[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6AFHBEDV4CHZ78K55Z6QD6X":3,"skill-same:01M6AFHBEDV4CHZ78K55Z6QD6X":95},{"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":26,"publishedAt":42,"linkOnly":43,"markdownContent":44,"markdownBody":45,"frontMatter":46,"refName":47,"commitSha":48,"skillDirectory":49,"forksCount":50,"repositoryHtmlUrl":51,"repositoryHomepageUrl":52,"ownerHtmlUrl":53,"ownerBlogUrl":54,"ownerDescription":55,"updatedAt":56,"install":57,"resources":70},"01M6AFHBEDV4CHZ78K55Z6QD6X","opentargets-database",null,"Query Open Targets Platform for target-disease associations, drug target discovery, tractability\u002Fsafety data, genetics\u002Fomics evidence, known drugs, for therapeutic target identification.","davila7\u002Fclaude-code-templates","davila7","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F6216945?v=4","01M6ADEWWFPS191NFM0Y1EX1JH","Daniel Avila","01M6ADJHGM78PHQRD3XZTFDVKK",33481,"MIT","https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fscientific\u002Fopentargets-database\u002FSKILL.md",[18,23],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000010","后端与接口","SCENARIO","使用场景",{"categoryNo":24,"categoryName":25,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000023","Skill与智能体开发",[27,28,29,30,31,32,33,34,35,36,37,38,39,40,41],"database","opentargets database","data","Safety","discovery","open","evidence","query","genetics","platform","drugs","identification","omics","targets","for","2026-11-10 10:12:30",false,"---\nname: opentargets-database\ndescription: \"Query Open Targets Platform for target-disease associations, drug target discovery, tractability\u002Fsafety data, genetics\u002Fomics evidence, known drugs, for therapeutic target identification.\"\n---\n\n# Open Targets Database\n\n## Overview\n\nThe Open Targets Platform is a comprehensive resource for systematic identification and prioritization of potential therapeutic drug targets. It integrates publicly available datasets including human genetics, omics, literature, and chemical data to build and score target-disease associations.\n\n**Key capabilities:**\n- Query target (gene) annotations including tractability, safety, expression\n- Search for disease-target associations with evidence scores\n- Retrieve evidence from multiple data types (genetics, pathways, literature, etc.)\n- Find known drugs for diseases and their mechanisms\n- Access drug information including clinical trial phases and adverse events\n- Evaluate target druggability and therapeutic potential\n\n**Data access:** The platform provides a GraphQL API, web interface, data downloads, and Google BigQuery access. This skill focuses on the GraphQL API for programmatic access.\n\n## When to Use This Skill\n\nThis skill should be used when:\n\n- **Target discovery:** Finding potential therapeutic targets for a disease\n- **Target assessment:** Evaluating tractability, safety, and druggability of genes\n- **Evidence gathering:** Retrieving supporting evidence for target-disease associations\n- **Drug repurposing:** Identifying existing drugs that could be repurposed for new indications\n- **Competitive intelligence:** Understanding clinical precedence and drug development landscape\n- **Target prioritization:** Ranking targets based on genetic evidence and other data types\n- **Mechanism research:** Investigating biological pathways and gene functions\n- **Biomarker discovery:** Finding genes differentially expressed in disease\n- **Safety assessment:** Identifying potential toxicity concerns for drug targets\n\n## Core Workflow\n\n### 1. Search for Entities\n\nStart by finding the identifiers for targets, diseases, or drugs of interest.\n\n**For targets (genes):**\n```python\nfrom scripts.query_opentargets import search_entities\n\n# Search by gene symbol or name\nresults = search_entities(\"BRCA1\", entity_types=[\"target\"])\n# Returns: [{\"id\": \"ENSG00000012048\", \"name\": \"BRCA1\", ...}]\n```\n\n**For diseases:**\n```python\n# Search by disease name\nresults = search_entities(\"alzheimer\", entity_types=[\"disease\"])\n# Returns: [{\"id\": \"EFO_0000249\", \"name\": \"Alzheimer disease\", ...}]\n```\n\n**For drugs:**\n```python\n# Search by drug name\nresults = search_entities(\"aspirin\", entity_types=[\"drug\"])\n# Returns: [{\"id\": \"CHEMBL25\", \"name\": \"ASPIRIN\", ...