def annotateVariantsPost(self, variants, **kwargs):
# print "biomine::webapi::ensembl::ensemblapi::annotateVariantsPost"
doAllOptions = kwargs.get('allOptions', True)
maxPost = kwargs.get(
'maxPost', 400
) #bc error 400 (bad request) or 504 (gateway/proxy server timeout)
#maxPost = 400 #https://github.com/ensembl/ensembl-rest/wiki/POST-Requests
#maxPost = 1000 #http://rest.ensembl.org/documentation/info/vep_region_post
lengthVariants = len(variants)
annotatedVariants = {} #dict of vepvariants
for i in range(0, lengthVariants, maxPost):
j = i + maxPost
if lengthVariants < maxPost:
j = lengthVariants
subsetVariants = variants[i:j]
formattedVariants = []
nullValue = "."
delim = " "
needReferences = self.checkInsertionsReference(subsetVariants,
nullValue=nullValue,
delim=delim)
self.fullReset()
self.setSubset(ensemblapi.regionSubset)
self.doAllOptions(data=doAllOptions)
for var in subsetVariants:
#inputVariant = var.vcf( delim=delim , null=nullValue )
#if var.reference == "-":
# if var.genomicVar() in needReferences:
#print inputVariant + " --> " ,
# inputVariant = delim.join( [ var.chromosome , str( int( var.start ) + 1 ) , str( int( var.stop ) - 1 ) , var.reference + "/" + var.alternate , var.strand ] )
# if vals[3] == nullValue:
# inputVariant = needReferences[var.genomicVar()]
#if var.alternate == "-":
# vals = inputVariant.split( delim )
# if vals[4] == nullValue:
# vals[4] = "-"
# inputVariant = delim.join( vals )
inputVariant = var.ensembl()
print inputVariant
formattedVariants.append(inputVariant)
vepvar = vepvariant(inputVariant=inputVariant,
parentVariant=var)
annotatedVariants[inputVariant] = vepvar
#following examples from documentation
self.addData("variants", formattedVariants)
self.addHeader("Accept", "application/json")
self.addHeader("Content-Type", "application/json")
self.submit(post=True, **kwargs)
if self.response.ok and self.response.text:
root = self.response.json()
for rootElement in root:
var = vepvariant()
var.parseEntryFromVEP(rootElement)
var.setInputVariant()
annotatedVariants[var.inputVariant] = var
else:
print "ensemblapi Error: cannot access desired XML fields/tags for variants ",
print "[" + str(i) + ":" + str(j) + "]"
return annotatedVariants
def annotateVariantsPost( self , variants , **kwargs ):
# print "biomine::webapi::ensembl::ensemblapi::annotateVariantsPost"
doAllOptions = kwargs.get( 'allOptions' , True )
maxPost = kwargs.get( 'maxPost' , 400 ) #bc error 400 (bad request) or 504 (gateway/proxy server timeout)
#maxPost = 400 #https://github.com/ensembl/ensembl-rest/wiki/POST-Requests
#maxPost = 1000 #http://rest.ensembl.org/documentation/info/vep_region_post
lengthVariants = len(variants)
annotatedVariants = {} #dict of vepvariants
for i in range(0,lengthVariants,maxPost):
j = i + maxPost
if lengthVariants < maxPost:
j = lengthVariants
subsetVariants = variants[i:j]
formattedVariants = []
nullValue = "."
