def readfile(format, filename):
"""Iterate over the molecules in a file.
Required parameters:
format - see the informats variable for a list of available
input formats
filename
You can access the first molecule in a file using the next() method
of the iterator:
mol = readfile("smi", "myfile.smi").next()
You can make a list of the molecules in a file using:
mols = list(readfile("smi", "myfile.smi"))
You can iterate over the molecules in a file as shown in the
following code snippet:
>>> atomtotal = 0
>>> for mol in readfile("sdf", "head.sdf"):
... atomtotal += len(mol.atoms)
...
>>> print atomtotal
43
"""
format = format.lower()
if not os.path.isfile(filename):
raise IOError, "No such file: '%s'" % filename
builder = cdk.DefaultChemObjectBuilder.getInstance()
if format=="sdf":
return (Molecule(mol) for mol in cdk.io.iterator.IteratingSDFReader(
java.io.FileInputStream(java.io.File(filename)),
builder)
)
elif format=="smi":
return (Molecule(mol) for mol in cdk.io.iterator.IteratingSmilesReader(
java.io.FileInputStream(java.io.File(filename)),
builder
))
elif format == 'inchi':
inputfile = open(filename, 'rb')
return (readstring('inchi', line.rstrip()) for line in inputfile)
elif format in informats:
reader = _informats[format](java.io.FileInputStream(java.io.File(filename)))
chemfile = reader.read(cdk.ChemFile())
manip = cdk.tools.manipulator.ChemFileManipulator
return iter(Molecule(manip.getAllAtomContainers(chemfile)[0]),)
else:
raise ValueError,"%s is not a recognised CDK format" % format
def readstring(format, string):
"""Read in a molecule from a string.
Required parameters:
format - see the informats variable for a list of available
input formats
string
Example:
>>> input = "C1=CC=CS1"
>>> mymol = readstring("smi", input)
>>> len(mymol.atoms)
5
"""
format = format.lower()
if format == "smi":
sp = cdk.smiles.SmilesParser(
cdk.DefaultChemObjectBuilder.getInstance())
try:
ans = sp.parseSmiles(string)
except InvalidSmilesException as ex:
if sys.platform[:4] != "java":
#Jpype exception
ex = ex.message()
raise IOError(ex)
return Molecule(ans)
elif format == 'inchi':
factory = cdk.inchi.InChIGeneratorFactory.getInstance()
intostruct = factory.getInChIToStructure(
string, cdk.DefaultChemObjectBuilder.getInstance())
return Molecule(intostruct.getAtomContainer())
elif format in informats:
reader = _informats[format](java.io.StringReader(string))
chemfile = reader.read(cdk.ChemFile())
manip = cdk.tools.manipulator.ChemFileManipulator
return Molecule(manip.getAllAtomContainers(chemfile)[0])
else:
raise ValueError("%s is not a recognised CDK format" % format)
try:
ans = sp.parseSmiles(string)
except InvalidSmilesException, ex:
if sys.platform[:4] != "java":
#Jpype exception
ex = ex.message()
raise IOError, ex
return Molecule(ans)
elif format == 'inchi':
factory = cdk.inchi.InChIGeneratorFactory.getInstance()
intostruct = factory.getInChIToStructure(
string, cdk.DefaultChemObjectBuilder.getInstance())
return Molecule(intostruct.getAtomContainer())
elif format in informats:
reader = _informats[format](java.io.StringReader(string))
chemfile = reader.read(cdk.ChemFile())
manip = cdk.tools.manipulator.ChemFileManipulator
return Molecule(manip.getAllAtomContainers(chemfile)[0])
else:
raise ValueError, "%s is not a recognised CDK format" % format
class Outputfile(object):
"""Represent a file to which *output* is to be sent.
Required parameters:
format - see the outformats variable for a list of available
output formats
filename
Optional parameters: