
from skbio.metadata import IntervalMetadata
from skbio.io.format._base import (_line_generator, _too_many_blanks,
_get_nth_sequence)
from skbio.io.format.fasta import _fasta_to_generator
from skbio.io.format._sequence_feature_vocabulary import (_vocabulary_change,
_vocabulary_skip)
from skbio.io import write
gff3 = create_format('gff3')
@gff3.sniffer()
def _gff3_sniffer(fh):
# check the 1st real line is a valid ID line
if _too_many_blanks(fh, 5):
return False, {}
try:
line = next(_line_generator(fh, skip_blanks=True, strip=False))
except StopIteration:
return False, {}
if re.match(r'##gff-version\s+3', line):
return True, {}
# ----------------------------------------------------------------------------
# Copyright (c) 2013--, scikit-bio development team.
#
# Distributed under the terms of the Modified BSD License.
#
# The full license is in the file COPYING.txt, distributed with this software.
# ----------------------------------------------------------------------------
from collections import OrderedDict
from skbio.alignment import TabularMSA
from skbio.sequence._grammared_sequence import GrammaredSequence
from skbio.io import create_format, StockholmFormatError
stockholm = create_format('stockholm')
@stockholm.sniffer()
def _stockholm_sniffer(fh):
# Smells a Stockholm file if the following conditions are met:
# - File isn't empty
# - File contains correct header
try:
line = next(fh)
except StopIteration:
return False, {}
if _is_header(line):
return True, {}
Reference
---------
.. [#] ftp://ftp.ebi.ac.uk/pub/databases/embl/doc/usrman.txt
'''
from skbio.io import create_format, FileFormatError
from skbio.sequence import Sequence, DNA, RNA, Protein
from skbio.io.format._base import (
_line_generator, _get_nth_sequence, _too_many_blanks)
class EMBLFormatError(FileFormatError):
pass
embl = create_format('embl')
# This list is ordered. From EMBL specification
_HEADERS = ['ID', # identification (begins each entry; 1 per entry)
'AC', # accession number (>=1 per entry)
'PR', # project identifier (0 or 1 per entry)
'DT', # date (2 per entry)
'DE', # description (>=1 per entry)
'KW', # keyword (>=1 per entry)
'OS', # organism species (>=1 per entry)
'OC', # organism classification (>=1 per entry)
'OG', # organelle (0 or 1 per entry)
'RN', # reference number (>=1 per entry)
'RC', # reference comment (>=0 per entry)
'RP', # reference positions (>=1 per entry)
'RX', # reference cross-reference (>=0 per entry)
import textwrap
import numpy as np
from skbio.io import create_format, FASTAFormatError, QUALFormatError
from skbio.io.registry import FileSentinel
from skbio.io.format._base import (_get_nth_sequence,
_parse_fasta_like_header,
_format_fasta_like_records, _line_generator,
_too_many_blanks)
from skbio.util._misc import chunk_str
from skbio.alignment import TabularMSA
from skbio.sequence import Sequence, DNA, RNA, Protein
fasta = create_format('fasta')
@fasta.sniffer()
def _fasta_sniffer(fh):
# Strategy:
# Ignore up to 5 blank/whitespace-only lines at the beginning of the
# file. Read up to 10 records. If at least one record is read (i.e.
# the file isn't empty) and no errors are thrown during reading, assume
# the file is in FASTA format. If a record appears to be QUAL, do *not*
# identify the file as FASTA since we don't want to sniff QUAL files as
# FASTA (technically they can be read as FASTA since the sequences may
# not be validated but it probably isn't what the user wanted). Also, if
# we add QUAL as its own file format in the future, we wouldn't want the
# FASTA and QUAL sniffers to both positively identify a QUAL file.
if _too_many_blanks(fh, 5):
"""
# ----------------------------------------------------------------------------
# Copyright (c) 2013--, scikit-bio development team.
#
# Distributed under the terms of the Modified BSD License.
#
# The full license is in the file COPYING.txt, distributed with this software.
# ----------------------------------------------------------------------------
import pandas as pd
from skbio.io import create_format
from skbio.io.format._blast import _parse_blast_data, _possible_columns
blast6 = create_format("blast+6")
_default_columns = [
"qseqid",
"sseqid",
"pident",
"length",
"mismatch",
"gapopen",
"qstart",
"qend",
"sstart",
"send",
"evalue",
"bitscore",
]
**Has Sniffer: Yes**
Format Specification
--------------------
An empty file consists of only whitespace characters.
