def __init__(self,
sequence,
complement_in=b"ACGT",
complement_out=b"TGCA",
letters="ACGT"):
""".. rubric:: Constructor
A sequence is just a string stored in the :attr:`sequence` attribute. It
has properties related to the type of alphabet authorised.
:param str sequence: May be a string of a Fasta File, in which case only
the first sequence is used.
:param complement_in:
:param complement_out:
:param letters: authorise letters. Used in :meth:`check` only.
.. todo:: use counter only once as a property
"""
if sequence.endswith(".fa") or sequence.endswith(".fasta"):
fasta = FastA(sequence)
sequence = fasta.next().sequence.upper()
else: # assume correct string sequence
pass
self._data = sequence
try:
self._translate = string.maketrans(complement_in, complement_out)
except:
self._translate = bytes.maketrans(complement_in, complement_out)
self._letters = letters
def __init__(self, sequence, complement_in=b"ACGT", complement_out=b"TGCA",
letters="ACGT"):
""".. rubric:: Constructor
A sequence is just a string stored in the :attr:`sequence` attribute. It
has properties related to the type of alphabet authorised.
:param str sequence: May be a string of a Fasta File, in which case only
the first sequence is used.
:param complement_in:
:param complement_out:
:param letters: authorise letters. Used in :meth:`check` only.
.. todo:: use counter only once as a property
"""
if sequence.endswith(".fa") or sequence.endswith(".fasta"):
fasta = FastA(sequence)
sequence = fasta.next().sequence.upper()
else: # assume correct string sequence
pass
self._data = sequence
try:
self._translate = string.maketrans(complement_in, complement_out)
except:
self._translate = bytes.maketrans(complement_in, complement_out)
self._letters = letters
def extract_fasta(self, fastafile, features=['rRNA']):
types = self.get_types()
for feature in features:
if feature not in types:
raise ValueError("{} not found".format(feature))
# fasta may have several contig/chromosome names
# the gene bank should be compatible !!
fasta = FastA(fastafile)
contig_names = fasta.get_lengths_as_dict()
# most of the times, the version is not in the gbk
contig_names = [x.split(".")[0] for x in contig_names]
# then we read the features from the genbank
records = self.genbank_features_parser()
contig_names_gbk = list(records.keys())
# FIXME FastA is not very efficient for eukaryotes but is enough for now
output = ""
for name in records.keys():
if name not in contig_names:
logger.warning(
"{} contig from genbank not found in fasta".format(name))
continue
index = contig_names.index(name)
sequence = fasta.sequences[index]
for item in records[name]:
if item['type'] in features:
start, end = item['gene_start'], item['gene_end']
try:
info = item['product']
output += ">{}_{}_{}_{} {}\n".format(
name, item['type'], start, end, info)
except:
output += ">{}_{}_{}_{} {}\n".format(
name, item['type'], start, end)
output += "{}\n".format(sequence[start:end])
return output
def __init__(self, filename):
""".. rubric:: Constructor
:param str filename: the input FASTA file
"""
if isinstance(filename, str):
# this is not large files so we load in memory all sequences/names
# and comments once for all. This has also the adavantage that
# data can now be changed on the fly
fasta = FastA(filename)
self._data = [self._to_read(this) for this in fasta]
elif isinstance(filename, AdapterReader):
self._data = [self._to_read(this) for this in filename._data]
elif isinstance(filename, list):
self._data = [self._to_read(this) for this in filename]
self._sanity_check()
def __init__(self, filename_fasta, merge=False, name=None):
""".. rubric:: Constructor
Input must be a fasta file with valid DNA or RNA characters
:param str filename_fasta: a Fasta file, only the first
sequence is used !
:param int threshold: Minimal length of repeat to output
:param str name: if name is provided, scan the Fasta file
and select the corresponding sequence. if you want to
analyse all sequences, you need to use a loop by setting
_header for each sequence with the sequence name found in
sequence header.
.. note:: known problems. Header with a > character (e.g. in the
comment) are left strip and only the comments is kept. Another issue
is for multi-fasta where one sequence is ignored (last or first ?)
"""
# used to check everything is fine with the header/name
self._fasta = FastA(filename_fasta)
# Define the attributes, and set the header if already provided
self._threshold = None
self._df_shustring = None
self._header = None
self._length = None
self._longest_shustring = None
self._begin_end_repeat_position = None
self._begin_end_repeat_position_merge = None
self._filename_fasta = filename_fasta
self._previous_thr = None
self._list_len_repeats = None
self._contig_names = None
if not isinstance(merge, bool):
raise TypeError("do_merge must be boolean")
self._do_merge = merge
if name is not None:
self.header = name
else:
self.header = self._fasta.names[0]
class Sequence(object):
"""Abstract base classe for other specialised sequences such as DNA.
