liveBook · Manning

Protomer space

As explained in Build AI Drug Discovery Pipelines

Protomer space is the set of chemically relevant protonation-state variants considered for a ligand.

Protomer space is the set of chemically relevant ligand variants produced by different protonation states and related tautomeric arrangements. Protonation adds or removes a proton and can change acidity, basicity, charge, and chemical behavior; tautomerization rearranges bonds and relocates a proton. Because these changes can influence one another, searching only the input structure may miss forms relevant to molecular descriptors or binding analysis. section 6.1.2

The space becomes especially important when data are scarce. In an RNA-binding case study with 48 ligands, comprehensive descriptor calculation searched both protomer space and conformer space, expanding the ligand set to roughly 1,500 protomer variants before downstream modeling. section 6.1.2 section 6.5

A practical enumeration workflow can:

  • Enumerate tautomers for each protonated structure, convert results back to molecules, and remove duplicates. section 6.1.2
  • Use the resulting variants as inputs for conformer generation and descriptor calculation rather than treating every ligand as one fixed structure. section 6.1.2

How Build AI Drug Discovery Pipelines covers it

How deep it goes
Defines protonation and tautomer variants, then demonstrates enumeration settings before connecting them to descriptor calculation.
Examples
Uses 48 ligands expanded to roughly 1,500 variants and demonstrates RDKit–Dimorphite-DL enumeration over pH 6.4–8.4.
What it assumes
Assumes basic molecular-structure and SMILES familiarity while defining protonation and tautomerization before computational use.
What you can do after
Build it from scratch with RDKit and Dimorphite-DL by validating SMILES and enumerating protonation and tautomeric variants.
How it connects
Connects protonation, tautomerization, conformer space, molecular descriptors, QSAR modeling, and RNA–small-molecule binding.

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.