}]\n```\n\n**Identifiers used:**\n- Targets: Ensembl gene IDs (e.g., `ENSG00000157764`)\n- Diseases: EFO (Experimental Factor Ontology) IDs (e.g., `EFO_0000249`)\n- Drugs: ChEMBL IDs (e.g., `CHEMBL25`)\n\n### 2. Query Target Information\n\nRetrieve comprehensive target annotations to assess druggability and biology.\n\n```python\nfrom scripts.query_opentargets import get_target_info\n\ntarget_info = get_target_info(\"ENSG00000157764\", include_diseases=True)\n\n# Access key fields:\n# - approvedSymbol: HGNC gene symbol\n# - approvedName: Full gene name\n# - tractability: Druggability assessments across modalities\n# - safetyLiabilities: Known safety concerns\n# - geneticConstraint: Constraint scores from gnomAD\n# - associatedDiseases: Top disease associations with scores\n```\n\n**Key annotations to review:**\n- **Tractability:** Small molecule, antibody, PROTAC druggability predictions\n- **Safety:** Known toxicity concerns from multiple databases\n- **Genetic constraint:** pLI and LOEUF scores indicating essentiality\n- **Disease associations:** Diseases linked to the target with evidence scores\n\nRefer to `references\u002Ftarget_annotations.md` for detailed information about all target features.\n\n### 3. Query Disease Information\n\nGet disease details and associated targets\u002Fdrugs.\n\n```python\nfrom scripts.query_opentargets import get_disease_info\n\ndisease_info = get_disease_info(\"EFO_0000249\", include_targets=True)\n\n# Access fields:\n# - name: Disease name\n# - description: Disease description\n# - therapeuticAreas: High-level disease categories\n# - associatedTargets: Top targets with association scores\n```\n\n### 4. Retrieve Target-Disease Evidence\n\nGet detailed evidence supporting a target-disease association.\n\n```python\nfrom scripts.query_opentargets import get_target_disease_evidence\n\n# Get all evidence\nevidence = get_target_disease_evidence(\n    ensembl_id=\"ENSG00000157764\",\n    efo_id=\"EFO_0000249\"\n)\n\n# Filter by evidence type\ngenetic_evidence = get_target_disease_evidence(\n    ensembl_id=\"ENSG00000157764\",\n    efo_id=\"EFO_0000249\",\n    data_types=[\"genetic_association\"]\n)\n\n# Each evidence record contains:\n# - datasourceId: Specific data source (e.g., \"gwas_catalog\", \"chembl\")\n# - datatypeId: Evidence category (e.g., \"genetic_association\", \"known_drug\")\n# - score: Evidence strength (0-1)\n# - studyId: Original study identifier\n# - literature: Associated publications\n```\n\n**Major evidence types:**\n1. **genetic_association:** GWAS, rare variants, ClinVar, gene burden\n2. **somatic_mutation:** Cancer Gene Census, IntOGen, cancer biomarkers\n3. **known_drug:** Clinical precedence from approved\u002Fclinical drugs\n4. **affected_pathway:** CRISPR screens, pathway analyses, gene signatures\n5. **rna_expression:** Differential expression from Expression Atlas\n6. **animal_model:** Mouse phenotypes from IMPC\n7. **literature:** Text-mining from Europe PMC\n\nRefer to `references\u002Fevidence_types.md` for detailed descriptions of all evidence types and interpretation guidelines.\n\n### 5. Find Known Drugs\n\nIdentify drugs used for a disease and their targets.\n\n```python\nfrom scripts.query_opentargets import get_known_drugs_for_disease\n\ndrugs = get_known_drugs_for_disease(\"EFO_0000249\")\n\n# drugs contains:\n# - uniqueDrugs: Total number of unique drugs\n# - uniqueTargets: Total number of unique targets\n# - rows: List of drug-target-indication records with:\n#   - drug: {name, drugType, maximumClinicalTrialPhase}\n#   - targets: Genes targeted by the drug\n#   - phase: Clinical trial phase for this indication\n#   - status: Trial status (active, completed, etc.)\n#   - mechanismOfAction: How drug works\n```\n\n**Clinical phases:**\n- Phase 4: Approved drug\n- Phase 3: Late-stage clinical trials\n- Phase 2: Mid-stage trials\n- Phase 1: Early safety trials\n\n### 6. Get Drug Information\n\nRetrieve detailed drug information including mechanisms and indications.\n\n```python\nfrom scripts.query_opentargets import get_drug_info\n\ndrug_info = get_drug_info(\"CHEMBL25\")\n\n# Access:\n# - name, synonyms: Drug identifiers\n# - drugType: Small molecule, antibody, etc.\n# - maximumClinicalTrialPhase: Development stage\n# - mechanismsOfAction: Target and action type\n# - indications: Diseases with trial phases\n# - withdrawnNotice: If withdrawn, reasons and countries\n```\n\n### 7. Get All Associations for a Target\n\nFind all diseases associated with a target, optionally filtering by score.