def countTaggedReads(infiles, outfile):
'''count number of reads in input files.'''
to_cluster = True
read1, read2 = infiles
m = PipelineMapping.Counter()
statement = m.build((read1, ), outfile)
P.run()
def mapReadsWithTophatFusion(infiles, outfile):
'''map reads from .fastq or .sra files and find candidate fusions
A list with known splice junctions expect from rnaseq pipeline
'''
job_threads = PARAMS["tophat_threads"]
if "--butterfly-search" in PARAMS["tophat_options"]:
# for butterfly search - require insane amount of
# RAM.
job_options += " -l mem_free=50G"
to_cluster = USECLUSTER
m = PipelineMapping.TopHat_fusion()
infile = infiles
# if a file of reference junctions, as generated by the rnaseq pipline,
# has been specified in the ini, then pass this to tophat-fusion
if not PARAMS['tophatfusion_reference_junctions'] is None:
reffile = PARAMS['tophatfusion_reference_junctions']
tophat_options = PARAMS["tophat_options"] + \
" --raw-juncs %(reffile)s" % locals()
tophatfusion_options = PARAMS["tophatfusion_options"]
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 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'''
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 mapReadsWithBismark(infile, outfile):
'''map reads with bismark'''
# can this handle paired end?
# it appears bismark uses twice as many CPUs as expeceted!
job_options = "-l mem_free=%s " % PARAMS["bismark_memory"]
job_threads = (PARAMS["bismark_threads"] * 2) + 1
outdir = "bismark.dir"
bismark_options = PARAMS["bismark_options"]
m = PipelineMapping.Bismark()
statement = m.build((infile, ), outfile)
# print statement
P.run()
def mapReads(infiles, outfile):
'''Map reads to the genome using BWA '''
job_threads = PARAMS["bwa_threads"]
m = PipelineMapping.BWA()
statement = m.build((infiles, ), outfile)
P.run()
def countReads(infile, outfile):
'''count number of reads in input files.'''
to_cluster = True
m = PipelineMapping.Counter()
statement = m.build((infile, ), outfile)
P.run()