liveBook · Manning

ETKDG

As explained in Build AI Drug Discovery Pipelines

ETKDG is a distance-geometry conformer-generation method that incorporates experimental torsion preferences and chemical knowledge constraints.

ETKDG generates molecular 3D conformers with distance geometry, experimental torsion preferences from the Cambridge Structural Database, and chemical-knowledge constraints such as flat aromatic rings and linear triple bonds. section 6.1.2

A practical conformer workflow uses ETKDG to produce candidate geometries, then evaluates or refines them:

  • Add hydrogens and generate multiple conformers with RDKit’s ETKDG parameters. section 6.1.2
  • Optimize geometries with the Universal Force Field when downstream analysis requires refinement. section 6.1.2
  • Compare relative energies, retain low-energy conformers, or apply Boltzmann weighting for descriptor computation. section 6.1.2

Generating esomeprazole conformers

RDKit generates ten esomeprazole conformers with AllChem.EmbedMultipleConfs(..., params=AllChem.ETKDG()), then aligns them around a shared substructure for visualization.

How Build AI Drug Discovery Pipelines covers it

How deep it goes
Explains the method’s geometric, torsional, and chemical constraints, then demonstrates embedding, optimization, energy filtering, and weighting.
Examples
Uses esomeprazole overlays, multiple conformer generation, UFF energies, and a three-kilocalorie-per-mole retention window.
What you can do after
Build it from scratch with RDKit by embedding, refining, comparing, and selecting molecular conformers.
How it connects
Connects distance geometry, force fields, torsion angles, conformers, steric strain, and Boltzmann weighting.

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.