def test():
# import cProfile
# primer = Primer(SeqRecord(Seq('ATARTCTYCGAMGGCTATKCAGNCTGGGANGGNTACGNGGGTAAANAAACG'),id='primer1'), 0.9e-6)
primer = Primer(SeqRecord(Seq('ATARTCTYCGAMGGCNATKCAGGNCTGRGGA'),id='primer1'), 0.9e-6)
primer.generate_components()
primer.calculate_Tms()
print primer.str_sequences
print primer.concentration
print repr(primer)
# from timeit import timeit
# from tests.violin_plot import violin_plot
# from matplotlib.pyplot import figure, show
#
# gen = [timeit('primer.generate_components()', 'from __main__ import primer', number=1) for _i in xrange(1)]
# gen_mp = [timeit('primer.generate_components_mp()', 'from __main__ import primer', number=1) for _i in xrange(1)]
# data = [gen, gen_mp]
# print data
#
# fig=figure()
# ax = fig.add_subplot(111)
# violin_plot(ax,data,range(len(data)),bp=1)
# show()
# cProfile.run('''
#for _n in xrange(100): primer.generate_components_mp()
#for _n in xrange(100): primer.generate_components()
#''',
# 'gen_components.profile')
print 'Done.'
def compile_primers(primer_alis, name_base, reverse=False):
primers = []
if reverse:
for pos, ali in primer_alis:
primers.append(
Primer.from_sequences(ali, 1, '%sR%d' % (name_base, pos)))
else:
for pos, ali in primer_alis:
primers.append(
Primer.from_sequences(ali, 1, '%sF%d' % (name_base, pos)))
return primers
def compile_pairs(falis, ralis, min_len, name_base):
pairs = []
for _i, (fs, fp) in enumerate(falis):
fprimer = Primer.from_sequences(fp, 1, '%sF%d' % (name_base, fs))
for _j, (rs, rp) in enumerate(ralis):
if rs - fs <= min_len: continue
pairs.append(
PrimerPair(
fprimer,
Primer.from_sequences(rp, 1,
'%sR%d' % (name_base, rs))))
return pairs
def test():
# import cProfile
# primer = Primer(SeqRecord(Seq('ATARTCTYCGAMGGCTATKCAGNCTGGGANGGNTACGNGGGTAAANAAACG'),id='primer1'), 0.9e-6)
primer = Primer(
SeqRecord(Seq('ATARTCTYCGAMGGCNATKCAGGNCTGRGGA'), id='primer1'),
0.9e-6)
primer.generate_components()
primer.calculate_Tms()
print primer.str_sequences
print primer.concentration
print repr(primer)
# from timeit import timeit
# from tests.violin_plot import violin_plot
# from matplotlib.pyplot import figure, show
#
# gen = [timeit('primer.generate_components()', 'from __main__ import primer', number=1) for _i in xrange(1)]
# gen_mp = [timeit('primer.generate_components_mp()', 'from __main__ import primer', number=1) for _i in xrange(1)]
# data = [gen, gen_mp]
# print data
#
# fig=figure()
# ax = fig.add_subplot(111)
# violin_plot(ax,data,range(len(data)),bp=1)
# show()
# cProfile.run('''
#for _n in xrange(100): primer.generate_components_mp()
#for _n in xrange(100): primer.generate_components()
#''',
# 'gen_components.profile')
print 'Done.'
