AI-guided de novo protein design — RFdiffusion backbone generation, ProteinMPNN sequence design, structure validation (pLDDT, pTM, MPNN scores). Use for designing therapeutic protein binders, novel scaffolds, enzyme variants, and miniprotein/protein-interface design before experimental validation.

Therapeutic Protein Designer AI guided de novo protein design using RFdiffusion backbone generation, ProteinMPNN sequence optimization, and structure validation for therapeutic protein development. KEY PRINCIPLES : 1. Structure first Generate backbone geometry before sequence 2. Target guided Design binders with target structure in mind 3. Iterative validation Predict structure to validate designs 4. Developability aware Consider aggregation, immunogenicity, expression 5. Evidence separated Report folding, pose, geometry, protonation and experimental evidence independently 6. Actionable output Provide sequences ready for experimental testing 7. English first queries Always use English terms in tool calls Therapeutic protein design starts with the target interaction. What binding surface do you need to cover? A small pocket = nanobody or peptide. A large flat surface = designed protein. Stability, immunogenicity, and manufacturability constrain the design space. LOOK UP, DON'T GUESS When uncertain about any scientific fact, SEARCH databases first rather than reasoning from memory. A database verified answer is always more reliable than a guess. COMPUTE, DON'T DESCRIBE When analysis requires computation (statistics, data processing, scoring, enrichment), write and run Python code via Bash. Don't describe what you would do — execute it and report actual results. Use ToolUniverse tools to retrieve data, then Python (pandas, scipy, statsmodels, matplotlib) to analyze it. When to Use Apply when user asks to: Design a protein binder, therapeutic protein, or scaffold Optimize a protein sequence for function Design a de novo enzyme Generate protein variants for target binding Workflow Overview Critical Requirements For iterative campaigns, conflicting predictions, glycosylated receptor checks, conditional pH binding, or competition preparation, use [Protein Design Campaign](../tooluniverse protein design campaign/SKILL.md) alongside this workflow. Verify installed tool schemas before executing examples; model confidence and successful execution do not establish binding. Report First Approach (MANDATORY) 1. Create [TARGET] protein design report.md first with section headers 2. Progressively update as designs are generated 3. Output [TARGET] designed sequences.fasta and [TARGET] top candidates.csv Design Documentation (MANDATORY) Every design MUST include: Sequence, Length, Target, Method, and available Quality Metrics (pLDDT, pTM, MPNN score, binding prediction). Mark unavailable metrics unmeasured or uncomputed; do not fabricate binding predictions or experimental values. NVIDIA NIM Tools Tool Purpose Key Parameter NvidiaNIM rfdiffusion (requires NVIDIA API KEY env var; free key at build.nvidia.com) Backbone generation contigs + input pdb (both required), diffusion steps (NOT num steps ; default 15) NvidiaNIM proteinmpnn (requires NVIDIA API KEY env var; free key at build.nvidia.com) Sequence design input pdb (required; NOT pdb or pdb string ), num seq per target , sampling temp (a list) ESMFold predict structure Fast validation sequence (NOT seq ) NvidiaNIM alphafold2 (requires NVIDIA API KEY env var; free key at build.nvidia.com) High accuracy structure inference from sequence sequence , algorithm NvidiaNIM esm2 650m (requires NVIDIA API KEY env var; free key at build.nvidia.com) Sequence embeddings sequences , format Common Parameter Mistakes Tool Wrong Correct NvidiaNIM rfdiffusion (requires NVIDIA API KEY) num steps=50 diffusion steps=50 (plus required contigs and input pdb ) NvidiaNIM proteinmpnn (requires NVIDIA API KEY) pdb=content or pdb string=content input pdb=content ESMFold predict structure seq="MVLS..." sequence="MVLS..." NvidiaNIM alphafold2 (requires NVIDIA API KEY) seq="MVLS..." sequence="MVLS..." NVIDIA NIM Requirements API Key : NVIDIA API KEY environment variable required Rate limits : 40 RPM (1.5 second minimum between calls) AlphaFold2 may return 202 (polling required); RFdiffusion and ESMFold are synchronous Supporting Tools Tool Purpose Key Parameters PDBe get uniprot mappings Find PDB structures uniprot id RCSBData get entry Download PDB file pdb id alphafold get prediction Get AlphaFold DB structure accession EMDB search structures Search cryo EM maps query EMDB get structure Get entry details entry id UniProt get entry by accession Get target sequence accession InterPro get protein domains Get domains accession Folding and Developability Screening These are illustrative computational screening tiers, not binding evidence grades or calibrated success probabilities. Benchmark screening with appropriate controls. Monomer pLDDT/pTM cannot establish a complex pose, affinity, cross species binding or pH selectivity. Report those dimensions separately, including missing evidence. Tier Criteria T1 (strongest in this screen) pLDDT 85, pTM 0.8, low aggregation, neutral pI T2 pLDDT 75, pTM 0.7, acceptable developability T3 pLDDT 70, pTM 0.65, developability concerns T4 Failed validation or major developability issues Completeness Checklist [ ] Target structure obtained (PDB or predicted) [ ] Binding epitope identified [ ] = 5 backbones generated, top 3 5 selected [ ] = 8 sequences per backbone, MPNN scores reported [ ] All sequences validated (ESMFold), pLDDT/pTM reported, = 3 passing [ ] Developability assessed (aggregation, pI, expression) [ ] Ranked candidate list, FASTA file, experimental recommendations Reference Files DESIGN PROCEDURES.md Phase by phase code examples, sampling parameters, fallback chains TOOLS REFERENCE.md Complete tool documentation with code examples EXAMPLES.md Sample design workflows and outputs CHECKLIST.md Detailed phase checklists and quality metrics design templates.md Report templates and output format examples

tooluniverse-protein-therapeutic-design