def __init__(self, faFileName, maxskip=50, name=None):
"""Open a fasta file and initialize :class:`MFaStream`."""
def add_instance_variables(name, firstSeqL, nextHL, faFileObject):
"""Add state objects."""
self.name = name
self.seqL = firstSeqL
self.nSpecies = len(self.seqL)
self.nextHeaderLine = nextHL
self.fo = faFileObject
flag = False
faFile = sb.gz_open(faFileName)
if name is None:
name = sb.stripFName(faFileName)
# Find the start of the first sequence.
for i in range(0, maxskip):
line = faFile.readline()
if line == '':
raise NotAFastaFileError("File contains no data.")
if line[0] == '>':
# species name found in line
flag = True
break
if flag is False:
raise NotAFastaFileError("Didn't find a species header within " +
maxskip + " lines.")
(nextHL, seqL) = read_align_from_fo(line, faFile)
try:
nextHL = nextHL.rstrip()
except:
pass
add_instance_variables(name, seqL, nextHL, faFile)
def open_seq(VCFFileName, maxskip=100, name=None):
"""Open a VCF4.1 file.
Try to open the given VCF file, checks if it is in VCF format and
reads the bases(s). It returns an :class:`VCFSeq` object that
contains all the information.
:param str VCFFileName: Name of the VCF file.
:param int maxskip: Only look *maxskip* lines for the start of the
bases (defaults to 80).
:param str name: Set the name of the sequence to *name*, otherwise
set it to the filename.
"""
def test_sequence(seq):
""" Test a given VCF sequence.
TODO: implement this.
:param seq:
:returns:
:rtype:
"""
pass
seq = VCFSeq()
seq.header = ""
flag = False
VCFFile = sb.gz_open(VCFFileName)
# set the vcf sequence name
if name is not None:
seq.name = name
else:
seq.name = sb.stripFName(VCFFileName)
# Find the start of the first base
for i in range(0, maxskip):
line = VCFFile.readline()
if line == '':
raise NotAVariantCallFormatFileError("File contains no data.")
if line[0:2] == '##':
seq.header += line
if line[0:6] == '#CHROM':
# Here starts the data.
check_fixed_field_header(line)
seq.speciesL = get_indiv_from_field_header(line)
seq.nSpecies = len(seq.speciesL)
flag = True
break
if flag is False:
raise NotAVariantCallFormatFileError(
"Didn't find any data within " + str(maxskip) + " lines.")
for line in VCFFile:
base = get_nuc_base_from_line(line)
seq.append_nuc_base(base)
VCFFile.close()
test_sequence(seq)
return seq
def __init__(self, faFileName, maxskip=50, name=None):
"""Open a fasta file and initialize :class:`MFaStream`."""
def add_instance_variables(name, firstSeqL, nextHL, faFileObject):
"""Add state objects."""
self.name = name
self.seqL = firstSeqL
self.nSpecies = len(self.seqL)
self.nextHeaderLine = nextHL
self.fo = faFileObject
flag = False
faFile = sb.gz_open(faFileName)
if name is None:
name = sb.stripFName(faFileName)
# Find the start of the first sequence.
for i in range(0, maxskip):
line = faFile.readline()
if line == '':
raise NotAFastaFileError("File contains no data.")
if line[0] == '>':
# species name found in line
flag = True
break
if flag is False:
raise NotAFastaFileError("Didn't find a species header within " +
maxskip + " lines.")
(nextHL, seqL) = read_align_from_fo(line, faFile)
try:
nextHL = nextHL.rstrip()
except:
pass
add_instance_variables(name, seqL, nextHL, faFile)
def open_seq(faFileName, maxskip=50, name=None):
"""Open and read a fasta file.
This function tries to open the given fasta file, checks if it is
in fasta format and reads the sequence(s). It returns an
:class:`FaSeq` object that contains a list of species names, a
list of the respective desriptions and a list with the sequences.
:param str faFileName: Name of the fasta file.
:param int maxskip: Only look *maxskip* lines for the start of a sequence
(defaults to 50).
:param str name: Set the name of the sequence to *name* otherwise
set it to the stripped filename.
