def extractCompartmentStatistics(bioNumber,useID,reactionDefinitions,speciesEquivalence):
'''
Iterate over the translated species and check which compartments
are used together, and how.
'''
reader = libsbml.SBMLReader()
document = reader.readSBMLFromFile(bioNumber)
parser =SBML2BNGL(document.getModel(),useID)
database = structures.Databases()
#call the atomizer (or not)
#if atomize:
translator,onlySynDec = mc.transformMolecules(parser,database,reactionDefinitions,speciesEquivalence)
#else:
# translator={}
compartmentPairs = {}
for element in translator:
temp = extractCompartmentCoIncidence(translator[element])
for element in temp:
if element not in compartmentPairs:
compartmentPairs[element] = temp[element]
else:
compartmentPairs[element].update(temp[element])
finalCompartmentPairs = {}
print '-----'
for element in compartmentPairs:
if element[0][0] not in finalCompartmentPairs:
finalCompartmentPairs[element[0][0]] = {}
finalCompartmentPairs[element[0][0]][tuple([element[0][1],element[1][1]])] = compartmentPairs[element]
return finalCompartmentPairs
def readFromString(inputString,
reactionDefinitions,
useID,
speciesEquivalence=None,
atomize=False):
'''
one of the library's main entry methods. Process data from a string
'''
try:
reader = libsbml.SBMLReader()
document = reader.readSBMLFromString(inputString)
parser = SBML2BNGL(document.getModel(), useID)
bioGrid = False
if bioGrid:
loadBioGrid()
database = structures.Databases()
namingConventions = resource_path('config/namingConventions.json')
if atomize:
translator, onlySynDec = mc.transformMolecules(
parser, database, reactionDefinitions, namingConventions,
speciesEquivalence, bioGrid)
else:
translator = {}
return analyzeHelper(document, reactionDefinitions, useID, '',
speciesEquivalence, atomize, translator)[-2]
except:
return -5
def analyzeFile(bioNumber,reactionDefinitions,useID,namingConventions,outputFile,
speciesEquivalence=None,atomize=False,bioGrid=False):
'''
one of the library's main entry methods. Process data from a string
'''
reader = libsbml.SBMLReader()
document = reader.readSBMLFromFile(bioNumber)
parser =SBML2BNGL(document.getModel(),useID)
database = structures.Databases()
#call the atomizer (or not)
bioGridDict = {}
if bioGrid:
bioGridDict = loadBioGrid()
if atomize:
translator = mc.transformMolecules(parser,database,reactionDefinitions,namingConventions,speciesEquivalence,bioGrid)
else:
translator={}
returnArray= analyzeHelper(document,reactionDefinitions,useID,outputFile,speciesEquivalence,atomize,translator)
with open(outputFile,'w') as f:
f.write(returnArray[-2])
#with open('{0}.dict'.format(outputFile),'wb') as f:
# pickle.dump(returnArray[-1],f)
return returnArray[0:-2]
def processDatabase():
reader = libsbml.SBMLReader()
#jsonFiles = [ f for f in listdir('./reactionDefinitions') if f[-4:-1] == 'jso']
history = np.load('stats3.npy')
index2 = 0
for index in range(1,410):
try:
nameStr = 'BIOMD0000000%03d' % (index)
document = reader.readSBMLFromFile('XMLExamples/curated/' + nameStr + '.xml')
parser = SBML2BNGL(document.getModel())
database = structures.Databases()
print nameStr + '.xml'
'''
for jsonFile in jsonFiles:
try:
#print jsonFile,
translator = m2c.transformMolecules(parser,database,'reactionDefinitions/' + jsonFile)
break
except:
print 'ERROR',sys.exc_info()[0]
continue
#translator = m2c.transformMolecules(parser,database,'reactionDefinition2.json')
'''
#translator = []
while(history[index2][0] < index):
index2=1
print history[index2][0],index
if (history[index2][0]==index) and history[index2][1] != 0:
print str( int(history[index2][1]))
translator = mc.transformMolecules(parser,database,'reactionDefinitions/reactionDefinition' + str( int(history[index2][1])) + '.json')
else:
translator = {}
#print len(parser.getSpecies()),len(translator),
evaluation(len(parser.getSpecies()),translator)
#translator = {}
param2 = parser.getParameters()
molecules,species,observables = parser.getSpecies(translator)
