def setUp(self):
self.hi = HiRapiAligner('rapi_bwa')
self.reads = test_utils.get_mini_ref_seqs()
for row in self.reads:
if len(row) != 5:
raise RuntimeError(
"Unexpected number of fields in mini_ref read record")
self.hi.load_pair(*row)
def test_base_quality(self):
hi = HiRapiAligner('rapi_bwa', paired=False)
one_read = self.reads[0][0:3]
hi.q_offset = self.hi.Qenc_Sanger
hi.load_read('sanger_read', one_read[1], one_read[2])
# 64: Illumina base quality offset
# 33: Sanger base quality offset
ill_quality = ''.join(chr(ord(c) + (64 - 33)) for c in one_read[2])
hi.q_offset = self.hi.Qenc_Illumina
hi.load_read('illumina_read', one_read[1], ill_quality)
loaded_qualities = [frag[0].qual for frag in hi.ifragments()]
self.assertEquals(2, len(loaded_qualities))
self.assertEquals(loaded_qualities[0], loaded_qualities[1])
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
def setUp(self):
self.hi = HiRapiAligner('rapi_bwa')
self._align_mini_ref_seqs()
def setUp(self):
self.hi = HiRapiAligner('rapi_bwa')
