liveBook · Manning

Hierarchical virtual screening

As explained in Build AI Drug Discovery Pipelines

Hierarchical virtual screening is a staged screening strategy that progressively applies more complex and computationally expensive methods to a shrinking compound set.

Hierarchical virtual screening reduces a large compound library through successive stages, beginning with fast, inexpensive filters and ending with rigorous methods applied to a small candidate set. section 2.1.1

A practical pipeline can proceed as follows:

  • Apply rule-based compound filters to remove obvious candidates of concern, including compounds with poor drug-likeness. section 2.1.1
  • Use ligand-based virtual screening to identify compounds resembling known active molecules. section 2.1.1
  • Apply protein-ligand docking or molecular dynamics simulations to the remaining compounds when a target structure is available. section 2.1.1
Figure 2.1 Virtual screening pipelines are often hierarchical, proceeding with a broad, large number of compounds through simpler, less restrictive, and computationally cheaper processes to whittle down the quantity of compounds. If the 3D structure of the target is not defined, we’re restricted to ligand-based virtual screening. If it is defined, then we can explore structure-based virtual screening, potentially as a downstream component to ligand-based virtual screening.

The pipeline moves from many compounds and simpler computations toward fewer compounds and more intensive analysis; target structure availability determines whether structure-based stages can follow. section 2.1.1

How Build AI Drug Discovery Pipelines covers it

How deep it goes
Explains the staged workflow and method progression but stops short of implementation details, scoring formulas, or validation procedures.
Examples
Uses rule-based filters, ligand-based screening, docking, molecular dynamics, and Lipinski’s rule of five as pipeline stages or checks.
What you can do after
Apply it via sequential filters and virtual screening methods to prioritize compounds for intensive downstream analysis.
How it connects
Connects compound filters, ligand-based virtual screening, structure-based virtual screening, protein-ligand docking, molecular dynamics, and ADMET prediction.

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.