def init(self,
reverse_read_strand=None,
reads_are_stranded=None,
pairs_are_opp_strand=None,
reads_are_paired=None,
frag_len_dist=None):
assert self.is_indexed()
#"ChIPSeq.GM12878.CTCF.BSID-ENCBS195XMM.REPID-1_1.EXPID-ENCSR000DRZ.bam"
#data = os.path.basename(self.filename).split('.')
#self.biosample = data[1]
#self.factor = data[2]
#self.bsid = data[3].split("-")[1]
#self.experiment_id = data[5].split("-")[1]
#self.repid = data[4].split("-")[1]
#self.id = "%s.%s.%s" % (self.factor, self.bsid, self.repid)
reads_are_stranded = True
if frag_len_dist == None:
frag_len_dist = build_normal_density(fl_min=100,
fl_max=200,
mean=150,
sd=25)
self.frag_len_dist = frag_len_dist
self.frag_len = int(frag_len_dist.mean_fragment_length())
read_pair_params = determine_read_pair_params(self)
# set whether the reads are paired or not
if reads_are_paired in ('auto', None):
if 'paired' in read_pair_params:
reads_are_paired = True
assert 'unpaired' in read_pair_params
else:
reads_are_paired = False
if pairs_are_opp_strand in ('auto', None):
if reads_are_paired or ('same_strand' in read_pair_params):
pairs_are_opp_strand = False
else:
pairs_are_opp_strand = True
reverse_read_strand = None
Reads.init(self, reads_are_paired, pairs_are_opp_strand,
reads_are_stranded, reverse_read_strand)
# we save these for fast reloads
self._init_kwargs = {
'reverse_read_strand': reverse_read_strand,
'reads_are_stranded': reads_are_stranded,
'pairs_are_opp_strand': pairs_are_opp_strand,
'reads_are_paired': reads_are_paired
}
return self
def init(self,
reverse_read_strand=None, reads_are_stranded=None,
pairs_are_opp_strand=None, reads_are_paired=None,
frag_len_dist=None):
assert self.is_indexed()
"ChIPSeq.GM12878.CTCF.BSID-ENCBS195XMM.REPID-1_1.EXPID-ENCSR000DRZ.bam"
data = os.path.basename(self.filename).split('.')
self.biosample = data[1]
self.factor = data[2]
self.bsid = data[3].split("-")[1]
self.experiment_id = data[5].split("-")[1]
self.repid = data[4].split("-")[1]
self.id = "%s.%s.%s" % (self.factor, self.bsid, self.repid)
reads_are_stranded = True
if frag_len_dist == None:
frag_len_dist = build_normal_density(
fl_min=100, fl_max=200, mean=150, sd=25)
self.frag_len_dist = frag_len_dist
self.frag_len = int(frag_len_dist.mean_fragment_length())
read_pair_params = determine_read_pair_params(self)
# set whether the reads are paired or not
if reads_are_paired in ('auto', None):
if 'paired' in read_pair_params:
reads_are_paired = True
assert 'unpaired' in read_pair_params
else:
reads_are_paired = False
if pairs_are_opp_strand in ('auto', None):
if reads_are_paired or ('same_strand' in read_pair_params):
pairs_are_opp_strand = False
else:
pairs_are_opp_strand = True
reverse_read_strand = None
Reads.init(self, reads_are_paired, pairs_are_opp_strand,
reads_are_stranded, reverse_read_strand )
# we save these for fast reloads
self._init_kwargs = {
'reverse_read_strand': reverse_read_strand,
'reads_are_stranded': reads_are_stranded,
'pairs_are_opp_strand': pairs_are_opp_strand,
'reads_are_paired': reads_are_paired
}
return self
def build_normal_fl_dist(fl_mean, fl_sd):
fl_min = max(0, fl_mean - (fl_sd * NUM_NORM_SDS))
fl_max = fl_mean + (fl_sd * NUM_NORM_SDS)
fl_dist = frag_len.build_normal_density(fl_min, fl_max, fl_mean, fl_sd)
return fl_dist
def build_normal_fl_dist( fl_mean, fl_sd ):
fl_min = max( 0, fl_mean - (fl_sd * NUM_NORM_SDS) )
fl_max = fl_mean + (fl_sd * NUM_NORM_SDS)
fl_dist = frag_len.build_normal_density( fl_min, fl_max, fl_mean, fl_sd )
return fl_dist