#print molecules,species,observables
print 'translated: {0}/{1}'.format(len(translator),len(observables)),
print evaluation(len(observables),translator)
param,rules,functions = parser.getReactions(translator)
compartments = parser.getCompartments()
param += param2
writer.finalText(param,molecules,species,observables,rules,functions,compartments,'output/' + nameStr + '.bngl')
with open('output/' + nameStr + '.log', 'w') as f:
f.write(parser.writeLog(translator))
except:
print 'ERROR',sys.exc_info()[0]
continue
def analyzeFile(bioNumber,
reactionDefinitions,
useID,
namingConventions,
outputFile,
speciesEquivalence=None,
atomize=False,
bioGrid=False):
'''
one of the library's main entry methods. Process data from a file
'''
logMess.log = []
logMess.counter = -1
reader = libsbml.SBMLReader()
document = reader.readSBMLFromFile(bioNumber)
parser = SBML2BNGL(document.getModel(), useID)
database = structures.Databases()
database.forceModificationFlag = True
bioGridDict = {}
if bioGrid:
bioGridDict = loadBioGrid()
#call the atomizer (or not). structured molecules are contained in translator
#onlysyndec is a boolean saying if a model is just synthesis of decay reactions
if atomize:
translator, onlySynDec = mc.transformMolecules(parser, database,
reactionDefinitions,
namingConventions,
speciesEquivalence,
bioGrid)
else:
translator = {}
#process other sections of the sbml file (functions reactions etc.)
returnArray = analyzeHelper(document, reactionDefinitions, useID,
outputFile, speciesEquivalence, atomize,
translator)
with open(outputFile, 'w') as f:
f.write(returnArray[-2])
#with open('{0}.dict'.format(outputFile),'wb') as f:
# pickle.dump(returnArray[-1],f)
if atomize and onlySynDec:
returnArray = list(returnArray)
returnArray[0] = -1
return tuple(returnArray[0:-2])
def readFromString(inputString,reactionDefinitions,useID,speciesEquivalence=None,atomize=False):
'''
one of the library's main entry methods. Process data from a string
'''
reader = libsbml.SBMLReader()
document = reader.readSBMLFromString(inputString)
parser =SBML2BNGL(document.getModel(),useID)
bioGrid = False
if bioGrid:
loadBioGrid()
database = structures.Databases()
namingConventions = 'config/namingConventions.json'
if atomize:
translator = mc.transformMolecules(parser,database,reactionDefinitions,namingConventions,speciesEquivalence,bioGrid)
else:
translator={}
return analyzeHelper(document,reactionDefinitions,useID,'',speciesEquivalence,atomize,translator)[-2]
def analyzeFile(bioNumber,reactionDefinitions,useID,namingConventions,outputFile,
speciesEquivalence=None,atomize=False,bioGrid=False):
'''
one of the library's main entry methods. Process data from a file
'''
logMess.log = []
logMess.counter = -1
reader = libsbml.SBMLReader()
document = reader.readSBMLFromFile(bioNumber)
parser =SBML2BNGL(document.getModel(),useID)
database = structures.Databases()
database.forceModificationFlag = True
bioGridDict = {}
if bioGrid:
bioGridDict = loadBioGrid()
#call the atomizer (or not). structured molecules are contained in translator
#onlysyndec is a boolean saying if a model is just synthesis of decay reactions
if atomize:
translator,onlySynDec = mc.transformMolecules(parser,database,reactionDefinitions,namingConventions,speciesEquivalence,bioGrid)
else:
translator={}
#process other sections of the sbml file (functions reactions etc.)
returnArray= analyzeHelper(document,reactionDefinitions,useID,outputFile,speciesEquivalence,atomize,translator)
with open(outputFile,'w') as f:
f.write(returnArray[-2])
#with open('{0}.dict'.format(outputFile),'wb') as f:
# pickle.dump(returnArray[-1],f)
if atomize and onlySynDec:
returnArray = list(returnArray)
returnArray[0] = -1
return tuple(returnArray[0:-2])
def extractCompartmentStatistics(bioNumber, useID, reactionDefinitions,
speciesEquivalence):
'''
Iterate over the translated species and check which compartments
are used together, and how.
