def __call__(self, is_paired, read0, read1):
"""
Actually does digital normalization - the core algorithm.
* get one (unpaired) or two (paired) reads;
* sanitize the sequences (convert Ns to As);
* get the median k-mer count of one/both reads;
* if any read's median k-mer count is below desired coverage, keep all;
* consume and yield kept reads.
"""
batch = ReadBundle(read0, read1)
desired_coverage = self.desired_coverage
# if any in batch have coverage below desired coverage, consume &yield
if not batch.coverages_at_least(self.countgraph, desired_coverage):
for record in batch.reads:
self.countgraph.consume(record.cleaned_seq)
yield record
def __call__(self, is_paired, read0, read1):
"""
Actually does digital normalization - the core algorithm.
* get one (unpaired) or two (paired) reads;
* sanitize the sequences (convert Ns to As);
* get the median k-mer count of one/both reads;
* if any read's median k-mer count is below desired coverage, keep all;
* consume and yield kept reads.
"""
batch = ReadBundle(read0, read1)
desired_coverage = self.desired_coverage
# if any in batch have coverage below desired coverage, consume &yield
if not batch.coverages_at_least(self.countgraph, desired_coverage):
for record in batch.reads:
self.countgraph.consume(record.cleaned_seq)
yield record
def pass2(self, reader):
"""
The second pass across the data does the following.
1. For each read, evaluate the coverage. If the coverage is
sufficient to trim, OR we are trimming low-abundance reads (-V not
set), do trimming.
2. Otherwise, return the untrimmed read pair.
"""
graph = self.graph
TRIM_AT_COVERAGE = self.trim_at_coverage
CUTOFF = self.cutoff
K = graph.ksize()
for n, is_pair, read1, read2 in reader:
bundle = ReadBundle(read1, read2)
# clean up the sequences for examination.
self.n_reads += bundle.num_reads
self.n_bp += bundle.total_length
if self.do_trim_low_abund or \
bundle.coverages_at_least(graph, TRIM_AT_COVERAGE):
for read in bundle.reads:
trimmed_record, did_trim = trim_record(graph, read, CUTOFF)
if did_trim:
self.trimmed_reads += 1
if trimmed_record:
yield trimmed_record
else:
for read in bundle.reads:
self.n_skipped += 1
self.bp_skipped += 1
yield read
def pass2(self, reader):
"""
The second pass across the data does the following.
1. For each read, evaluate the coverage. If the coverage is
sufficient to trim, OR we are trimming low-abundance reads (-V not
set), do trimming.
2. Otherwise, return the untrimmed read pair.
"""
graph = self.graph
TRIM_AT_COVERAGE = self.trim_at_coverage
CUTOFF = self.cutoff
K = graph.ksize()
for n, is_pair, read1, read2 in reader:
bundle = ReadBundle(read1, read2)
# clean up the sequences for examination.
self.n_reads += bundle.num_reads
self.n_bp += bundle.total_length
if self.do_trim_low_abund or \
bundle.coverages_at_least(graph, TRIM_AT_COVERAGE):
for read in bundle.reads:
trimmed_record, did_trim = trim_record(graph, read, CUTOFF)
if did_trim:
self.trimmed_reads += 1
if trimmed_record:
yield trimmed_record
else:
for read in bundle.reads:
self.n_skipped += 1
self.bp_skipped += 1
yield read
