def test_parse_reaxys_xml(self):
parsed = self.parser.parse_reaxys_xml(self.filename)
# Ensure that all proper reactions are present
self.assertEqual(len(parsed), 3)
indices = [x["meta"]["index"] for x in parsed]
for index in [1, 9, 10]:
self.assertTrue(index in indices)
rxn_ids = [x["meta"]["rxn_id"] for x in parsed]
for rxn_id in [28100547, 3553459, 8633298]:
self.assertTrue(rxn_id in rxn_ids)
# Ensure that all reactions are actually appropriate
for rxn in parsed:
pro_species = list()
rct_species = list()
for pro in rxn["pros"]:
molecule = BabelMolAdaptor.from_string(pro, "mol")
molecule.add_hydrogen()
mol = molecule.pymatgen_mol
pro_species += [str(site.specie) for site in mol]
for rct in rxn["rcts"]:
molecule = BabelMolAdaptor.from_string(rct, "mol")
molecule.add_hydrogen()
mol = molecule.pymatgen_mol
rct_species += [str(site.specie) for site in mol]
self.assertSequenceEqual(sorted(pro_species), sorted(rct_species))
# Test one reaction to make sure metadata is recorded correctly
rxn = parsed[-1]["meta"]
self.assertEqual(rxn["solvents"], {'dichloromethane'})
self.assertEqual(len(rxn["pro_meta"]), 1)
self.assertEqual(len(rxn["rct_meta"]), 2)
self.assertSequenceEqual(
rxn["pro_meta"],
[(5424566, '(4,5-dimethylcyclohexa-1,4-dienyl)trimethylsilane')])
self.assertSequenceEqual(rxn["rct_meta"],
[(605285, '2,3-dimethyl-buta-1,3-diene'),
(906752, 'trimethylsilylacetylene')])
def insert_g3testset(coll):
for f in glob.glob("g*.txt"):
print("Parsing " + f)
for (m, charge, spin) in parse_file(f):
try:
clean_sites = []
for site in m:
if Element.is_valid_symbol(site.specie.symbol):
clean_sites.append(site)
clean_mol = Molecule.from_sites(clean_sites,
charge=charge,
spin_multiplicity=spin)
xyz = XYZ(clean_mol)
bb = BabelMolAdaptor.from_string(str(xyz), "xyz")
pbmol = pb.Molecule(bb.openbabel_mol)
smiles = pbmol.write("smi").split()[0]
can = pbmol.write("can").split()[0]
inchi = pbmol.write("inchi")
svg = pbmol.write("svg")
d = {"molecule": clean_mol.as_dict()}
comp = clean_mol.composition
d["pretty_formula"] = comp.reduced_formula
d["formula"] = comp.formula
d["composition"] = comp.as_dict()
d["elements"] = list(comp.as_dict().keys())
d["nelements"] = len(comp)
d["charge"] = charge
d["spin_multiplicity"] = spin
d["smiles"] = smiles
d["can"] = can
d["inchi"] = inchi
# d["names"] = get_nih_names(smiles)
d["svg"] = svg
d["xyz"] = str(xyz)
d["tags"] = ["G305 test set"]
coll.update(
{
"inchi": inchi,
"charge": charge,
"spin_multiplicity": spin
}, {"$set": d},
upsert=True)
except Exception as ex:
print("Error in {}".format(f))
exc_type, exc_value, exc_traceback = sys.exc_info()
traceback.print_exception(exc_type,
exc_value,
exc_traceback,
limit=2,
file=sys.stdout)
print("{} parsed!".format(f))
def insert_elements(coll):
print("adding missing elements.")