"""
# ----------------------------------------------------------------------------
# Copyright (c) 2013--, scikit-bio development team.
#
# Distributed under the terms of the Modified BSD License.
#
# The full license is in the file COPYING.txt, distributed with this software.
# ----------------------------------------------------------------------------
from __future__ import (absolute_import, division, print_function,
unicode_literals)
from skbio.io import create_format
emptyfile = create_format('<emptyfile>')
@emptyfile.sniffer()
def _empty_file_sniffer(fh):
for line in fh:
if line.strip():
return False, {}
return True, {}
# ----------------------------------------------------------------------------
# Copyright (c) 2013--, scikit-bio development team.
#
# Distributed under the terms of the Modified BSD License.
#
# The full license is in the file COPYING.txt, distributed with this software.
# ----------------------------------------------------------------------------
import csv
import numpy as np
from skbio.stats.distance import DissimilarityMatrix, DistanceMatrix
from skbio.io import create_format, LSMatFormatError
lsmat = create_format('lsmat')
@lsmat.sniffer()
def _lsmat_sniffer(fh):
header = _find_header(fh)
if header is not None:
try:
dialect = csv.Sniffer().sniff(header)
delimiter = dialect.delimiter
ids = _parse_header(header, delimiter)
first_id, _ = next(_parse_data(fh, delimiter), (None, None))
if first_id is not None and first_id == ids[0]:
import re
from collections import Iterable
from skbio.sequence import DNA, Sequence
from skbio.io import create_format, GFF3FormatError
from skbio.metadata import IntervalMetadata
from skbio.io.format._base import (
_line_generator, _too_many_blanks, _get_nth_sequence)
from skbio.io.format.fasta import _fasta_to_generator
from skbio.io.format._sequence_feature_vocabulary import (
_vocabulary_change, _vocabulary_skip)
from skbio.io import write
gff3 = create_format('gff3')
@gff3.sniffer()
def _gff3_sniffer(fh):
# check the 1st real line is a valid ID line
if _too_many_blanks(fh, 5):
return False, {}
try:
line = next(_line_generator(fh, skip_blanks=True, strip=False))
except StopIteration:
return False, {}
if re.match(r'##gff-version\s+3', line):
return True, {}
# Copyright (c) 2013--, scikit-bio development team.
#
# Distributed under the terms of the Modified BSD License.
#
# The full license is in the file COPYING.txt, distributed with this software.
# ----------------------------------------------------------------------------
from __future__ import absolute_import, division, print_function, unicode_literals
from collections import OrderedDict
from skbio.alignment import TabularMSA
from skbio.sequence._iupac_sequence import IUPACSequence
from skbio.io import create_format, StockholmFormatError
stockholm = create_format("stockholm")
@stockholm.sniffer()
def _stockholm_sniffer(fh):
# Smells a Stockholm file if the following conditions are met:
# - File isn't empty
# - File contains correct header
try:
line = next(fh)
except StopIteration:
return False, {}
if _is_header(line):
return True, {}
# ----------------------------------------------------------------------------
# Copyright (c) 2015--, micronota development team.
#
# Distributed under the terms of the Modified BSD License.
#
# The full license is in the file COPYING.txt, distributed with this software.
# ----------------------------------------------------------------------------
from logging import getLogger
from skbio.metadata import IntervalMetadata
from skbio.io import create_format
from ..util import split, SplitterID
rnammer = create_format('rnammer')
@rnammer.reader(None)
def _generator(fh):
'''Parse the annotation and add it to interval metadata.
