{"id":"690ba5e7-9c06-4f95-b59f-0730bdf0fe32","shortId":"ubK9BS","kind":"skill","title":"protein-design-workflow","tagline":"End-to-end guidance for protein design pipelines. Use this skill when: (1) Starting a new protein design project, (2) Need step-by-step workflow guidance, (3) Understanding the full design pipeline, (4) Planning compute resources and timelines, (5) Integrating multiple design too","description":"# Protein Design Workflow Guide\n\n## Standard binder design pipeline\n\n### Overview\n```\nTarget Preparation --> Backbone Generation --> Sequence Design\n         |                     |                     |\n         v                     v                     v\n    (pdb skill)          (rfdiffusion)         (proteinmpnn)\n                               |                     |\n                               v                     v\n                        Structure Validation --> Filtering\n                               |                     |\n                               v                     v\n                         (alphafold/chai)      (protein-qc)\n```\n\n## Phase 1: Target preparation\n\n### 1.1 Obtain target structure\n```bash\n# Download from PDB\ncurl -o target.pdb \"https://files.rcsb.org/download/XXXX.pdb\"\n```\n\n### 1.2 Clean and prepare\n```python\n# Extract target chain\n# Remove waters, ligands if needed\n# Trim to binding region + 10A buffer\n```\n\n### 1.3 Select hotspots\n- Choose 3-6 exposed residues\n- Prefer charged/aromatic (K, R, E, D, W, Y, F)\n- Check surface accessibility\n- Verify residue numbering\n\n**Output**: `target_prepared.pdb`, hotspot list\n\n## Phase 2: Backbone generation\n\n### Option A: RFdiffusion (diverse exploration)\n```bash\nmodal run modal_rfdiffusion.py \\\n  --pdb target_prepared.pdb \\\n  --contigs \"A1-150/0 70-100\" \\\n  --hotspot \"A45,A67,A89\" \\\n  --num-designs 500\n```\n\n### Option B: BindCraft (end-to-end)\n```bash\nmodal run modal_bindcraft.py \\\n  --target-pdb target_prepared.pdb \\\n  --hotspots \"A45,A67,A89\" \\\n  --num-designs 100\n```\n\n**Output**: 100-500 backbone PDBs\n\n## Phase 3: Sequence design\n\n### For RFdiffusion backbones\n```bash\nfor backbone in backbones/*.pdb; do\n  modal run modal_proteinmpnn.py \\\n    --pdb-path \"$backbone\" \\\n    --num-seq-per-target 8 \\\n    --sampling-temp 0.1\ndone\n```\n\n**Output**: 8 sequences per backbone (800-4000 total)\n\n## Phase 4: Structure validation\n\n### Predict complexes\n```bash\n# Prepare FASTA with binder + target\n# binder:target format for multimer\n\nmodal run modal_colabfold.py \\\n  --input-faa all_sequences.fasta \\\n  --out-dir predictions/\n```\n\n**Output**: AF2 predictions with pLDDT, ipTM, PAE\n\n## Phase 5: Filtering and selection\n\n### Apply standard thresholds\n```python\nimport pandas as pd\n\n# Load metrics\ndesigns = pd.read_csv('all_metrics.csv')\n\n# Filter\nfiltered = designs[\n    (designs['pLDDT'] > 0.85) &\n    (designs['ipTM'] > 0.50) &\n    (designs['PAE_interface'] < 10) &\n    (designs['scRMSD'] < 2.0) &\n    (designs['esm2_pll'] > 0.0)\n]\n\n# Rank by composite score\nfiltered['score'] = (\n    0.3 * filtered['pLDDT'] +\n    0.3 * filtered['ipTM'] +\n    0.2 * (1 - filtered['PAE_interface'] / 20) +\n    0.2 * filtered['esm2_pll']\n)\n\ntop_designs = filtered.nlargest(50, 'score')\n```\n\n**Output**: 50-200 filtered candidates\n\n## Resource planning\n\n### Compute requirements\n\n| Stage | GPU | Time (100 designs) |\n|-------|-----|-------------------|\n| RFdiffusion | A10G | 30 min |\n| ProteinMPNN | T4 | 15 min |\n| ColabFold | A100 | 4-8 hours |\n| Filtering | CPU | 15 min |\n\n### Total timeline\n- Small campaign (100 designs): 8-12 hours\n- Medium campaign (500 designs): 24-48 hours\n- Large campaign (1000+ designs): 2-5 days\n\n## Quality checkpoints\n\n### After backbone generation\n- [ ] Visual inspection of diverse backbones\n- [ ] Secondary structure present\n- [ ] No clashes with target\n\n### After sequence design\n- [ ] ESM2 PLL > 0.0 for most sequences\n- [ ] No unwanted cysteines (unless intentional)\n- [ ] Reasonable sequence diversity\n\n### After validation\n- [ ] pLDDT > 0.85\n- [ ] ipTM > 0.50\n- [ ] PAE_interface < 10\n- [ ] Self-consistency RMSD < 2.0 A\n\n### Final selection\n- [ ] Diverse sequences (cluster if needed)\n- [ ] Manufacturable (no problematic motifs)\n- [ ] Reasonable molecular weight\n\n## Common issues\n\n| Problem | Solution |\n|---------|----------|\n| Low ipTM | Check hotspots, increase designs |\n| Poor diversity | Higher temperature, more backbones |\n| High scRMSD | Backbone may be unusual |\n| Low pLDDT | Check design quality |\n\n## Advanced workflows\n\n### Multi-tool combination\n1. RFdiffusion for initial backbones\n2. ColabDesign for refinement\n3. ProteinMPNN diversification\n4. AF2 final validation\n\n### Iterative refinement\n1. Run initial campaign\n2. Analyze failures\n3. Adjust hotspots/parameters\n4. Repeat with insights","tags":["protein","design","workflow","skills","adaptyvbio","agent-skills","claude-code","protein-design","protein-engineering"],"capabilities":["skill","source-adaptyvbio","skill-protein-design-workflow","topic-agent-skills","topic-claude-code","topic-protein-design","topic-protein-engineering"],"categories":["protein-design-skills"],"synonyms":[],"warnings":[],"endpointUrl":"https://skills.sh/adaptyvbio/protein-design-skills/protein-design-workflow","protocol":"skill","transport":"skills-sh","auth":{"type":"none","details":{"cli":"npx skills add adaptyvbio/protein-design-skills","source_repo":"https://github.com/adaptyvbio/protein-design-skills","install_from":"skills.sh"}},"qualityScore":"0.513","qualityRationale":"deterministic score 0.51 from registry signals: · indexed on github topic:agent-skills · 126 github stars · SKILL.md body (4,330 chars)","verified":false,"liveness":"unknown","lastLivenessCheck":null,"agentReviews":{"count":0,"score_avg":null,"cost_usd_avg":null,"success_rate":null,"latency_p50_ms":null,"narrative_summary":null,"summary_updated_at":null},"enrichmentModel":"deterministic:skill-github:v1","enrichmentVersion":1,"enrichedAt":"2026-05-02T12:54:48.896Z","embedding":null,"createdAt":"2026-04-18T22:10:11.494Z","updatedAt":"2026-05-02T12:54:48.896Z","lastSeenAt":"2026-05-02T12:54:48.896Z","tsv":"'-100':167 '-12':383 '-150':164 '-200':347 '-4000':242 '-48':390 '-5':397 '-500':201 '-6':125 '-8':370 '/0':165 '/download/xxxx.pdb':100 '0.0':317,421 '0.1':234 '0.2':330,336 '0.3':324,327 '0.50':306,438 '0.85':303,436 '1':18,84,331,495,513 '1.1':87 '1.2':101 '1.3':120 '10':310,441 '100':198,200,357,380 '1000':394 '10a':118 '15':365,374 '2':25,148,396,500,517 '2.0':313,446 '20':335 '24':389 '3':33,124,205,504,520 '30':361 '4':39,245,369,507,523 '5':45,280 '50':343,346 '500':175,387 '70':166 '8':230,237,382 '800':241 'a1':163 'a100':368 'a10g':360 'a45':169,192 'a67':170,193 'a89':171,194 'access':139 'adjust':521 'advanc':489 'af2':273,508 'all_metrics.csv':297 'all_sequences.fasta':267 'alphafold/chai':79 'analyz':518 'appli':284 'b':177 'backbon':61,149,202,210,213,215,224,240,402,408,477,480,499 'bash':91,156,183,211,250 'bind':116 'bindcraft':178 'binder':55,254,256 'buffer':119 'campaign':379,386,393,516 'candid':349 'chain':108 'charged/aromatic':129 'check':137,468,486 'checkpoint':400 'choos':123 'clash':413 'clean':102 'cluster':452 'colabdesign':501 'colabfold':367 'combin':494 'common':462 'complex':249 'composit':320 'comput':41,352 'consist':444 'contig':162 'cpu':373 'csv':296 'curl':95 'cystein':427 'd':133 'day':398 'design':3,12,23,37,48,51,56,64,174,197,207,294,300,301,304,307,311,314,341,358,381,388,395,418,471,487 'dir':270 'divers':154,407,432,450,473 'diversif':506 'done':235 'download':92 'e':132 'end':6,8,180,182 'end-to-end':5,179 'esm2':315,338,419 'explor':155 'expos':126 'extract':106 'f':136 'faa':266 'failur':519 'fasta':252 'files.rcsb.org':99 'files.rcsb.org/download/xxxx.pdb':98 'filter':76,281,298,299,322,325,328,332,337,348,372 'filtered.nlargest':342 'final':448,509 'format':258 'full':36 'generat':62,150,403 'gpu':355 'guid':53 'guidanc':9,32 'high':478 'higher':474 'hotspot':122,145,168,191,469 'hotspots/parameters':522 'hour':371,384,391 'import':288 'increas':470 'initi':498,515 'input':265 'input-faa':264 'insight':526 'inspect':405 'integr':46 'intent':429 'interfac':309,334,440 'iptm':277,305,329,437,467 'issu':463 'iter':511 'k':130 'larg':392 'ligand':111 'list':146 'load':292 'low':466,484 'manufactur':455 'may':481 'medium':385 'metric':293 'min':362,366,375 'modal':157,184,218,261 'modal_bindcraft.py':186 'modal_colabfold.py':263 'modal_proteinmpnn.py':220 'modal_rfdiffusion.py':159 'molecular':460 'motif':458 'multi':492 'multi-tool':491 'multim':260 'multipl':47 'need':26,113,454 'new':21 'num':173,196,226 'num-design':172,195 'num-seq-per-target':225 'number':142 'o':96 'obtain':88 'option':151,176 'out-dir':268 'output':143,199,236,272,345 'overview':58 'pae':278,308,333,439 'panda':289 'path':223 'pd':291 'pd.read':295 'pdb':68,94,160,189,216,222 'pdb-path':221 'pdbs':203 'per':228,239 'phase':83,147,204,244,279 'pipelin':13,38,57 'plan':40,351 'plddt':276,302,326,435,485 'pll':316,339,420 'poor':472 'predict':248,271,274 'prefer':128 'prepar':60,86,104,251 'present':411 'problem':464 'problemat':457 'project':24 'protein':2,11,22,50,81 'protein-design-workflow':1 'protein-qc':80 'proteinmpnn':71,363,505 'python':105,287 'qc':82 'qualiti':399,488 'r':131 'rank':318 'reason':430,459 'refin':503,512 'region':117 'remov':109 'repeat':524 'requir':353 'residu':127,141 'resourc':42,350 'rfdiffus':70,153,209,359,496 