ProteinMPNN
SkillMediaYour AI can design protein sequences that fit a 3D backbone structure you already have. Once added, it can take on backbone-based sequence design tasks, suggest mutations, keep chosen residues unchanged, and filter the designs it produces.
Available today. Use it from your connected AI after setup.
No other account needed.
Add the skill, then give your AI a backbone structure and describe the design you want, including any residues that must stay fixed. It can then handle tasks that ask for sequence design, mutation suggestions, or design filtering.
Then ask your AI: use the ProteinMPNN skill
What your AI can do with it
- Design protein sequences that fit a given 3D backbone structure
- Suggest mutations to a protein sequence
- Keep chosen residues fixed while designing the rest of the sequence
- Filter sequence designs to narrow down the candidates
What this skill tells your AI
The instructions your AI receives, as published by companion-inc/feynman in skills/proteinmpnn/SKILL.md and read by ahel’s review.
Use this skill for fixed-backbone protein sequence design.
Workflow:
- Record input structure, chain ids, designed positions, fixed residues, tied positions, symmetry, and design objective.
- Verify the local or remote execution route before running.
- Save PDB/mmCIF inputs, design masks, command, seeds, model version, FASTA outputs, and score tables.
- Filter designs by constraints, diversity, motifs, structure prediction, conservation, and assay-ready feasibility.
- Attach provenance and a verification plan before recommending candidates.
Treat generated sequences as candidates that require structural and experimental validation.
Signals
- GitHub stars
- 9k
- Forks
- 1k
- Last commit
- Sep 2026
Advanced
- Catalog kind
- skill
- Gateway key
proteinmpnn-companion-inc- Source
- github.com/companion-inc/feynman