def trim_anchor(anchor_name, anchor_list, sequence, readDir):
print 'looking for anchor:', anchor_name
exact = ''
exactTrimmedOff = ''
#print sequence
freedom = C.mbl_anchors[anchor_name]['freedom']
length = C.mbl_anchors[anchor_name]['length']
start = C.mbl_anchors[anchor_name]['start']
reversed = C.mbl_anchors[anchor_name]['reversed']
max_divergence = C.max_divergence
if (reversed == True and readDir == 'F') or (reversed == False
and readDir == 'R'):
print "anchor reversed vs readDir mismatch -Skipping", reversed, readDir
return '', '', sequence
#print 'Reversed',reversed
list_of_tuples = anchortrim.generate_tuples(start,
freedom,
length,
reversed_read=reversed)
#print list_of_tuples
if readDir == 'R':
import pipeline.utils as utils
anchor_list = utils.revcomp(anchor_list)
print anchor_list
anchor, location = anchortrim.find_best_distance(sequence, anchor_list,
max_divergence,
list_of_tuples)
if anchor and location:
print 'anchor:', anchor, 'loc:', location
# busines time.
if reversed:
trimmed_sequence = sequence[
location[0]:] # this includes the anchor in trimmed sequence..
else:
trimmed_sequence = sequence[:location[
1]] # same thing here for the reversed == False
#trimmed_sequence = anchortrim.trim_sequence(seq, location, s)
#print 'trimmed',trimmed_sequence
exact = anchor
if reversed:
exactTrimmedOff = sequence[:location[0]]
#return sequence[location[0]:] # this includes the anchor in trimmed sequence..
else:
exactTrimmedOff = sequence[location[1]:]
#return sequence[:location[1]] # same thing here for the reversed == False
else:
print 'no anchor location found'
trimmed_sequence = sequence
return exact, exactTrimmedOff, trimmed_sequence
def trim_anchor(anchor_name, anchor_list, sequence, readDir):
print 'looking for anchor:',anchor_name
exact = ''
exactTrimmedOff = ''
#print sequence
freedom = C.mbl_anchors[anchor_name]['freedom']
length = C.mbl_anchors[anchor_name]['length']
start = C.mbl_anchors[anchor_name]['start']
reversed = C.mbl_anchors[anchor_name]['reversed']
max_divergence = C.max_divergence
if (reversed == True and readDir == 'F') or (reversed == False and readDir == 'R'):
print "anchor reversed vs readDir mismatch -Skipping",reversed,readDir
return '','',sequence
#print 'Reversed',reversed
list_of_tuples = anchortrim.generate_tuples(start, freedom, length, reversed_read = reversed)
#print list_of_tuples
if readDir == 'R':
import pipeline.utils as utils
anchor_list = utils.revcomp(anchor_list)
print anchor_list
anchor, location = anchortrim.find_best_distance(sequence, anchor_list, max_divergence, list_of_tuples)
if anchor and location:
print 'anchor:',anchor,'loc:',location
# busines time.
if reversed:
trimmed_sequence = sequence[location[0]:] # this includes the anchor in trimmed sequence..
else:
trimmed_sequence = sequence[:location[1]] # same thing here for the reversed == False
#trimmed_sequence = anchortrim.trim_sequence(seq, location, s)
#print 'trimmed',trimmed_sequence
exact = anchor
if reversed:
exactTrimmedOff = sequence[:location[0]]
#return sequence[location[0]:] # this includes the anchor in trimmed sequence..
else:
exactTrimmedOff = sequence[location[1]:]
#return sequence[:location[1]] # same thing here for the reversed == False
else:
print 'no anchor location found'
trimmed_sequence = sequence
return exact, exactTrimmedOff, trimmed_sequence
def __init__(self, runobj, domain, region, lane_key):
self.domain = domain
self.region = region
# list of included primer classes
self.primer_list ={}
self.primer_list['F']=[]
self.primer_list['R']=[]
# list of primer sequences
self.primer_seq_list={}
self.primer_seq_list['F'] = []
self.primer_seq_list['R'] = []
# list of expanded primer sequences
self.primer_expanded_seq_list={}
self.primer_expanded_seq_list['F'] = []
self.primer_expanded_seq_list['R'] = []
self.primer_names ={}
self.primer_names_by_reverse_complement = {}
# changes Bacteria to Bacterial for the name
if self.domain[-1:] != 'l':
self.domain = self.domain + "l"
self.name = self.domain + ":" + self.region
# now they can specify to not use the mbl primers for this lane/runkey
if runobj.samples[lane_key].use_mbl_primers == 1:
suite = runobj.primer_suites[self.name]
if suite != None:
for key, value in suite.items():
direction = value['direction']
sequence = value['sequence']
domain = value['domain']
region = value['region']
p = Primer(key,direction,domain,region,sequence)
self.primer_list[direction].append(p)
self.primer_seq_list[direction].append(sequence)
self.primer_expanded_seq_list[direction] = self.primer_expanded_seq_list[direction] + p.expanded_seqs
for eseq in p.expanded_seqs:
self.primer_names[eseq] = key
# we will need this for Reverse reads
self.primer_names_by_reverse_complement[revcomp(eseq)] = key
# they may have given some forward/reverse primers on a per lane/runkey basis
direction = 'F'
for idx, sequence in enumerate(runobj.samples[lane_key].forward_primers):
key = "cust_" + lane_key + "_" + direction + "_" + str(idx)
p = Primer(key,dir,'custom','custom',sequence)
self.primer_list[direction].append(p)
self.primer_seq_list[direction].append(sequence)
self.primer_expanded_seq_list[direction] = self.primer_expanded_seq_list[direction] + p.expanded_seqs
for eseq in p.expanded_seqs:
self.primer_names[eseq] = key
# we will need this for Reverse reads
self.primer_names_by_reverse_complement[revcomp(eseq)] = key
direction = 'R'
for idx, sequence in enumerate(runobj.samples[lane_key].reverse_primers):
key = "cust_" + lane_key + "_" + direction + "_" + str(idx)
p = Primer(key,dir,'custom','custom',sequence)
self.primer_list[direction].append(p)
self.primer_seq_list[direction].append(sequence)
self.primer_expanded_seq_list[direction] = self.primer_expanded_seq_list[direction] + p.expanded_seqs
for eseq in p.expanded_seqs:
self.primer_names[eseq] = key
# we will need this for Reverse reads
self.primer_names_by_reverse_complement[revcomp(eseq)] = key
def test_revcomp(self):
self.assertEqual(utils.revcomp('TGGGCGTAAAG'),'CTTTACGCCCA')
