def _get_tile_info(self):
identifiers = []
tiles = {}
with FastqReader(self.filename) as f:
for i, record in enumerate(f):
if i < self.max_sample:
identifier = Identifier(record.name)
identifiers.append(identifier.info)
tiles['x'] = [float(this['x_coordinate']) for this in identifiers]
tiles['y'] = [float(this['y_coordinate']) for this in identifiers]
tiles['tiles'] = [this['tile_number'] for this in identifiers]
return tiles
def _get_qualities(self):
from sequana import logger
logger.info("Extracting qualities")
qualities = []
with FastqReader(self.filename) as f:
for i, record in enumerate(f):
if i < self.max_sample:
quality = [ord(x) -33 for x in record.qualities]
qualities.append(quality)
else:
break
return qualities
def test_context_manager(self):
filename = "tests/data/simple.fastq"
with open(filename) as f:
assert not f.closed
reads = list(openseq(f))
assert not f.closed
assert f.closed
with FastqReader(filename) as sr:
tmp_sr = sr
assert not sr._file.closed
reads = list(sr)
assert not sr._file.closed
assert tmp_sr._file is None
def _get_info(self):
"""Populates the data structures for plotting.
Will be called on request"""
stats = {"A":0, "C":0, "G":0, "T":0, "N":0}
stats["qualities"] = []
stats["mean_qualities"] = []
stats["mean_length"] = 0
stats["sequences"] = []
minimum = 1e6
maximum = 0
# FIXME this self.N takes time in the cosntructor
# do we need it ?
self.lengths = np.empty(self.N)
self.gc_list = []
total_length = 0
C = defaultdict(int)
if self.verbose:
pb = Progress(self.N)
sequences = []
mean_qualities = []
qualities = []
# could use multiprocessing
# FastxFile has shown some errors while handling gzip files
# created with zlib (e.g. from atropos). This is now replaced
# by the Atropos FastqReader for now.
#fastq = pysam.FastxFile(self.filename)
with FastqReader(self.filename) as f:
for i, record in enumerate(f):
N = len(record.sequence)
self.lengths[i] = N
# we can store all qualities and sequences reads, so
# just max_sample are stored:
if i < self.max_sample:
quality = [ord(x) -33 for x in record.qualities]
mean_qualities.append(sum(quality) / N)
qualities.append(quality)
sequences.append(record.sequence)
# store count of all qualities
for k in record.qualities:
C[k] += 1
GG = record.sequence.count('G')
CC = record.sequence.count('C')
self.gc_list.append((GG+CC)/float(N)*100)
# not using a counter, or loop speed up the code
stats["A"] += record.sequence.count("A")
stats["C"] += CC
stats["G"] += GG
stats["T"] += record.sequence.count("T")
stats["N"] += record.sequence.count("N")
total_length += len(record.sequence)
if self.verbose:
pb.animate(i+1)
# other data
self.qualities = qualities
self.mean_qualities = mean_qualities
self.minimum = int(self.lengths.min())
self.maximum = int(self.lengths.max())
self.sequences = sequences
self.gc_content = np.mean(self.gc_list)
stats['mean_length'] = total_length / float(self.N)
stats['total_bp'] = stats['A'] + stats['C'] + stats['G'] + stats["T"] + stats['N']
stats['mean_quality'] = sum([(ord(k) -33)*v for k,v in C.items()]) / stats['total_bp']
self.stats = stats
def test_alphabet(self):
filename = "tests/data/bad_bases.fq"
with FastqReader(filename, alphabet=ALPHABETS['dna']) as f:
reads = list(f)
assert reads[0].sequence == 'ACGNGGACT'
assert reads[1].sequence == 'CGGACNNNC'
def test_fastq_incomplete(self):
fastq = StringIO("@name\nACGT+\n")
with raises(FormatError), FastqReader(fastq) as fq:
list(fq)
def test_fastq_wrongformat(self):
with raises(FormatError), FastqReader(
"tests/data/withplus.fastq") as f:
reads = list(f)
def test_fastqreader_dos(self):
with FastqReader("tests/data/dos.fastq") as f:
dos_reads = list(f)
with FastqReader("tests/data/small.fastq") as f:
unix_reads = list(f)
assert dos_reads == unix_reads
def test_fastqreader(self):
with FastqReader("tests/data/simple.fastq") as f:
reads = list(f)
assert reads == simple_fastq