ESM / ESMFold
ESM / ESMFold (Evolutionary Scale Modeling)
617 million protein structures in two weeks
Latest: ESM-2/ESMFold (2022); Meta repo archived August 2024; ESM3 is EvolutionaryScale's, not Meta's
Meta's protein language models: ESM-2 (up to 15B parameters, 2022) learned protein structure from sequences alone, and ESMFold predicted atomic-level 3D structure ~60x faster than AlphaFold2 without multiple sequence alignments (Science, 2023). The core team left Meta in 2023 to found EvolutionaryScale, whose ESM3 (2024) continues the family — outside Meta.
Why it matters
Showed protein language models trained on sequences alone learn structure: ESMFold predicted 3D structure about 60x faster than AlphaFold2 without multiple sequence alignments, enabling the ESM Metagenomic Atlas. The core team left to found EvolutionaryScale in 2023, and Meta archived the repository in August 2024.
Facts
- A language model that never saw a 3D structure during pretraining learned to fold proteins — then mapped 617 million of them in a fortnight.
- ESMFold folded 617 million metagenomic proteins in two weeks on ~2,000 GPUs to launch the ESM Metagenomic Atlas (Nov 2022), later expanded to ~772 million structures.
- EvolutionaryScale launched in June 2024 with a reported $142M seed round — one of the biggest ever — and ESM3 generated esmGFP, a fluorescent protein it framed as '500 million years of evolution' away from known ones.
- Predicted 617 million protein structures in just two weeks on ~2,000 GPUs; structure emerged spontaneously in the language model's representations as it scaled from 8M to 15B parameters.
Try it yourself
Browse the ESM Metagenomic Atlas ↗ ESMFold on Hugging Face ↗ Fold a sequence in Colab (ColabFold ESMFold) ↗
Sources
Science ↗GitHub · esm ↗Meta AI blog ↗esmatlas.com ↗evolutionaryscale.ai ↗