"""
def test_sequence(faSequence):
"""Tests if sequences contain data."""
length = faSequence.nSpecies
names = []
for i in range(length):
names.append(faSequence.seqL[i].name)
if faSequence.seqL[i].name == '' or faSequence.seqL[i].data == '':
raise sb.SequenceDataError("Sequence name or data is missing.")
if length > len(set(names)):
raise sb.SequenceDataError("Sequence names are not unique.")
return
fastaSeq = FaSeq()
flag = False
faFile = sb.gz_open(faFileName)
if name is not None:
fastaSeq.name = name
else:
fastaSeq.name = sb.stripFName(faFileName)
# Find the start of the first sequence.
for i in range(0, maxskip):
line = faFile.readline()
if line == '':
raise NotAFastaFileError("File contains no data.")
if line[0] == '>':
# species name found in line
flag = True
break
if flag is False:
raise NotAFastaFileError("Didn't find a species header within " +
maxskip + " lines.")
while line is not None:
(nextLine, seq) = read_seq_from_fo(line, faFile)
line = nextLine
fastaSeq.seqL.append(seq)
fastaSeq.nSpecies += 1
faFile.close()
test_sequence(fastaSeq)
for s in fastaSeq.seqL:
fastaSeq.seqD[s.name] = s
return fastaSeq
def open_seq(faFileName, maxskip=50, name=None):
"""Open and read a fasta file.
This function tries to open the given fasta file, checks if it is
in fasta format and reads the sequence(s). It returns an
:class:`FaSeq` object that contains a list of species names, a
list of the respective desriptions and a list with the sequences.
:param str faFileName: Name of the fasta file.
:param int maxskip: Only look *maxskip* lines for the start of a sequence
(defaults to 50).
:param str name: Set the name of the sequence to *name* otherwise
set it to the stripped filename.
"""
def test_sequence(faSequence):
"""Tests if sequences contain data."""
l = faSequence.nSpecies
names = []
for i in range(l):
names.append(faSequence.seqL[i].name)
if faSequence.seqL[i].name == '' or faSequence.seqL[i].data == '':
raise sb.SequenceDataError("Sequence name or data is missing.")
if l > len(set(names)):
raise sb.SequenceDataError("Sequence names are not unique.")
return
fastaSeq = FaSeq()
flag = False
faFile = sb.gz_open(faFileName)
if name is not None:
fastaSeq.name = name
else:
fastaSeq.name = sb.stripFName(faFileName)
# Find the start of the first sequence.
for i in range(0, maxskip):
line = faFile.readline()
if line == '':
raise NotAFastaFileError("File contains no data.")
if line[0] == '>':
# species name found in line
flag = True
break
if flag is False:
raise NotAFastaFileError("Didn't find a species header within " +
maxskip + " lines.")
while line is not None:
(nextLine, seq) = read_seq_from_fo(line, faFile)
line = nextLine
fastaSeq.seqL.append(seq)
fastaSeq.nSpecies += 1
faFile.close()
test_sequence(fastaSeq)
for s in fastaSeq.seqL:
fastaSeq.seqD[s.name] = s
return fastaSeq
def __init__(self, CFFileName, name=None):
CFFile = sb.gz_open(CFFileName)
# Set the cf sequence name.
if name is None:
name = sb.stripFName(CFFileName)
# Find the start of the first base.
ln = CFFile.readline()
if ln == '':
raise NotACountsFormatFileError("File contains no data.")
# Skip comments.
while ln[0] == '#':
ln = CFFile.readline()
# Read in first line.
lnL = ln.split()
length = len(lnL)
if (lnL[0] != "COUNTSFILE") or (length != 5):
raise NotACountsFormatFileError("First line is corrupt.")
# TODO: The first line is needed by IQ-Tree, but not by
# cflib. Maybe I should use this information here!
ln = CFFile.readline()
# Skip comments.
while ln[0] == '#':
ln = CFFile.readline()
# Read in headerline.
lnL = ln.split()
length = len(lnL)
indivL = []
if (lnL[0] in ["CHROM", "Chrom"]) and (lnL[1] in ["POS", "Pos"]):
for i in range(2, length):
indivL.append(lnL[i].strip())
else:
raise NotACountsFormatFileError("Header line is corrupt.")
ln = CFFile.readline()
(chrom, pos, countsL) = interpret_cf_line(ln)
if (len(countsL) != len(indivL)):
raise NotACountsFormatFileError("Line doesn't fit nr. of species.")
self.name = name
self.chrom = chrom
self.pos = pos
self.fo = CFFile
self.indivL = indivL
self.countsL = countsL
self.nIndiv = len(countsL)
def __init__(self, CFFileName, name=None):
CFFile = sb.gz_open(CFFileName)
# Set the cf sequence name.
if name is None:
name = sb.stripFName(CFFileName)
# Find the start of the first base.
ln = CFFile.readline()
if ln == '':
raise NotACountsFormatFileError("File contains no data.")
# Skip comments.
while ln[0] == '#':
ln = CFFile.readline()
# Read in first line.
lnL = ln.split()
l = len(lnL)
if (lnL[0] != "COUNTSFILE") or (l != 5):
raise NotACountsFormatFileError("First line is corrupt.")