\n\n```python\nfrom scripts.query_opentargets import get_target_associations\n\n# Get associations with score >= 0.5\nassociations = get_target_associations(\n    ensembl_id=\"ENSG00000157764\",\n    min_score=0.5\n)\n\n# Each association contains:\n# - disease: {id, name}\n# - score: Overall association score (0-1)\n# - datatypeScores: Breakdown by evidence type\n```\n\n**Association scores:**\n- Range: 0-1 (higher = stronger evidence)\n- Aggregate evidence across all data types using harmonic sum\n- NOT confidence scores but relative ranking metrics\n- Under-studied diseases may have lower scores despite good evidence\n\n## GraphQL API Details\n\n**For custom queries beyond the provided helper functions**, use the GraphQL API directly or modify `scripts\u002Fquery_opentargets.py`.\n\nKey information:\n- **Endpoint:** `https:\u002F\u002Fapi.platform.opentargets.org\u002Fapi\u002Fv4\u002Fgraphql`\n- **Interactive browser:** `https:\u002F\u002Fapi.platform.opentargets.org\u002Fapi\u002Fv4\u002Fgraphql\u002Fbrowser`\n- **No authentication required**\n- **Request only needed fields** to minimize response size\n- **Use pagination** for large result sets: `page: {size: N, index: M}`\n\nRefer to `references\u002Fapi_reference.md` for:\n- Complete endpoint documentation\n- Example queries for all entity types\n- Error handling patterns\n- Best practices for API usage\n\n## Best Practices\n\n### Target Prioritization Strategy\n\nWhen prioritizing drug targets:\n\n1. **Start with genetic evidence:** Human genetics (GWAS, rare variants) provides strongest disease relevance\n2. **Check tractability:** Prefer targets with clinical or discovery precedence\n3. **Assess safety:** Review safety liabilities, expression patterns, and genetic constraint\n4. **Evaluate clinical precedence:** Known drugs indicate druggability and therapeutic window\n5. **Consider multiple evidence types:** Convergent evidence from different sources increases confidence\n6. **Validate mechanistically:** Pathway evidence and biological plausibility\n7. **Review literature manually:** For critical decisions, examine primary publications\n\n### Evidence Interpretation\n\n**Strong evidence indicators:**\n- Multiple independent evidence sources\n- High genetic association scores (especially GWAS with L2G > 0.5)\n- Clinical precedence from approved drugs\n- ClinVar pathogenic variants with disease match\n- Mouse models with relevant phenotypes\n\n**Caution flags:**\n- Single evidence source only\n- Text-mining as sole evidence (requires manual validation)\n- Conflicting evidence across sources\n- High essentiality + ubiquitous expression (poor therapeutic window)\n- Multiple safety liabilities\n\n**Score interpretation:**\n- Scores rank relative strength, not absolute confidence\n- Under-studied diseases have lower scores despite potentially valid targets\n- Weight expert-curated sources higher than computational predictions\n- Check evidence breakdown, not just overall score\n\n### Common Workflows\n\n**Workflow 1: Target Discovery for a Disease**\n1. Search for disease → get EFO ID\n2. Query disease info with `include_targets=True`\n3. Review top targets sorted by association score\n4. For promising targets, get detailed target info\n5. Examine evidence types supporting each association\n6. Assess tractability and safety for prioritized targets\n\n**Workflow 2: Target Validation**\n1. Search for target → get Ensembl ID\n2. Get comprehensive target info\n3. Check tractability (especially clinical precedence)\n4. Review safety liabilities and genetic constraint\n5. Examine disease associations to understand biology\n6. Look for chemical probes or tool compounds\n7. Check known drugs targeting gene for mechanism insights\n\n**Workflow 3: Drug Repurposing**\n1. Search for disease → get EFO ID\n2. Get known drugs for disease\n3. For each drug, get detailed drug info\n4. Examine mechanisms of action and targets\n5. Look for related disease indications\n6. Assess clinical trial phases and status\n7. Identify repurposing opportunities based on mechanism\n\n**Workflow 4: Competitive Intelligence**\n1. Search for target of interest\n2. Get associated diseases with evidence\n3. For each disease, get known drugs\n4. Review clinical phases and development status\n5. Identify competitors and their mechanisms\n6. Assess clinical precedence and market