def getClabDescSignList(self, smiles, getMolFile=False):
# Create an Orange ExampleTable with a smiles attribute
smilesAttr = orange.EnumVariable("SMILEStoPred", values=[smiles])
myDomain = orange.Domain([smilesAttr], 0)
smilesData = dataUtilities.DataTable(myDomain, [[smiles]])
# Calculate descriptors defined in the model files
try:
descList = self.model.varNames
except: # Consensus object different
attributes = self.model.domain.variables
descList = []
for attr in attributes:
descList.append(attr.name)
# Determine Signature and non-Signature descriptor names
cinfonyDesc, clabDesc, signatureHeight, bbrcDesc, signDesc = descUtilities.getDescTypes(
descList)
# Signatures
if "sign" in DescMethodsAvailable and signatureHeight:
print "Calculating signatures..."
preCalcData = dataUtilities.DataTable(self.preDefSignatureFile)
startHeight = 0 # Not used desc ignored in model prediction
endHeight = signatureHeight
dataSign, cmpdSignDict, cmpdSignList, sdfStr = getSignatures.getSignatures(
smilesData,
startHeight,
endHeight,
preCalcData,
returnAtomID=True)
else:
cmpdSignList = [[]]
sdfStr = ""
if not getMolFile:
return (clabDesc, cmpdSignList[0])
elif not sdfStr:
return (clabDesc, cmpdSignList[0], "", "")
# create a mol file
molFile = miscUtilities.generateUniqueFile(desc="NN", ext="mol")
file = open(molFile, "w")
molStr = ""
for line in sdfStr[0]:
if "$$$$" in line:
break
molStr += line
file.write(line)
file.close()
return (clabDesc, cmpdSignList[0], molFile, molStr)
def getClabDescSignList(self, smiles, getMolFile=False):
# Create an Orange ExampleTable with a smiles attribute
smilesAttr = orange.EnumVariable("SMILEStoPred", values = [smiles])
myDomain = orange.Domain([smilesAttr], 0)
smilesData = dataUtilities.DataTable(myDomain, [[smiles]])
# Calculate descriptors defined in the model files
try:
descList = self.model.varNames
except: # Consensus object different
attributes = self.model.domain.variables
descList = []
for attr in attributes:
descList.append(attr.name)
# Determine Signature and non-Signature descriptor names
cinfonyDesc, clabDesc, signatureHeight, bbrcDesc, signDesc = descUtilities.getDescTypes(descList)
# Signatures
if "sign" in DescMethodsAvailable and signatureHeight:
print "Calculating signatures..."
preCalcData = dataUtilities.DataTable(self.preDefSignatureFile)
startHeight = 0 # Not used desc ignored in model prediction
endHeight = signatureHeight
dataSign,cmpdSignDict, cmpdSignList, sdfStr = getSignatures.getSignatures(smilesData, startHeight, endHeight, preCalcData, returnAtomID=True)
else:
cmpdSignList = [[]]
sdfStr = ""
if not getMolFile:
return (clabDesc,cmpdSignList[0])
elif not sdfStr:
return (clabDesc,cmpdSignList[0],"","")
# create a mol file
molFile = miscUtilities.generateUniqueFile(desc="NN", ext = "mol")
file= open(molFile,"w")
molStr=""
for line in sdfStr[0]:
if "$$$$" in line:
break
molStr += line
file.write(line)
file.close()
return (clabDesc,cmpdSignList[0],molFile,molStr)
def createSignImg(self,
smi,
signature,
atomColor,
imgPath,
endHeight=None):
colors = []
print "Creating signature image..."
if not signature or not atomColor or not smi:
print "Missing inputs:", str([smi, signature, atomColor])
return "", "", [], []
if hasattr(self.model, "specialType") and self.model.specialType == 1:
# Create an Orange ExampleTable with a smiles attribute
smilesAttr = orange.EnumVariable("SMILEStoPred", values=[smi])
myDomain = orange.Domain([smilesAttr], 0)
smilesData = dataUtilities.DataTable(myDomain, [[smi]])
preCalcData = None
startHeight = 0
dataSign, cmpdSignDict, cmpdSignList, sdfStr = getSignatures.getSignatures(
smilesData,
startHeight,
endHeight,
preCalcData,
returnAtomID=True)
cmpdSignList = cmpdSignList[0]
CLabDesc = []
# create a mol file
tmpFile = miscUtilities.generateUniqueFile(desc="NN", ext="mol")
file = open(tmpFile, "w")
molStr = ""
for line in sdfStr[0]:
if "$$$$" in line:
break
molStr += line
file.write(line)
file.close()
else:
CLabDesc, cmpdSignList, tmpFile, molStr = self.getClabDescSignList(
smi, getMolFile=True)
if not cmpdSignList or not tmpFile:
print "Couldn't get the cmpd list or the mol file"
return "", "", [], []
# create an RDKit mol
mol = Chem.MolFromMolFile(tmpFile, True, False)
if not mol:
mol = Chem.MolFromMolFile(tmpFile, False, False)
if not mol:
print "Could not create mol for: ", smi
return "", "", [], []
adj = GetAdjacencyMatrix(mol)
# find the NN
hights = []
for i in miscUtilities.Range(0, len(cmpdSignList), mol.GetNumAtoms()):
hList = cmpdSignList[i:i + mol.GetNumAtoms()]
if len(hList):
hights.append(cmpdSignList[i:i + mol.GetNumAtoms()])
atoms = []
hight = None
for idx, h in enumerate(hights):
if signature in h:
for i, a in enumerate(h):
if a == signature:
atoms.append(i)
hight = idx
break
if len(atoms) == 0:
print "ERROR: Could not find the atom for ", signature
return "signatureNOTfound", "", [], []
#print "IniAtoms: ",atoms
visitedAtoms = []
for n in range(hight):
for atom in copy.deepcopy(atoms):
if atom not in visitedAtoms:
lNN = findNeighbors(atom, adj)
visitedAtoms.append(atom)
for lnn in lNN:
if lnn not in atoms:
atoms.append(lnn)
atoms.sort()
os.system("rm " + tmpFile)
#Specify the atom colors
colors = [atomColor] * len(atoms)
if not imgPath:
return "", molStr, atoms, colors
try:
#Draw the image
MolDrawing.elemDict = defaultdict(lambda: (0, 0, 0))
Draw.MolToImageFile(mol,
imgPath,
size=(300, 300),
kekulize=True,
wedgeBonds=True,
highlightAtoms=atoms)
#Color the Highlighted atoms with the choosen atomColor.
