def test_blastn(self):
p = self.plus['locus']
# If indel in the sequence, retrieves corrected sequence
indel = p.seq[:90] + p.seq[100:]
seqloc = locus.Locus(dna.Dna(indel))
self.assertEquals(seqloc.name, self.plus['coord'])
self.assertEquals(seqloc.seq.lower(), self.plus['seq_file'].lower())
with self.assertRaises(ValueError):
# Nonsense
locus.Locus(dna.Dna('tact' * 1000))
with self.assertRaises(ValueError):
# Paste together in wrong order
locus.Locus(dna.Dna(p.down + p.seq + p.up))
def test_search_by_seq(self):
# Ensure that searching by sequence using blastn gives same results"""
for d in self.dicts:
seqloc = locus.Locus(dna.Dna(d['locus'].seq), context=self.context)
self.assertEquals(seqloc.name, d['coord'])
self.assertEquals(seqloc.seq.lower(), d['seq_file'].lower())
full = d['locus'].up + d['locus'].seq + d['locus'].down
self.assertEquals(full.lower(), d['context_file'].lower())
def setUp(self):
# short genes on each strand. Seqs from Ensembl in static/testdata/
self.context = 100
self.plus = {}
self.plus['id'] = 'PAS_chr2-1_0751'
self.plus['coord'] = '2:1427323-1427517(+)'
self.minus = {}
self.minus['id'] = 'PAS_chr1-4_0504'
self.minus['coord'] = '1:2322810-2322980(-)'
self.dicts = (self.plus, self.minus)
for d in self.dicts:
d['locus'] = locus.Locus(dna.Dna('', name=d['id']),
context=self.context)
with open(paths.TESTDATA_PATH + d['id'] + '.seq', 'r') as f:
d['seq_file'] = f.read().strip()
with open(paths.TESTDATA_PATH + d['id'] + '_context100.seq',
'r') as f:
d['context_file'] = f.read().strip()
def __init__(self, target, common_frags, in_frame=False):
"""Args:
target (Dna):
common_frags (list of Dna): Dna fragments shared by Batch.
in_frame (bool): True if tag should create a protein fusion
(maintain START or STOP codon)"""
# super() required to call next __init__() method in the
# multiple resolution order. (object.__init__() is no-op)
super(Design, self).__init__()
self.in_frame = in_frame
self.target = target
# Single retrieval of outermost sequences
self.locus = locus.Locus(target,
context=self.opt_arm + 2 * self.search)
self.M, self.T, self.V = common_frags
# T overhangs are unique to the design, though Pcr common to batch.
self.T = copy.deepcopy(self.T)
self.U = self.D = self.colony = None
def LoadLoci(locfile, datafiles, minsamples, maxsamples, \
locuspriors, locusfeatures, use_features, \
stderrs, jackknife_blocksize, isvcf, eststutter, usestutter, uselikelihoods, \
use_sample_pairs, use_locus_means, usesmm, \
debug=False):
sys.stderr.write("Loading priors\n")
priors = LoadPriors(locuspriors, use_locus_means, locfile)
sys.stderr.write("Loading features\n")
features = LoadLocusFeatures(locusfeatures,
locfile,
use_features=use_features)
sys.stderr.write("Loading stutter\n")
stutter = LoadStutter(usestutter)
loci = []
with open(locfile, "r") as f:
for line in f:
chrom, start, end = line.strip().split()[0:3]
chrom = str(chrom)
start = int(start)
end = int(end)
loc = locus.Locus(chrom, start, end, datafiles, minsamples, maxsamples, \
stderrs, isvcf, eststutter, uselikelihoods, _debug=debug)
loc.jkblocksize = jackknife_blocksize
loc.usesmm = usesmm
key = (chrom, start, end)
if priors is not None and key not in priors: continue
if features is not None and key not in features: continue
if stutter is not None and key not in stutter: continue
if priors is not None and key in priors:
loc.LoadPriors(*priors[key])
if features is not None and key in features:
loc.LoadFeatures(features[key])
sys.stderr.write("%s,%s\n" % (str(key), str(features[key])))
if use_sample_pairs is not None:
loc.use_sample_pairs = True
loc.pair_file = use_sample_pairs
if stutter is not None and key in stutter:
loc.LoadStutter(*stutter[key])
loci.append(loc)
return loci