Topological polar surface area (TPSA) estimates the surface contribution of a molecule’s polar atoms and bonds. In solubility modeling, it is one of several molecular descriptors computed from chemical structures. section 4.1.3
Listing 4.3 Compute RDKit Descriptors
from rdkit.Chem import (
Crippen,
Descriptors,
GraphDescriptors,
Lipinski,
MolFromSmarts,
rdMolDescriptors,
)
def AromaticProportion(mol):
if mol is None or mol.GetNumAtoms() == 0: #A
return 0.0 #A
aromatic_atoms = mol.GetSubstructMatches(
MolFromSmarts("a")
)
return len(aromatic_atoms) / mol.GetNumAtoms()
RDKIT_DESCRIPTORS = {
'Molecular Weight' : Descriptors.MolWt,
'Number of H-Bond Donors' : Descriptors.NumHDonors,
'TPSA' : Descriptors.TPSA,
'logP' : Crippen.MolLogP,
'Molar Refractivity' : Crippen.MolMR,
'Number of Rotatable Bonds' : Lipinski.NumRotatableBonds,
'Number of Rings' : rdMolDescriptors.CalcNumRings,
'LabuteASA' : rdMolDescriptors.CalcLabuteASA,
'BalabanJ' : GraphDescriptors.BalabanJ,
'BertzCT' : GraphDescriptors.BertzCT,
'Aromatic Proportion' : AromaticProportion,
}
for desc, func in RDKIT_DESCRIPTORS.items():
train_df[desc] = train_df["Molecule"].apply(func)Use the RDKit descriptor listing to compute TPSA alongside molecular weight, hydrogen-bond donors, logP, rings, and other features. section 4.1.3
Scatterplots and Pearson correlation show little apparent relationship between TPSA and solubility in the analyzed dataset. Treating it as uninformative may be reasonable for that model, but feature selection should consider noise and descriptor redundancy. section 4.1.3