Parameters
----------
fn : str
the file name from RNAmmer prediction
Yield
-----
tuple of str and IntervalMetadata
seq_id and interval metadata
from six.moves import zip_longest
import textwrap
import numpy as np
from skbio.io import create_format, FASTAFormatError, QUALFormatError
from skbio.io.registry import FileSentinel
from skbio.io.format._base import (_get_nth_sequence, _parse_fasta_like_header,
_format_fasta_like_records, _line_generator,
_too_many_blanks)
from skbio.util._misc import chunk_str
from skbio.alignment import SequenceCollection, Alignment
from skbio.sequence import Sequence, DNA, RNA, Protein
fasta = create_format('fasta')
@fasta.sniffer()
def _fasta_sniffer(fh):
# Strategy:
# Ignore up to 5 blank/whitespace-only lines at the beginning of the
# file. Read up to 10 records. If at least one record is read (i.e.
# the file isn't empty) and no errors are thrown during reading, assume
# the file is in FASTA format. If a record appears to be QUAL, do *not*
# identify the file as FASTA since we don't want to sniff QUAL files as
# FASTA (technically they can be read as FASTA since the sequences may
# not be validated but it probably isn't what the user wanted). Also, if
# we add QUAL as its own file format in the future, we wouldn't want the
# FASTA and QUAL sniffers to both positively identify a QUAL file.
if _too_many_blanks(fh, 5):
# ----------------------------------------------------------------------------
# Copyright (c) 2013--, scikit-bio development team.
#
# Distributed under the terms of the Modified BSD License.
#
# The full license is in the file COPYING.txt, distributed with this software.
# ----------------------------------------------------------------------------
import numpy as np
import pandas as pd
from skbio.stats.ordination import OrdinationResults
from skbio.io import create_format, OrdinationFormatError
ordination = create_format("ordination")
@ordination.sniffer()
def _ordination_sniffer(fh):
# Smells an ordination file if *all* of the following lines are present
# *from the beginning* of the file:
# - eigvals header (minimally parsed)
# - another line (contents ignored)
# - a whitespace-only line
# - proportion explained header (minimally parsed)
try:
_parse_header(fh, "Eigvals", 1)
next_line = next(fh, None)
if next_line is not None:
Reference
---------
.. [1] Eric P. Nawrocki and Sean R. Eddy, "Infernal 1.1: 100-fold faster RNA
homology searches", Bioinformatics 2013,
doi: 10.1093/bioinformatics/btt509
'''
from skbio.io import create_format, FileFormatError
from skbio.metadata import IntervalMetadata, Feature
from skbio.io.format._base import (_line_generator, _too_many_blanks)
from skbio.io.format._base import _get_nth_sequence as _get_nth_record
cmscan = create_format('cmscan')
# column headers
_COLUMNS = ['MODEL_NAME', 'MODEL_ACCESSION', 'SEQUENCE_NAME',
'SEQUENCE_ACCESSION', 'TYPE_OF_MODEL', 'MODEL_START_POSITION',
'MODEL_END_POSITION', 'SEQUENCE_START_POSITION',
'SEQUENCE_END_POSITION', 'STRAND', 'TRUNCATED', 'PASS',
'GC_CONTENT', 'BIAS', 'BITSCORE', 'EVALUE', 'INC', 'DESCRIPTION']
class CmscanFormatError(FileFormatError):
pass
def _construct(record, constructor=None, **kwargs):
if constructor is None:
"""
# ----------------------------------------------------------------------------
# Copyright (c) 2013--, scikit-bio development team.
#
# Distributed under the terms of the Modified BSD License.
#
# The full license is in the file COPYING.txt, distributed with this software.
# ----------------------------------------------------------------------------
from skbio.alignment import TabularMSA
from skbio.io import create_format, PhylipFormatError
from skbio.util._misc import chunk_str
phylip = create_format('phylip')
@phylip.sniffer()
def _phylip_sniffer(fh):