delim = " "
needReferences = self.checkInsertionsReference( subsetVariants , nullValue=nullValue , delim=delim )
self.fullReset()
self.setSubset( ensemblapi.regionSubset )
self.doAllOptions( data=doAllOptions )
for var in subsetVariants:
#inputVariant = var.vcf( delim=delim , null=nullValue )
#if var.reference == "-":
# if var.genomicVar() in needReferences:
#print inputVariant + " --> " ,
# inputVariant = delim.join( [ var.chromosome , str( int( var.start ) + 1 ) , str( int( var.stop ) - 1 ) , var.reference + "/" + var.alternate , var.strand ] )
# if vals[3] == nullValue:
# inputVariant = needReferences[var.genomicVar()]
#if var.alternate == "-":
# vals = inputVariant.split( delim )
# if vals[4] == nullValue:
# vals[4] = "-"
# inputVariant = delim.join( vals )
inputVariant = var.ensembl()
print inputVariant
formattedVariants.append( inputVariant )
vepvar = vepvariant( inputVariant=inputVariant , parentVariant=var )
annotatedVariants[inputVariant] = vepvar
#following examples from documentation
self.addData( "variants" , formattedVariants )
self.addHeader( "Accept" , "application/json" )
self.addHeader( "Content-Type" , "application/json" )
self.submit( post=True , **kwargs )
if self.response.ok and self.response.text:
root = self.response.json()
for rootElement in root:
var = vepvariant()
var.parseEntryFromVEP( rootElement )
var.setInputVariant()
annotatedVariants[var.inputVariant] = var
else:
print "ensemblapi Error: cannot access desired XML fields/tags for variants " ,
print "[" + str(i) + ":" + str(j) + "]"
return annotatedVariants
def trySubmit( self , lastSubmitTime , **kwargs ):
annotatedVariants = {}
attempts = 0
keepGoing = True
timeAtSubmit = lastSubmitTime
timeSinceSubmit = time.time()
waitTime = 0
frequencyLimit = 1/15 #max seconds between requests: 15 requests/second
for attempts in range(0,30):
if timeSinceSubmit - timeAtSubmit > waitTime:
attempts += 1
timeAtSubmit = time.time()
self.submit( post=True , **kwargs )
if self.response.ok and self.response.text:
root = self.response.json()
keepGoing = False
for rootElement in root:
var = vepvariant()
var.parseEntryFromVEP( rootElement )
var.setInputVariant()
annotatedVariants[var.inputVariant] = var
return [ annotatedVariants , attempts , True , timeAtSubmit ]
else:
try:
waitTime = self.headers['X-RateLimit-Remaining']
except:
print( "BioMine::webapi::ensembl::ensemblapi::trySubmit Error: failed to query due to " + str( self.status_code ) + ": " + self.reason )
return [ annotatedVariants , attempts , False , timeAtSubmit ]
print( "BioMine::webapi::ensembl::ensemblapi::trySubmit Error: failed to query after " + str( attempts ) + " attempts. Stopping due to " + str( self.status_code ) + ": " + self.reason )
return [ annotatedVariants , attempts , False , timeAtSubmit ]
def annotateVariantsPost(self, variants, **kwargs):
# print "biomine::webapi::ensembl::ensemblapi::annotateVariantsPost"
doAllOptions = kwargs.get('allOptions', True)
maxPost = kwargs.get(
'maxPost', 150
) #bc error 400 (bad request), 403 (banned), or 504 (gateway/proxy server timeout)
#maxPost = 400 #https://github.com/ensembl/ensembl-rest/wiki/POST-Requests
#maxPost = 1000 #http://rest.ensembl.org/documentation/info/vep_region_post
lengthVariants = len(variants)
annotatedVariants = {} #dict of vepvariants
timeAtSubmit = 0
for i in range(0, lengthVariants, maxPost):
j = i + maxPost
if lengthVariants < maxPost:
j = lengthVariants
subsetVariants = variants[i:j]
formattedVariants = []
nullValue = "."
