def __init__(self, parent):
# Save parent #
self.parent, self.assemble_group = parent, parent
self.samples = parent.samples
self.pool = self.parent.pool
self.primers = self.pool.primers
# Auto paths #
self.base_dir = parent.p.groups_dir + self.short_name + '/'
self.p = AutoPaths(self.base_dir, self.all_paths)
# More #
self.orig_reads = self.parent.cls(self.p.orig_fastq, samples=self.samples)
self.n_filtered = self.parent.cls(self.p.n_filtered, samples=self.samples)
# Quality filtered #
if self.parent == 'assembled':
self.qual_filtered = BarcodedFASTQ(self.p.qual_filtered, samples=self.samples, primers=self.primers)
self.len_filtered = BarcodedFASTQ(self.p.len_filtered_fastq, samples=self.samples, primers=self.primers)
self.trimmed_barcodes = FASTA(self.p.trimmed_barcodes)
# Further #
self.load()
class PrimerGroup(object):
"""A bunch of sequences all having the same type of primer outcome
(and assembly outcome)"""
all_paths = """
/orig.fastq
/n_filtered.fastq
/qual_filtered.fastq
/len_filtered.fastq
/trimmed_barcodes.fasta
"""
qual_threshold = 5
qual_windowsize = 10
min_length = 400
def __repr__(self): return '<%s object of %s>' % (self.__class__.__name__, self.parent)
def __len__(self): return len(self.orig_reads)
def create(self): self.orig_reads.create()
def add_seq(self, read): self.orig_reads.add_seq(read)
def close(self): self.orig_reads.close()
def __init__(self, parent):
# Save parent #
self.parent, self.assemble_group = parent, parent
self.samples = parent.samples
self.pool = self.parent.pool
self.primers = self.pool.primers
# Auto paths #
self.base_dir = parent.p.groups_dir + self.short_name + '/'
self.p = AutoPaths(self.base_dir, self.all_paths)
# More #
self.orig_reads = self.parent.cls(self.p.orig_fastq, samples=self.samples)
self.n_filtered = self.parent.cls(self.p.n_filtered, samples=self.samples)
# Quality filtered #
if self.parent == 'assembled':
self.qual_filtered = BarcodedFASTQ(self.p.qual_filtered, samples=self.samples, primers=self.primers)
self.len_filtered = BarcodedFASTQ(self.p.len_filtered_fastq, samples=self.samples, primers=self.primers)
self.trimmed_barcodes = FASTA(self.p.trimmed_barcodes)
# Further #
self.load()
def load(self): pass
def n_filter(self):
"""Called from AssembleGroup.discard_reads_with_n"""
def no_n_iterator(reads):
fwd_len = self.pool.primers.fwd_len
rev_len = self.pool.primers.rev_len
for read in reads:
if 'N' in read[fwd_len:-rev_len]: continue
yield read
self.n_filtered.write(no_n_iterator(self.orig_reads))
def qual_filter(self):
"""Called from Assemble.quality_filter"""
def good_qual_iterator(reads):
for read in reads:
averaged = moving_average(read.letter_annotations["phred_quality"], self.qual_windowsize)
if any([value < self.qual_threshold for value in averaged]): continue
yield read
self.qual_filtered.write(good_qual_iterator(self.n_filtered))
def len_filter(self):
"""Called from Assemble.length_filter"""
def good_len_iterator(reads):
for read in reads:
if len(read) < self.min_length: continue
yield read
self.len_filtered.write(good_len_iterator(self.qual_filtered))
def trim_bc(self):
"""Called from Assemble.trim_barcodes"""
def no_barcodes_iterator(reads):
for read in reads:
yield read[self.pool.bar_len:-self.pool.bar_len]
if self.pool.bar_len == 0:
self.len_filtered.to_fasta(self.trimmed_barcodes)
else:
self.trimmed_barcodes.write(no_barcodes_iterator(self.len_filtered))
