[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6DAR5VY1NBAGCEG8WT6HST3":3,"skill-same:01M6DAR5VY1NBAGCEG8WT6HST3":67},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":16,"categories":17,"keywords":23,"publishedAt":36,"linkOnly":37,"markdownContent":38,"markdownBody":39,"frontMatter":40,"refName":41,"commitSha":42,"skillDirectory":43,"forksCount":14,"repositoryHtmlUrl":44,"repositoryHomepageUrl":6,"ownerHtmlUrl":45,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":46,"install":47,"resources":60},"01M6DAR5VY1NBAGCEG8WT6HST3","tooluniverse-gpcr-structural-pharmacology",null,"Research GPCR receptors, antibody structures, and protein interface analysis using GPCRdb, SAbDab, and PDBePISA. Retrieves receptor families, known ligands (agonists\u002Fantagonists\u002Fbiased), mutations, crystal\u002Fcryo-EM structures, antibody CDR annotations, and protein-protein interface geometry. Use when asked about GPCR drug targets, receptor-ligand interactions, antibody structural data, or protein assembly interfaces.","Prekzursil\u002Fagent-skills-toolchain","Prekzursil","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F54636077?v=4","01M6DACZ1PCQHD99SCR1YXG28B","Andrei Mihai Visalon","01M6DACZ670WZF535V3WYYSS4Z",0,"MIT","https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002F.agents\u002Flibrary\u002Fskills\u002Ftooluniverse-gpcr-structural-pharmacology\u002FSKILL.md",[18],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000021","资料检索与研究","SCENARIO","使用场景",[24,25,26,27,28,29,30,31,32,33,34,35],"structural","tooluniverse gpcr structural pharmacology","research","data","CDR","analysis","annotations","use","assembly","mutations","geometry","crystal","2026-11-10 10:12:30",false,"---\nname: tooluniverse-gpcr-structural-pharmacology\ndescription: >\n  Research GPCR receptors, antibody structures, and protein interface analysis using GPCRdb, SAbDab, and PDBePISA. Retrieves receptor families, known ligands (agonists\u002Fantagonists\u002Fbiased), mutations, crystal\u002Fcryo-EM structures, antibody CDR annotations, and protein-protein interface geometry. Use when asked about GPCR drug targets, receptor-ligand interactions, antibody structural data, or protein assembly interfaces.\n---\n\n# GPCR and Structural Pharmacology Research\n\n**GPCR pharmacology**: agonist vs antagonist vs inverse agonist vs biased agonist — each has different clinical implications. Biased agonism (preferential G-protein vs β-arrestin signaling) can separate efficacy from side effects; for example, G-protein-biased opioid agonists aim to retain analgesia while reducing β-arrestin-mediated respiratory depression. Always classify retrieved ligands by their pharmacological type, not just their chemical structure. Receptor state (active vs inactive crystal structure) determines which ligands and mutations are interpretable — an inactive-state structure is appropriate for antagonist binding analysis, active-state for agonist-bound complexes. Generic GPCR numbering (Ballesteros-Weinstein) enables cross-receptor mutation comparison; always report positions in this system alongside sequence positions.\n\n**LOOK UP DON'T GUESS**: never assume GPCRdb entry names (e.g., `adrb2_human`) or PDB IDs — always use `GPCRdb_list_proteins` to find the correct entry name and `GPCRdb_get_structures` to confirm available structures.\n\nResearch skill integrating GPCRdb (GPCR receptor biology), SAbDab (antibody structures), and PDBePISA (protein interface analysis) to support structural pharmacology, antibody engineering, and GPCR-targeted drug discovery.\n\n**KEY PRINCIPLES**:\n1. **Receptor-first** — Identify GPCR entry name before any GPCRdb queries\n2. **Ligand classification** — Distinguish agonists, antagonists, partial agonists, biased agonists\n3. **Structure-guided** — Pair GPCRdb mutation data with PDB structures via PDBePISA\n4. **Antibody context** — Use SAbDab for therapeutic antibody structure retrieval and CDR analysis\n5. **English-first queries** — Use standard receptor names (e.g., \"beta-2 adrenergic receptor\") in searches; convert to GPCRdb entry names for API calls\n\n---\n\n## When to Use\n\nApply when user asks:\n- \"What ligands are known for [GPCR receptor]?\"\n- \"What crystal structures exist for [receptor]?\"\n- \"Find antibody structures targeting [antigen]\"\n- \"Analyze the protein-protein interface in PDB [ID]\"\n- \"What mutations affect [GPCR] function or pharmacology?\"\n- \"Which GPCRs are in the [family] family?