def compare_kmers(self):
'''
'''
self.kmers['ref'] = {}
jellyfish = self.params.get_param('jellyfish')
kmer_size = int(self.params.get_param('kmer_size'))
for i in range(len(self.files['target_ref_fn'])):
utils.log(self.logging_name, 'info', 'Indexing kmers for reference sequence %s' % self.files['target_ref_fn'][i])
self.kmers['ref'] = utils.load_kmers(utils.run_jellyfish(self.files['target_ref_fn'][i], jellyfish, kmer_size), self.kmers['ref'])
# if 'target_altref_fn' in self.files:
# for i in range(len(self.files['target_altref_fn'])):
# for j in range(len(self.files['target_altref_fn'][i])):
# utils.log(self.logging_name, 'info', 'Indexing kmers for reference sequence %s' % self.files['target_altref_fn'][i])
# self.kmers['ref'] = utils.load_kmers(utils.run_jellyfish(self.files['target_altref_fn'][i][j], jellyfish, kmer_size), self.kmers['ref'])
utils.log(self.logging_name, 'info', 'Indexing kmers for sample sequence %s' % self.files['sv_cleaned_fq'])
self.kmers['case'] = {}
self.kmers['case'] = utils.load_kmers(utils.run_jellyfish(self.files['sv_cleaned_fq'], jellyfish, kmer_size), self.kmers['case'])
self.kmers['case_sc'] = {}
self.kmers['case_sc'] = utils.load_kmers(utils.run_jellyfish(self.files['sv_sc_unmapped_fa'], jellyfish, kmer_size), self.kmers['case_sc'])
sc_mers = set(self.kmers['case'].keys()) & set(self.kmers['case_sc'])
sample_only_mers = list(sc_mers.difference(set(self.kmers['ref'].keys())))
if 'normal_bam_file' in self.params.opts:
norm_kmers = {}
norm_kmers = utils.load_kmers(utils.run_jellyfish(self.files['norm_cleaned_fq'], jellyfish, kmer_size), norm_kmers)
sample_only_mers = set(sample_only_mers).difference(set(norm_kmers.keys()))
sample_only_mers = list(sample_only_mers)
# Write case only kmers out to file.
self.files['sample_kmers'] = os.path.join(self.paths['kmers'], self.name + "_sample_kmers.out")
sample_kmer_fout = open(self.files['sample_kmers'], 'w')
self.kmers['case_only'] = {}
for mer in sample_only_mers:
sample_kmer_fout.write("\t".join([str(x) for x in [mer, str(self.kmers['case'][mer])]]) + "\n")
self.kmers['case_only'][mer] = self.kmers['case'][mer]
sample_kmer_fout.close()
self.kmers['ref'] = {}
self.kmers['case'] = {}
self.kmers['case_sc'] = {}
utils.log(self.logging_name, 'info', 'Writing %d sample-only kmers to file %s' % (len(self.kmers['case_only']), self.files['sample_kmers']))
self.files['kmer_clusters'] = os.path.join(self.paths['kmers'], self.name + "_sample_kmers_merged.out")
utils.log(self.logging_name, 'info', 'Writing kmer clusters to file %s' % self.files['kmer_clusters'])
self.contigs = assembler.init_assembly(self.kmers['case_only'], self.cleaned_read_recs['sv'], kmer_size, int(self.params.get_param('trl_sr_thresh')), self.params.get_param('read_len'))
self.cleaned_read_recs = None
self.kmers['case_only'] = {}
self.finalize_contigs()
def compare_kmers(self):
'''
'''
self.kmers['ref'] = {}
jellyfish = self.params.get_param('jellyfish')
kmer_size = int(self.params.get_param('kmer_size'))
for i in range(len(self.files['target_ref_fn'])):
utils.log(self.logging_name, 'info', 'Indexing kmers for reference sequence %s' % self.files['target_ref_fn'][i])
self.kmers['ref'] = utils.load_kmers(utils.run_jellyfish(self.files['target_ref_fn'][i], jellyfish, kmer_size), self.kmers['ref'])
# if 'target_altref_fn' in self.files:
# for i in range(len(self.files['target_altref_fn'])):
# for j in range(len(self.files['target_altref_fn'][i])):
# utils.log(self.logging_name, 'info', 'Indexing kmers for reference sequence %s' % self.files['target_altref_fn'][i])
# self.kmers['ref'] = utils.load_kmers(utils.run_jellyfish(self.files['target_altref_fn'][i][j], jellyfish, kmer_size), self.kmers['ref'])
utils.log(self.logging_name, 'info', 'Indexing kmers for sample sequence %s' % self.files['sv_cleaned_fq'])
self.kmers['case'] = {}
self.kmers['case'] = utils.load_kmers(utils.run_jellyfish(self.files['sv_cleaned_fq'], jellyfish, kmer_size), self.kmers['case'])
self.kmers['case_sc'] = {}
self.kmers['case_sc'] = utils.load_kmers(utils.run_jellyfish(self.files['sv_sc_unmapped_fa'], jellyfish, kmer_size), self.kmers['case_sc'])
sc_mers = set(self.kmers['case'].keys()) & set(self.kmers['case_sc'])
sample_only_mers = list(sc_mers.difference(set(self.kmers['ref'].keys())))
if 'normal_bam_file' in self.params.opts:
norm_kmers = {}
norm_kmers = utils.load_kmers(utils.run_jellyfish(self.files['norm_cleaned_fq'], jellyfish, kmer_size), norm_kmers)
sample_only_mers = set(sample_only_mers).difference(set(norm_kmers.keys()))
sample_only_mers = list(sample_only_mers)
