# Genomic and protein language models: Evo 2, Enformer, ESM

Source: https://onco.cc/terms/genomic-and-protein-language-models/  
OnCo record `genomic-and-protein-language-models` (Term). Data CC BY-NC 4.0, attribute "Data from OnCo (onco.cc)"; commercial use needs a licence.

## TL;DR

Sequence models read DNA or protein letters the way language models read text: ESM predicts protein structure and function, Enformer predicts gene expression from DNA sequence, and Evo 2 models whole genomes with a million-base context.

## Summary

ESM-2, from Lin and colleagues at Meta, is a protein language model whose embeddings predict atomic-level structure and are reused as gene tokens by cell models such as UCE. Enformer, from Avsec and colleagues at DeepMind, predicts expression and chromatin signals from 200 kilobases of DNA by combining convolutions with transformer attention. Evo 2 is a 40-billion-parameter genomic model on the StripedHyena 2 architecture with a one-million-base context; its zero-shot variant-effect claims are the kind of result that must be checked on clinical variant sets, and at least one independent check found them wanting.

## Fields

- Kind: Term
- Last checked: 2026-09-24
- Also known as: protein language model; protein language models; ESM2; ESM-2; ESM-3; Enformer; genomic language model; DNA language model; Evo 2 model; StripedHyena
- Tags: cansim-terms

## Notes

- Listed in the CanSim terms map 1.0.0 (docs/onco/terms.json, generated 2026-09-24), CC BY 4.0, attribution: CanSim project, an open, public-data-first cancer foundation-model programme; CanSim page path /terms/evo-2.

## Sources

- Lin et al., Evolutionary-scale prediction of atomic-level protein structure with a language model (ESM-2, Science 2023): https://doi.org/10.1126/science.ade2574
- ESM on GitHub (facebookresearch/esm): https://github.com/facebookresearch/esm
- Avsec et al., Enformer: effective gene expression prediction from sequence by integrating long-range interactions (Nature Methods 2021): https://doi.org/10.1038/s41592-021-01252-x

## Connected records

- terms: [Autoregressive (next-token) modelling](https://onco.cc/terms/autoregressive-modelling/), [Cancer AI vocabulary (CanSim terms map)](https://onco.cc/terms/cancer-ai-vocabulary/), [Tokenisation (genes, tiles and sequence as tokens)](https://onco.cc/terms/tokenisation/), [Variant effect prediction](https://onco.cc/terms/variant-effect-prediction/), [Zero-shot prediction](https://onco.cc/terms/zero-shot/)
- technologies: [Evo 2 (Arc Institute, NVIDIA)](https://onco.cc/technologies/evo2/), [Nucleotide Transformer (InstaDeep)](https://onco.cc/technologies/nucleotide-transformer/)

---
JSON: https://onco.cc/api/v1/entities/genomic-and-protein-language-models.json