\"\n- \"What are the CDR loops in antibody PDB [ID]?\"\n- \"What is the biological assembly for [PDB ID]?\"\n\n---\n\n## Tool Parameter Reference (CRITICAL)\n\n| Tool | Key Parameters | Notes |\n|------|---------------|-------|\n| `GPCRdb_get_protein` | `protein` | GPCRdb entry name (e.g., `adrb2_human`), NOT gene symbol or UniProt accession |\n| `GPCRdb_list_proteins` | `family` (optional), `protein_class` (optional) | Lists all GPCRs; filter by family slug (e.g., `\"adrenoceptors\"`) OR by human-readable class name via `protein_class` (e.g., `\"chemokine receptors\"`, `\"opioid receptors\"`) |\n| `GPCRdb_get_structures` | `protein` (optional), `state` (optional) | `state`: `\"active\"`, `\"inactive\"`, `\"intermediate\"` |\n| `GPCRdb_get_ligands` | `protein` | Returns agonists, antagonists, biased ligands with affinities |\n| `GPCRdb_get_mutations` | `protein` | Returns mutation effects on receptor function and ligand binding |\n| `SAbDab_search_structures` | `query` | Antigen name, species, or keywords; returns browse URL + metadata |\n| `SAbDab_get_structure` | `pdb_id` | 4-character PDB code (e.g., `\"6W41\"`); returns CDR annotations |\n| `SAbDab_get_summary` | (no required params) | Database statistics and summary |\n| `PDBePISA_get_interfaces` | `pdb_id` | 4-character PDB code; returns all interface pairs with buried area |\n| `PDBePISA_get_assemblies` | `pdb_id` | Predicted biological assemblies from crystal packing |\n| `PDBePISA_get_monomer_analysis` | `pdb_id` | Per-chain solvent-accessible surface area (SASA) breakdown |\n\n### GPCRdb Entry Name Format\n\nGPCRdb uses its own entry name format: `{receptor_slug}_{species}`. Common examples:\n- Beta-2 adrenergic receptor: `adrb2_human`\n- Beta-1 adrenergic receptor: `adrb1_human`\n- Mu-opioid receptor: `oprm1_human`\n- Dopamine D2 receptor: `drd2_human`\n- Glucagon-like peptide-1 receptor: `glp1r_human`\n- CXCR4 chemokine receptor: `cxcr4_human`\n\nIf entry name is unknown, use `GPCRdb_list_proteins()` to browse and find the correct slug. You can also filter by receptor class using the `protein_class` parameter with a human-readable name — e.g., `GPCRdb_list_proteins(protein_class=\"chemokine receptors\")` — instead of the numeric family slug. Both `family` and `protein_class` are accepted and serve overlapping purposes; prefer `protein_class` when the user provides a receptor class name.\n\n---\n\n## Workflow Overview\n\n```\nPhase 1: Receptor Identification (for GPCR queries)\n  -> GPCRdb_list_proteins: find receptor family and entry name\n  -> GPCRdb_get_protein: receptor details, family, species\n\nPhase 2: Ligand Landscape\n  -> GPCRdb_get_ligands: all known ligands by pharmacology class\n  -> Cross-reference with ChEMBL\u002FPubChem for chemical properties\n\nPhase 3: Structural Data\n  -> GPCRdb_get_structures: available PDB\u002FEMDB structures with resolution\n  -> PDBePISA_get_interfaces: interface analysis on best structure\n  -> PDBePISA_get_assemblies: biological assembly determination\n\nPhase 4: Mutation & Pharmacology Data\n  -> GPCRdb_get_mutations: pharmacological mutation map\n  -> Compare to ligand binding sites from structure\n\nPhase 5: Antibody Structures (for antibody queries)\n  -> SAbDab_search_structures: find structures by antigen\n  -> SAbDab_get_structure: CDR annotations, chain details\n  -> PDBePISA_get_interfaces: antibody-antigen interface analysis\n```\n\n---\n\n## Phase 1: GPCR Receptor Identification\n\n```python\n# List all GPCRs in a family to find entry name (by slug)\nfamily_list = GPCRdb_list_proteins(family=\"adrenoceptors\")\n\n# Filter by human-readable class name (new -- preferred when user says e.g. \"chemokine receptors\")\nchemokine_list = GPCRdb_list_proteins(protein_class=\"chemokine receptors\")\n\n# Browse all GPCRs (no family filter)\nall_gpcrs = GPCRdb_list_proteins()\n\n# Get detailed protein info once you have the entry name\nreceptor = GPCRdb_get_protein(protein=\"adrb2_human\")\n# Returns: family classification, endogenous ligands, tissue expression,\n#          GPCRdb-specific annotations, sequence features\n```\n\n## Phase 2: Ligand Landscape\n\n```python\n# Get all known ligands for a GPCR\nligands = GPCRdb_get_ligands(protein=\"adrb2_human\")\n# Returns: ligand names, types (agonist\u002Fantagonist\u002Fpartial\u002Fbiased\u002Fallosteric),\n#          binding affinities (Ki, IC50, EC50), references\n\n# Ligand type classification:\n# - Agonist: activates receptor\n# - Antagonist\u002FInverse agonist: blocks