# Strategy:
# Read the header and a single sequence; verify that the sequence length
# matches the header information. Do not verify that the total number of
# lines matches the header information, since that would require reading
# the whole file.
try:
header = next(_line_generator(fh))
_, seq_len = _validate_header(header)
line = next(_line_generator(fh))
_validate_line(line, seq_len)
except (StopIteration, PhylipFormatError):
import re
import numpy as np
from skbio.io import create_format, FASTQFormatError
from skbio.io.format._base import (
_decode_qual_to_phred, _encode_phred_to_qual, _get_nth_sequence,
_parse_fasta_like_header, _format_fasta_like_records, _line_generator,
_too_many_blanks)
from skbio.alignment import SequenceCollection, Alignment
from skbio.sequence import Sequence, DNA, RNA, Protein
_whitespace_regex = re.compile(r'\s')
fastq = create_format('fastq')
@fastq.sniffer()
def _fastq_sniffer(fh):
# Strategy:
# Ignore up to 5 blank/whitespace-only lines at the beginning of the
# file. Read up to 10 records. If at least one record is read (i.e. the
# file isn't empty) and the quality scores are in printable ASCII range,
# assume the file is FASTQ.
if _too_many_blanks(fh, 5):
return False, {}
try:
not_empty = False
for _ in zip(range(10), _fastq_to_generator(fh, phred_offset=33)):
# Copyright (c) 2013--, scikit-bio development team.
#
# Distributed under the terms of the Modified BSD License.
#
# The full license is in the file COPYING.txt, distributed with this software.
# ----------------------------------------------------------------------------
from __future__ import (absolute_import, division, print_function,
unicode_literals)
import pandas as pd
from skbio.io import create_format, BLAST7FormatError
from skbio.io.format._blast import _parse_blast_data
blast7 = create_format('blast+7')
column_converter = {'query id': 'qseqid', 'query gi': 'qgi',
'query acc.': 'qacc', 'query acc.ver': 'qaccver',
'query length': 'qlen', 'subject id': 'sseqid',
'subject ids': 'sallseqid', 'subject gi': 'sgi',
'subject gis': 'sallgi', 'subject acc.': 'sacc',
'subject acc.ver': 'saccver', 'subject accs.': 'sallacc',
'subject length': 'slen', 'q. start': 'qstart',
'q. end': 'qend', 's. start': 'sstart', 's. end': 'send',
'query seq': 'qseq', 'subject seq': 'sseq',
'evalue': 'evalue', 'bit score': 'bitscore',
'score': 'score', 'alignment length': 'length',
'% identity': 'pident', 'identical': 'nident',
'mismatches': 'mismatch', 'positives': 'positive',
'gap opens': 'gapopen', 'gaps': 'gaps',
import re
import numpy as np
from skbio.io import create_format, FASTQFormatError
from skbio.io.format._base import (_decode_qual_to_phred,
_encode_phred_to_qual, _get_nth_sequence,
_parse_fasta_like_header,
_format_fasta_like_records, _line_generator,
_too_many_blanks)
from skbio.alignment import SequenceCollection, Alignment
from skbio.sequence import Sequence, DNA, RNA, Protein
_whitespace_regex = re.compile(r'\s')
fastq = create_format('fastq')
@fastq.sniffer()
def _fastq_sniffer(fh):
# Strategy:
# Ignore up to 5 blank/whitespace-only lines at the beginning of the
# file. Read up to 10 records. If at least one record is read (i.e. the
# file isn't empty) and the quality scores are in printable ASCII range,
# assume the file is FASTQ.
if _too_many_blanks(fh, 5):
return False, {}
try:
not_empty = False
for _ in zip(range(10), _fastq_to_generator(fh, phred_offset=33)):
.. [2] http://evolution.genetics.washington.edu/phylip/newicktree.html
"""
# ----------------------------------------------------------------------------
# Copyright (c) 2013--, scikit-bio development team.
#
# Distributed under the terms of the Modified BSD License.
#
# The full license is in the file COPYING.txt, distributed with this software.
# ----------------------------------------------------------------------------
from skbio.io import create_format, NewickFormatError
from skbio.tree import TreeNode
newick = create_format('newick')
@newick.sniffer()
def _newick_sniffer(fh):
# Strategy:
# The following conditions preclude a file from being newick:
# * It is an empty file.
# * There is whitespace inside of a label (handled by tokenizer)
# * : is followed by anything that is an operator
# * ( is not preceded immediately by , or another (
# * The parens are unablanced when ; is found.
# If 100 tokens (or less if EOF occurs earlier) then it is probably
# newick, or at least we can't prove it isn't.
operators = set(",;:()")