'''
reader = libsbml.SBMLReader()
document = reader.readSBMLFromFile(bioNumber)
parser = SBML2BNGL(document.getModel(), useID)
database = structures.Databases()
#call the atomizer (or not)
#if atomize:
translator, onlySynDec = mc.transformMolecules(parser, database,
reactionDefinitions,
speciesEquivalence)
#else:
# translator={}
compartmentPairs = {}
for element in translator:
temp = extractCompartmentCoIncidence(translator[element])
for element in temp:
if element not in compartmentPairs:
compartmentPairs[element] = temp[element]
else:
compartmentPairs[element].update(temp[element])
finalCompartmentPairs = {}
print '-----'
for element in compartmentPairs:
if element[0][0] not in finalCompartmentPairs:
finalCompartmentPairs[element[0][0]] = {}
finalCompartmentPairs[element[0][0]][tuple(
[element[0][1], element[1][1]])] = compartmentPairs[element]
return finalCompartmentPairs
def identifyNamingConvention():
'''
extracts statistics from the code
'''
reader = libsbml.SBMLReader()
jsonFiles = [ f for f in listdir('./reactionDefinitions') if f[-4:-1] == 'jso' and 'reactionDefinition' in f]
translationLevel = []
arrayMolecules = []
rules = 0
#go through all curated models in the biomodels database
signal.signal(signal.SIGALRM, handler)
for index in range(1,410):
bestTranslator = {}
nameStr = 'BIOMD0000000%03d' % (index)
document = reader.readSBMLFromFile('XMLExamples/curated/' + nameStr + '.xml')
parser = SBML2BNGL(document.getModel())
database = structures.Databases()
print nameStr + '.xml',
naming = 'reactionDefinition0.json'
bestUseID = True
numberofMolecules = numberOfSpecies = 0
#iterate through our naming conventions and selects that which
#creates the most rulified elements in the translator
for jsonFile in jsonFiles:
for useID in [True,False]:
oldmaxi = numberOfSpecies
parser = SBML2BNGL(document.getModel(),useID)
database = structures.Databases()
signal.alarm(30)
try:
mc.transformMolecules(parser,database,'reactionDefinitions/' + jsonFile,None)
except:
print '--error',jsonFile,useID
continue
translator = database.translator
numberOfSpecies = max(numberOfSpecies,evaluation(len(parser.getSpecies()),database.translator))
if oldmaxi != numberOfSpecies:
naming = jsonFile
bestTranslator = translator
bestUseID = useID
_,rules,_ = parser.getReactions(translator)
numberofMolecules = len(translator)
_,_,obs = parser.getSpecies()
rdfAnnotations = analyzeRDF.getAnnotations(parser,'miriam')
#go through the annotation list and assign which species
#correspond to which uniprot number (if it exists)
#similarly list the number of times each individual element appears
analyzeRDF.getAnnotations(parser,'miriam')
molecules = {}
if naming[-6] != 0:
for element in bestTranslator:
if len(bestTranslator[element].molecules) == 1:
name = bestTranslator[element].molecules[0].name
for annotation in rdfAnnotations:
if name in rdfAnnotations[annotation]:
if name not in molecules:
molecules[name] = [0,[]]
if annotation not in molecules[name][1]:
molecules[name][1].extend(annotation)
if name not in molecules:
molecules[name] = [1,[]]
for rule in rules:
if name in rule:
molecules[name][0] += 1
# _,rules,_ = parser.getReactions(bestTranslator)
#for rule in rules:
if len(obs) != 0:
print index*1.0,(naming[-6]),numberOfSpecies*1.0/len(obs),numberofMolecules*1.0/len(obs),len(obs)*1.0,bestUseID
arrayMolecule = [[x,molecules[x]] for x in molecules]
arrayMolecules.append(arrayMolecule)
translationLevel.append([nameStr+'.xml',(naming[-6]),numberOfSpecies*1.0/len(obs),numberofMolecules*1.0/len(obs),len(obs)*1.0,bestUseID])
else:
arrayMolecules.append([])
with open('stats4.npy','wb') as f:
pickle.dump(translationLevel,f)
