Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →xuzhougeng/esmfold2
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`.
Passed 22 of 22 test cases with the skill, and 9 of 22 without it.
and 17 more in the full report
13 fixed9 passed either way0 still failing0 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 13 test cases the skill fixed. Same model, same prompt, with and without the skill.
What default value for num_loops parameter corresponds to the standard folding trunk recycle count in the ESMFold2 publication?
| Checked | Without skill | With skill |
|---|---|---|
| Sets num_loops parameter to 10 | Missed | Passed |
The instructions your model reads when the skill loads.
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).
CUDA 12.x GPU (H100/A100-class); Python 3.12 only. Fresh venv; needs egress to HF Hub, GitHub, PyPI:
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.
For remote execution, install this version-pinned recipe on a selected and
probed direct SSH GPU context, then submit inference through
run_in_context. Wisp does not currently provide a Modal execution backend.
Gotchas:
None (reference PyTorch, ~12x slower than paper). Call model.set_kernel_backend('fused') after from_pretrained(). See section below.<2.8 targets CUDA 12.2.HF_HOME=/work/hf_cache.test cases passed, vs 9 / 22 without
Published skills whose descriptions closely match this one, with their headline benchmark lift.
More skills from the same source and nearby in the registry, with their headline benchmark lift.