liveBook · Manning

Phenom model

As explained in Build AI Drug Discovery Pipelines

Phenom-Beta is a vision-transformer biological foundation model that learns biologically meaningful representations from cellular microscopy images.

Phenom-Beta is a vision-transformer model that learns biologically meaningful features from cellular microscopy images. Its training dataset contains 2.2 million images spanning thousands of compound or genetic perturbations across multiple cell types. section 13.2.1

The model divides each image into square patches, embeds the patches as tokens, and processes the token sequence through transformer layers to build an image representation. section 13.2.1

In phenotypic screening, compounds are evaluated by their effects on cell shape and behavior. A challenge is deconvolution: identifying the cellular targets responsible for those effects. Phenom’s learned features can connect observed phenotypes with possible molecular mechanisms. section 13.2.1

A possible kinase inhibitor

If a new compound produces a cellular phenotype similar to that of a known kinase inhibitor, Phenom’s features might suggest that the new compound also inhibits kinases. The similarity is a clue, not an established mechanism. section 13.2.1

How Build AI Drug Discovery Pipelines covers it

How deep it goes
Explains patch embedding and transformer processing, but does not provide implementation or evaluation details.
Examples
Uses a compound resembling a known kinase inhibitor to illustrate a possible mechanism hypothesis.
What you can do after
Understand how cellular image features can suggest targets responsible for a compound’s effects.
How it connects
Links vision transformers, phenotypic screening, genetic perturbations, and molecular mechanisms.

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.