def post_filter_contaminants(self):
contaminants.post_filter(self.file_names['accepted_hits'],
self.file_names['genes'],
self.file_names['clean_bam'],
self.file_names['more_rRNA_bam'],
self.file_names['tRNA_bam'],
self.file_names['other_ncRNA_bam'],
)
tRNA_length_counts = sam.get_length_counts(self.file_names['tRNA_bam'])
tRNA_lengths = self.zero_padded_array(tRNA_length_counts)
other_ncRNA_length_counts = sam.get_length_counts(self.file_names['other_ncRNA_bam'])
other_ncRNA_lengths = self.zero_padded_array(other_ncRNA_length_counts)
rRNA_length_counts = sam.get_length_counts(self.file_names['rRNA_bam'])
rRNA_length_counts += sam.get_length_counts(self.file_names['more_rRNA_bam'])
rRNA_lengths = self.zero_padded_array(rRNA_length_counts)
clean_length_counts = sam.get_length_counts(self.file_names['clean_bam'])
clean_lengths = self.zero_padded_array(clean_length_counts)
self.write_file('lengths', {'clean': clean_lengths,
'tRNA': tRNA_lengths,
'other_ncRNA': other_ncRNA_lengths,
'rRNA': rRNA_lengths,
},
)
def filter_phiX(self, reads):
filtered_reads = contaminants.pre_filter(self.phiX_bowtie2_index_prefix,
reads,
self.file_names['phiX_bam'],
)
for read in filtered_reads:
yield read
phiX_length_counts = sam.get_length_counts(self.file_names['phiX_bam'])
phiX_lengths = self.zero_padded_array(phiX_length_counts)
self.write_file('lengths', {'phiX': phiX_lengths})
def find_unambiguous_lengths(self):
if self.adapter_type == 'polyA':
trim.unambiguously_trimmed(self.file_names['clean_bam'],
self.file_names['unambiguous_bam'],
self.file_names['genome'],
)
unambiguous_length_counts = sam.get_length_counts(self.file_names['unambiguous_bam'])
unambiguous_lengths = self.zero_padded_array(unambiguous_length_counts)
else:
# Need to write the file so that there is something to merge.
unambiguous_lengths = np.zeros(self.max_read_length + 1, int)
self.write_file('lengths', {'unambiguous': unambiguous_lengths})