Evolutionary Scale Modeling (ESM)
A collection of transformer protein language models for predicting structure, function, and designing proteins from sequences.
What is Evolutionary Scale Modeling (ESM)?
ESM (Evolutionary Scale Modeling) is a collection of pretrained transformer language models specifically designed for protein sequences. It enables researchers to predict protein 3D structures, analyze variant effects, and design novel proteins using AI, directly from amino acid sequences without requiring multiple sequence alignments or experimental data.
Computational biologists, bioinformaticians, and protein engineers who need state-of-the-art AI tools for protein structure prediction, function analysis, and de novo protein design.
ESM provides open-source, cutting-edge protein language models that outperform other single-sequence methods, offer end-to-end structure prediction comparable to AlphaFold2, and enable novel protein design—all while being freely available and self-hostable.
Overview
Evolutionary Scale Modeling (esm): Pretrained language models for proteins
Use Cases
Best For
- Predicting protein 3D structures from single sequences without MSAs
Related Projects
Found a gem we're missing?
Open-Awesome is built by the community, for the community. Submit a project, suggest an awesome list, or help improve the catalog on GitHub.
