liveBook · Manning

MOSES

As explained in Build AI Drug Discovery Pipelines

MOSES is a benchmark dataset and evaluation suite for molecular generation models.

MOSES (MOlecular SEtS) is a benchmark for molecular generation models, combining a curated dataset, fixed data splits, standardized evaluation metrics, implementations, and baseline results. section 10.2.4

Its standardized collection contains:

  • 1.9 million drug-like molecules from the ZINC Clean Leads subset. section 10.2.4
  • Canonical SMILES, removed stereochemistry, stripped salts, and filtering for drug-likeness, synthetic accessibility, and molecular size. section 10.2.4
  • Predefined train, test, and scaffold splits supporting fair model comparison. section 10.2.4
  • Evaluation of reconstruction quality, latent-space organization, chemical validity, and generation diversity. section 10.2.4

How Build AI Drug Discovery Pipelines covers it

How deep it goes
Defines dataset curation and evaluation dimensions, including reconstruction, latent-space quality, and generation quality.
Examples
Uses 1.9 million standardized drug-like molecules filtered by molecular weight, logP, synthetic accessibility, and rotatable bonds.
What you can do after
Evaluate molecular generation models across reconstruction fidelity, latent-space organization, validity, and diversity.
How it connects
Connects molecular generation with autoencoders, latent spaces, canonical SMILES, synthetic accessibility, and scaffold splits.

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.