or suppresses receptor\n# - Partial agonist: submaximal activation\n# - Biased agonist: selective signaling (Gs vs. beta-arrestin bias)\n# - Positive\u002FNegative allosteric modulator (PAM\u002FNAM)\n```\n\nAfter retrieving ligands from GPCRdb, optionally cross-reference with:\n- `PubChem_get_CID_by_compound_name(compound_name=ligand_name)` — get CID, SMILES\n- `ChEMBL_search_molecules(query=ligand_name)` — get ChEMBL ID, bioactivity data\n\n## Phase 3: Structural Data\n\n```python\n# Get available crystal\u002Fcryo-EM structures\nstructures = GPCRdb_get_structures(protein=\"adrb2_human\", state=\"inactive\")\n# state options: \"active\", \"inactive\", \"intermediate\" (omit for all)\n# Returns: PDB IDs, resolution, ligand in structure, publication info\n\n# Analyze a specific structure's interfaces\ninterfaces = PDBePISA_get_interfaces(pdb_id=\"2rh1\")  # adrb2 inactive structure\n# Returns: interface pairs, buried solvent-accessible area (BSA),\n#          interface residues, hydrogen bonds, salt bridges\n\n# Determine biological assembly\nassemblies = PDBePISA_get_assemblies(pdb_id=\"2rh1\")\n# Returns: predicted oligomeric state, assembly stability score,\n#          subunit composition\n\n# Per-chain SASA breakdown\nmonomers = PDBePISA_get_monomer_analysis(pdb_id=\"2rh1\")\n# Returns: accessible\u002Fburied surface area per chain\n```\n\n**Interface Analysis Interpretation**:\n- BSA > 1500 Ų: Strong interface (likely biologically relevant)\n- BSA 800-1500 Ų: Moderate interface\n- BSA \u003C 800 Ų: Weak or crystal contact\n\n## Phase 4: Mutation Data\n\n```python\n# Get all mutations characterized for a GPCR\nmutations = GPCRdb_get_mutations(protein=\"adrb2_human\")\n# Returns: mutation positions (generic GPCR numbering), effects on:\n#   - Expression\u002Ffolding\n#   - Ligand binding (affinity changes)\n#   - G-protein coupling\n#   - Receptor activation\n\n# Generic GPCR numbering (Ballesteros-Weinstein):\n# e.g., 3.32 = position 32 in TM helix 3 — conserved across GPCR classes\n```\n\n## Phase 5: Antibody Structure Retrieval\n\n```python\n# Search SAbDab for antibody structures by antigen\nresults = SAbDab_search_structures(query=\"EGFR\", limit=20)\n# Returns: browse URL + metadata table of matching structures\n\n# Get detailed annotations for a specific antibody structure\nstructure = SAbDab_get_structure(pdb_id=\"1IQD\")\n# Returns: VH\u002FVL chain IDs, CDR1-3 (Kabat\u002FIMGT), antigen info,\n#          heavy\u002Flight chain types, resolution\n\n# Get database overview\nsummary = SAbDab_get_summary()\n# Returns: total structures, species breakdown, antigen coverage stats\n```\n\n**CDR Analysis**:\n- CDR-H3 is most variable and typically dominates antigen contact\n- CDR length distribution: SAbDab provides Kabat, Chothia, and IMGT numbering\n- After retrieving SAbDab structure, use `PDBePISA_get_interfaces(pdb_id=...)` to compute antibody-antigen buried surface area\n\n---\n\n## Common Research Patterns\n\n### Pattern 1: GPCR Drug Target Profiling\n```\nInput: GPCR name (e.g., \"GLP-1 receptor\")\nFlow: GPCRdb_list_proteins -> find \"glp1r_human\" ->\n      GPCRdb_get_protein (receptor details) ->\n      GPCRdb_get_ligands (approved + investigational drugs) ->\n      GPCRdb_get_structures (available PDB structures) ->\n      PDBePISA_get_interfaces on best structure ->\n      GPCRdb_get_mutations (pharmacological mutants)\nOutput: Complete GPCR pharmacology profile with structural context\n```\n\n### Pattern 2: Antibody-Antigen Interface Analysis\n```\nInput: Target antigen (e.g., \"PD-L1\") or specific PDB code\nFlow: SAbDab_search_structures(query=\"PD-L1\") ->\n      SAbDab_get_structure(pdb_id=\"best hit\") (CDR annotations) ->\n      PDBePISA_get_interfaces(pdb_id=...) (buried area, key contacts) ->\n      PDBePISA_get_assemblies (assembly context)\nOutput: CDR sequences, epitope contact residues, interface energetics\n```\n\n### Pattern 3: GPCR Family Survey\n```\nInput: Drug class question (e.g., \"beta-adrenergic receptors\")\nFlow: GPCRdb_list_proteins(family=\"adrenoceptors\") ->\n      GPCRdb_get_protein per receptor (adrb1\u002F2\u002F3) ->\n      GPCRdb_get_ligands per receptor (selectivity landscape) ->\n      GPCRdb_get_structures per receptor (structural coverage)\nOutput: Family-wide selectivity map, structural availability, ligand classes\n```\n\n### Pattern 4: Structure Interface Characterization\n```\nInput: PDB code\nFlow: PDBePISA_get_assemblies (oligomeric state) ->\n      