liveBook · Manning

Topological polar surface area

As explained in Build AI Drug Discovery Pipelines

Topological polar surface area (TPSA) is a molecular descriptor estimating the surface area contributed by polar atoms and their bonding contributions.

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

How Build AI Drug Discovery Pipelines covers it

How deep it goes
Computes TPSA with RDKit and evaluates its correlation with solubility, without explaining the descriptor’s underlying calculation.
Examples
Computes TPSA in an RDKit descriptor dictionary and compares it with solubility using scatterplots and correlations.
What it assumes
Uses molecular descriptors, solubility, Pearson correlation, and feature engineering as the surrounding analytical vocabulary.
What you can do after
Apply it via RDKit and evaluate whether TPSA contributes useful signal to a solubility feature set.
How it connects
Connects TPSA to molecular descriptors, solubility, feature engineering, Pearson correlation, and logP.

This explainer was generated by Manning's knowledge graph from the text of Build AI Drug Discovery Pipelines. The section links point to the parts of the book it draws on.