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 getIdentifiersConversionTableUsingGff3():
global altIdentifiers
if altIdentifiers:
return altIdentifiers
gm = getGenomeModelFromCache(taxId)
for protId in SpeciesCDSSource(taxId):
cds = CDSHelper(taxId, protId)
geneId = cds.getGeneId()
alts = gm.findEquivalentIdentifiers(geneId)
for i in alts:
altIdentifiers[i] = protId
altIdentifiers[geneId] = protId
def testCDSand3UTRRandomizationIncludingNextCDS(
taxId: int = 511145,
geneticCode: int = 11,
constantOverlaps: bool = False) -> int:
from data_helpers import SpeciesCDSSource
from genome_model import getGenomeModelFromCache
rand = CDSand3UTRRandomizationIncludingNextCDS(
SynonymousCodonPermutingRandomization(geneticCode=geneticCode),
NucleotidePermutationRandomization(),
taxId,
constantOverlaps=constantOverlaps)
#for protId in SpeciesCDSSource(taxId):
countOK = 0
countNotOK = 0
countNotOK2 = 0
countSkipped = 0
for protId in getGenomeModelFromCache(taxId).allCDSSource():
try:
cds = CDSHelper(taxId, protId)
seq = cds.sequence()
#if str(seq).find("n") != -1:
# countSkipped += 1
# continue
except Exception as e:
countNotOK += 1
continue
for i in range(20):
try:
ret = rand.randomize(seq, protId)
except Exception as e:
print(
"Caught exception during call to randomize(), protId={}!".
format(protId))
print(e)
countNotOK += 1
countNotOK2 += 1
continue
if ret[0] < 1e5:
print(protId)
if not (len(ret[2]) == len(seq)):
print(ret)
rand.randomize(seq, protId)
assert (len(ret[2]) == len(seq))
countOK += 1
#print("{} -> {}".format( protId, ret ))
print("OK: {}, NotOK: {}, Skipped: {}, Total: {}".format(
countOK, countNotOK, countSkipped,
countOK + countNotOK + countSkipped))
print("randomize exception: {}".format(countNotOK2))
return 0
def processGenome(args, taxId):
alreadyProcessedGenes = {}
totalProteinsProcessed = 0
totalSkipped = 0
seqsForWriting=[]
recordsForWriting={}
gm = getGenomeModelFromCache( taxId )
for protId in SpeciesCDSSource(taxId):
cds = CDSHelper( taxId, protId )
totalProteinsProcessed += 1
#feature = gm.findFeatureById( protId )
geneId = cds.getGeneId()
#flanking3UTRRegionLengthNt = cds.flankingRegion3UtrLength()
feature = gm.findFeatureById( protId )
#feature = cds.getMatchingFeatureFromGenomeModel()
#print(feature)
strand = feature[1].data['strand']
if strand=='+':
otherFeature = gm.moleculeModels[ feature[0] ].find5PrimeFlankingRegion( feature[1] )
if otherFeature is None:
totalSkipped += 1
continue
assert( otherFeature['downstream-feature'].begin <= otherFeature['downstream-feature'].end)
flanking3UTRRegionLengthNt = otherFeature['curr-feature'].begin - otherFeature['downstream-feature'].end
threePrimeUTRCoords = (feature[1].begin-20, feature[1].begin+2, False) # include the first 3 nucleotides of the CDS
else:
otherFeature = gm.moleculeModels[ feature[0] ].find5PrimeFlankingRegion( feature[1] )
if otherFeature is None:
totalSkipped += 1
continue
assert( otherFeature['downstream-feature'].begin <= otherFeature['downstream-feature'].end)
flanking3UTRRegionLengthNt = otherFeature['downstream-feature'].begin - otherFeature['curr-feature'].end
threePrimeUTRCoords = (feature[1].end-3, feature[1].end+20, True) # include the first 3 nucleotides of the CDS
threePrimeUTR = gm.moleculeModels[ feature[0] ].getSequence( *threePrimeUTRCoords )
if flanking3UTRRegionLengthNt < -50:
print("Warning: found gene with apparent long overlap: {},{},{},{},{}".format( protId, geneId, strand, flanking3UTRRegionLengthNt, threePrimeUTR.seq ))
#totalSkipped += 1
#continue
if threePrimeUTR.seq[-2:] != 'TG':
print("Warning: skipping gene with start codon at the correct place: {},{},{},{},{}".format( protId, geneId, strand, flanking3UTRRegionLengthNt, threePrimeUTR.seq ))
totalSkipped += 1
continue
# All done - emit the output
#fout.write("{},{},{},{},{}".format( protId, geneId, strand, flanking3UTRRegionLengthNt, threePrimeUTR.seq ))
recordsForWriting[protId] = (geneId, strand, flanking3UTRRegionLengthNt, threePrimeUTR.seq )
seqsForWriting.append( SeqRecord( Seq(threePrimeUTR.seq[:-3], NucleotideAlphabet), id=protId) )
aSD = calculateaSDEnergies( seqsForWriting, args, taxId )
print(len(aSD))
with open( outputData.format(taxId), 'wt') as fout:
for protId, record in recordsForWriting.items():
aSDval = aSD.get(protId, None)
vals = (protId,) + record + (aSDval,)
fout.write("{},{},{},{},{},{}\n".format( *vals ))
print("Processed {} coding sequences for taxid {}".format( totalProteinsProcessed, taxId ))
print("Skipped {} coding sequences".format( totalSkipped ))
def readFile(self):
self.geneInfo = {}
with open(ODB4_csv_path) as csvfile:
reader = csv.reader(csvfile, delimiter='\t')
rowNum = 0
for row in reader:
rowNum += 1
if rowNum == 1: continue # skip header line
taxId = int(row[ODB4_format.TaxId])
if (not self.taxIdFilter is None) and (taxId !=
self.taxIdFilter):
continue # filter rows by taxId (if specified)
gm = getGenomeModelFromCache(taxId)
operonName = row[ODB4_format.OperonName]
genesInOrder = row[ODB4_format.GenesOrder].split(',')
# For some reason, the genes in ODB4 appear relative to the positive strand, even for operons transcribed from the negative strand...
# Consequently, to determine the real order of genes we need to determine the strand for this operon.
# First, collect the strands for all genes in this operon
strands = []
for gid in genesInOrder: # for each gene, find equivalent identifiers
idents = gm.findEquivalentIdentifiers(
gid
) # try each identifier to find one associated with a gff3 feature
if idents is None:
if gid[:2] == "HP" and gid[:3] != "HP_": # Workaround for H. pylori
idents = gm.findEquivalentIdentifiers("HP_" +
gid[2:])
if idents is None:
continue
for i in idents:
f = gm.findFeatureById(i)
if not f is None:
strands.append(
f[1].data['strand']) # store all strands
break
if not strands: # With no strand found, we cannot use this operon
print("Missing info for {}".format(operonName))
continue
# Make sure all strands are the same
if not allItemsAreEqual(strands):
print("Conflicting info for {}".format(operonName))
continue
strand = strands[0]
assert (strand in ('+', '-'))
# Store position information for every gene in this operon
for pos, gene in enumerate(genesInOrder):
if gene[:2] == "HP" and gene[:3] != "HP_": # Workaround for H. pylori
gene = "HP_" + gene[2:]
if strand == '+':
geneData = (pos, len(genesInOrder), operonName)
else:
if taxId != 169963:
geneData = (len(genesInOrder) - pos - 1,
len(genesInOrder), operonName)
else: # Workaround for Listeria
geneData = (pos, len(genesInOrder), operonName)
if self.taxIdFilter is None: # No filter defined; store the taxId with the entry
self.geneInfo[self.getGeneIdentifier(
gene, taxId=taxId)] = geneData
else: # Taxonomy filtered to single species; no need to store taxId with entry
self.geneInfo[self.getGeneIdentifier(gene)] = geneData