PDBePISA_get_interfaces (all interface pairs ranked by BSA) ->\n      PDBePISA_get_monomer_analysis (per-chain surface burial)\nOutput: Biologically relevant assembly, key interface residues, buried areas\n```\n\n---\n\n## Tool Combinations with Other Skills\n\nThis skill complements other ToolUniverse skills:\n\n| Goal | This skill provides | Complement with |\n|------|--------------------|--------------------|\n| GPCR drug discovery | Receptor\u002Fligand\u002Fstructure data | `tooluniverse-binder-discovery` for virtual screening |\n| Antibody engineering | SAbDab structure + CDR data | `tooluniverse-antibody-engineering` for optimization |\n| Variant impact on GPCR | GPCRdb mutation effects | `tooluniverse-variant-functional-annotation` for ACMG |\n| Target validation | GPCR expression, ligand data | `tooluniverse-drug-target-validation` |\n| PDB structure analysis | PDBePISA interfaces | `tooluniverse-protein-structure-retrieval` for RCSB\u002FPDBe |\n\n---\n\n## Fallback Chains\n\n| Primary Tool | Fallback | Use When |\n|-------------|----------|----------|\n| `GPCRdb_get_protein` | UniProt search + PubMed | Entry name unknown or non-GPCR target |\n| `GPCRdb_get_ligands` | ChEMBL bioactivity search | Receptor not in GPCRdb |\n| `GPCRdb_get_structures` | RCSB PDB text search | Structures not yet in GPCRdb |\n| `SAbDab_search_structures` | RCSB PDB antibody search | Antigen not indexed in SAbDab |\n| `PDBePISA_get_interfaces` | PDBe graph API | PDBePISA returns no interfaces |\n\n---\n\n## Completeness Checklist\n\nFor GPCR profiling:\n- [ ] Entry name resolved via `GPCRdb_list_proteins` or `GPCRdb_get_protein`\n- [ ] Receptor family and class documented\n- [ ] Ligand landscape retrieved with pharmacology types\n- [ ] Available structures listed with resolution and state\n- [ ] Best structure analyzed with PDBePISA (interfaces + assembly)\n- [ ] Mutation data retrieved for pharmacological context\n\nFor antibody structure:\n- [ ] SAbDab search run with antigen name\n- [ ] Best structure retrieved with `SAbDab_get_structure`\n- [ ] CDR1-3 sequences extracted for VH and VL chains\n- [ ] Antibody-antigen interface analyzed with PDBePISA\n- [ ] Buried surface area and key contact residues documented\n\n---\n\n## Key References\n\n- GPCRdb: https:\u002F\u002Fgpcrdb.org — standardized GPCR data with generic numbering\n- SAbDab: https:\u002F\u002Fopig.stats.ox.ac.uk\u002Fwebapps\u002Fnewsabdab\u002Fsabdab — structural antibody database\n- PDBePISA: https:\u002F\u002Fwww.ebi.ac.uk\u002Fpdbe\u002Fpisa — protein interface analysis\n","# GPCR and Structural Pharmacology Research\n\n**GPCR pharmacology**: agonist vs antagonist vs inverse agonist vs biased agonist — each has different clinical implications. Biased agonism (preferential G-protein vs β-arrestin signaling) can separate efficacy from side effects; for example, G-protein-biased opioid agonists aim to retain analgesia while reducing β-arrestin-mediated respiratory depression. Always classify retrieved ligands by their pharmacological type, not just their chemical structure. Receptor state (active vs inactive crystal structure) determines which ligands and mutations are interpretable — an inactive-state structure is appropriate for antagonist binding analysis, active-state for agonist-bound complexes. Generic GPCR numbering (Ballesteros-Weinstein) enables cross-receptor mutation comparison; always report positions in this system alongside sequence positions.\n\n**LOOK UP DON'T GUESS**: never assume GPCRdb entry names (e.g., `adrb2_human`) or PDB IDs — always use `GPCRdb_list_proteins` to find the correct entry name and `GPCRdb_get_structures` to confirm available structures.\n\nResearch skill integrating GPCRdb (GPCR receptor biology), SAbDab (antibody structures), and PDBePISA (protein interface analysis) to support structural pharmacology, antibody engineering, and GPCR-targeted drug discovery.\n\n**KEY PRINCIPLES**:\n1. **Receptor-first** — Identify GPCR entry name before any GPCRdb queries\n2. **Ligand classification** — Distinguish agonists, antagonists, partial agonists, biased agonists\n3. **Structure-guided** — Pair GPCRdb mutation data with PDB structures via PDBePISA\n4. **Antibody context** — Use SAbDab for therapeutic antibody structure retrieval and CDR analysis\n5. **English-first queries** — Use standard receptor names (e.g., \"beta-2 adrenergic receptor\") in searches; convert to GPCRdb entry names for API calls\n\n---\n\n## When to Use\n\nApply when user asks:\n- \"What ligands are known for [GPCR receptor]?