# Only using one color
if atomColor == 'r':
rgb = (255, 0, 0)
elif atomColor == 'g':
rgb = (0, 255, 0)
else:
rgb = (0, 0, 255) #Blue
img = Image.open(imgPath)
img = img.convert("RGBA")
pixdata = img.getdata()
newData = list()
for item in pixdata:
if item[0] == 255 and item[1] == 0 and item[2] == 0:
newData.append(rgb + (255, ))
else:
newData.append(item)
img.putdata(newData)
img.save(imgPath)
if os.path.isfile(imgPath):
return imgPath, molStr, atoms, colors
else:
return "", molStr, atoms, colors
except:
return "", molStr, atoms, colors
def createSignImg(self,smi,signature,atomColor,imgPath, endHeight = None):
colors = []
print "Creating signature image..."
if not signature or not atomColor or not smi:
print "Missing inputs:",str([smi,signature,atomColor])
return "","",[], []
if hasattr(self.model, "specialType") and self.model.specialType == 1:
# Create an Orange ExampleTable with a smiles attribute
smilesAttr = orange.EnumVariable("SMILEStoPred", values = [smi])
myDomain = orange.Domain([smilesAttr], 0)
smilesData = dataUtilities.DataTable(myDomain, [[smi]])
preCalcData = None
startHeight = 0
dataSign,cmpdSignDict, cmpdSignList, sdfStr = getSignatures.getSignatures(smilesData, startHeight, endHeight, preCalcData, returnAtomID=True)
cmpdSignList = cmpdSignList[0]
CLabDesc = []
# create a mol file
tmpFile = miscUtilities.generateUniqueFile(desc="NN", ext = "mol")
file= open(tmpFile,"w")
molStr=""
for line in sdfStr[0]:
if "$$$$" in line:
break
molStr += line
file.write(line)
file.close()
else:
CLabDesc,cmpdSignList, tmpFile, molStr = self.getClabDescSignList(smi, getMolFile=True)
if not cmpdSignList or not tmpFile:
print "Couldn't get the cmpd list or the mol file"
return "","",[], []
# create an RDKit mol
mol = Chem.MolFromMolFile(tmpFile,True,False)
if not mol:
mol = Chem.MolFromMolFile(tmpFile,False,False)
if not mol:
print "Could not create mol for: ",smi
return "","",[], []
adj = GetAdjacencyMatrix(mol)
# find the NN
hights = []
for i in miscUtilities.Range(0,len(cmpdSignList),mol.GetNumAtoms()):
hList = cmpdSignList[i:i+mol.GetNumAtoms()]
if len(hList):
hights.append(cmpdSignList[i:i+mol.GetNumAtoms()])
atoms = []
hight = None
for idx,h in enumerate(hights):
if signature in h:
for i,a in enumerate(h):
if a == signature:
atoms.append(i)
hight = idx
break
if len(atoms) == 0:
print "ERROR: Could not find the atom for ",signature
return "signatureNOTfound","",[],[]
#print "IniAtoms: ",atoms
visitedAtoms = []
for n in range(hight):
for atom in copy.deepcopy(atoms):
if atom not in visitedAtoms:
lNN = findNeighbors(atom,adj)
visitedAtoms.append(atom)
for lnn in lNN:
if lnn not in atoms:
atoms.append(lnn)
atoms.sort()
os.system("rm " + tmpFile)
#Specify the atom colors
colors=[atomColor]*len(atoms)
if not imgPath:
return "",molStr,atoms,colors
try:
#Draw the image
MolDrawing.elemDict=defaultdict(lambda : (0,0,0))
Draw.MolToImageFile(mol,imgPath,size=(300, 300), kekulize=True, wedgeBonds=True, highlightAtoms=atoms)
#Color the Highlighted atoms with the choosen atomColor.
# Only using one color
if atomColor == 'r':
rgb = (255,0,0)
elif atomColor == 'g':
rgb = (0,255,0)
else:
rgb = (0,0,255) #Blue
img = Image.open(imgPath)
img = img.convert("RGBA")
pixdata = img.getdata()
newData = list()
for item in pixdata:
if item[0] == 255 and item[1] == 0 and item[2] == 0:
newData.append(rgb + (255,) )
else:
newData.append(item)
img.putdata(newData)
img.save(imgPath)
if os.path.isfile(imgPath):
return imgPath,molStr,atoms,colors
else:
return "",molStr,atoms,colors
except:
return "",molStr,atoms,colors