def _main(self):
min_prod = 400
silva_db = '/home/allis/Documents/INMI/SILVA-DB/SILVA_123_SSURef_Nr99_tax_silva.fasta'
alifile = '/home/allis/Documents/INMI/SunS-metagenome/Bathy/BA2_SunS_16S.aln.fasta'
add_filename = FilenameParser.strip_ext(alifile)+'.with_additions.fasta'
outgroups = ['Thermococcus_chitonophagus', 'SMTZ1-55', 'contig72135_1581_sunspring_meta']
add = ['KF836721.1.1270','EU635905.1.1323']
exclude = []#['Thermococcus_chitonophagus', 'SMTZ1-55', 'BA1-16S', 'contig72135_1581_sunspring_meta']
#load alignment
if os.path.isfile(add_filename):
alifile = add_filename
add_filename = ''
with user_message('Loadding initial alignment...', '\n'):
orig_ali = AlignmentUtils.load_first(alifile)
if not orig_ali: return 1
#load homologs
if add_filename:
with user_message('Loadding additional sequences...', '\n'):
add_seqs = []
db = SeqView()
if db.load(silva_db):
for sid in add:
seq = db.get(sid)
if seq: add_seqs.append(seq)
else: print '%s not found in %s' % (sid, silva_db)
#realign data if needed
if add_seqs:
with user_message('Realigning data...', '\n'):
add_filename = FilenameParser.strip_ext(alifile)+'.with_additions.fasta'
AlignmentUtils.align(list(orig_ali)+add_seqs, add_filename)
orig_ali = AlignmentUtils.load_first(add_filename)
if not orig_ali: return 2
#process the alignment
ali = orig_ali.remove(*exclude).trim()
for out in outgroups:
if not ali.index(out):
print '%s not found in the alignment' % out
return 3
ali.sort(key=lambda r: 'zzzzzzzz' if r.id in outgroups else r.id)
ali_len = ali.get_alignment_length()
AlignmentUtils.save(ali, '/home/allis/Documents/INMI/SunS-metagenome/Bathy/BA2_SunS_16S.aln.trimmed.fasta')
args = dict(plen = (20,40),
max_mismatches = 8,
min_match_mismatches = 1,
first_match_mismatches = 1,
first_may_match = 1,
AT_first=True,
outgroup=len(outgroups))
fprimers = self._find_primers(ali, **args)
rprimers = self._find_primers(ali.reverse_complement(), **args)
pairs = []
for i, (fs, fp) in enumerate(fprimers):
start = fs
fprimer = Primer.from_sequences(fp[:-1], 1, 'SSBaF%d' % fs)
for _j, (rs, rp) in enumerate(rprimers):
end = ali_len-rs
if end-start <= min_prod: continue
pairs.append((fprimer, Primer.from_sequences(rp[:-1], 1, 'SSBaR%d' % (ali_len-rs+1))))
if not pairs:
print '\nNo suitable primer pairs found'
return 3
added = set()
for i, (fp, rp) in enumerate(pairs):
print '\npair %d' % (i+1)
print '%s: %s' % (fp.id, fp)
print '%s: %s' % (rp.id, rp)
if fp.id not in added:
orig_ali.append(fp.master_sequence+'-'*(orig_ali.get_alignment_length()-len(fp)))
added.add(fp.id)
if rp.id not in added:
orig_ali.append(copy_attrs(rp.master_sequence,
rp.master_sequence.reverse_complement())+
'-'*(orig_ali.get_alignment_length()-len(rp)))
added.add(rp.id)
print
orig_ali = AlignmentUtils.align(orig_ali)
AlignmentUtils.save(orig_ali, '/home/allis/Documents/INMI/SunS-metagenome/Bathy/BA2_SunS_16S.with_primers.aln.fasta')
print 'Done'
def _main(self):
from threading import Lock
from BioUtils.Tools import WaitingThread
from DegenPrimer.Primer import Primer
from DegenPrimer.SeqUtils import load_sequence
from DegenPrimer.PCR_Optimizer import PCR_Optimizer
from DegenPrimer import TD_Functions as tdf
tdf.PCR_P.PCR_T = 53
tdf.PCR_P.Mg = 3e-3
tdf.PCR_P.dNTP = 300e-6
tdf.PCR_P.DNA = 1e-10
fwd_primer = Primer(
load_sequence('ATATTCTACRACGGCTATCC', 'fwd_test', 'fwd_test'),
0.43e-6, True)
rev_primer = Primer(
load_sequence('GAASGCRAAKATYGGGAAC', 'rev_test', 'rev_test'),
0.43e-6, True)
optimizer = PCR_Optimizer(self.abort_event,
100,
5,
max_mismatches=5,
job_id='test-job',
primers=[fwd_primer, rev_primer],