delim = " "
needReferences = self.checkInsertionsReference(subsetVariants,
nullValue=nullValue,
delim=delim)
self.fullReset()
self.setSubset(ensemblapi.regionSubset)
self.doAllOptions(data=doAllOptions)
for var in subsetVariants:
inputVariant = var.ensembl()
print inputVariant
formattedVariants.append(inputVariant)
vepvar = vepvariant(inputVariant=inputVariant,
parentVariant=var)
annotatedVariants[inputVariant] = vepvar
#following examples from documentation
self.addData("variants", formattedVariants)
self.addHeader("Accept", "application/json")
self.addHeader("Content-Type", "application/json")
[annotatedVariants, attempts, success,
timeAtSubmit] = self.trySubmit(timeAtSubmit, **kwargs)
if not success:
print "BioMine::webapi::ensembl::ensemblapi Error: cannot access desired XML fields/tags for variants ",
print "[" + str(i) + ":" + str(j) + "]"
return annotatedVariants
def trySubmit(self, lastSubmitTime, **kwargs):
annotatedVariants = {}
attempts = 0
keepGoing = True
timeAtSubmit = lastSubmitTime
timeSinceSubmit = time.time()
waitTime = 0
frequencyLimit = 1 / 15 #max seconds between requests: 15 requests/second
for attempts in range(0, 30):
if timeSinceSubmit - timeAtSubmit > waitTime:
attempts += 1
timeAtSubmit = time.time()
self.submit(post=True, **kwargs)
if self.response.ok and self.response.text:
root = self.response.json()
keepGoing = False
for rootElement in root:
var = vepvariant()
var.parseEntryFromVEP(rootElement)
var.setInputVariant()
annotatedVariants[var.inputVariant] = var
return [annotatedVariants, attempts, True, timeAtSubmit]
else:
try:
waitTime = self.headers['X-RateLimit-Remaining']
except:
print(
"BioMine::webapi::ensembl::ensemblapi::trySubmit Error: failed to query due to "
+ str(self.response.status_code) + ": " +
self.response.reason)
return [
annotatedVariants, attempts, False, timeAtSubmit
]
print(
"BioMine::webapi::ensembl::ensemblapi::trySubmit Error: failed to query after "
+ str(attempts) + " attempts. Stopping due to " +
str(self.response.status_code) + ": " + self.response.reason)
return [annotatedVariants, attempts, False, timeAtSubmit]
def annotateVariantsPost( self , variants , **kwargs ):
# print "biomine::webapi::ensembl::ensemblapi::annotateVariantsPost"
doAllOptions = kwargs.get( 'allOptions' , True )
maxPost = kwargs.get( 'maxPost' , 150 ) #bc error 400 (bad request), 403 (banned), or 504 (gateway/proxy server timeout)
#maxPost = 400 #https://github.com/ensembl/ensembl-rest/wiki/POST-Requests
#maxPost = 1000 #http://rest.ensembl.org/documentation/info/vep_region_post
lengthVariants = len(variants)
annotatedVariants = {} #dict of vepvariants
timeAtSubmit = 0
for i in range(0,lengthVariants,maxPost):
j = i + maxPost
if lengthVariants < maxPost:
j = lengthVariants
subsetVariants = variants[i:j]
formattedVariants = []
nullValue = "."