landscape\n\n## Resources\n\n### Scripts\n\n**scripts\u002Fquery_opentargets.py**\nHelper functions for common API operations:\n- `search_entities()` - Search for targets, diseases, or drugs\n- `get_target_info()` - Retrieve target annotations\n- `get_disease_info()` - Retrieve disease information\n- `get_target_disease_evidence()` - Get supporting evidence\n- `get_known_drugs_for_disease()` - Find drugs for a disease\n- `get_drug_info()` - Retrieve drug details\n- `get_target_associations()` - Get all associations for a target\n- `execute_query()` - Execute custom GraphQL queries\n\n### References\n\n**references\u002Fapi_reference.md**\nComplete GraphQL API documentation including:\n- Endpoint details and authentication\n- Available query types (target, disease, drug, search)\n- Example queries for all common operations\n- Error handling and best practices\n- Data licensing and citation requirements\n\n**references\u002Fevidence_types.md**\nComprehensive guide to evidence types and data sources:\n- Detailed descriptions of all 7 major evidence types\n- Scoring methodologies for each source\n- Evidence interpretation guidelines\n- Strengths and limitations of each evidence type\n- Quality assessment recommendations\n\n**references\u002Ftarget_annotations.md**\nComplete target annotation reference:\n- 12 major annotation categories explained\n- Tractability assessment details\n- Safety liability sources\n- Expression, essentiality, and constraint data\n- Interpretation guidelines for target prioritization\n- Red flags and green flags for target assessment\n\n## Data Updates and Versioning\n\nThe Open Targets Platform is updated **quarterly** with new data releases. The current release (as of October 2025) is available at the API endpoint.\n\n**Release information:** Check https:\u002F\u002Fplatform-docs.opentargets.org\u002Frelease-notes for the latest updates.\n\n**Citation:** When using Open Targets data, cite:\nOchoa, D. et al. (2025) Open Targets Platform: facilitating therapeutic hypotheses building in drug discovery. Nucleic Acids Research, 53(D1):D1467-D1477.\n\n## Limitations and Considerations\n\n1. **API is for exploratory queries:** For systematic analyses of many targets\u002Fdiseases, use data downloads or BigQuery\n2. **Scores are relative, not absolute:** Association scores rank evidence strength but don't predict clinical success\n3. **Under-studied diseases score lower:** Novel or rare diseases may have strong evidence but lower aggregate scores\n4. **Evidence quality varies:** Weight expert-curated sources higher than computational predictions\n5. **Requires biological interpretation:** Scores and evidence must be interpreted in biological and clinical context\n6. **No authentication required:** All data is freely accessible, but cite appropriately\n","# Open Targets Database\n\n## Overview\n\nThe Open Targets Platform is a comprehensive resource for systematic identification and prioritization of potential therapeutic drug targets. It integrates publicly available datasets including human genetics, omics, literature, and chemical data to build and score target-disease associations.\n\n**Key capabilities:**\n- Query target (gene) annotations including tractability, safety, expression\n- Search for disease-target associations with evidence scores\n- Retrieve evidence from multiple data types (genetics, pathways, literature, etc.)\n- Find known drugs for diseases and their mechanisms\n- Access drug information including clinical trial phases and adverse events\n- Evaluate target druggability and therapeutic potential\n\n**Data access:** The platform provides a GraphQL API, web interface, data downloads, and Google BigQuery access. This skill focuses on the GraphQL API for programmatic access.\n\n## When to Use This Skill\n\nThis skill should be used when:\n\n- **Target discovery:** Finding potential therapeutic targets for a disease\n- **Target assessment:** Evaluating tractability, safety, and druggability of genes\n- **Evidence gathering:** Retrieving supporting evidence for target-disease associations\n- **Drug repurposing:** Identifying existing drugs that could be repurposed for new indications\n- **Competitive intelligence:** Understanding clinical precedence and drug development landscape\n- **Target prioritization:** Ranking targets based on genetic evidence and other data types\n- **Mechanism research:** Investigating biological pathways and gene functions\n- **Biomarker discovery:** Finding genes differentially expressed in disease\n- **Safety assessment:** Identifying potential toxicity concerns for drug targets\n\n## Core Workflow\n\n### 1. Search for Entities\n\nStart by finding the identifiers for targets, diseases, or drugs of interest.