Agent skill

boltz

Structure prediction using Boltz-1/Boltz-2, an open biomolecular structure predictor. Use this skill when: (1) Predicting protein complex structures, (2) Validating designed binders, (3) Need open-source alternative to AF2, (4) Predicting protein-ligand complexes, (5) Using local GPU resources. For QC thresholds, use protein-qc. For AlphaFold2 prediction, use alphafold. For Chai prediction, use chai.

View SKILL.md on GitHub Repository
Stars 125
Forks 14

Install this agent skill to your Project

npx add-skill https://github.com/adaptyvbio/protein-design-skills/tree/main/skills/boltz

SKILL.md

Boltz Structure Prediction

Prerequisites

Requirement Minimum Recommended
Python 3.10+ 3.11
CUDA 12.0+ 12.1+
GPU VRAM 24GB 48GB (L40S)
RAM 32GB 64GB

How to run

First time? See Installation Guide to set up Modal and biomodals.

Option 1: Modal

bash
cd biomodals
modal run modal_boltz.py \
  --input-faa complex.fasta \
  --out-dir predictions/

GPU: L40S (48GB) | Timeout: 1800s default

Option 2: Local installation

bash
pip install boltz

boltz predict \
  --fasta complex.fasta \
  --output predictions/

Key parameters

Parameter Default Range Description
--recycling_steps 3 1-10 Recycling iterations
--sampling_steps 200 50-500 Diffusion steps
--use_msa_server true bool Use MSA server

FASTA Format

>protein_A
MKTAYIAKQRQISFVK...
>protein_B
MVLSPADKTNVKAAWG...

Output format

predictions/
├── model_0.cif       # Best model (CIF format)
├── confidence.json   # pLDDT, pTM, ipTM
└── pae.npy          # PAE matrix

Note: Boltz outputs CIF format. Convert to PDB if needed:

python
from Bio.PDB import MMCIFParser, PDBIO
parser = MMCIFParser()
structure = parser.get_structure("model", "model_0.cif")
io = PDBIO()
io.set_structure(structure)
io.save("model_0.pdb")

Comparison

Feature Boltz-1 Boltz-2 AF2-Multimer
MSA-free mode Yes Yes No
Diffusion Yes Yes No
Speed Fast Faster Slower
Open source Yes Yes Yes

Sample output

Successful run

$ boltz predict --fasta complex.fasta --output predictions/
[INFO] Loading Boltz-1 weights...
[INFO] Predicting structure...
[INFO] Saved model to predictions/model_0.cif

predictions/confidence.json:
{
  "ptm": 0.78,
  "iptm": 0.65,
  "plddt": 0.81
}

What good output looks like:

  • pTM: > 0.7 (confident global structure)
  • ipTM: > 0.5 (confident interface)
  • pLDDT: > 0.7 (confident per-residue)
  • CIF file: ~100-500 KB for typical complex

Decision tree

Should I use Boltz?
│
├─ What are you predicting?
│  ├─ Protein-protein complex → Boltz ✓ or Chai or ColabFold
│  ├─ Protein + ligand → Boltz ✓ or Chai
│  └─ Single protein → Use ESMFold (faster)
│
├─ Need MSA?
│  ├─ No / want speed → Boltz ✓
│  └─ Yes / maximum accuracy → ColabFold
│
└─ Why Boltz over Chai?
   ├─ Open weights preference → Boltz ✓
   ├─ Boltz-2 speed → Boltz ✓
   └─ DNA/RNA support → Consider Chai

Typical performance

Campaign Size Time (L40S) Cost (Modal) Notes
100 complexes 30-45 min ~$8 Standard validation
500 complexes 2-3h ~$35 Large campaign
1000 complexes 4-6h ~$70 Comprehensive

Per-complex: ~15-30s for typical binder-target complex.

Verify

bash
find predictions -name "*.cif" | wc -l  # Should match input count

Troubleshooting

Low confidence: Increase recycling_steps OOM errors: Use MSA-free mode or A100-80GB Slow prediction: Reduce sampling_steps

Error interpretation

Error Cause Fix
RuntimeError: CUDA out of memory Complex too large Use --use_msa_server false or larger GPU
KeyError: 'iptm' Single chain only Ensure FASTA has 2+ chains
FileNotFoundError: weights Missing model Run boltz download first
ValueError: invalid residue Non-standard AA Check for modified residues in sequence

Boltz-1 vs Boltz-2

Aspect Boltz-1 Boltz-2
Speed Fast ~2x faster
Accuracy Good Improved
Ligands Basic Better support
Release 2024 Late 2024

Next: protein-qc for filtering and ranking.

Recommended Agent Skills

Expand your agent's capabilities with these related and highly-rated skills.

adaptyvbio/protein-design-skills

proteinmpnn

Design protein sequences using ProteinMPNN inverse folding. Use this skill when: (1) Designing sequences for RFdiffusion backbones, (2) Redesigning existing protein sequences, (3) Fixing specific residues while designing others, (4) Optimizing sequences for expression or stability, (5) Multi-state or negative design. For backbone generation, use rfdiffusion or bindcraft. For ligand-aware design, use ligandmpnn. For solubility optimization, use solublempnn.

125 14
Explore
adaptyvbio/protein-design-skills

campaign-manager

Goal-oriented binder design campaign planning and health assessment. Use this skill when: (1) Planning a complete binder design campaign, (2) Converting high-level goals into runnable pipelines, (3) Assessing campaign health and pass rates, (4) Diagnosing why designs are failing QC, (5) Estimating time, cost, and expected yields, (6) Selecting between design tools for a specific target. This skill orchestrates the other protein design tools. For individual tool parameters, use the specific tool skills.

125 14
Explore
adaptyvbio/protein-design-skills

esm

ESM2 protein language model for embeddings and sequence scoring. Use this skill when: (1) Computing pseudo-log-likelihood (PLL) scores, (2) Getting protein embeddings for clustering, (3) Filtering designs by sequence plausibility, (4) Zero-shot variant effect prediction, (5) Analyzing sequence-function relationships. For structure prediction, use chai or boltz. For QC thresholds, use protein-qc.

125 14
Explore
adaptyvbio/protein-design-skills

binding-characterization

Guidance for SPR and BLI binding characterization experiments. Use when: (1) Planning binding kinetics experiments, (2) Troubleshooting poor/no binding signal, (3) Interpreting kinetic data artifacts, (4) Choosing between SPR vs BLI platforms.

125 14
Explore
adaptyvbio/protein-design-skills

cell-free-expression

Guidance for cell-free protein synthesis (CFPS) optimization. Use when: (1) Planning CFPS experiments, (2) Troubleshooting low yield or aggregation, (3) Optimizing DNA template design for CFPS, (4) Expressing difficult proteins (disulfide-rich, toxic, membrane).

125 14
Explore
adaptyvbio/protein-design-skills

ligandmpnn

Ligand-aware protein sequence design using LigandMPNN. Use this skill when: (1) Designing sequences around small molecules, (2) Enzyme active site design, (3) Ligand binding pocket optimization, (4) Metal coordination site design, (5) Cofactor binding proteins. For standard protein design, use proteinmpnn. For solubility optimization, use solublempnn.

125 14
Explore

Didn't find tool you were looking for?

Be as detailed as possible for better results