Predicting a protein’s shape from its sequence
ESMFold applies a protein language model to infer three-dimensional structure directly from an amino-acid sequence, with checkpoints and bulk prediction tools available to researchers.
- Maturity
- Demonstrated, stage 3 of 4
- Support
- 3 sources · paper, repository, government
- Evidence detail
- How we know ↓
Experimental structure determination cannot keep pace with the vast number of protein sequences found in nature.
Structure prediction and experimental measurement both demanded substantial time and compute per protein.
Learned sequence representations are converted into predicted atomic structure without requiring a multiple-sequence alignment for every target.
What was shown, and what wasn’t
Shown
The Science study used the approach to help create the ESM Metagenomic Atlas, a public collection of predicted structures for hundreds of millions of metagenomic proteins.
Not shown · limits
- Predicted structures vary in confidence and require scientific follow-up. The MIT repository and CC-BY-4.0 Atlas do not amount to a complete released training corpus and recipe.
- The peer-reviewed paper and public artifacts establish the research result; neither establishes experimental validity for every predicted protein.
Bright editorial interpretation
Portable predictions can help researchers choose where to investigate, but a model output is evidence to test rather than a measured structure.
How we know3 sources · checked 2026-09-19 · no corrections
Original sources
- Evolutionary-scale prediction of atomic-level protein structure with a language model ↗ · paper
- Evolutionary Scale Modeling ↗ · repository
- Evolutionary-scale prediction of atomic-level protein structure with a language model ↗ · government
Institutions: Meta Fundamental AI Research
- Maturity
- Demonstrated
- Source published
- 2023-03-16
- Captured
- 2026-09-19
- Last source review
- 2026-09-19
- Editorial method
- AI-assisted source review
Bright compared this account with the linked original and supporting sources and kept reported, budgeted, projected, and observed claims distinct. Bright did not independently audit the underlying records.
Maturity describes the tested or operational setting. Confidence describes support for the particular claim; one does not determine the other.
Revision & correction history
2026-09-19 · Bright added this source-checked open-model application record. The cited source publication date is 2023-03-16; 2026-09-19 is when Bright added this record.
No corrections recorded.
Keep exploring
Explore the shared question in another setting. These connections do not imply replication.