liveBook · Manning

Ligand-based machine learning

As explained in Build AI Drug Discovery Pipelines

Ligand-based machine learning predicts compound activity from relationships between molecular structural features and observed activity data.

Ligand-based machine learning trains a model to relate molecular structural features to observed compound activity. With known active and inactive compounds, it can discriminate between the classes and predict activity for new compounds. These activity-prediction models are sometimes called quantitative structure–activity relationship (QSAR) models, although not every QSAR model uses machine learning; quantitative structure–property relationship (QSPR) is the broader term. section 2.1.1

Use ligand-based machine learning when:

  • Both positive and negative examples are available; with only known actives, similarity or pharmacophore searching is more appropriate. section 2.1.1
  • A virtual-screening workflow needs a learned activity filter before more intensive downstream methods. section 2.1.1
Figure 2.2 Regarding ligand-based strategies, machine learning becomes available if we have examples of both positive class and negative class compounds within our data. If we only have examples of positive class compounds, then search based strategies are more appropriate. Positive class means the compound is “positive” for the property we are assessing whether it be activity, toxicity, or some other property.

The decision diagram clarifies when ligand-based machine learning becomes appropriate and contrasts it with search-based strategies. section 2.1.1

How Build AI Drug Discovery Pipelines covers it

How deep it goes
Defines the modeling goal and data requirement but defers structural-similarity methods and implementation details.
Examples
Uses known active and inactive compounds as positive- and negative-class examples for activity discrimination.
What it assumes
Assumes labeled active and inactive compounds while defining structural features, activity classes, QSAR, and QSPR.
What you can do after
Build activity classifiers from labeled compounds and assess whether predictions may generalize to unseen compounds.
How it connects
Connects ligand-based virtual screening with QSAR, QSPR, similarity searching, pharmacophore searching, and hierarchical virtual screening.

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.