delim = " "
needReferences = self.checkInsertionsReference( subsetVariants , nullValue=nullValue , delim=delim )
self.fullReset()
self.setSubset( ensemblapi.regionSubset )
self.doAllOptions( data=doAllOptions )
for var in subsetVariants:
inputVariant = var.ensembl()
print inputVariant
formattedVariants.append( inputVariant )
vepvar = vepvariant( inputVariant=inputVariant , parentVariant=var )
annotatedVariants[inputVariant] = vepvar
#following examples from documentation
self.addData( "variants" , formattedVariants )
self.addHeader( "Accept" , "application/json" )
self.addHeader( "Content-Type" , "application/json" )
[ annotatedVariants , attempts , success , timeAtSubmit ] = self.trySubmit( timeAtSubmit , **kwargs )
if not success:
print "BioMine::webapi::ensembl::ensemblapi Error: cannot access desired XML fields/tags for variants " ,
print "[" + str(i) + ":" + str(j) + "]"
return annotatedVariants
def getCSQ(self, var, record, begin, end, ref, alt, alti, **kwargs):
info = record.INFO
csq = info.get('CSQ', "noCSQ")
preVEP = []
if not csq == "noCSQ":
vepDone = True
exacDone = True
var.vepVariant = vepvariant()
for thisCSQ in csq:
values = thisCSQ.split("|")
var.vcfInfo = values
aas = [None, None]
if self.getVCFKeyIndex(values,
"Amino_acids"): #8 => Amino_acids
aas = self.getVCFKeyIndex(values, "Amino_acids").split("/")
if len(aas) > 1:
aas[0] = mafvariant().convertAA(aas[0])
aas[1] = mafvariant().convertAA(aas[1])
else:
#28 => HGVSc
#29 => HGVSp
hgvsp = self.getVCFKeyIndex(values, "HGVSp").split(":")
changep = None
if len(hgvsp) > 1:
changep = re.match("p\.", hgvsp[1])
if changep:
aas = mafvariant().splitHGVSp(hgvsp[1])
aas[0] = mafvariant().convertAA(aas[0])
aas[2] = mafvariant().convertAA(aas[2])
else:
aas.append(None)
needVEP = True
preVEP.append(var)
exons = [None, None]
if self.getVCFKeyIndex(values, "EXON"): #25 => EXON
exons = self.getVCFKeyIndex(values, "EXON").split("/")
if len(exons) == 1:
exons.append(None)
introns = [None, None]
if self.getVCFKeyIndex(values, "INTRON"): #26 => INTRON
introns = self.getVCFKeyIndex(values, "INTRON").split("/")
if len(introns) == 1:
introns.append(None)
siftStuff = [None, None]
if self.getVCFKeyIndex(values, "SIFT"):
siftStuff = self.getVCFKeyIndex(values, "SIFT").split("(")
if len(siftStuff) == 1:
siftStuff.append(None)
else:
siftStuff[1] = siftStuff[1].rstrip(")")
polyPhenStuff = [None, None]
if self.getVCFKeyIndex(values, "PolyPhen"):
polyPhenStuff = self.getVCFKeyIndex(values,
"PolyPhen").split("(")
if len(polyPhenStuff) == 1:
polyPhenStuff.append(None)
else:
polyPhenStuff[1] = polyPhenStuff[1].rstrip(")")
vcv = vepconsequencevariant( \
chromosome = record.CHROM , \
start = begin , \
stop = end , \
dbsnp = record.ID , \
reference = ref , \
alternate = alt , \
gene_id=self.getVCFKeyIndex( values , "Gene" ) , \
transcriptCodon=self.getVCFKeyIndex( values , "Feature" ) , \
consequence_terms=self.getVCFKeyIndex( values , "Consequence" ).split( "&" ) , \
positionCodon=self.getVCFKeyIndex( values , "cDNA_position" ) , \
positionPeptide=self.getVCFKeyIndex( values , "Protein_position" ) , \
referencePeptide=aas[0] , \
alternatePeptide=aas[1] , \
strand=self.getVCFKeyIndex( values , "STRAND" ) , \
gene=self.getVCFKeyIndex( values , "SYMBOL" ) , \
gene_symbol_source=self.getVCFKeyIndex( values , "SYMBOL_SOURCE" ) , \