# Write case only kmers out to file.
self.files['sample_kmers'] = os.path.join(self.paths['kmers'], self.name + "_sample_kmers.out")
sample_kmer_fout = open(self.files['sample_kmers'], 'w')
self.kmers['case_only'] = {}
for mer in sample_only_mers:
sample_kmer_fout.write("\t".join([str(x) for x in [mer, str(self.kmers['case'][mer])]]) + "\n")
self.kmers['case_only'][mer] = self.kmers['case'][mer]
sample_kmer_fout.close()
self.kmers['ref'] = {}
self.kmers['case'] = {}
self.kmers['case_sc'] = {}
utils.log(self.logging_name, 'info', 'Writing %d sample-only kmers to file %s' % (len(self.kmers['case_only']), self.files['sample_kmers']))
self.files['kmer_clusters'] = os.path.join(self.paths['kmers'], self.name + "_sample_kmers_merged.out")
utils.log(self.logging_name, 'info', 'Writing kmer clusters to file %s' % self.files['kmer_clusters'])
self.contigs = assembler.init_assembly(self.kmers['case_only'], self.cleaned_read_recs['sv'], kmer_size, int(self.params.get_param('trl_sr_thresh')), self.params.get_param('read_len'))
self.cleaned_read_recs = None
self.kmers['case_only'] = {}
self.finalize_contigs()
def compare_kmers(self, kmerPath, name, readLen, targetRefFns):
"""
"""
# Set the reference sequence kmers.
self.set_reference_kmers(targetRefFns)
# Set sample kmers.
self.set_sample_kmers()
# Merge the kmers from the cleaned sample sequences and the unmapped and softclipped sequences.
scKmers = set(self.kmers['case'].keys()) & set(
self.kmers['case_sc'].keys())
# Take the difference from the reference kmers.
sampleOnlyKmers = list(
scKmers.difference(set(self.kmers['ref'].keys())))
# Add normal sample kmers if available.
if self.params.get_param('normal_bam_file'):
normKmers = {}
self.get_kmers(self.files['norm_cleaned_fq'], normKmers)
sampleOnlyKmers = list(
set(sampleOnlyKmers).difference(set(normKmers.keys())))
# Write case only kmers out to file.
self.files['sample_kmers'] = os.path.join(kmerPath,
name + "_sample_kmers.out")
sample_kmer_fout = open(self.files['sample_kmers'], 'w')
kmer_counter = 1
self.kmers['case_only'] = {}
for mer in sampleOnlyKmers:
sample_kmer_fout.write("\t".join(
[str(x) for x in [mer, str(self.kmers['case'][mer])]]) + "\n")
self.kmers['case_only'][mer] = self.kmers['case'][mer]
sample_kmer_fout.close()
# Clean out data structures.
self.kmers['ref'] = {}
self.kmers['case'] = {}
self.kmers['case_sc'] = {}
utils.log(
self.loggingName, 'info',
'Writing %d sample-only kmers to file %s' %
(len(self.kmers['case_only']), self.files['sample_kmers']))
self.files['kmer_clusters'] = os.path.join(
kmerPath, name + "_sample_kmers_merged.out")
utils.log(
self.loggingName, 'info',
'Writing kmer clusters to file %s' % self.files['kmer_clusters'])
self.kmers['clusters'] = assembly.init_assembly(
self.kmers['case_only'], self.cleaned_read_recs['sv'],
self.params.get_kmer_size(), self.params.get_sr_thresh('min'),
readLen)
self.clear_cleaned_reads()
self.kmers['case_only'] = {}
def compare_kmers(self, kmerPath, name, readLen, targetRefFns):
"""
"""
# Set the reference sequence kmers.
self.set_reference_kmers(targetRefFns)
# Set sample kmers.
self.set_sample_kmers()
# Merge the kmers from the cleaned sample sequences and the unmapped and softclipped sequences.
scKmers = set(self.kmers['case'].keys()) & set(self.kmers['case_sc'].keys())
# Take the difference from the reference kmers.
sampleOnlyKmers = list(scKmers.difference(set(self.kmers['ref'].keys())))
# Add normal sample kmers if available.
if self.params.get_param('normal_bam_file'):
normKmers = {}
self.get_kmers(self.files['norm_cleaned_fq'], normKmers)
sampleOnlyKmers = list(set(sampleOnlyKmers).difference(set(normKmers.keys())))
# Write case only kmers out to file.
self.files['sample_kmers'] = os.path.join(kmerPath, name + "_sample_kmers.out")
sample_kmer_fout = open(self.files['sample_kmers'], 'w')
kmer_counter = 1
self.kmers['case_only'] = {}
for mer in sampleOnlyKmers:
sample_kmer_fout.write("\t".join([str(x) for x in [mer, str(self.kmers['case'][mer])]]) + "\n")
self.kmers['case_only'][mer] = self.kmers['case'][mer]
sample_kmer_fout.close()
# Clean out data structures.
self.kmers['ref'] = {}
self.kmers['case'] = {}
self.kmers['case_sc'] = {}
utils.log(self.loggingName, 'info', 'Writing %d sample-only kmers to file %s' % (len(self.kmers['case_only']), self.files['sample_kmers']))
self.files['kmer_clusters'] = os.path.join(kmerPath, name + "_sample_kmers_merged.out")
utils.log(self.loggingName, 'info', 'Writing kmer clusters to file %s' % self.files['kmer_clusters'])
self.kmers['clusters'] = assembly.init_assembly(self.kmers['case_only'], self.cleaned_read_recs['sv'], self.params.get_kmer_size(), self.params.get_sr_thresh('min'), readLen)
self.clear_cleaned_reads()
self.kmers['case_only'] = {}