def _init_list_results(self):
# init IJ content and IJ skew
IJ_content_res = np.empty((1, self.__len__()))
IJ_content_res[:] = np.NAN
IJ_skew_res = np.empty((1, self.__len__()))
IJ_skew_res[:] = np.NAN
return IJ_content_res, IJ_skew_res
def _init_list_results(self):
# init IJ content and IJ skew
IJ_content_res = np.empty((1,self.__len__()))
IJ_content_res[:] = np.NAN
IJ_skew_res = np.empty((1,self.__len__()))
IJ_skew_res[:] = np.NAN
return IJ_content_res, IJ_skew_res
def _base_content(filename, window_size, letters, circular=False):
# DOC: see gc_content
fasta = FastxFile(filename)
checker = set(letters)
chrom_gc_content = dict()
for chrom in fasta:
mid = int(window_size / 2)
# Create gc_content array
gc_content = np.empty(len(chrom.sequence))
gc_content[:] = np.nan
if circular:
chrom.sequence = (chrom.sequence[-mid:] + chrom.sequence +
chrom.sequence[:mid])
# Does not shift index of array
mid = 0
# Count first window content
counter = Counter(chrom.sequence[0:window_size])
gc_count = 0
for letter in letters:
gc_count += counter[letter]
gc_content[mid] = gc_count
for i in range(1, len(chrom.sequence) - window_size + 1):
if chrom.sequence[i - 1] in checker:
gc_count -= 1
if chrom.sequence[i + window_size - 1] in checker:
gc_count += 1
gc_content[i + mid] = gc_count
chrom_gc_content[chrom.name] = gc_content / window_size
return chrom_gc_content
def _base_content(filename, window_size, letters, circular=False):
# DOC: see gc_content
fasta = FastxFile(filename)
checker = set(letters)
chrom_gc_content = dict()
for chrom in fasta:
mid = int(window_size / 2)
# Create gc_content array
gc_content = np.empty(len(chrom.sequence))
gc_content[:] = np.nan
if circular:
chrom.sequence = (chrom.sequence[-mid:] + chrom.sequence +
chrom.sequence[:mid])
# Does not shift index of array
mid = 0
# Count first window content
counter = Counter(chrom.sequence[0:window_size])
gc_count = 0
for letter in letters:
gc_count += counter[letter]
gc_content[mid] = gc_count
for i in range(1, len(chrom.sequence) - window_size + 1):
if chrom.sequence[i - 1] in checker:
gc_count -= 1
if chrom.sequence[i + window_size - 1] in checker:
gc_count += 1
gc_content[i + mid] = gc_count
chrom_gc_content[chrom.name] = gc_content / window_size
return chrom_gc_content
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