\n\n**For targets (genes):**\n```python\nfrom scripts.query_opentargets import search_entities\n\n# Search by gene symbol or name\nresults = search_entities(\"BRCA1\", entity_types=[\"target\"])\n# Returns: [{\"id\": \"ENSG00000012048\", \"name\": \"BRCA1\", ...}]\n```\n\n**For diseases:**\n```python\n# Search by disease name\nresults = search_entities(\"alzheimer\", entity_types=[\"disease\"])\n# Returns: [{\"id\": \"EFO_0000249\", \"name\": \"Alzheimer disease\", ...}]\n```\n\n**For drugs:**\n```python\n# Search by drug name\nresults = search_entities(\"aspirin\", entity_types=[\"drug\"])\n# Returns: [{\"id\": \"CHEMBL25\", \"name\": \"ASPIRIN\", ...}]\n```\n\n**Identifiers used:**\n- Targets: Ensembl gene IDs (e.g., `ENSG00000157764`)\n- Diseases: EFO (Experimental Factor Ontology) IDs (e.g., `EFO_0000249`)\n- Drugs: ChEMBL IDs (e.g., `CHEMBL25`)\n\n### 2. Query Target Information\n\nRetrieve comprehensive target annotations to assess druggability and biology.\n\n```python\nfrom scripts.query_opentargets import get_target_info\n\ntarget_info = get_target_info(\"ENSG00000157764\", include_diseases=True)\n\n# Access key fields:\n# - approvedSymbol: HGNC gene symbol\n# - approvedName: Full gene name\n# - tractability: Druggability assessments across modalities\n# - safetyLiabilities: Known safety concerns\n# - geneticConstraint: Constraint scores from gnomAD\n# - associatedDiseases: Top disease associations with scores\n```\n\n**Key annotations to review:**\n- **Tractability:** Small molecule, antibody, PROTAC druggability predictions\n- **Safety:** Known toxicity concerns from multiple databases\n- **Genetic constraint:** pLI and LOEUF scores indicating essentiality\n- **Disease associations:** Diseases linked to the target with evidence scores\n\nRefer to `references\u002Ftarget_annotations.md` for detailed information about all target features.\n\n### 3. Query Disease Information\n\nGet disease details and associated targets\u002Fdrugs.\n\n```python\nfrom scripts.query_opentargets import get_disease_info\n\ndisease_info = get_disease_info(\"EFO_0000249\", include_targets=True)\n\n# Access fields:\n# - name: Disease name\n# - description: Disease description\n# - therapeuticAreas: High-level disease categories\n# - associatedTargets: Top targets with association scores\n```\n\n### 4. Retrieve Target-Disease Evidence\n\nGet detailed evidence supporting a target-disease association.\n\n```python\nfrom scripts.query_opentargets import get_target_disease_evidence\n\n# Get all evidence\nevidence = get_target_disease_evidence(\n    ensembl_id=\"ENSG00000157764\",\n    efo_id=\"EFO_0000249\"\n)\n\n# Filter by evidence type\ngenetic_evidence = get_target_disease_evidence(\n    ensembl_id=\"ENSG00000157764\",\n    efo_id=\"EFO_0000249\",\n    data_types=[\"genetic_association\"]\n)\n\n# Each evidence record contains:\n# - datasourceId: Specific data source (e.g., \"gwas_catalog\", \"chembl\")\n# - datatypeId: Evidence category (e.g., \"genetic_association\", \"known_drug\")\n# - score: Evidence strength (0-1)\n# - studyId: Original study identifier\n# - literature: Associated publications\n```\n\n**Major evidence types:**\n1. **genetic_association:** GWAS, rare variants, ClinVar, gene burden\n2. **somatic_mutation:** Cancer Gene Census, IntOGen, cancer biomarkers\n3. **known_drug:** Clinical precedence from approved\u002Fclinical drugs\n4. **affected_pathway:** CRISPR screens, pathway analyses, gene signatures\n5. **rna_expression:** Differential expression from Expression Atlas\n6. **animal_model:** Mouse phenotypes from IMPC\n7. **literature:** Text-mining from Europe PMC\n\nRefer to `references\u002Fevidence_types.md` for detailed descriptions of all evidence types and interpretation guidelines.\n\n### 5. Find Known Drugs\n\nIdentify drugs used for a disease and their targets.