\"\n- \"What crystal structures exist for [receptor]?\"\n- \"Find antibody structures targeting [antigen]\"\n- \"Analyze the protein-protein interface in PDB [ID]\"\n- \"What mutations affect [GPCR] function or pharmacology?\"\n- \"Which GPCRs are in the [family] family?\"\n- \"What are the CDR loops in antibody PDB [ID]?\"\n- \"What is the biological assembly for [PDB ID]?\"\n\n---\n\n## Tool Parameter Reference (CRITICAL)\n\n| Tool | Key Parameters | Notes |\n|------|---------------|-------|\n| `GPCRdb_get_protein` | `protein` | GPCRdb entry name (e.g., `adrb2_human`), NOT gene symbol or UniProt accession |\n| `GPCRdb_list_proteins` | `family` (optional), `protein_class` (optional) | Lists all GPCRs; filter by family slug (e.g., `\"adrenoceptors\"`) OR by human-readable class name via `protein_class` (e.g., `\"chemokine receptors\"`, `\"opioid receptors\"`) |\n| `GPCRdb_get_structures` | `protein` (optional), `state` (optional) | `state`: `\"active\"`, `\"inactive\"`, `\"intermediate\"` |\n| `GPCRdb_get_ligands` | `protein` | Returns agonists, antagonists, biased ligands with affinities |\n| `GPCRdb_get_mutations` | `protein` | Returns mutation effects on receptor function and ligand binding |\n| `SAbDab_search_structures` | `query` | Antigen name, species, or keywords; returns browse URL + metadata |\n| `SAbDab_get_structure` | `pdb_id` | 4-character PDB code (e.g., `\"6W41\"`); returns CDR annotations |\n| `SAbDab_get_summary` | (no required params) | Database statistics and summary |\n| `PDBePISA_get_interfaces` | `pdb_id` | 4-character PDB code; returns all interface pairs with buried area |\n| `PDBePISA_get_assemblies` | `pdb_id` | Predicted biological assemblies from crystal packing |\n| `PDBePISA_get_monomer_analysis` | `pdb_id` | Per-chain solvent-accessible surface area (SASA) breakdown |\n\n### GPCRdb Entry Name Format\n\nGPCRdb uses its own entry name format: `{receptor_slug}_{species}`. Common examples:\n- Beta-2 adrenergic receptor: `adrb2_human`\n- Beta-1 adrenergic receptor: `adrb1_human`\n- Mu-opioid receptor: `oprm1_human`\n- Dopamine D2 receptor: `drd2_human`\n- Glucagon-like peptide-1 receptor: `glp1r_human`\n- CXCR4 chemokine receptor: `cxcr4_human`\n\nIf entry name is unknown, use `GPCRdb_list_proteins()` to browse and find the correct slug. You can also filter by receptor class using the `protein_class` parameter with a human-readable name — e.g., `GPCRdb_list_proteins(protein_class=\"chemokine receptors\")` — instead of the numeric family slug. Both `family` and `protein_class` are accepted and serve overlapping purposes; prefer `protein_class` when the user provides a receptor class name.\n\n---\n\n## Workflow Overview\n\n```\nPhase 1: Receptor Identification (for GPCR queries)\n  -> GPCRdb_list_proteins: find receptor family and entry name\n  -> GPCRdb_get_protein: receptor details, family, species\n\nPhase 2: Ligand Landscape\n  -> GPCRdb_get_ligands: all known ligands by pharmacology class\n  -> Cross-reference with ChEMBL\u002FPubChem for chemical properties\n\nPhase 3: Structural Data\n  -> GPCRdb_get_structures: available PDB\u002FEMDB structures with resolution\n  -> PDBePISA_get_interfaces: interface analysis on best structure\n  -> PDBePISA_get_assemblies: biological assembly determination\n\nPhase 4: Mutation & Pharmacology Data\n  -> GPCRdb_get_mutations: pharmacological mutation map\n  -> Compare to ligand binding sites from structure\n\nPhase 5: Antibody Structures (for antibody queries)\n  -> SAbDab_search_structures: find structures by antigen\n  -> SAbDab_get_structure: CDR annotations, chain details\n  -> PDBePISA_get_interfaces: antibody-antigen interface analysis\n```\n\n---\n\n## Phase 1: GPCR Receptor Identification\n\n```python\n# List all GPCRs in a family to find entry name (by slug)\nfamily_list = GPCRdb_list_proteins(family=\"adrenoceptors\")\n\n# Filter by human-readable class name (new -- preferred when user says e.g. \"chemokine receptors\")\nchemokine_list = GPCRdb_list_proteins(protein_class=\"chemokine receptors\")\n\n# Browse all GPCRs (no family filter)\nall_gpcrs = GPCRdb_list_proteins()\n\n# Get detailed protein info once you have the entry name\nreceptor = GPCRdb_get_protein(protein=\"adrb2_human\")\n# Returns: family classification, endogenous ligands, tissue expression,\n#          GPCRdb-specific annotations, sequence features\n```\n\n## Phase 2: Ligand Landscape\n\n```python\n# Get all known ligands