How deeply does Graph Neural Networks in Action cover SMILES?

Explains notation use through parsing and graph conversion, but does not detail SMILES syntax or chemical validation rules.

SMILES

As explained in Graph Neural Networks in Action

SMILES is a textual notation for encoding the structure of chemical compounds as molecular strings.

SMILES (Simplified Molecular Input Line Entry System) encodes a molecule’s structure as an ASCII molecular string. It provides a practical bridge from chemical records to molecular graphs used in graph-learning workflows. section 5.4.1

A typical SMILES-to-graph workflow proceeds as follows:

Package the resulting graphs as PyTorch Geometric data objects for model training. section 5.4.1

Drug-candidate generation

A variational graph autoencoder can encode SMILES-derived molecular graphs into a latent space, predict QED there, and decode optimized representations into candidate molecules. section 5.4.2

How Graph Neural Networks in Action covers it

Cover of Graph Neural Networks in Action

liveBook manning.com

Read Graph Neural Networks in Action on liveBook Get the book at manning.com

Related concepts

molecular graphalternative to · A molecular graph is a graph representation of a molecule in which atoms are nodes and chemical bonds are edges.
sanitizationused by · Sanitization is the process of checking, modifying, removing, or normalizing data to meet relevant safety, privacy, consistency, or domain requirements before use or sharing.

This explainer was generated by Manning's knowledge graph from the text of Graph Neural Networks in Action. The section links point to the parts of the book it draws on.