liveBook · Manning

Probability of improvement

As explained in Build AI Drug Discovery Pipelines

Probability of improvement is an acquisition criterion that estimates the probability that a candidate will outperform the best observed result.

Probability of improvement (PI) is an acquisition criterion that estimates how likely a candidate is to outperform the best observed binding-affinity result. It helps an active-learning system choose which molecule to evaluate next. section 9.2.5

Use PI within a drug-discovery active-learning loop:

  • Train a surrogate model on molecules whose binding affinities have already been evaluated. section 9.4
  • Score the unlabeled molecular pool by each candidate’s estimated probability of beating the current best result. section 9.2.5
  • Evaluate the selected molecules with an expensive method such as docking, add the results to the training data, and repeat. section 9.4

Deep docking for VEGFR-2

PI was one of several acquisition functions used to prioritize compounds for docking against the VEGFR-2 kinase target (PDB ID: 4AG8). The broader active-learning experiment recovered 73 of the top 100 molecules after 10 iterations while docking only a small fraction of the library. section 9.4

How Build AI Drug Discovery Pipelines covers it

How deep it goes
Defines PI and its selection role, but defers the implementation details to a separate notebook.
Examples
Uses molecular pools, binding-affinity predictions, docking, and a VEGFR-2 experiment recovering 73 of the top 100 molecules.
What it assumes
Assumes familiarity with molecular binding affinity, surrogate models, and active learning while defining PI’s selection purpose.
What you can do after
Apply PI to prioritize the next molecules for expensive evaluation in an active-learning screening loop.
How it connects
Connects probability of improvement to active learning, surrogate models, acquisition functions, docking, and exploration-exploitation trade-offs.

Also explained in

Compare how 2 books explain probability of improvement →

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.