for a GPCR\nligands = GPCRdb_get_ligands(protein=\"adrb2_human\")\n# Returns: ligand names, types (agonist\u002Fantagonist\u002Fpartial\u002Fbiased\u002Fallosteric),\n#          binding affinities (Ki, IC50, EC50), references\n\n# Ligand type classification:\n# - Agonist: activates receptor\n# - Antagonist\u002FInverse agonist: blocks or suppresses receptor\n# - Partial agonist: submaximal activation\n# - Biased agonist: selective signaling (Gs vs. beta-arrestin bias)\n# - Positive\u002FNegative allosteric modulator (PAM\u002FNAM)\n```\n\nAfter retrieving ligands from GPCRdb, optionally cross-reference with:\n- `PubChem_get_CID_by_compound_name(compound_name=ligand_name)` — get CID, SMILES\n- `ChEMBL_search_molecules(query=ligand_name)` — get ChEMBL ID, bioactivity data\n\n## Phase 3: Structural Data\n\n```python\n# Get available crystal\u002Fcryo-EM structures\nstructures = GPCRdb_get_structures(protein=\"adrb2_human\", state=\"inactive\")\n# state options: \"active\", \"inactive\", \"intermediate\" (omit for all)\n# Returns: PDB IDs, resolution, ligand in structure, publication info\n\n# Analyze a specific structure's interfaces\ninterfaces = PDBePISA_get_interfaces(pdb_id=\"2rh1\")  # adrb2 inactive structure\n# Returns: interface pairs, buried solvent-accessible area (BSA),\n#          interface residues, hydrogen bonds, salt bridges\n\n# Determine biological assembly\nassemblies = PDBePISA_get_assemblies(pdb_id=\"2rh1\")\n# Returns: predicted oligomeric state, assembly stability score,\n#          subunit composition\n\n# Per-chain SASA breakdown\nmonomers = PDBePISA_get_monomer_analysis(pdb_id=\"2rh1\")\n# Returns: accessible\u002Fburied surface area per chain\n```\n\n**Interface Analysis Interpretation**:\n- BSA > 1500 Ų: Strong interface (likely biologically relevant)\n- BSA 800-1500 Ų: Moderate interface\n- BSA \u003C 800 Ų: Weak or crystal contact\n\n## Phase 4: Mutation Data\n\n```python\n# Get all mutations characterized for a GPCR\nmutations = GPCRdb_get_mutations(protein=\"adrb2_human\")\n# Returns: mutation positions (generic GPCR numbering), effects on:\n#   - Expression\u002Ffolding\n#   - Ligand binding (affinity changes)\n#   - G-protein coupling\n#   - Receptor activation\n\n# Generic GPCR numbering (Ballesteros-Weinstein):\n# e.g., 3.32 = position 32 in TM helix 3 — conserved across GPCR classes\n```\n\n## Phase 5: Antibody Structure Retrieval\n\n```python\n# Search SAbDab for antibody structures by antigen\nresults = SAbDab_search_structures(query=\"EGFR\", limit=20)\n# Returns: browse URL + metadata table of matching structures\n\n# Get detailed annotations for a specific antibody structure\nstructure = SAbDab_get_structure(pdb_id=\"1IQD\")\n# Returns: VH\u002FVL chain IDs, CDR1-3 (Kabat\u002FIMGT), antigen info,\n#          heavy\u002Flight chain types, resolution\n\n# Get database overview\nsummary = SAbDab_get_summary()\n# Returns: total structures, species breakdown, antigen coverage stats\n```\n\n**CDR Analysis**:\n- CDR-H3 is most variable and typically dominates antigen contact\n- CDR length distribution: SAbDab provides Kabat, Chothia, and IMGT numbering\n- After retrieving SAbDab structure, use `PDBePISA_get_interfaces(pdb_id=...)` to compute antibody-antigen buried surface area\n\n---\n\n## Common Research Patterns\n\n### Pattern 1: GPCR Drug Target Profiling\n```\nInput: GPCR name (e.g., \"GLP-1 receptor\")\nFlow: GPCRdb_list_proteins -> find \"glp1r_human\" ->\n      GPCRdb_get_protein (receptor details) ->\n      GPCRdb_get_ligands (approved + investigational drugs) ->\n      GPCRdb_get_structures (available PDB structures) ->\n      PDBePISA_get_interfaces on best structure ->\n      GPCRdb_get_mutations (pharmacological mutants)\nOutput: Complete GPCR pharmacology profile with structural context\n```\n\n### Pattern 2: Antibody-Antigen Interface Analysis\n```\nInput: Target antigen (e.g., \"PD-L1\") or specific PDB code\nFlow: SAbDab_search_structures(query=\"PD-L1\") ->\n      SAbDab_get_structure(pdb_id=\"best hit\") (CDR annotations) ->\n      PDBePISA_get_interfaces(pdb_id=...) (buried area, key contacts) ->\n      PDBePISA_get_assemblies (assembly context)\nOutput: CDR sequences, epitope contact residues, interface energetics\n```\n\n### Pattern 3: GPCR Family Survey\n```\nInput: Drug class question (e.g., \"beta-adrenergic receptors\")\nFlow: GPCRdb_list_proteins(family=\"adrenoceptors\") ->\n      GPCRdb_get_protein per receptor (adrb1\u002F2\u002F3) ->\n      GPCRdb_get_ligands