# TODO: The first line is needed by IQ-Tree, but not by
# cflib. Maybe I should use this information here!
ln = CFFile.readline()
# Skip comments.
while ln[0] == '#':
ln = CFFile.readline()
# Read in headerline.
lnL = ln.split()
l = len(lnL)
indivL = []
if (lnL[0] in ["CHROM", "Chrom"]) and (lnL[1] in ["POS", "Pos"]):
for i in range(2, l):
indivL.append(lnL[i].strip())
else:
raise NotACountsFormatFileError("Header line is corrupt.")
ln = CFFile.readline()
(chrom, pos, countsL) = interpret_cf_line(ln)
if (len(countsL) != len(indivL)):
raise NotACountsFormatFileError("Line doesn't fit nr. of species.")
self.name = name
self.chrom = chrom
self.pos = pos
self.fo = CFFile
self.indivL = indivL
self.countsL = countsL
self.nIndiv = len(countsL)
def init_seq(faFileName, maxskip=50, name=None):
"""Open a fasta file and initialize an :class:`FaStream`.
This function tries to open the given fasta file, checks if it is
in fasta format and reads the first sequence. It returns an
:class:`FaStream` object. This object can later be used to parse
the whole fasta file.
Please close the associated file object with
:func:`FaStream.close` when you don't need it anymore.
:param str faFileName: File name of the fasta file.
:param int maxskip: Only look *maxskip* lines for the start of a
sequence (defaults to 50).
:param str name: Set the name of the sequence to *name*, otherwise
set it to the stripped filename.
"""
flag = False
faFile = sb.gz_open(faFileName)
if name is None:
name = sb.stripFName(faFileName)
# Find the start of the first sequence.
for i in range(0, maxskip):
line = faFile.readline()
if line == '':
raise NotAFastaFileError("File contains no data.")
if line[0] == '>':
# species name found in line
flag = True
break
if flag is False:
raise NotAFastaFileError("Didn't find a species header within " +
maxskip + " lines.")
(nextHL, seq) = read_seq_from_fo(line, faFile)
try:
nextHL = nextHL.rstrip()
except:
pass
faStr = FaStream(name, seq, nextHL, faFile)
return faStr
def init_seq(faFileName, maxskip=50, name=None):
"""Open a fasta file and initialize an :class:`FaStream`.
This function tries to open the given fasta file, checks if it is
in fasta format and reads the first sequence. It returns an
:class:`FaStream` object. This object can later be used to parse
the whole fasta file.
Please close the associated file object with
:func:`FaStream.close` when you don't need it anymore.
:param str faFileName: File name of the fasta file.
:param int maxskip: Only look *maxskip* lines for the start of a
sequence (defaults to 50).
:param str name: Set the name of the sequence to *name*, otherwise
set it to the stripped filename.
"""
flag = False
faFile = sb.gz_open(faFileName)
if name is None:
name = sb.stripFName(faFileName)
# Find the start of the first sequence.
for i in range(0, maxskip):
line = faFile.readline()
if line == '':
raise NotAFastaFileError("File contains no data.")
if line[0] == '>':
# species name found in line
flag = True
break
if flag is False:
raise NotAFastaFileError("Didn't find a species header within " +
maxskip + " lines.")
(nextHL, seq) = read_seq_from_fo(line, faFile)
try:
nextHL = nextHL.rstrip()
except:
pass
faStr = FaStream(name, seq, nextHL, faFile)
return faStr
def init_seq(VCFFileName, maxskip=100, name=None):
"""Open a (gzipped) VCF4.1 file.
Try to open the given VCF file, checks if it is in VCF format.
Initialize a :class:`VCFStream` object that contains the first
base.
Please close the associated file object with
:func:`VCFStream.close` when you don't need it anymore.
:param str VCFFileName: Name of the VCF file.
:param int maxskip: Only look *maxskip* lines for the start of the
bases (defaults to 80).
:param str name: Set the name of the sequence to *name*, otherwise
set it to the filename.
"""
flag = False
VCFFile = sb.gz_open(VCFFileName)
# Set the vcf sequence name.
if name is None:
name = sb.stripFName(VCFFileName)
# Find the start of the first base.
for i in range(0, maxskip):
line = VCFFile.readline()
if line == '':
raise NotAVariantCallFormatFileError("File contains no data.")
if line[0:6] == '#CHROM':
# Here starts the data.
check_fixed_field_header(line)
speciesL = get_indiv_from_field_header(line)
flag = True
break
if flag is False:
raise NotAVariantCallFormatFileError(
"Didn't find any data within " + str(maxskip) + " lines.")
line = VCFFile.readline()
base = get_nuc_base_from_line(line, info=False)
base.set_ploidy()
return VCFStream(name, VCFFile, speciesL, base)