empty = True
# Copyright (c) 2013--, scikit-bio development team.
#
# Distributed under the terms of the Modified BSD License.
#
# The full license is in the file COPYING.txt, distributed with this software.
# ----------------------------------------------------------------------------
import csv
import numpy as np
from skbio.stats.distance import DissimilarityMatrix, DistanceMatrix
from skbio.io import create_format, LSMatFormatError
lsmat = create_format('lsmat')
@lsmat.sniffer()
def _lsmat_sniffer(fh):
header = _find_header(fh)
if header is not None:
try:
dialect = csv.Sniffer().sniff(header)
delimiter = dialect.delimiter
ids = _parse_header(header, delimiter)
first_id, _ = next(_parse_data(fh, delimiter), (None, None))
if first_id is not None and first_id == ids[0]:
# The full license is in the file COPYING.txt, distributed with this software.
# ----------------------------------------------------------------------------
import re
import numpy as np
import pandas as pd
from functools import partial
from skbio.io import create_format, GenBankFormatError
from skbio.io.format._base import (
_get_nth_sequence, _line_generator, _too_many_blanks)
from skbio.util._misc import chunk_str
from skbio.sequence import Sequence, DNA, RNA, Protein
genbank = create_format('genbank')
# This list is ordered
# used to read and write genbank file.
_HEADERS = ['LOCUS',
'DEFINITION',
'ACCESSION',
'VERSION',
'DBSOURCE',
'DBLINK',
'KEYWORDS',
'SOURCE',
'REFERENCE',
'COMMENT',
'FEATURES',
'ORIGIN']
# Copyright (c) 2013--, scikit-bio development team.
#
# Distributed under the terms of the Modified BSD License.
#
# The full license is in the file COPYING.txt, distributed with this software.
# ----------------------------------------------------------------------------
from __future__ import (absolute_import, division, print_function,
unicode_literals)
from skbio.io import create_format, ClustalFormatError
from skbio.sequence import Sequence
from skbio.alignment import Alignment
clustal = create_format('clustal')
def _label_line_parser(record, strict=True):
"""Returns dict mapping list of data to labels, plus list with field order.
Field order contains labels in order encountered in file.
NOTE: doesn't care if lines are out of order in different blocks. This
should never happen anyway, but it's possible that this behavior should
be changed to tighten up validation.
"""
labels = []
result = {}
for line in record:
split_line = line.strip().rsplit(None, 1)
from __future__ import (absolute_import, division, print_function,
unicode_literals)
from future.builtins import zip, range
from skbio.io import create_format, QSeqFormatError
from skbio.io.format._base import _decode_qual_to_phred, _get_nth_sequence
from skbio.alignment import SequenceCollection
from skbio.sequence import Sequence, DNA, RNA, Protein
_default_phred_offset = None
_default_variant = None
_will_filter = True
qseq = create_format('qseq')
@qseq.sniffer()
def _qseq_sniffer(fh):
empty = True
try:
for _, line in zip(range(10), fh):
_record_parser(line)
empty = False
return not empty, {}
except QSeqFormatError:
return False, {}
@qseq.reader(None)
+------+------+---------------------------------------------------------------+
|Yes |No |generator of :mod:`skbio.sequence.Sequence` objects |
+------+------+---------------------------------------------------------------+
Reference
---------
.. [#] https://samtools.github.io/hts-specs/SAMv1.pdf
'''
from skbio.io import create_format
from skbio.sequence import Sequence, DNA, RNA, Protein
from skbio.io.format._base import (_line_generator, _get_nth_sequence,
_too_many_blanks)
sam = create_format('sam')
# Alignment headers
_REQUIRED_FIELDS = [
'QNAME', # Query template NAME.
'FLAG', # Combination of bitwise FLAGs
'RNAME', # Reference sequence NAME of the alignment
'POS', # 1-based leftmost mapping position of the first base
'MAPQ', # Mapping quality. -10log10(P_err).
'CIGAR', # CIGAR string
'RNEXT', # Reference sequence name of the primary alignment of NEXT
'PNEXT', # Position of the primary alignment of the NEXT read
'TLEN', # signed observed template length
'SEQ', # segment sequence
'QUAL', # ASCII of base quality
]