hgnc_id=self.getVCFKeyIndex( values , "HGNC_ID" ) , \
biotype=self.getVCFKeyIndex( values , "BIOTYPE" ) , \
canonical=self.getVCFKeyIndex( values , "CANONICAL" ) , \
ccds=self.getVCFKeyIndex( values , "CCDS" ) , \
transcriptPeptide=self.getVCFKeyIndex( values , "ENSP" ) , \
predictionSIFT=siftStuff[0] , \
scoreSIFT=siftStuff[1] , \
predictionPolyphen=polyPhenStuff[0] , \
scorePolyphen=polyPhenStuff[1] , \
exon=exons[0] , \
totalExons=exons[1] , \
intron=introns[0] , \
totalIntrons=introns[1] , \
)
var.alleleFrequency = self.getVCFKeyIndex(values, "GMAF")
var.vepVariant.consequences.append(vcv)
self.determineMostSevere(var, **kwargs)
self.setAlleleMeasures(var, info, **kwargs)
return None
def __init__( self , **kwargs ):
super(chargervariant,self).__init__(**kwargs)
self.PVS1 = kwargs.get( 'PVS1' , False )
self.PS1 = kwargs.get( 'PS1' , False )
self.PS2 = kwargs.get( 'PS2' , False )
self.PS3 = kwargs.get( 'PS3' , False )
self.PS4 = kwargs.get( 'PS4' , False )
self.PM1 = kwargs.get( 'PM1' , False )
self.PM2 = kwargs.get( 'PM2' , False )
self.PM3 = kwargs.get( 'PM3' , False )
self.PM4 = kwargs.get( 'PM4' , False )
self.PM5 = kwargs.get( 'PM5' , False )
self.PM6 = kwargs.get( 'PM6' , False )
self.PP1 = kwargs.get( 'PP1' , False )
self.PP2 = kwargs.get( 'PP2' , False )
self.PP3 = kwargs.get( 'PP3' , False )
self.PP4 = kwargs.get( 'PP4' , False )
self.PP5 = kwargs.get( 'PP5' , False )
self.BA1 = kwargs.get( 'BA1' , False )
self.BS1 = kwargs.get( 'BS1' , False )
self.BS2 = kwargs.get( 'BS2' , False )
self.BS3 = kwargs.get( 'BS3' , False )
self.BS4 = kwargs.get( 'BS4' , False )
self.BP1 = kwargs.get( 'BP1' , False )
self.BP2 = kwargs.get( 'BP2' , False )
self.BP3 = kwargs.get( 'BP3' , False )
self.BP4 = kwargs.get( 'BP4' , False )
self.BP5 = kwargs.get( 'BP5' , False )
self.BP6 = kwargs.get( 'BP6' , False )
self.BP7 = kwargs.get( 'BP7' , False )
self.PSC1 = kwargs.get( 'PSC1' , False )
self.PMC1 = kwargs.get( 'PMC1' , False )
self.PPC1 = kwargs.get( 'PPC1' , False )
self.PPC2 = kwargs.get( 'PPC2' , False )
self.BSC1 = kwargs.get( 'BSC1' , False )
self.BMC1 = kwargs.get( 'BMC1' , False )
self.otherTranscripts = kwargs.get( 'otherTranscripts' , {} )
self.alleleFrequency = kwargs.get( 'alleleFrequency' , None )
self.vepAnnotations = kwargs.get( 'VEP' , None )
self.vcfHeaders = kwargs.get( 'headers' , None )
self.vcfInfo = kwargs.get( 'INFO' , [] )
self.pathogenicity = kwargs.get( 'pathogenicity' , \
{ "CharGer" : chargervariant.uncertain , \
"ACMG" : chargervariant.uncertain
}
)
self.clinical = kwargs.get( 'clinical' , { "description" : chargervariant.uncertain , "review_status" : "" } )
self.pathogenicScore = kwargs.get( 'pathogenicScore' , 0 )
self.benignScore = kwargs.get( 'benignScore' , 0 )
self.chargerScore = kwargs.get( 'chargerScore' , 0 )
self.callSummary = kwargs.get( 'summary' , [] )
aParentVariant = kwargs.get( 'parentVariant' , None )
if aParentVariant:
super( chargervariant , self ).copyInfo( aParentVariant )
# make vep and clinvar variants attributes of chargervariant
self.vepVariant = kwargs.get( 'vepvariant' , vepvariant() )
self.clinvarVariant = kwargs.get( 'clinvarvariant' , clinvarvariant() )
self.transvarVariant = kwargs.get( 'transvarvariant' , None )
self.scoresMap = kwargs.get( 'scoresMap' , dict() )
def test_empty_init(self):
v = vepvariant()
self.assertFalse(v)
