skills.rest
LiorZ
LiorZCOMMUNITY
Explore all skills by this author →
𝕏@LiorZmanGitHub

boltzgen

Generate ranked protein binder designs from YAML specifications using diffusion and inverse folding.

2|Updated May 12, 2026
Search Tags:#diffusion-model#inverse-folding#protein-design#binder-design#design-pipeline#biomolecular-design
One-click install
npx skills add https://github.com/LiorZ/protein-design-skills --skill boltzgen-liorz
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: boltzgen
Source: https://github.com/LiorZ/protein-design-skills/tree/main/skills/boltzgen
Command: npx skills add https://github.com/LiorZ/protein-design-skills --skill boltzgen-liorz

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

BoltzGen enables researchers to design and validate protein binders using a diffusion-based, end-to-end pipeline from a YAML specification, reducing manual trial-and-error in binder discovery.

Core Features & Use Cases

  • End-to-end binder design: from YAML to refolded, scored designs for proteins, peptides, antibodies, nanobodies, and small-molecule binders.
  • Inverse folding and folding with Boltz-2, affinity prediction for small molecules, and filtering to a final, diverse design set.
  • Use cases include de novo binder design, designing CDR loops, disulfide/staple chemistries, covalent ligands, and large campaigns on SLURM.

Quick Start

Run BoltzGen with a YAML spec to generate ranked binder designs against a target.

Frequently Asked Questions about boltzgen

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I design protein binders using a diffusion model from a YAML specification?▼

Protein binder design from a YAML specification is executed by running BoltzGen to apply diffusion, inverse folding, folding, and analysis steps, producing ranked final designs.

Can I generate antibody and nanobody binders against small-molecule targets?▼

You can generate antibody, nanobody, peptide, and small-molecule binders by applying BoltzGen across diverse targets, including affinity prediction for small molecules, to filter a final design set.

What do I need to run an end-to-end binder design pipeline?▼

Running the end-to-end binder design pipeline requires GPU-enabled hardware, a properly formatted BoltzGen YAML schema, and access to model weights to generate and filter designs.

Does this diffusion-based inverse folding pipeline support large campaigns on SLURM?▼

Large campaigns on SLURM are supported for designing CDR loops, covalent ligands, and disulfide chemistries by executing the pipeline across distributed computing resources.

How does diffusion-based binder design reduce manual trial-and-error?▼

Diffusion-based binder design reduces manual trial-and-error by automating the end-to-end workflow from a YAML specification to refolded, scored designs, validating protein binders systematically.

Are there limitations when designing disulfide or staple chemistries for protein binders?▼

Limitations depend on GPU-enabled hardware availability and model weights access; the pipeline processes disulfide and staple chemistries but requires correctly formatted YAML specifications to function.

Related Skills

Explore More Education & Research Skills→
adaptyvbioadaptyvbio
151

boltzgen

Automate all-atom protein design with diffusion models via YAML configuration.

Official
Advanced
alex-hhalex-hh

pgdh_ipsae

Score 15-PGDH binder designs using the ipSAE metric on Lyceum.

Community
Intermediate
Blake-JohnBlake-John

feishu-cli-auth

Manage Feishu OAuth 2.0 user access tokens with automatic refresh.

Community
Intermediate
adaptyvbioadaptyvbio
151

binder-design

Guide researchers in selecting protein binder design tools via a decision-tree workflow.

Official
Basic