def readFlsFile(fileName, isomers):
"""Reads molecule file (fls file).
:param fileName: (str) File name.
:param isomers: (pandas Dataframe) Table with ENU code, molecular formula and SMILEs string..
:return:
molecules: (list) List of molecules.
"""
with open(fileName, 'r') as f:
lines = f.readlines()
lines = [row.strip().split() for row in lines]
molecules = []
for i in range(len(lines)):
if not lines[i]:
continue
if lines[i][0] == '#':
# couldn't find a decomposition
if len(lines[i]) > 2 and lines[i][1] == "couldn\'t":
smiles = lines[i][6]
iso = isomers[isomers.smiles == smiles]
mol = Molecule(smiles, '', '', '', 0, [], 0, '')
mol.form = iso.frm.iloc[0]
mol.code = iso.nam.iloc[0]
mol.enu_code = iso.nam.iloc[0]
molecules.append(mol)
else:
continue
if lines[i][0][0] == '#':
continue
if lines[i][0] == 'NEWMOLECULE':
pos = i + 1
mol = readFlsFile_helper(pos, lines)
smi = mol.smiles
iso = isomers[isomers.smiles == smi]
mol.form = iso.frm.iloc[0]
mol.code = iso.nam.iloc[0]
molecules.append(mol)
return molecules
def getMolecules(isomers):
"""Returns list of molecules created from table with SMILES.
:param isomers: (pandas DataFrame) List of constitutional isomers together with molecular formula and SMILES.
:return:
molecules: (list) List of Molecules.
"""
molecules = []
for idx, row in isomers.iterrows():
smiles = row['smiles']
form = row['frm']
nam = row['nam']
mol = Molecule(smiles, '', nam, '', 0, [], 0, '')
mol.form = form
molecules.append(mol)
return molecules