\n\n```python\nfrom scripts.query_opentargets import get_known_drugs_for_disease\n\ndrugs = get_known_drugs_for_disease(\"EFO_0000249\")\n\n# drugs contains:\n# - uniqueDrugs: Total number of unique drugs\n# - uniqueTargets: Total number of unique targets\n# - rows: List of drug-target-indication records with:\n#   - drug: {name, drugType, maximumClinicalTrialPhase}\n#   - targets: Genes targeted by the drug\n#   - phase: Clinical trial phase for this indication\n#   - status: Trial status (active, completed, etc.)\n#   - mechanismOfAction: How drug works\n```\n\n**Clinical phases:**\n- Phase 4: Approved drug\n- Phase 3: Late-stage clinical trials\n- Phase 2: Mid-stage trials\n- Phase 1: Early safety trials\n\n### 6. Get Drug Information\n\nRetrieve detailed drug information including mechanisms and indications.\n\n```python\nfrom scripts.query_opentargets import get_drug_info\n\ndrug_info = get_drug_info(\"CHEMBL25\")\n\n# Access:\n# - name, synonyms: Drug identifiers\n# - drugType: Small molecule, antibody, etc.\n# - maximumClinicalTrialPhase: Development stage\n# - mechanismsOfAction: Target and action type\n# - indications: Diseases with trial phases\n# - withdrawnNotice: If withdrawn, reasons and countries\n```\n\n### 7. Get All Associations for a Target\n\nFind all diseases associated with a target, optionally filtering by score.\n\n```python\nfrom scripts.query_opentargets import get_target_associations\n\n# Get associations with score >= 0.5\nassociations = get_target_associations(\n    ensembl_id=\"ENSG00000157764\",\n    min_score=0.5\n)\n\n# Each association contains:\n# - disease: {id, name}\n# - score: Overall association score (0-1)\n# - datatypeScores: Breakdown by evidence type\n```\n\n**Association scores:**\n- Range: 0-1 (higher = stronger evidence)\n- Aggregate evidence across all data types using harmonic sum\n- NOT confidence scores but relative ranking metrics\n- Under-studied diseases may have lower scores despite good evidence\n\n## GraphQL API Details\n\n**For custom queries beyond the provided helper functions**, use the GraphQL API directly or modify `scripts\u002Fquery_opentargets.py`.\n\nKey information:\n- **Endpoint:** `https:\u002F\u002Fapi.platform.opentargets.org\u002Fapi\u002Fv4\u002Fgraphql`\n- **Interactive browser:** `https:\u002F\u002Fapi.platform.opentargets.org\u002Fapi\u002Fv4\u002Fgraphql\u002Fbrowser`\n- **No authentication required**\n- **Request only needed fields** to minimize response size\n- **Use pagination** for large result sets: `page: {size: N, index: M}`\n\nRefer to `references\u002Fapi_reference.md` for:\n- Complete endpoint documentation\n- Example queries for all entity types\n- Error handling patterns\n- Best practices for API usage\n\n## Best Practices\n\n### Target Prioritization Strategy\n\nWhen prioritizing drug targets:\n\n1. **Start with genetic evidence:** Human genetics (GWAS, rare variants) provides strongest disease relevance\n2. **Check tractability:** Prefer targets with clinical or discovery precedence\n3. **Assess safety:** Review safety liabilities, expression patterns, and genetic constraint\n4. **Evaluate clinical precedence:** Known drugs indicate druggability and therapeutic window\n5. **Consider multiple evidence types:** Convergent evidence from different sources increases confidence\n6. **Validate mechanistically:** Pathway evidence and biological plausibility\n7. **Review literature manually:** For critical decisions, examine primary publications\n\n### Evidence Interpretation\n\n**Strong evidence indicators:**\n- Multiple independent evidence sources\n- High genetic association scores (especially GWAS with L2G > 0.5)\n- Clinical precedence from approved drugs\n- ClinVar pathogenic variants with disease match\n- Mouse models with relevant phenotypes\n\n**Caution flags:**\n- Single evidence source only\n- Text-mining as sole evidence (requires manual validation)\n- Conflicting evidence across sources\n- High essentiality + ubiquitous expression (poor therapeutic window)\n- Multiple safety liabilities\n\n**Score interpretation:**\n- Scores rank relative strength, not absolute confidence\n- Under-studied diseases have lower scores despite potentially valid targets\n- Weight expert-curated sources higher than computational predictions\n- Check evidence breakdown, not just overall score\n\n### Common Workflows\n\n**Workflow 1: Target Discovery for a Disease**\n1. Search for disease → get EFO ID\n2. Query disease info with `include_targets=True`\n3. Review top targets sorted by association score\n4. For promising targets, get detailed target info\n5. Examine evidence types supporting each