liveBook · Manning

REOS

As explained in Build AI Drug Discovery Pipelines

REOS is a compound-filtering concept for rapidly removing low-quality molecules likely to be unproductive or produce assay artifacts.

REOS (Rapid Elimination of Swill) is a compound-filtering strategy for removing low-quality molecules unlikely to become viable drug candidates. It improves screening efficiency by reducing compounds likely to produce assay artifacts or false positives. section 2.3.2

REOS is a goal rather than one fixed ruleset. PAINS and BRENK provide related predefined filters, while custom structural-alert filters can implement the same objective. section 2.3.2

A practical REOS workflow can:

  • Distinguish hard filters, which automatically reject matches, from soft filters, which trigger closer examination. section 2.3.2

Library reduction

PAINS and BRENK filtering reduced 199,640 compounds to 105,630, or 52.9% of the starting library. A subsequent Glaxo Wellcome hard filter removed 135 more, leaving 105,495.

How Build AI Drug Discovery Pipelines covers it

How deep it goes
Defines REOS and demonstrates catalog-based and custom SMARTS filtering, but stops short of prescribing one universal ruleset.
Examples
Uses PAINS, BRENK, and Glaxo Wellcome alerts to filter a public compound library.
What it assumes
Assumes molecular structures and RDKit basics while defining SMARTS as substructure patterns analogous to chemical regular expressions.
What you can do after
Apply it via RDKit to construct custom structural-alert filters and inspect compliant compound libraries.
How it connects
Connects REOS with PAINS, BRENK, structural alerts, SMARTS, RDKit, and substructure matching.

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.