def mapReadsAgainstSpadesContigs(infiles, outfile):
'''
map reads against spades contigs
'''
inf = infiles[0]
to_cluster = True
index_dir = os.path.dirname(outfile)
if "agg" not in infiles[1]:
genome = re.search(
".*R[0-9]*", infiles[0]).group(0) + ".filtered.contigs.fa"
else:
genome = "agg-agg-agg.filtered.contigs.fa"
if infiles[1].endswith(".bt2") or infiles[1].endswith(".ebwt"):
infile, reffile = infiles[0], os.path.join(index_dir, genome) + ".fa"
m = PipelineMapping.Bowtie(
executable=P.substituteParameters(**locals())["bowtie_executable"])
elif infiles[1].endswith("bwt"):
genome = genome
job_options = " -l mem_free=%s" % (PARAMS["bwa_memory"])
bwa_index_dir = index_dir
bwa_mem_options = PARAMS["bwa_mem_options"]
bwa_threads = PARAMS["bwa_threads"]
m = PipelineMapping.BWAMEM(remove_non_unique=True)
statement = m.build((inf,), outfile)
P.run()
def mapBowtieAgainstTranscriptomeGSE65525(infiles, outfile):
''' map reads using Bowtie against transcriptome
bowtie parameterised according to Allon et al 2015 except
random reporting of alignments where more than one "best" exist (-M 1):
-n 1 number of mismatches allowed
-l 15 seed length
-e 300 maxmimum permitted sum of sequence qualities at all mismatched
positions
-M 1 if more than one "best" alignment exist, report one at random
--best report in best to worst order
--strata only report reads falling into the best stratum
'''
infile, reference = infiles
job_threads = 2
job_options = "-l mem_free=1.9G"
bowtie_options = "-n1 -l 15 -e 300 -M 1 --best --strata"
bowtie_index_dir = os.path.abspath(os.path.dirname(reference))
genome = P.snip(os.path.basename(reference), ".1.ebwt")
reffile = reference
bowtie_threads = job_threads
m = PipelineMapping.Bowtie(tool_options=bowtie_options,
remove_non_unique=0,
strip_sequence=0)
statement = m.build((infile, ), outfile)
P.run()
def run_mapping(infile, outfile):
''' Map reads with the specified read mapper '''
if PARAMS["mapper"] == "star":
job_threads = PARAMS["star_threads"]
job_memory = PARAMS["star_memory"]
star_mapping_genome = PARAMS["star_genome"] or PARAMS["genome"]
m = PipelineMapping.STAR(
executable=P.substituteParameters(**locals())["star_executable"],
strip_sequence=0)
elif PARAMS["mapper"] == "bowtie":
job_threads = PARAMS["bowtie_threads"]
job_memory = PARAMS["bowtie_memory"]
m = PipelineMapping.Bowtie(executable="bowtie",
tool_options=PARAMS["bowtie_options"],
strip_sequence=0)
genome = PARAMS["bowtie_genome"]
reffile = os.path.join(PARAMS["bowtie_index_dir"],
PARAMS["bowtie_genome"] + ".fa")
statement = m.build((infile, ), outfile)
P.run()
def buildBAM(infile, outfile):
'''map reads with bowtie'''
track = P.snip(os.path.basename(outfile), ".bam")
job_threads = PARAMS["bowtie_threads"]
m = PipelineMapping.Bowtie()
reffile = PARAMS["samtools_genome"]
statement = m.build((infile, ), outfile)
P.run()
def buildBAM(infile, outfile):
'''map reads with bowtie'''
to_cluster = True
track = P.snip(os.path.basename(outfile), ".bam")
job_options = "-pe dedicated %i -R y" % PARAMS["bowtie_threads"]
m = PipelineMapping.Bowtie()
reffile = PARAMS["samtools_genome"]
statement = m.build((infile, ), outfile)
P.run()
def buildBAM(infile, outfile, options):
'''map reads with bowtie'''
job_threads = PARAMS["bowtie_threads"]
m = PipelineMapping.Bowtie()
reffile = PARAMS["samtools_genome"]
bowtie_options = options
statement = m.build((infile,), outfile)
# print(statement)
P.run()
def alignReadsToTranscriptome(infile, outfile):
'''map reads to transcriptome with bowtie'''
track = P.snip(os.path.basename(outfile), ".bam")
job_threads = PARAMS["bowtie_threads"]
m = PipelineMapping.Bowtie()
reffile = PARAMS["bowtie_transcriptome"]
bowtie_options = PARAMS["bowtie_options"]
statement = m.build((infile,), outfile)
P.run()
def buildBAM(infile, outfile, options):
'''map reads with bowtie'''
to_cluster = True
job_options = "-pe dedicated %i -R y" % PARAMS["bowtie_threads"]
m = PipelineMapping.Bowtie()
reffile = PARAMS["samtools_genome"]
bowtie_options = options
statement = m.build((infile,), outfile)
# print(statement)
P.run()
def mapReadsWithBowtieAgainstRayContigs(infile, outfile):
'''
map reads against contigs with bowtie
'''
PARAMS["bowtie_index_dir"] = "ray.dir"
PARAMS["genome"] = TRACKS.getTracks(infile)[0].split(".")[0]
infile, reffile = infile, os.path.join("ray.dir",
TRACKS.getTracks(infile)[0])
m = PipelineMapping.Bowtie(executable=P.substituteParameters(
**locals())["bowtie_executable"])
statement = m.build((infile, ), outfile)
P.run()
def run_mapping(infile, outfile):
''' Map reads using the selected read mapper '''
job_threads = PARAMS["bowtie_threads"]
job_memory = PARAMS["bowtie_memory"]
m = PipelineMapping.Bowtie(
executable="bowtie",
tool_options=PARAMS["bowtie_options"],
strip_sequence=0)
genome = PARAMS["bowtie_genome"]
reffile = os.path.join(PARAMS["bowtie_index_dir"],
PARAMS["bowtie_genome"] + ".fa")
statement = m.build((infile,), outfile)
P.run()
def filterPhiX(infiles, outfile):
''' Use mapping to bowtie to remove any phiX mapping reads '''
infile, reffile = infiles
outfile = P.snip(outfile, ".gz")
bam_out = P.snip(infile, ".fastq.gz") + ".phix.bam"
job_threads = PARAMS["phix_bowtie_threads"]
job_memory = PARAMS["phix_bowtie_memory"]
options = PARAMS["phix_bowtie_options"] + " --un %s" % outfile
genome = PARAMS["phix_genome"]
bowtie_threads = PARAMS["phix_bowtie_threads"]
m = PipelineMapping.Bowtie(executable=PARAMS["phix_bowtie_exe"],
strip_sequence=False,
remove_non_unique=False,
tool_options=options)
statement = m.build((infile, ), bam_out)
statement += "checkpoint; gzip %(outfile)s"
P.run()