for z in range(1, 19):
el = Element.from_Z(z)
r = coll.find(filter={"formula": "{}1".format(el.symbol)})
if r.count() == 0:
try:
clean_mol = Molecule([el], [[0, 0, 0]])
xyz = XYZ(clean_mol)
bb = BabelMolAdaptor.from_string(str(xyz), "xyz")
pbmol = pb.Molecule(bb.openbabel_mol)
smiles = pbmol.write("smi").split()[0]
can = pbmol.write("can").split()[0]
inchi = pbmol.write("inchi")
svg = pbmol.write("svg")
d = {"molecule": clean_mol.as_dict()}
comp = clean_mol.composition
d["pretty_formula"] = comp.reduced_formula
d["formula"] = comp.formula
d["composition"] = comp.as_dict()
d["elements"] = list(comp.as_dict().keys())
d["nelements"] = len(comp)
d["charge"] = 0
d["spin_multiplicity"] = clean_mol.spin_multiplicity
d["smiles"] = smiles
d["can"] = can
d["inchi"] = inchi
# d["names"] = get_nih_names(smiles)
d["svg"] = svg
d["xyz"] = str(xyz)
d["tags"] = ["G305 test set"]
coll.insert(d)
except Exception as ex:
print("Error in {}".format(el))
elif r.count() > 1:
print("More than 1 {} found. Removing...".format(el))
results = list(r)
for r in results[1:]:
print(r["_id"])
coll.remove({"_id": r["_id"]})
def test_from_string(self):
xyz = XYZ(self.mol)
adaptor = BabelMolAdaptor.from_string(str(xyz), "xyz")
mol = adaptor.pymatgen_mol
self.assertEqual(mol.formula, "H4 C1")
def test_from_string(self):
xyz = XYZ(self.mol)
adaptor = BabelMolAdaptor.from_string(str(xyz), "xyz")
mol = adaptor.pymatgen_mol
self.assertEqual(mol.formula, "H4 C1")
def parse_reaxys_xml(self, filename):
"""
Parses an XML file generated by the Reaxys API.
:param filename: str referring to XML file from Reaxys.
:return: List of dicts including reactant CTAB, product CTAB, and
metadata.
"""
results = []
filepath = os.path.join(self.base_dir, filename)
with open(filepath, 'r') as fileobj:
xml = fileobj.read()
parsed = BeautifulSoup(xml, "lxml-xml")
reactions = parsed.find_all("reaction")
for reaction in reactions:
# Screen for reactions with more than two reactants
# or more than one product
pros = reaction.find_all("RY.PRO")
rcts = reaction.find_all("RY.RCT")
if not ((len(pros) == 1 and len(rcts) == 2) or
(len(pros) == 2 and len(rcts) == 1)):
continue
# Generate metadata from reaction header information
# Will be passed along with CTAB information
index = int(reaction["index"])
rxn_id = int(reaction.find("RX.ID").text)
solvents = set(
[sol.text for sol in reaction.find_all("RXD.SOL")])
rct_ids = reaction.find_all("RX.RXRN")
rct_names = reaction.find_all("RX.RCT")
rct_meta = [(int(e.text), rct_names[i].text)
for i, e in enumerate(rct_ids)]
pro_ids = reaction.find_all("RX.PXRN")
pro_names = reaction.find_all("RX.PRO")
pro_meta = [(int(e.text), pro_names[i].text)
for i, e in enumerate(pro_ids)]
meta = {
"index": index,
"rxn_id": rxn_id,
"solvents": solvents,
"rct_meta": sorted(rct_meta, key=lambda x: x[0]),
"pro_meta": sorted(pro_meta, key=lambda x: x[0])
}
# Capture reactant CTAB information
# Make sure that ordering is the same for metadata and CTAB
rcts = sorted(reaction.find_all("RY.RCT"),
key=lambda x: int(x["rn"]))
rcts = [rct.text for rct in rcts]
pros = sorted(reaction.find_all("RY.PRO"),
key=lambda x: int(x["rn"]))
pros = [pro.text for pro in pros]
rxn = {"rcts": rcts, "pros": pros, "meta": meta}
try:
pro_atoms = []
for pro in rxn["pros"]:
ad = BabelMolAdaptor.from_string(pro,
file_format="mol")
ad.add_hydrogen()
for site in ad.pymatgen_mol:
pro_atoms.append(str(site.specie))
rct_atoms = []
for rct in rxn["rcts"]:
ad = BabelMolAdaptor.from_string(rct,
file_format="mol")
ad.add_hydrogen()
for site in ad.pymatgen_mol:
rct_atoms.append(str(site.specie))
if sorted(pro_atoms) == sorted(rct_atoms):
results.append(rxn)
except:
continue
return results
