SolubleMPNN
SkillMediaOnce added, your AI can design new protein sequences and check existing ones for solubility, meaning how likely they are to be produced in a usable form. It follows structured design workflows, so tasks like creating soluble proteins or expression-friendly variants are handled step by step. It can also filter out sequences that carry solubility risk.
Available today. Use it from your connected AI after setup.
No other account needed.
After adding it, describe the protein you want to design or the sequences you want checked, and mention if solubility is the priority. The AI will then run the matching design or screening workflow.
Then ask your AI: use the SolubleMPNN skill
What your AI can do with it
- Design protein sequences with solubility-aware constraints
- Screen existing sequences for solubility risk
- Create expression-friendly protein variants
- Filter out candidate sequences with solubility problems
- Work through structured, step-by-step design workflows
What this skill tells your AI
The instructions your AI receives, as published by companion-inc/feynman in skills/solublempnn/SKILL.md and read by ahel’s review.
Use this skill for solubility-aware protein design.
Workflow:
- Record input structure or sequence, design positions, expression system, forbidden motifs, and stability/solubility constraints.
- Verify model availability and execution path before running.
- Save input files, masks, command, model version, generated sequences, scores, and filtering tables.
- Filter candidates for hydrophobic patches, charge balance, repeats, liabilities, conservation, and structure-confidence impact.
- Attach assay or expression-screen recommendations when a decision depends on solubility.
Do not equate a solubility score with confirmed expression.
Signals
- GitHub stars
- 9k
- Forks
- 1k
- Last commit
- Sep 2026
Advanced
- Catalog kind
- skill
- Gateway key
solublempnn-companion-inc- Source
- github.com/companion-inc/feynman