---
license:
- mit
license_link: https://github.com/Biohub/esm/blob/main/THIRD_PARTY_NOTICE.md
language: en
tags:
- biology
- esm
- protein
- protein-structure-prediction
- structure-prediction
- protein-design
- 3d-structure
- confidence-estimation
- molecular-dynamics
- transformers
---

The ESMFold2 Experimental Models are being released to support reproducibility of the findings in our paper, please refer to [the paper](https://www.biorxiv.org/content/10.64898/2026.06.03.729735) and [github](https://github.com/Biohub/esm) for details. Please use [ESMFold2](https://huggingface.co/biohub/ESMFold2) model for research work. ESMFold2 predicts high-resolution, all-atom 3D protein structures from either single-sequence or MSA conditioned structure prediction for improved accuracy on difficult targets.