def samtools_index(self):
if not self.has_been_sorted:
raise Exception(
'BAM must be sorted before it can be indexed'
)
with namedpipe.temp_named_pipe() as (
bam_pipe
), namedpipe.temp_named_pipe() as (
index_pipe
):
with subprocess.Popen(
(
'sh',
'-c',
(
'cat {0} & '
'samtools index {1} {0} &'
'cat > {1}'
)
.format(
index_pipe.name,
bam_pipe.name
)
),
stdin=subprocess.PIPE,
stdout=subprocess.PIPE,
stderr=self.log
) as samtools_index:
self.index, _ = samtools_index.communicate(input=self.bam)
def get_fasta(self):
with namedpipe.temp_named_pipe() as peaks_pipe:
with subprocess.Popen(
(
'sh',
'-c',
(
'bedtools getfasta -bed {0} -fi {1} & cat > {0}'
.format(peaks_pipe.name, self.reference_genome_path)
)
),
stdin=subprocess.PIPE,
stdout=subprocess.PIPE
) as bedtools_getfasta:
self.fasta, _ = bedtools_getfasta.communicate(input=self.peaks)
def bwa_aln(self, sequence_alignment):
"""Perform sequence alignment using the bwa aln algorithm
Single-end and paired end reads are handled appropriately based on the
type of the SequenceAlignment's raw reads path
Parameters
----------
sequence_alignment : SequenceAlignment
a SequenceAlignemnt object
Returns
-------
bytes
A BAM file
"""
if not isinstance(sequence_alignment.raw_reads_path, str):
with namedpipe.temp_named_pipe() as (
sai_pipe_0), namedpipe.temp_named_pipe() as (sai_pipe_1):
with subprocess.Popen(
('sh', '-c',
('bwa sampe {0} {1} {2} {3} {4} & '
'bwa aln -t {5} -q {6} -l {7} -k {8} {0} {3} > '
'{1} & '
'bwa aln -t {5} -q {6} -l {7} -k {8} {0} {4} > '
'{2} & ').format(
self.reference_genome_path, sai_pipe_0.name,
sai_pipe_1.name,
sequence_alignment.raw_reads_path[0],
sequence_alignment.raw_reads_path[1],
math.floor(sequence_alignment.processes / 2),
self.trim_qual, self.seed_len, self.max_seed_diff)),
stdout=subprocess.PIPE,
stderr=sequence_alignment.log) as bwa_aln_sampe:
with subprocess.Popen(
('samtools', 'view', '-Sbq',
str(sequence_alignment.phred_quality_score), '-@',
str(sequence_alignment.processes)),
stdin=bwa_aln_sampe.stdout,
stdout=subprocess.PIPE,
stderr=sequence_alignment.log) as samtools_view:
return samtools_view.communicate()[0]
else:
with namedpipe.temp_named_pipe() as sai_pipe:
with subprocess.Popen(
('sh', '-c',
('bwa samse {0} {1} {2} & '
'bwa aln -t {3} -q {4} -l {5} -k {6} {0} {2} > {1}; '
).format(self.reference_genome_path, sai_pipe.name,
sequence_alignment.raw_reads_path,
sequence_alignment.processes, self.trim_qual,
self.seed_len, self.max_seed_diff)),
stdout=subprocess.PIPE,
stderr=sequence_alignment.log) as bwa_aln_samse:
with subprocess.Popen(
('samtools', 'view', '-bhq',
str(sequence_alignment.phred_quality_score), '-@',
str(sequence_alignment.processes)),
stdin=bwa_aln_samse.stdout,
stdout=subprocess.PIPE,
stderr=sequence_alignment.log) as samtools_view:
return samtools_view.communicate()[0]
def bwa_aln(self):
if isinstance(self.sa.raw_reads_path, tuple):
with namedpipe.temp_named_pipe() as (
sai_pipe_0
), namedpipe.temp_named_pipe() as (
sai_pipe_1
):
with subprocess.Popen(
(
'sh',
'-c',
(
'bwa sampe {0} {1} {2} {3} {4} & '
'bwa aln -t {5} -q {6} {0} {3} > {1} & '
'bwa aln -t {5} -q {6} {0} {4} > {2} & '
)
.format(
self.reference_genome_path,
sai_pipe_0.path,
sai_pipe_1.path,
self.sa.raw_reads_path[0],
self.sa.raw_reads_path[1],
math.floor(self.sa.processes / 2),
self.trims_reads_by
)
),
stdout=subprocess.PIPE,
stderr=self.sa.log
) as bwa_aln_sampe:
with subprocess.Popen(
(
'samtools',
'view',
'-Sbq', str(self.sa.phred_quality_score),
'-@', str(self.sa.processes)
),
stdin=bwa_aln_sampe.stdout,
stdout=subprocess.PIPE,
stderr=self.sa.log
) as samtools_view:
self.sa.bam, _ = samtools_view.communicate()
elif isinstance(self.sa.raw_reads_path, str):
with namedpipe.temp_named_pipe() as sai_pipe:
with subprocess.Popen(
(
'sh',
'-c',
(
'bwa samse {0} {1} {2} & '
'bwa aln -t {3} -q {4} {0} {2} > {1}; '
)
.format(
self.reference_genome_path,
sai_pipe.name,
self.sa.raw_reads_path,
self.sa.processes,
self.trims_reads_by
)
),
stdout=subprocess.PIPE,
stderr=self.sa.log
) as bwa_aln_samse:
with subprocess.Popen(
(
'samtools',
'view',
'-bhq', str(self.sa.phred_quality_score),
'-@', str(self.sa.processes)
),
stdin=bwa_aln_samse.stdout,
stdout=subprocess.PIPE,
stderr=self.sa.log
) as samtools_view:
self.sa.bam, _ = samtools_view.communicate()