min_amplicon=50,
max_amplicon=2000,
polymerase=40000,
with_exonuclease=False,
num_cycles=30,
side_reactions=None,
side_concentrations=None,
include_side_annealings=False)
plock = Lock()
job = WaitingThread(
plock,
1,
target=optimizer.optimize_PCR_parameters,
name='optimize PCR',
args=(
'../data/ThGa.fa',
({
'start': 47920,
'end': 49321
}, ),
({
'name': 'PCR_T',
'min': 50,
'ini': 60,
'max': 72
},
# {'name':'dNTP',
# 'min':100e-6, 'ini':200e-6, 'max':900e-6},
),
))
job.start()
print ''
job.join()
optimizer.write_report()
def _main(self):
import time
import DegenPrimer.TD_Functions as tdf
from DegenPrimer.Primer import Primer
from DegenPrimer.SeqUtils import load_sequence
from DegenPrimer.WorkCounter import WorkCounterManager
from BioUtils.Tools import WaitingThread
from DegenPrimer.iPCR import iPCR
from threading import Lock
import cProfile
tdf.PCR_P.PCR_T = 53
tdf.PCR_P.Mg = 3e-3
tdf.PCR_P.dNTP = 300e-6
tdf.PCR_P.DNA = 1e-10
fwd_primer = Primer(
load_sequence('ATATTCTACRACGGCTATCC', 'fwd_test', 'fwd_test'),
0.43e-6, True)
rev_primer = Primer(
load_sequence('GAASGCRAAKATYGGGAAC', 'rev_test', 'rev_test'),
0.43e-6, True)
ipcr = iPCR(self.abort_event,
max_mismatches=6,
job_id='test-job',
primers=[fwd_primer, rev_primer],
min_amplicon=50,
max_amplicon=2000,
polymerase=40000,
with_exonuclease=False,
num_cycles=30,
side_reactions=None,
side_concentrations=None,
include_side_annealings=True)
cmgr = WorkCounterManager()
cmgr.start()
counter = cmgr.WorkCounter()
plock = Lock()
job = WaitingThread(
plock,
1,
target=ipcr.simulate_PCR,
name='simulate_PCR',
args=(
counter,
(
'../data/ThGa.fa', #single sequence
# '../data/Ch5_gnm.fa', '../data/ThDS1.fa', '../data/ThES1.fa', #long sequences
'../data/ThDS1-FC.fa',
'../data/ThDS1-850b-product.fa', #short sequences
),
))
job.start()
print ''
while job.is_alive():
if counter.changed_percent():
with plock:
print counter
time.sleep(1)
job.join()
with plock:
print counter
ipcr.write_report()
cProfile.runctx('for i in xrange(100): ipcr.write_reports()',
globals(), locals(), 'iPCR.write_reports.profile')
seq_file = '../data/ThGa.fa'
try:
record_file = open(seq_file, 'r')
except IOError, e:
print 'Unable to open %s' % seq_file
print e
sys.exit(1)
template = SeqIO.read(record_file, 'fasta', IUPAC.unambiguous_dna)
record_file.close()
ftgam = Seq('ATATTCTACRACGGCTATCC', IUPAC.ambiguous_dna)
rtgam = Seq('GAASGCRAAKATYGGGAAC', IUPAC.ambiguous_dna)
# primer = Primer(SeqRecord(ftgam, id='ftgam'), 0.43e-6, True)
primer = Primer(SeqRecord(rtgam, id='rtgam'), 0.43e-6,
True) #48C, 9mism, results: 564.85Mb, 410.37Mb, 240.07Mb
def print_out(out, name):
print name
for i, results in enumerate(out):
if not results:
print 'No results.'
else:
print 'Results %d' % i
for res in results:
print res[0]
for dup, _id in res[1]:
print _id
print dup
#print 'mismatches:', dup.mismatches
print '\n'
from DegenPrimer.TD_Functions import PCR_P
from DegenPrimer.BlastPrimers import BlastPrimers
from threading import Lock
os.chdir('../')
mgr = Manager()
abort_event = mgr.Event()
PCR_P.PCR_T = 53
PCR_P.Mg = 3e-3
PCR_P.dNTP = 300e-6
PCR_P.DNA = 1e-10
fwd_primer = Primer(
load_sequence('ATATTCTACRACGGCTATCC', 'F-TGAM_0057-268_d1',
'F-TGAM_0057-268_d1'), 0.43e-6, True)
rev_primer = Primer(
load_sequence('GAASGCRAAKATYGGGAAC', 'R-TGAM_0055-624-d4',
'R-TGAM_0055-624-d4'), 0.43e-6, True)
blastp = BlastPrimers(abort_event,
job_id='F-TGAM_0057-268_d1-R-TGAM_0055-624-d4',
primers=[fwd_primer, rev_primer],
min_amplicon=50,
max_amplicon=2000,
polymerase=40000,
with_exonuclease=False,
num_cycles=30,
side_reactions=None,
side_concentrations=None,