Sequenced is the base class for other classes such as :class:`DNA` and
:class:`RNA`.
::
from sequana import Sequence
s = Sequence("ACGT")
s.stats()
s.get_complement()
.. note:: You may use a Fasta file as input (see constructor)
"""
def __init__(self,
sequence,
complement_in=b"ACGT",
complement_out=b"TGCA",
letters="ACGT"):
""".. rubric:: Constructor
A sequence is just a string stored in the :attr:`sequence` attribute. It
has properties related to the type of alphabet authorised.
:param str sequence: May be a string of a Fasta File, in which case only
the first sequence is used.
:param complement_in:
:param complement_out:
:param letters: authorise letters. Used in :meth:`check` only.
.. todo:: use counter only once as a property
"""
if sequence.endswith(".fa") or sequence.endswith(".fasta"):
self.fasta = FastA(sequence)
sequence = self.fasta.next().sequence.upper()
else: # assume correct string sequence
pass
self._data = sequence
try:
self._translate = string.maketrans(complement_in, complement_out)
except:
self._translate = bytes.maketrans(complement_in, complement_out)
self._letters = letters
def __iter__(self):
return self
def __next__(self):
self._data = self.fasta.next().sequence.upper()
return self._data
def _get_sequence(self):
return self._data
sequence = property(_get_sequence)
def get_complement(self):
"""Return complement """
return self._data.translate(self._translate)
def get_reverse_complement(self):
"""Return reverse complement """
return self.get_complement()[::-1]
def get_reverse(self):
"""Return reverse sequence"""
return self._data[::-1]
def complement(self):
"""Alias to :meth:`get_complement`"""
self._data = self.get_complement()
def reverse(self):
"""Alias to :meth:`get_reverse`"""
self._data = self.get_reverse()
def reverse_complement(self):
"""Alias to get_reverse_complement"""
self._data = self.get_reverse_complement()
def check(self):
"""Check that all letters are valid"""
counter = Counter(self._data).keys()
for key in counter:
if key not in self._letters:
raise ValueError(
"Found unexpected letter in the sequence (%s)" % key)
def __len__(self):
return len(self._data)
def gc_content(self):
"""Return mean GC content"""
c = Counter(self._data)
ratio = (c['G'] + c['C']) / len(self.sequence)
return ratio
def stats(self):
"""Return basic stats about the number of letters"""
from collections import Counter
return Counter(self.sequence)
def get_occurences(self, pattern, overlap=False):
"""Return position of the input pattern in the sequence
::
>>> from sequana import Sequence
>>> s = Sequence('ACGTTTTACGT')
>>> s.get_occurences("ACGT")
[0, 7]
"""
if overlap is False:
res = [m.start() for m in re.finditer(pattern, self.sequence)]
elif overlap is True:
res = [
m.start()
for m in re.finditer('(?=%s)' % pattern, self.sequence)
]
return res
def summary(**kwargs):
"""Create a HTML report for various type of NGS formats.
\b
* bamqc
* fastq
This will process all files in the given pattern (in back quotes)
sequentially and procude one HTML file per input file.
Other module all work in the same way. For example, for FastQ files::
sequana summary one_input.fastq
sequana summary `ls *fastq`
"""
names = kwargs['name']
module = kwargs['module']
if module is None:
if names[0].endswith('fastq.gz') or names[0].endswith('.fastq'):
module = "fastq"
elif names[0].endswith('.bam'):
module = "bam"
elif names[0].endswith('.gff') or names[0].endswith('gff3'):
module = "gff"
elif names[0].endswith('fasta.gz') or names[0].endswith('.fasta'):
module = "fasta"
else:
logger.error(
"please use --module to tell us about the input fimes")
sys.exit(1)
if module == "bamqc":
for name in names:
print(f"Processing {name}")
from sequana.modules_report.bamqc import BAMQCModule
report = BAMQCModule(name, "bamqc.html")
elif module == "fasta": # there is no module per se. HEre we just call FastA.summary()
from sequana.fasta import FastA
for name in names:
f = FastA(name)
f.summary()
elif module == "fastq": # there is no module per se. HEre we just call FastA.summary()
from sequana.fastq import FastQ
from sequana import FastQC
for filename in names:
ff = FastQC(filename, max_sample=1e6, verbose=False)
stats = ff.get_stats()
print(stats)
elif module == "bam":
import pandas as pd
from sequana import BAM
for filename in names:
ff = BAM(filename)
stats = ff.get_stats()
df = pd.Series(stats).to_frame().T
print(df)
elif module == "gff":
import pandas as pd
from sequana import GFF3
for filename in names:
ff = GFF3(filename)
print("#filename: {}".format(filename))
print("#Number of entries per genetic type:")
print(ff.df.value_counts('type').to_string())
print("#Number of duplicated attribute (if any) per attribute:")
ff.get_duplicated_attributes_per_type()