per receptor (selectivity landscape) ->\n      GPCRdb_get_structures per receptor (structural coverage)\nOutput: Family-wide selectivity map, structural availability, ligand classes\n```\n\n### Pattern 4: Structure Interface Characterization\n```\nInput: PDB code\nFlow: PDBePISA_get_assemblies (oligomeric state) ->\n      PDBePISA_get_interfaces (all interface pairs ranked by BSA) ->\n      PDBePISA_get_monomer_analysis (per-chain surface burial)\nOutput: Biologically relevant assembly, key interface residues, buried areas\n```\n\n---\n\n## Tool Combinations with Other Skills\n\nThis skill complements other ToolUniverse skills:\n\n| Goal | This skill provides | Complement with |\n|------|--------------------|--------------------|\n| GPCR drug discovery | Receptor\u002Fligand\u002Fstructure data | `tooluniverse-binder-discovery` for virtual screening |\n| Antibody engineering | SAbDab structure + CDR data | `tooluniverse-antibody-engineering` for optimization |\n| Variant impact on GPCR | GPCRdb mutation effects | `tooluniverse-variant-functional-annotation` for ACMG |\n| Target validation | GPCR expression, ligand data | `tooluniverse-drug-target-validation` |\n| PDB structure analysis | PDBePISA interfaces | `tooluniverse-protein-structure-retrieval` for RCSB\u002FPDBe |\n\n---\n\n## Fallback Chains\n\n| Primary Tool | Fallback | Use When |\n|-------------|----------|----------|\n| `GPCRdb_get_protein` | UniProt search + PubMed | Entry name unknown or non-GPCR target |\n| `GPCRdb_get_ligands` | ChEMBL bioactivity search | Receptor not in GPCRdb |\n| `GPCRdb_get_structures` | RCSB PDB text search | Structures not yet in GPCRdb |\n| `SAbDab_search_structures` | RCSB PDB antibody search | Antigen not indexed in SAbDab |\n| `PDBePISA_get_interfaces` | PDBe graph API | PDBePISA returns no interfaces |\n\n---\n\n## Completeness Checklist\n\nFor GPCR profiling:\n- [ ] Entry name resolved via `GPCRdb_list_proteins` or `GPCRdb_get_protein`\n- [ ] Receptor family and class documented\n- [ ] Ligand landscape retrieved with pharmacology types\n- [ ] Available structures listed with resolution and state\n- [ ] Best structure analyzed with PDBePISA (interfaces + assembly)\n- [ ] Mutation data retrieved for pharmacological context\n\nFor antibody structure:\n- [ ] SAbDab search run with antigen name\n- [ ] Best structure retrieved with `SAbDab_get_structure`\n- [ ] CDR1-3 sequences extracted for VH and VL chains\n- [ ] Antibody-antigen interface analyzed with PDBePISA\n- [ ] Buried surface area and key contact residues documented\n\n---\n\n## Key References\n\n- GPCRdb: https:\u002F\u002Fgpcrdb.org — standardized GPCR data with generic numbering\n- SAbDab: https:\u002F\u002Fopig.stats.ox.ac.uk\u002Fwebapps\u002Fnewsabdab\u002Fsabdab — structural antibody database\n- PDBePISA: https:\u002F\u002Fwww.ebi.ac.uk\u002Fpdbe\u002Fpisa — protein interface analysis\n",{"name":5,"description":7},"main","a298c929b6cbd662e1fce54302ce520d5ceea1a5",".agents\u002Flibrary\u002Fskills\u002Ftooluniverse-gpcr-structural-pharmacology","https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain","https:\u002F\u002Fgithub.com\u002FPrekzursil","2026-11-02 14:30:57",{"source":8,"skillName":5,"commands":48,"prompt":58,"zipAvailable":59},[49,52,55],{"tool":50,"command":51},"npx","npx skills add Prekzursil\u002Fagent-skills-toolchain --skill tooluniverse-gpcr-structural-pharmacology",{"tool":53,"command":54},"bunx","bunx skills add Prekzursil\u002Fagent-skills-toolchain --skill tooluniverse-gpcr-structural-pharmacology",{"tool":56,"command":57},"pnpm","pnpm dlx skills add Prekzursil\u002Fagent-skills-toolchain --skill tooluniverse-gpcr-structural-pharmacology","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002F.agents\u002Flibrary\u002Fskills\u002Ftooluniverse-gpcr-structural-pharmacology\u002FSKILL.md",true,[61],{"path":62,"resourceType":63,"resourceTypeDesc":64,"sizeBytes":65,"sourceHtmlUrl":66},"agents\u002Fopenai.yaml","REFERENCE","参考文档",82,"https:\u002F\u002Fgithub.com\u002Fnexuslinkproductions\u002Fyuri-os\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Forgan-discovery-precision-gate\u002Fagents\u002Fopenai.yaml",[68,89,118,145,159,175],{"skillNo":69,"name":70,"nameZh":6,"description":71,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":72,"categories":73,"keywords":74,"publishedAt":36},"01M6DF7D7478R55P46REYH4QAC","clarify-requirements","Resolve genuine pre-execution ambiguity by scanning repo context, generating 1-6 grounded