def LoadGroups(self, FromDatabase=False, FromFile=None):
if FromDatabase and self.db.DoesTableExist('groups'):
self.groups_data = GroupsData.FromDatabase(
self.db, transformed=self.transformed)
self.group_decomposer = GroupDecomposer(self.groups_data)
else:
if FromFile is None:
FromFile = open('../data/thermodynamics/groups_species.csv',
'r')
self.groups_data = GroupsData.FromGroupsFile(
FromFile, transformed=self.transformed)
self.groups_data.ToDatabase(self.db)
self.group_decomposer = GroupDecomposer(self.groups_data)
def LoadGroups(self, FromDatabase=False):
#if self.transformed:
# fname = "../data/thermodynamics/groups_species_transformed.csv"
#else:
if FromDatabase and self.db.DoesTableExist('groups'):
self.groups_data = GroupsData.FromDatabase(
self.db, transformed=self.transformed)
self.group_decomposer = GroupDecomposer(self.groups_data)
else:
fp = open("../data/thermodynamics/groups_species.csv", 'r')
self.groups_data = GroupsData.FromGroupsFile(
fp, transformed=self.transformed)
self.groups_data.ToDatabase(self.db)
self.group_decomposer = GroupDecomposer(self.groups_data)
def FromDatabase(self, db):
self.groups_data = GroupsData.FromDatabase(
db, transformed=self.transformed)
self.group_decomposer = GroupDecomposer(self.groups_data)
self.g_pgc = db.LoadNumpyMatrix('ugc_group_contributions').T
self.P_L_pgc = db.LoadSparseNumpyMatrix('ugc_group_nullspace')
def main():
parser = MakeOpts()
args = parser.parse_args()
dissociation = DissociationConstants.FromPublicDB()
groups_data = GroupsData.FromGroupsFile(args.groups_species,
transformed=False)
group_decomposer = GroupDecomposer(groups_data)
while DecomposeInputString(group_decomposer, dissociation):
pass
def FromDatabase(db, filename=None):
"""Factory that initializes a GroupDecomposer from the database.
Args:
db: a Database object.
filename: an optional filename to load data from when
it's not in the DB. Will write to DB if reading from file.
Returns:
An initialized GroupsData object.
"""
assert db
gd = GroupsData.FromDatabase(db, filename)
return GroupDecomposer(gd)
def dissociation_decomposition_test():
"""
Verifies that the decomposition of the compounds in the dissociation table match the nH of each species.
"""
db = SqliteDatabase('../res/gibbs.sqlite')
dissociation = DissociationConstants.FromPublicDB()
groups_data = GroupsData.FromDatabase(db)
group_decomposer = GroupDecomposer(groups_data)
kegg = Kegg.getInstance()
for cid in dissociation.GetAllCids():
id = "C%05d (%s)" % (cid, kegg.cid2name(cid))
if kegg.cid2compound(cid).get_atom_bag() is None:
logging.debug('%s: has no explicit formula' % id)
else:
diss = dissociation.GetDissociationTable(cid,
create_if_missing=False)
test_dissociation_table(diss,
group_decomposer,
id,
ignore_missing_smiles=True)
def nist_dissociation_test():
"""
Verifies that all the compounds in NIST are covered by the dissociation table, including SMILES strings.
"""
db = SqliteDatabase('../res/gibbs.sqlite')
nist_regression = NistRegression(db, html_writer=NullHtmlWriter())
dissociation = nist_regression.dissociation
groups_data = GroupsData.FromDatabase(db)
group_decomposer = GroupDecomposer(groups_data)
kegg = Kegg.getInstance()
nist = nist_regression.nist
for cid in nist.GetAllCids():
id = "C%05d (%s)" % (cid, kegg.cid2name(cid))
if kegg.cid2compound(cid).get_atom_bag() is None:
logging.debug('%s: has no explicit formula' % id)
else:
diss = dissociation.GetDissociationTable(cid,
create_if_missing=False)
test_dissociation_table(diss,
group_decomposer,
id,
ignore_missing_smiles=False)
def FromGroupsFile(fp):
"""Factory that initializes a GroupDecomposer from a CSV file."""
gd = GroupsData.FromGroupsFile(fp)
return GroupDecomposer(gd)