association\n6. Assess tractability and safety for prioritized targets\n\n**Workflow 2: Target Validation**\n1. Search for target → get Ensembl ID\n2. Get comprehensive target info\n3. Check tractability (especially clinical precedence)\n4. Review safety liabilities and genetic constraint\n5. Examine disease associations to understand biology\n6. Look for chemical probes or tool compounds\n7. Check known drugs targeting gene for mechanism insights\n\n**Workflow 3: Drug Repurposing**\n1. Search for disease → get EFO ID\n2. Get known drugs for disease\n3. For each drug, get detailed drug info\n4. Examine mechanisms of action and targets\n5. Look for related disease indications\n6. Assess clinical trial phases and status\n7. Identify repurposing opportunities based on mechanism\n\n**Workflow 4: Competitive Intelligence**\n1. Search for target of interest\n2. Get associated diseases with evidence\n3. For each disease, get known drugs\n4. Review clinical phases and development status\n5. Identify competitors and their mechanisms\n6. Assess clinical precedence and market landscape\n\n## Resources\n\n### Scripts\n\n**scripts\u002Fquery_opentargets.py**\nHelper functions for common API operations:\n- `search_entities()` - Search for targets, diseases, or drugs\n- `get_target_info()` - Retrieve target annotations\n- `get_disease_info()` - Retrieve disease information\n- `get_target_disease_evidence()` - Get supporting evidence\n- `get_known_drugs_for_disease()` - Find drugs for a disease\n- `get_drug_info()` - Retrieve drug details\n- `get_target_associations()` - Get all associations for a target\n- `execute_query()` - Execute custom GraphQL queries\n\n### References\n\n**references\u002Fapi_reference.md**\nComplete GraphQL API documentation including:\n- Endpoint details and authentication\n- Available query types (target, disease, drug, search)\n- Example queries for all common operations\n- Error handling and best practices\n- Data licensing and citation requirements\n\n**references\u002Fevidence_types.md**\nComprehensive guide to evidence types and data sources:\n- Detailed descriptions of all 7 major evidence types\n- Scoring methodologies for each source\n- Evidence interpretation guidelines\n- Strengths and limitations of each evidence type\n- Quality assessment recommendations\n\n**references\u002Ftarget_annotations.md**\nComplete target annotation reference:\n- 12 major annotation categories explained\n- Tractability assessment details\n- Safety liability sources\n- Expression, essentiality, and constraint data\n- Interpretation guidelines for target prioritization\n- Red flags and green flags for target assessment\n\n## Data Updates and Versioning\n\nThe Open Targets Platform is updated **quarterly** with new data releases. The current release (as of October 2025) is available at the API endpoint.\n\n**Release information:** Check https:\u002F\u002Fplatform-docs.opentargets.org\u002Frelease-notes for the latest updates.\n\n**Citation:** When using Open Targets data, cite:\nOchoa, D. et al. (2025) Open Targets Platform: facilitating therapeutic hypotheses building in drug discovery. Nucleic Acids Research, 53(D1):D1467-D1477.\n\n## Limitations and Considerations\n\n1. **API is for exploratory queries:** For systematic analyses of many targets\u002Fdiseases, use data downloads or BigQuery\n2. **Scores are relative, not absolute:** Association scores rank evidence strength but don't predict clinical success\n3. **Under-studied diseases score lower:** Novel or rare diseases may have strong evidence but lower aggregate scores\n4. **Evidence quality varies:** Weight expert-curated sources higher than computational predictions\n5. **Requires biological interpretation:** Scores and evidence must be interpreted in biological and clinical context\n6. **No authentication required:** All data is freely accessible, but cite appropriately\n",{"name":5,"description":7},"main","2b749c82b5d11fac39d9a6e021ce3f5b8a541bd1","cli-tool\u002Fcomponents\u002Fskills\u002Fscientific\u002Fopentargets-database",3931,"https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates","https:\u002F\u002Faitmpl.com","https:\u002F\u002Fgithub.com\u002Fdavila7","https:\u002F\u002Fdanielavila.me","Building AI dev tools with LLMs","2026-11-14 06:14:46",{"source":8,"skillName":5,"commands":58,"prompt":68,"zipAvailable":69},[59,62,65],{"tool":60,"command":61},"npx","npx skills add