options, and asking 1-3 focused questions via AskUserQuestion. NOT for mid-task use (injection risk); NOT when the goal is already unambiguous; use to disambiguate vague prompts before any file edits.","https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002Ftools\u002Fworkspace-hooks\u002Fskills\u002Fclarify-requirements\u002FSKILL.md",[],[75,76,77,78,79,80,81,82,83,31,84,85,86,87,88],"clarify requirements","clarify","requirements","risk","options","task","prompts","goal","scanning","context","repo","injection","execution","file",{"skillNo":90,"name":91,"nameZh":6,"description":92,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":93,"categories":94,"keywords":98,"publishedAt":36},"01M6DF79CA4BHJS66J8EZDBPWJ","openmm-md","Run FREE, open-source, Windows-native GPU molecular dynamics via the openmm-md MCP (OpenMM + CUDA on the local NVIDIA GPU). Use for protein \u002F protein-ligand MD when you want a free stack or are on Windows without a Schrodinger license. Covers the full workflow (prepare, solvate, minimize, equilibrate, production, analyze, mmgbsa) AND an honest decision guide vs Schrodinger Desmond, including how to run Desmond legitimately on Linux or a cloud GPU with a real license. This is a deliberately LESSER free alternative and does NOT replace the schrodinger MCP tools. Do NOT use it to pick a free tool when a validated FEP+, WaterMap, IFD-MD, or Prime MM-GBSA result is actually required.","https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002Ftools\u002Fmcp\u002Fopenmm-md-mcp\u002Fskill\u002Fopenmm-md\u002FSKILL.md",[95],{"categoryNo":96,"categoryName":97,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000023","Skill与智能体开发",[99,100,101,102,103,104,105,106,107,108,109,110,111,112,31,113,114,115,116,117],"openmm md","how","decision","pick","linux","analyze","tool","stack","open","NVIDIA","gpu","license","workflow","windows","free","molecular dynamics","local","do","MCP",{"skillNo":119,"name":120,"nameZh":6,"description":121,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":122,"categories":123,"keywords":130,"publishedAt":36},"01M6DF76C1MG85VEWP8VZCBNMN","visual-review","Take screenshots of web pages and UI using Playwright for visual review and iteration","https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002Ftools\u002Feditor\u002Fmetaswarm\u002Fskills\u002Fvisual-review\u002FSKILL.md",[124,127],{"categoryNo":125,"categoryName":126,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000003","演示文稿",{"categoryNo":128,"categoryName":129,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000008","测试与质量",[131,132,133,134,135,136,137,138,139,140,100,141,142,143,144],"review","visual","visual review","pages","web","false","iteration","take","check","slides","ui","screenshot","playwright","screenshots",{"skillNo":146,"name":147,"nameZh":6,"description":148,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":149,"categories":150,"keywords":151,"publishedAt":36},"01M6DF73AQVCBZKEN0YXEX9FXP","status","Diagnostic status report — shows metaswarm installation state, project setup, and potential issues","https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002Ftools\u002Feditor\u002Fmetaswarm\u002Fskills\u002Fstatus\u002FSKILL.md",[],[147,152,153,154,155,156,157,158],"setup","report","project","installation","project setup","issues","state",{"skillNo":160,"name":161,"nameZh":6,"description":162,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":163,"categories":164,"keywords":166,"publishedAt":36},"01M6DF6X6C2XB0P6GX76P7TTYV","start","Use when starting work on any task, when the user mentions metaswarm, or when the user wants to begin tracked development work","https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002Ftools\u002Feditor\u002Fmetaswarm\u002Fskills\u002Fstart\u002FSKILL.md",[165],{"categoryNo":96,"categoryName":97,"taxonomyType":21,"taxonomyTypeDesc":22},[161,167,80,168,169,170,31,171,172,173,174],"start issue","issue","ready","work on issue","user","work","work on","development",{"skillNo":176,"name":152,"nameZh":6,"description":177,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":178,"categories":179,"keywords":180,"publishedAt":36},"01M6DF6QMJ9AJKFKHHKRT005PQ","Interactive project setup — detects your project, configures metaswarm, writes project-local files","https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002Ftools\u002Feditor\u002Fmetaswarm\u002Fskills\u002Fsetup\u002FSKILL.md",[],[152,154,115,181,156,182],"files","interactive"]