# Boltz

Structure prediction for protein, nucleic-acid, and small-molecule complexes with...

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

## Description

Structure prediction for protein, nucleic-acid, and small-molecule complexes with Boltz-2 (Passaro & Wohlwend et al. 2025, github.com/jwohlwend/boltz). Reach for this skill to validate designed binders against a target, to co-fold a protein with a SMILES or CCD ligand, or to get an open-source AlphaFold3 alternative with optional binding-affinity prediction.

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

# Boltz-2

Boltz-2 is the open-weights diffusion co-folder closest in surface to
AlphaFold3: a YAML describing protein, DNA, RNA, and ligand chains in, mmCIF
plus pTM/ipTM/pLDDT confidences out, with an optional small-molecule affinity
head. Among our four co-fold skills it is the default for binder-validation
campaigns, fully open MIT weights and the fastest sampler; pick `chai1` when
you want a second independent model for consensus, `openfold3` when AF3-faithful
settings matter, and `esmfold2` when you can live without an MSA. Code and
weights are MIT (PyPI `boltz`, github.com/jwohlwend/boltz).

## Running it

```yaml
# complex.yaml
version: 1
sequences:
  - protein:
      id: A
      sequence: MVTPEGNVSLVDESLLVGVTDEDRAVRS... # target
  - protein:
      id: B
      sequence: AIQRTPKIQVYSRHPAENG... # binder
  - ligand:
      id: L
      smiles: 'N[C@@H](Cc1ccc(O)cc1)C(=O)O' # or  ccd: SAH
```

```bash
boltz predict complex.yaml \
    --use_msa_server --out_dir out/ --recycling_steps 3 --diffusion_samples 5
```

Each protein chain needs an MSA; without one the run exits before the model
loads. `--use_msa_server` queries `api.colabfold.com` (expect a 30, 90 s pause
per chain) and is the right default unless you already have an `.a3m` to name
under `msa:` in the YAML. Setting `msa: empty` forces single-sequence mode, that is an accuracy sacrifice, not a speed or memory optimization, because the
MSA search runs on CPU before the GPU stage starts.

Per input the output lands at `out/boltz_results_complex/predictions/complex/`.
Read `confidence_complex_model_0.json` first: `iptm` > 0.5 is the community
pass line for an interface, `complex_plddt` > 0.7 for the fold itself, and
`confidence_score` is the weighted aggregate the structures are ranked by.
Structures themselves are `complex_model_{0..N-1}.cif` (or `.pdb` with
`--output_format pdb`).

## Affinity head

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