def testRegionSpecificRandomization2(codon, taxId):
#assert(fraction>=0)
#assert(fraction < numFractions)
assert(type(taxId)==type(0))
startTime = time()
shuffler = SynonymousCodonPermutingRandomization(getSpeciesTranslationTable(taxId))
numShuffles = 1
numSeqsDone = 0
#diffStats = CalcStats2(taxId)
#allNativeStats = CalcStats2(taxId)
data = []
poolCodons = []
for (seqId, seq) in nativeSequencesSource(taxId, 0, 1):
if len(seq) >= (codon+1)*3-1:
codon = seq[codon*3:(codon+1)*3]
assert(len(codon)==3)
poolCodons.append( codon )
pool = ''.join(poolCodons)
totalPermutationsCountForSeq = None
numAttempts = 0
while True:
identity = None
shuffledSeq = None
#if time() - startTime > 300:
# raise Exception("Calculation took to much time!")
try:
numAttempts += 1
totalPermutationsCountForSeq, identity, shuffledSeq = shuffler.randomize(pool)
except Exception as e:
print(e)
#continue # skip this sequence
raise e
if numAttempts >= 3:
break
#data.append( (len(seq), totalPermutationsCountForSeq) )
#numSeqsDone += 1
#logging.warning(mod3.getResults())
#logging.warning(mod4.getResults())
#logging.warning(mod5.getResults())
return (taxId, codon, len(pool), totalPermutationsCountForSeq)
def createRandomizedSeqs(cds,
newShuffleIds,
shuffleType=db.Sources.ShuffleCDSv2_python):
shuffler = SynonymousCodonPermutingRandomization(cds.getTranslationTable())
nativeSeq = cds.sequence()
#print(nativeSeq[:10])
newShuffles = []
for shuffleId in newShuffleIds:
totalPermutationsCount, identity, newseq = None, None, None
try:
totalPermutationsCount, identity, newseq = shuffler.randomize(
nativeSeq)
except Exception as e:
print(e)
raise
assert ((identity <= 1.0) and (identity > 0.0))
if (identity > 0.95):
print(
"Warning: Identity of randomized sequence is high - %.3g%% (length=%d nt, total permutations=%.2g)"
% (identity * 100.0, len(newseq), totalPermutationsCount))
if (totalPermutationsCount < 500):
raise Exception(
"Low number of possible permutations %.2g (length=%d nt, identity=%.3g%%)"
% (totalPermutationsCount, len(newseq), identity * 100.0))
newShuffles.append(newseq)
return newShuffles
def getRandomizedSequenceCacheForVerticalPermutations(taxId):
global _caches
if (taxId, db.Sources.ShuffleCDS_vertical_permutation_1nt) in _caches:
cache = _caches[(taxId, db.Sources.ShuffleCDS_vertical_permutation_1nt)]
else:
# read all native sequences
protIds = []
cdss = []
for protId in SpeciesCDSSource(taxId):
cds = CDSHelper(taxId, protId)
if( cds.length()%3 != 0 ):
continue
seq = cds.sequence()
protIds.append(protId)
cdss.append(seq)
geneticCode = getSpeciesTranslationTable( taxId )
scpr = SynonymousCodonPermutingRandomization( geneticCode )
randomizer = lambda cdss: scpr.verticalPermutation( cdss )
cache = VerticalRandomizationCache(shuffleType=db.Sources.ShuffleCDS_vertical_permutation_1nt,
taxId=taxId,
nativeSeqsMap=dict(zip(protIds, cdss)),
geneticCode=geneticCode,
randomizer=randomizer )
_caches[(taxId, db.Sources.ShuffleCDS_vertical_permutation_1nt)] = cache
print(_caches.keys())
return cache
def createRandomizedSeqs_CDS_with_3UTR(
cds,
newShuffleIds,
shuffleType=db.Sources.
ShuffleCDS_synon_perm_and_3UTR_nucleotide_permutation,
taxId=None):
#NucleotidePermutationRandomization, CDSand3UTRRandomization
cdsRand = SynonymousCodonPermutingRandomization(cds.getTranslationTable())
utrRand = NucleotidePermutationRandomization()
if shuffleType == db.Sources.ShuffleCDS_synon_perm_and_3UTR_nucleotide_permutation:
shuffler = CDSand3UTRRandomization(cdsRand, utrRand)
elif shuffleType == db.Sources.ShuffleCDS_synon_perm_and_3UTR_nucleotide_permutation_Including_Next_CDS:
shuffler = CDSand3UTRRandomizationIncludingNextCDS(
cdsRand, utrRand, taxId=taxId, constantOverlaps=False)
elif shuffleType == db.Sources.ShuffleCDS_synon_perm_and_3UTR_nucleotide_permutation_Including_Next_CDS_Constant_Overlaps:
shuffler = CDSand3UTRRandomizationIncludingNextCDS(
cdsRand, utrRand, taxId=taxId, constantOverlaps=True)
else:
raise Exception("Unknown shuffleType={}".format(shuffleType))
genomeModel = getGenomeModelFromCache(cds.getTaxId())
nativeSeq = cds.sequence()
stopCodonPos = cds.CDSlength()
#print(nativeSeq[:10])
newShuffles = []
for shuffleId in newShuffleIds:
totalPermutationsCount, identity, newseq = None, None, None
try:
totalPermutationsCount, identity, newseq = shuffler.randomize(
nativeSeq, cds.getProtId())
except Exception as e:
print(e)
raise
assert ((identity <= 1.0) and (identity > 0.0))
if (identity > 0.95):
print(
"Warning: Identity of randomized sequence is high - %.3g%% (length=%d nt, total permutations=%.2g)"
% (identity * 100.0, len(newseq), totalPermutationsCount))
if (totalPermutationsCount < 500):
raise Exception(
"Low number of possible permutations %.2g (length=%d nt, identity=%.3g%%)"
% (totalPermutationsCount, len(newseq), identity * 100.0))
newShuffles.append(newseq)
return newShuffles
def testRegionSpecificRandomization(fraction, taxId, numFractions):
assert(fraction>=0)
assert(fraction < numFractions)
assert(type(taxId)==type(0))
startTime = time()
shuffler = SynonymousCodonPermutingRandomization(getSpeciesTranslationTable(taxId))
numShuffles = 1
numSeqsDone = 0
#diffStats = CalcStats2(taxId)
#allNativeStats = CalcStats2(taxId)
data = []
for (seqId, seq) in nativeSequencesSource(taxId, fraction, numFractions):
if random.randint(0,1)>0:
continue
#print(seqId)
#nativeStats = CalcStats2(taxId)
#nativeStats.calcSeq(seq)
#allNativeStats += nativeStats
numShufflesIncluded = 0
numAttempts = 0
totalPermutationsCountForSeq = None
while True:
identity = None
shuffledSeq = None
#if time() - startTime > 300:
# raise Exception("Calculation took to much time!")
try:
numAttempts += 1
totalPermutationsCountForSeq, identity, shuffledSeq = shuffler.randomizeWithMask(seq, getCodonMaskForSeq(seq, 0, 22) )
except Exception as e:
print(e)
#continue # skip this sequence
raise e
if numAttempts >= 3:
break
data.append( (len(seq), totalPermutationsCountForSeq) )
numSeqsDone += 1
#logging.warning(mod3.getResults())
#logging.warning(mod4.getResults())
#logging.warning(mod5.getResults())
return (taxId, fraction, numSeqsDone, data)