def test_fileName(self):
f = chemkit.MoleculeFile()
self.assertEqual(f.fileName(), "")
f.setFileName("methane.sdf")
self.assertEqual(f.fileName(), "methane.sdf")
f.setFileName("")
self.assertEqual(f.fileName(), "")
f = chemkit.MoleculeFile("ethanol.cml")
self.assertEqual(f.fileName(), "ethanol.cml")
def test_methanol(self):
f = chemkit.MoleculeFile(dataPath + "methanol.sdf")
ok = f.read()
if not ok:
print f.errorString()
self.assertTrue(ok)
self.assertEqual(f.moleculeCount(), 1)
molecule = f.molecule(0)
self.assertIsNotNone(molecule)
self.assertEqual(molecule.formula(), "CH4O")
def test_readString(self):
f = chemkit.MoleculeFile()
f.setFormat("xyz")
# string containing the file's data
data = "5\n"
data += "methane\n"
data += "C 0.000000 0.000000 0.000000\n"
data += "H 0.000000 0.000000 1.089000\n"
data += "H 1.026719 0.000000 -0.363000\n"
data += "H -0.513360 -0.889165 -0.363000\n"
data += "H -0.513360 0.889165 -0.363000\n"
ok = f.readString(data)
if not ok:
print f.errorString()
self.assertTrue(ok)
self.assertEqual(f.moleculeCount(), 1)
molecule = f.molecule(0)
self.assertIsNotNone(molecule)
self.assertEqual(molecule.formula(), "CH4")
# make-descriptors-csv-file.py: creates a csv file with descriptor values
import os
import sys
import chemkit
if len(sys.argv) < 4:
print 'usage: ' + sys.argv[0] + ' [INPUT_FILENAME] [OUTPUT_FILENAME] [DESCRIPTORS...]'
input_filename = sys.argv[1]
output_filename = sys.argv[2]
# read input file
input_file = chemkit.MoleculeFile(input_filename)
if not input_file.read():
print 'error reading file: ' + input_file.errorString()
sys.exit(-1)
# create output file
output_file = open(output_filename, "w")
# get descriptor names
descriptors = sys.argv[3:]
# write header
output_file.write("inchikey,")
for descriptor in descriptors:
output_file.write(descriptor + ",")
output_file.write("\n")
for molecule in input_file.molecules():
settings = json.load(file(sys.argv[1]))
host = settings['server']['host']
port = settings['server']['port']
collection_name = settings['server']['collection']
except:
print 'Failed to load server settings'
sys.exit(-1)
# connect to mongochem mongo server
connection = pymongo.Connection(host, port)
db = connection[collection_name]
molecules_collection = db['molecules']
# open and read pubchem file
fileName = sys.argv[2]
moleculeFile = chemkit.MoleculeFile(fileName)
if not moleculeFile.read():
print 'Error reading file: ' + moleculeFile.errorString()
sys.exit(-1)
print 'Read file \'' + os.path.basename(
fileName) + '\' (%d molecules)' % moleculeFile.moleculeCount()
for molecule in moleculeFile.molecules():
# data values
name = molecule.data("PUBCHEM_IUPAC_TRADITIONAL_NAME")
if not len(name):
name = molecule.data("PUBCHEM_IUPAC_SYSTEMATIC_NAME")
formula = molecule.formula()
inchi = molecule.formula("inchi")
def importFile(fileName, collection):
moleculeFile = chemkit.MoleculeFile(fileName)
if not moleculeFile.read():
print 'Error reading file: ' + moleculeFile.errorString()
return False
elif moleculeFile.isEmpty():
print 'Error: file is empty'
return False
molecule = moleculeFile.molecule()
# data values
name = molecule.name()
formula = molecule.formula()
inchi = molecule.formula("inchi")
inchikey = molecule.formula("inchikey")
# atom counts
atomCount = molecule.atomCount()
hydrogenAtomCount = len([atom for atom in molecule.atoms() if atom.isTerminalHydrogen()])
heavyAtomCount = atomCount - hydrogenAtomCount
# descriptors
mass = molecule.mass()
molecularWeight = 0.0
try: molecularWeight = float(molecule.data("Molecular weight"))
except: pass
monoisotopicWeight = 0.0
try: monoisotopicWeight = float(molecule.data("Monoisotopic weight"))
except: pass
meltingPoint = 0.0
try: meltingPoint = float(molecule.data("Melting point"))
except: pass
boilingPoint = 0.0
try: boilingPoint = float(molecule.data("Boiling point"))
except: pass
# insert molecule document
document = {
"name" : name,
"formula" : formula,
"inchi" : inchi,
"inchikey" : inchikey,
"atomCount" : atomCount,
"heavyAtomCount" : heavyAtomCount,
"mass" : mass,
"descriptors" :
{"molecular-weight" : molecularWeight,
"monoisotopic-weight" : monoisotopicWeight,
"melting-point" : meltingPoint,
"boiling-point" : boilingPoint}
}
collection.update({"inchikey" : inchikey}, document, True)
return True