pyrosetta-pack-design
/pyrosetta-pack-design
Projektuje sekwencje białek w PyRosetta: przepakowanie, skanowanie mutacji i ranking mutacji według wyniku.
- Autor
- ekko8600 ↗
- Repozytorium
- enzyme_design_harness ↗
- Licencja
- Apache-2.0
- Ostatnia zmiana repozytorium
- 08.11.2026
Ocena i bezpieczeństwo
- Pliki w paczce
- 7
- Skrypty
- 3
- Komentarze HTML
- 0
- Adresy URL w SKILL.md
- 0
Brak sygnałów. Repozytorium zmienione 08.11.2026, bez odwołań do wycofanych modeli i API.
Apache-2.0, otwarta: można używać i zmieniać, z zachowaniem licencji i informacji o zmianach.
- 3 skrypty w paczce. Przejrzyj je przed instalacją, bo Claude może je uruchomić.
Skrypty: scripts/pyrosetta_tools.py, scripts/saturation_scan.py, scripts/verify_mutation_results.py
Co robi i kiedy
Projektuje sekwencje białek w PyRosetta: przepakowanie, skanowanie mutacji i ranking mutacji według wyniku.
Oryginalny opis (EN)
Use PyRosetta packing and design workflows, including repacking, point mutation scans, resfile-guided design, and score-based mutation ranking. Use this skill for Rosetta sequence design around fixed or flexible backbones.
Jak działa
- Commands
- Decision Rules
- PyRosetta Performance Policy
- Independent mutation output checks
- Retained saturation scan
Podgląd SKILL.md
--- name: pyrosetta-pack-design description: 'Use PyRosetta packing and design workflows, including repacking, point mutation scans, resfile-guided design, and score-based mutation ranking. Use this skill for Rosetta sequence design around fixed or flexible backbones. ' metadata: category: design tags: pyrosetta, packing, design, mutation-scan, resfile legacy_category: design-tools taxonomy_version: enzyme-agent/taxonomy/v1 capability_ids: - design.molecular_design --- # PyRosetta Pack And Design Use this skill for side-chain packing and mutation/design scans. PyRosetta packing is CPU-bound. GPU hardware does not accelerate standard PyRosetta score functions, rotamer packing, or FastRelax. Use parallel processes and local repacking for saturation scans, then reserve relax for a shortlist. ## Commands Smoke test the local PyRosetta runtime: ```bash enzyme-core run pyrosetta-pack-design --work-dir ./runs/pyrosetta-pack-design --operation pyrosetta_tools -- smoke-test --relax ``` Point mutation scan by Pose position: ```bash enzyme-core run pyrosetta-pack-design --work-dir ./runs/pyrosetta-pack-design --operation pyrosetta_tools -- \ mutate-scan \ --pdb input.pdb \ --positions 35,42,88 \ --out out/pyrosetta-design/mutations.tsv ``` Parallel saturation/ddG scan by Pose position: ```bash enzyme-core run pyrosetta-pack-design --work-dir ./runs/pyrosetta-pack-design --operation pyrosetta_tools -- \ mutation-ddg-scan \ --pdb input.pdb \ --positions 35,42,88 \ --workers 8 \ --pack-radius 8 \ --skip-wt \ --resume \ --out out/pyrosetta-design/mutation_ddg.tsv ``` Repack side chains: ```bash enzyme-core run pyrosetta-pack-design --work-dir ./runs/pyrosetta-pack-design --operation pyrosetta_tools -- \ pack-design \ --pdb input.pdb \ --repack-only \ --out out/pyrosetta-design/repacked.pdb ``` ## Decision Rules - Mutation positions are Pose positions, not PDB residue numbers. - Use repacking for interface cleanup before scoring. - For full resfile design, create a task/resfile workflow explicitly rather than mutating unconstrained positions. - For saturation scans, prefer `mutation-ddg-scan` over serial `mutate-scan`. ## PyRosetta Performance Policy Standard PyRosetta/Rosetta score functions, rotamer packing, and FastRelax are CPU-bound and do not use GPU acceleration. For saturation mutagenesis, use the shared `mutation-ddg-scan` command with multiple CPU workers, local repacking, `--skip-wt`, and `--resume`; reserve FastRelax for shortlisted or conflicting mutations. ## Independent mutation output checks `verify_mutation_results` checks paired-panel or scan TSV outputs against the original PDB and a frozen JSON list of pose-numbered mutation strings. Paired-panel mode checks all WT/variant identities and all original backbone coordinates (0.001 A), seeds and nstruct coverage. Both modes check complete coverage and paired-score arithmetic. Read complete numeric output JSON. It does not recompute Rosetta energies or establish biological accuracy. ## Retained saturation scan `saturation_scan` uses a frozen mutations_file JSON list and input_pdb. It locally repacks per-site WT controls and mutants, saves every generated structure, scan.tsv and manifest.json. Controls are reused per site and identified explicitly. Primary scores are evaluated on exported/reloaded PDB coordinates; raw in-memory scores are separate fields. Use `verify_mutation_results`, mode=scan and require_structures=true, against the input PDB and the same expected mutation list. Report complete coverage and all failures; REU differences are not experimental ddG or activity.
Pliki w paczce (7)
- SKILL.md 4 KB
- execution_profile.json 1 KB
- scientific_contract.yaml 1 KB
- agents/openai.yaml 1 KB
- scripts/pyrosetta_tools.py 1 KB
- scripts/saturation_scan.py 5 KB
- scripts/verify_mutation_results.py 6 KB
Wersje
W bazie nie ma innych skilli o nazwie pyrosetta-pack-design.
Migawka bazy z 13.11.2026 · wersja paczki de19a73d1c49 (skrót SHA-256 całej paczki)
Pobrania w ostatnich 30 dniach: 0 · ranking
Zgłoś problem z tym skillem: szkodliwa treść, błędny opis albo prośba autora o usunięcie.
Podobne skille
- 100pyrosetta-scoring
Ocenia struktury białek funkcją punktową PyRosetta ref2015 i liczy energię interfejsu, dG, dSASA oraz komplementarność. - 100pyrosetta-relax-refine
Udoskonala struktury białek w PyRosetta przez FastRelax, minimalizację i generowanie decoys przed oceną. - 100protein-qc
Podaje metryki kontroli jakości i progi filtrowania dla projektowania białek: pLDDT, ipTM, PAE, ryzyka sekwencji, metryki interfejsu PyRosetta i właściwości biofizyczne. - 87invrotzyme
Składa zestawy miejsc aktywnych enzymu wokół ligandu z pliku ograniczeń Rosetta w PyRosetta, jako zarodki do projektowania enzymów. - 87bindcraft
Projektuje białka wiążące od zera, łącząc AF2, ProteinMPNN i filtry PyRosetta dla zadanego celu w PDB. - 100protein-qc
Dostarcza metryki kontroli jakości i progi filtrowania dla projektów białek, takie jak pLDDT, ipTM i PAE, oraz pułapki sekwencji.