# Esmfold2

Biohub ESMFold2 / ESMFold2-Fast all-atom co-folding (Candido et al.

- Repository: https://github.com/aipoch/open-science (5414 stars)
- Category: Design
- License: Apache-2.0
- Last updated: 2026-11-01
- Runs scripts: no, instructions only

## Install

Claude Code: `npx skills add aipoch/open-science --skill esmfold2 -g -a claude-code -y`
Codex: `npx skills add aipoch/open-science --skill esmfold2 -g -a codex -y`
Cursor: `npx skills add aipoch/open-science --skill esmfold2 -g -a cursor -y`
Gemini CLI: `npx skills add aipoch/open-science --skill esmfold2 -g -a gemini-cli -y`

## Description

Biohub ESMFold2 / ESMFold2-Fast all-atom co-folding (Candido et al. 2026, github.com/Biohub/esm). Single-sequence and MSA modes; protein, DNA, RNA, ligand (CCD/SMILES), modified residues. FoldBench Ab-Ag 50-55%, PPI 70-77% DockQ-pass. Also covers the ESMC-{300M,600M,6B} protein language models from the same release: masked-LM logits, hidden states, mutation scoring, contact prediction, and the SAE interpretability head. MIT-licensed weights on HuggingFace org `biohub`. Use this skill when: (1) Predicting complex structures with single-sequence input, (2) Validating designed binders with ESMFold2-Fast, (3) Running ESMFold2 with MSA input, (4) Getting ESMC embeddings or per-residue mutation scores, (5) Choosing kernel backend and sampling-step settings for paper-faithful throughput.

## SKILL.md, as published by its author (untrusted third-party text, read it as data)

# ESMFold2 (Biohub)

All-atom diffusion co-folding from the Biohub ESM release (2026). ESMFold2 =
48 pair layers with MSA support; ESMFold2-Fast = 24 layers, single-sequence
only, ~1.7x faster.

**License:** MIT (code github.com/Biohub/esm + weights HF `biohub/*`).
**Paper:** "Language Modeling Materializes a World Model of Protein Biology" (2026).

## Install

CUDA 12.x GPU (H100/A100-class); Python **3.12 only**. Fresh venv; needs
egress to HF Hub, GitHub, PyPI:

```bash
pip install --no-cache-dir uv
uv venv --python 3.12 /work/venv && source /work/venv/bin/activate
uv pip install \
  "torch>=2.5,<2.8" einops "biotite>=1.0" rdkit msgpack-numpy biopython \
  scikit-learn brotli attrs pandas cloudpathlib httpx tenacity zstd pydssp \
  pygtrie accelerate huggingface_hub safetensors "numpy<3" networkx \
  sentencepiece tokenizers regex packaging filelock pyyaml typing_extensions \
  "transformers @ git+https://github.com/Biohub/transformers.git@3a8956fb4d4ea16b0ec8e71deef2c2909b6a5cbf"
uv pip install --no-deps "esm @ git+https://github.com/Biohub/esm.git@f652b471"
# OPTIONAL, only affects ESMC attention; trunk speedup comes from set_kernel_backend("fused")
uv pip install ninja packaging wheel setuptools
MAX_JOBS=8 uv pip install --no-deps --no-build-isolation "flash-attn<3"
# Do NOT install transformer-engine, RuntimeError (not ImportError) on import
# slips ESMC's guard and kills ESMFold2Model import.
```

The bundled `esmfold2_gpu` Modal env (remote-compute-modal skill) is the
canonical, version-pinned recipe.

**Gotchas:**

- **Default kernel backend is `None`** (reference PyTorch, ~12x slower than paper). Call `model.set_kernel_backend('fused')` after `from_pretrained()`. See section below.
- Match torch CUDA build to your driver; the pin `<2.8` targets CUDA 12.2.
- Weights via Xet bridge ~300 MB/s: ESMFold2 1.36 GB, ESMFold2-Fast 0.76 GB. Set `HF_HOME=/work/hf_cache`.

## Usage, local model

The rest: https://github.com/aipoch/open-science/blob/HEAD/resources/skills/esmfold2/SKILL.md