def __init__(self, ctx):
super(type(self), self).__init__(ctx)
self.__get_configuration(ctx)
logging.basicConfig(level=self.log_level)
self.event_monitor = HadoopEventMonitor(self.COUNTER_CLASS,
logging.getLogger("mapper"),
ctx)
self.aligner = BwaAligner()
self.aligner.event_monitor = self.event_monitor
self.aligner.qformat = self.format
self.aligner.max_isize = self.max_isize
self.aligner.nthreads = self.nthreads
self.aligner.trim_qual = self.trim_qual
self.aligner.mmap_enabled = True
######## assemble hit processor chain
chain = FilterLink(self.event_monitor)
chain.remove_unmapped = self.remove_unmapped
chain.min_hit_quality = self.min_hit_quality
if self.__map_only:
chain.set_next(EmitSamLink(ctx, self.event_monitor))
else:
chain.set_next(MarkDuplicatesEmitter(ctx, self.event_monitor))
self.aligner.hit_visitor = chain
######## set the path to the reference index
self.ref_archive = utils.get_ref_archive(ctx.getJobConf())
self.aligner.reference = self.get_reference_root(self.ref_archive)
# part of the code is a workaround for accumulating records, see #331
isplit = InputSplit(ctx.getInputSplit())
self.split_end = isplit.offset + isplit.length
def __init__(self, ctx):
super(type(self), self).__init__(ctx)
self.__get_configuration(ctx)
logging.basicConfig(level=self.log_level)
self.event_monitor = HadoopEventMonitor(self.COUNTER_CLASS, logging.getLogger("mapper"), ctx)
self.aligner = BwaAligner()
self.aligner.event_monitor = self.event_monitor
self.aligner.qformat = self.format
self.aligner.max_isize = self.max_isize
self.aligner.nthreads = self.nthreads
self.aligner.trim_qual = self.trim_qual
self.aligner.mmap_enabled = True
######## assemble hit processor chain
chain = FilterLink(self.event_monitor)
chain.remove_unmapped = self.remove_unmapped
chain.min_hit_quality = self.min_hit_quality
if self.__map_only:
chain.set_next( EmitSamLink(ctx, self.event_monitor) )
else:
chain.set_next( MarkDuplicatesEmitter(ctx, self.event_monitor) )
self.aligner.hit_visitor = chain
######## set the path to the reference index
self.ref_archive = utils.get_ref_archive(ctx.getJobConf())
self.aligner.reference = self.get_reference_root(self.ref_archive)
# part of the code is a workaround for accumulating records, see #331
isplit = InputSplit(ctx.getInputSplit())
self.split_end = isplit.offset + isplit.length
def __init__(self, ctx):
super(mapper, self).__init__(ctx)
self.logger = logging.getLogger("seqal")
self.__get_configuration(ctx)
logging.basicConfig(level=self.log_level)
self.event_monitor = HadoopEventMonitor(self.COUNTER_CLASS, logging.getLogger("mapper"), ctx)
pe = True # single-end sequencen alignment not yet supported by Seqal
self.hi_rapi = HiRapiAligner('rapi_bwa', paired=pe)
# opts
self.hi_rapi.opts.n_threads = self.nthreads
self.hi_rapi.opts.isize_max = self.max_isize
if self.min_isize is not None:
self.hi_rapi.opts.isize_min = self.min_isize
self.hi_rapi.qoffset = self.hi_rapi.Qenc_Illumina if self.format == "fastq-illumina" else self.hi_rapi.Qenc_Sanger
# end opts
self.logger.info("Using the %s aligner plugin, aligner version %s, plugin version %s",
self.hi_rapi.aligner_name, self.hi_rapi.aligner_version, self.hi_rapi.plugin_version)
self.logger.info("Working in %s mode", 'paired-end' if pe else 'single-end')
# allocate space for reads
self.logger.debug("Reserving batch space for %s reads", self.batch_size)
self.hi_rapi.reserve_space(self.batch_size)
# load reference
reference_root = self.get_reference_root_from_archive(utils.get_ref_archive(ctx.getJobConf()))
self.logger.info("Full reference path (prefix): %s", reference_root)
with self.event_monitor.time_block("Loading reference %s" % reference_root):
self.hi_rapi.load_ref(reference_root)
######## assemble hit processor chain
chain = RapiFilterLink(self.event_monitor)
chain.remove_unmapped = self.remove_unmapped
chain.min_hit_quality = self.min_hit_quality
if self.__map_only:
chain.set_next( RapiEmitSamLink(ctx, self.event_monitor, self.hi_rapi) )
else:
raise NotImplementedError("Only mapping mode is supported at the moment")
self.hit_visitor_chain = chain