'rmsd':445 'run':158,185,219,262,514 'sampl':232 'sampling-temp':231 'score':321,323,344 'scrmsd':312,479 'secondari':409 'select':121,283,449 'self':443 'self-consist':442 'seq':227 'sequenc':63,206,238,417,424,431,451 'skill':16,69 'skill-protein-design-workflow' 'small':378 'solut':465 'source-adaptyvbio' 'stage':354 'standard':54,285 'start':19 'step':28,30 'step-by-step':27 'structur':74,90,246,410 'surfac':138 't4':364 'target':59,85,89,107,188,229,255,257,415 'target-pdb':187 'target.pdb':97 'target_prepared.pdb':144,161,190 'temp':233 'temperatur':475 'threshold':286 'time':356 'timelin':44,377 'tool':493 'top':340 'topic-agent-skills' 'topic-claude-code' 'topic-protein-design' 'topic-protein-engineering' 'total':243,376 'trim':114 'understand':34 'unless':428 'unusu':483 'unwant':426 'use':14 'v':65,66,67,72,73,77,78 'valid':75,247,434,510 'verifi':140 'visual':404 'w':134 'water':110 'weight':461 'workflow':4,31,52,490 'y':135","prices":[{"id":"05a3cad0-2b98-4136-b954-5d8db5e72246","listingId":"690ba5e7-9c06-4f95-b59f-0730bdf0fe32","amountUsd":"0","unit":"free","nativeCurrency":null,"nativeAmount":null,"chain":null,"payTo":null,"paymentMethod":"skill-free","isPrimary":true,"details":{"org":"adaptyvbio","category":"protein-design-skills","install_from":"skills.sh"},"createdAt":"2026-04-18T22:10:11.494Z"}],"sources":[{"listingId":"690ba5e7-9c06-4f95-b59f-0730bdf0fe32","source":"github","sourceId":"adaptyvbio/protein-design-skills/protein-design-workflow","sourceUrl":"https://github.com/adaptyvbio/protein-design-skills/tree/main/skills/protein-design-workflow","isPrimary":false,"firstSeenAt":"2026-04-18T22:10:11.494Z","lastSeenAt":"2026-05-02T12:54:48.896Z"}],"details":{"listingId":"690ba5e7-9c06-4f95-b59f-0730bdf0fe32","quickStartSnippet":null,"exampleRequest":null,"exampleResponse":null,"schema":null,"openapiUrl":null,"agentsTxtUrl":null,"citations":[],"useCases":[],"bestFor":[],"notFor":[],"kindDetails":{"org":"adaptyvbio","slug":"protein-design-workflow","github":{"repo":"adaptyvbio/protein-design-skills","stars":126,"topics":["agent-skills","claude-code","protein-design","protein-engineering"],"license":"mit","html_url":"https://github.com/adaptyvbio/protein-design-skills","pushed_at":"2026-01-19T13:06:29Z","description":"Claude Code skills for protein design","skill_md_sha":"0d194c761a40e4c43294b7a4d573e34d5ac061e0","skill_md_path":"skills/protein-design-workflow/SKILL.md","default_branch":"main","skill_tree_url":"https://github.com/adaptyvbio/protein-design-skills/tree/main/skills/protein-design-workflow"},"layout":"multi","source":"github","category":"protein-design-skills","frontmatter":{"name":"protein-design-workflow","license":"MIT","description":"End-to-end guidance for protein design pipelines. Use this skill when: (1) Starting a new protein design project, (2) Need step-by-step workflow guidance, (3) Understanding the full design pipeline, (4) Planning compute resources and timelines, (5) Integrating multiple design tools.  For tool selection, use binder-design. For QC thresholds, use protein-qc."},"skills_sh_url":"https://skills.sh/adaptyvbio/protein-design-skills/protein-design-workflow"},"updatedAt":"2026-05-02T12:54:48.896Z"}}