Chapter 5 of Cheminformatics

Molecules as data soon

How a molecule becomes something a computer can compute with: SMILES strings, RDKit molecule objects, descriptors and fingerprints, and similarity search.

soon This chapter is planned and not yet written. The outline below is the current plan; it may change.

What it will cover

• SMILES: reading, writing and canonicalising molecular structures
• RDKit: parsing, drawing and sanitising molecules
• Descriptors: molecular weight, logP, TPSA, H-bond counts, rotatable bonds
• Fingerprints: Morgan/ECFP bit vectors and what the bits mean
• Tanimoto similarity and nearest-neighbour search
• Lab 5: recompute the ESOL descriptors from SMILES and rebuild the Chapter 2 model

Planned learning outcomes

1. Convert SMILES to RDKit molecules, compute descriptors and fingerprints, and build an X matrix from them.
2. Explain what a Morgan fingerprint encodes and compute Tanimoto similarities.
3. Find the nearest neighbours of a query molecule in a library and judge whether they are chemically sensible.

In the meantime

Everything here builds on Part I, in particular the evaluation habits of Chapter 2. Episode 2.6 already introduces the group splits that become scaffold splits here.

PreviousChapter 4 Deep learning essentials with PyTorchNextChapter 6 QSAR and property prediction

Edit this pageReport a problemLast updated 2026-11-02