liveBook · Manning

Biological foundation model

As explained in Build AI Drug Discovery Pipelines

A biological foundation model is a foundation model pretrained to represent biological entities, processes, or data across one or more biological modalities.

A biological foundation model is pretrained to represent biological entities, processes, or data across one or more modalities. The goal is a unified model that relates DNA sequences, protein structures, cellular phenotypes, tissue organization, and organism-level physiology. section 13.4.4

Multimodal pretraining can align representations of the same gene across DNA sequence, RNA expression, and protein structure. Knowledge learned from one modality can then inform predictions in another, supporting transfer across biological tasks. section 13.4.4

Examples span ESM-2 for proteins, MegaMolBART for small molecules, Phenom for cellular imaging, LucaOne for genes, ProCyon across five biological knowledge domains, and Evo 2 across genome-scale sequences. Applications include protein function prediction, drug-target interaction prediction, clinical outcome prediction, variant-effect prediction, and genetic-circuit engineering. section 13.4.4

How Build AI Drug Discovery Pipelines covers it

How deep it goes
Explains pretrained representations, cross-modal transfer, knowledge domains, and long-context sequence modeling without implementation details.
Examples
Uses ESM-2, MegaMolBART, Phenom, LucaOne, ProCyon, and Evo 2 as concrete model examples.
What you can do after
Understand how shared biological representations can support prediction across sequences, structures, expression, phenotypes, and clinical outcomes.
How it connects
Links foundation models with multimodal learning, protein function prediction, drug-target interaction prediction, and genome-scale modeling.

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.