liveBook · Manning

Scaffold decoration

As explained in Build AI Drug Discovery Pipelines

Scaffold decoration is the systematic variation of substituents attached to a common molecular scaffold to create and evaluate analogs.

Scaffold decoration varies substituents attached to a common molecular scaffold, creating analog libraries for property optimization and activity analysis. section 7.2.2

A practical scaffold-decoration workflow:

  • Identify a core scaffold and its attachment sites. section 7.2.2
  • Collect molecular fragments and define compatible reaction rules. section 7.2.2
  • Enumerate analogs, then filter or prioritize them for drug-likeness, synthetic feasibility, or predicted activity. section 7.2.2

RDKit library construction

An RDKit workflow extracts Murcko scaffolds and R-groups, applies reaction SMARTS, and generates expanded analog sets; BRICS decomposition and building provide an alternative retrosynthetic route. section 7.2.2

Figure 7.8 Scaffold hopping requires identifying a new scaffold that can bear the required R-groups in the appropriate relative positions. Replacement of the benzene ring with a pyridine ring would give a similar structure, but a pyrimidine scaffold would not work since the two nitrogens won’t accommodate the necessary R-group orientation.

Contrast scaffold decoration with scaffold hopping: decoration retains the core, whereas hopping replaces it while preserving R-group placement requirements. section 7.2.2

How Build AI Drug Discovery Pipelines covers it

How deep it goes
Defines the technique and outlines fragment selection, attachment rules, enumeration, filtering, and prioritization.
Examples
Uses Murcko scaffold extraction, reaction SMARTS, and BRICS decomposition to construct analog libraries.
What it assumes
Introduces scaffolds and R-groups before applying fragment-based library construction.
What you can do after
Apply it via RDKit to generate, filter, and prioritize scaffold-based molecular analogs.
How it connects
Connects molecular scaffolds, R-groups, chemical series, QSAR models, combinatorial libraries, and scaffold hopping.

Related concepts

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.