davila7\u002Fclaude-code-templates --skill opentargets-database",{"tool":63,"command":64},"bunx","bunx skills add davila7\u002Fclaude-code-templates --skill opentargets-database",{"tool":66,"command":67},"pnpm","pnpm dlx skills add davila7\u002Fclaude-code-templates --skill opentargets-database","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fscientific\u002Fopentargets-database\u002FSKILL.md",true,[71,77,81,85,89],{"path":72,"resourceType":73,"resourceTypeDesc":74,"sizeBytes":75,"sourceHtmlUrl":76},"references\u002Fapi_reference.md","REFERENCE","参考文档",6332,"https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fscientific\u002Fopentargets-database\u002Freferences\u002Fapi_reference.md",{"path":78,"resourceType":73,"resourceTypeDesc":74,"sizeBytes":79,"sourceHtmlUrl":80},"references\u002Fcomparison-rules.md",5723,"https:\u002F\u002Fgithub.com\u002Fnoirelab\u002Flinux-setup\u002Fblob\u002Fmain\u002Fconfigs\u002Fcommon\u002Fclaude\u002Fskills\u002Fseo-drift\u002Freferences\u002Fcomparison-rules.md",{"path":82,"resourceType":73,"resourceTypeDesc":74,"sizeBytes":83,"sourceHtmlUrl":84},"references\u002Fevidence_types.md",8765,"https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fscientific\u002Fopentargets-database\u002Freferences\u002Fevidence_types.md",{"path":86,"resourceType":73,"resourceTypeDesc":74,"sizeBytes":87,"sourceHtmlUrl":88},"references\u002Ftarget_annotations.md",10292,"https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fscientific\u002Fopentargets-database\u002Freferences\u002Ftarget_annotations.md",{"path":90,"resourceType":91,"resourceTypeDesc":92,"sizeBytes":93,"sourceHtmlUrl":94},"scripts\u002Fquery_opentargets.py","SCRIPT","脚本",10641,"https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fscientific\u002Fopentargets-database\u002Fscripts\u002Fquery_opentargets.py",[96,123,150,179,214,238],{"skillNo":97,"name":98,"nameZh":6,"description":99,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":100,"categories":101,"keywords":103,"publishedAt":42},"01M70NHBTQ8BV0A2SCAZXEPHCX","wealthville-pool-scoring","Score DeFi liquidity pools before providing liquidity. Returns a 0-100 pool score and an Enter\u002FHold\u002FExit\u002FReduce\u002FAvoid verdict with calibrated confidence for ~68,800 Solana pools and 575 EVM pools, plus a public miss-inclusive track record. Use when asked whether a pool is worth LPing into, which pools look best right now, or how accurate the scores have actually been.","https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fweb-data\u002Fwealthville-pool-scoring\u002FSKILL.md",[102],{"categoryNo":24,"categoryName":25,"taxonomyType":21,"taxonomyTypeDesc":22},[104,105,106,107,108,41,109,110,111,112,113,114,115,116,117,118,119,120,121,122],"scoring","pool","wealthville pool scoring","liquidity","which","exit","now","use","when","reduce","with","record","track","verdict","evm","solana","how","public","look",{"skillNo":124,"name":125,"nameZh":6,"description":126,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":127,"categories":128,"keywords":130,"publishedAt":42},"01M70MB6VR8ERJ4EM8D5KHBMEV","technical-debt-auditor","Scans a codebase and produces a quantified technical debt report with a prioritized remediation plan. Analyzes dead code, TODO\u002FFIXME\u002FHACK markers, dependency staleness, complexity hotspots, code duplication signals, test coverage gaps, unused exports, and outdated patterns. Use this skill when the user asks to audit their codebase for tech debt, wants a health check of their code quality, says things like \"where should I focus refactoring\", \"find code smells\", \"audit my codebase\", \"what technical debt do we have\", \"prioritize cleanup work\", or asks about code quality metrics. Also trigger when the user mentions \"code rot\", \"legacy cleanup\", \"refactoring priorities\", or wants to understand the overall health of a project before a major effort. Trigger even if the user doesn't say \"technical debt\" explicitly — any request to systematically assess code quality and identify improvement priorities belongs here.","https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fdevelopment\u002Ftechnical-debt-auditor\u002FSKILL.md",[129],{"categoryNo":24,"categoryName":25,"taxonomyType":21,"taxonomyTypeDesc":22},[131,132,133,134,135,136,137,138,139,140,141,112,142,143,144,145,146,147,148,149],"technical debt","debt","technical","technical debt auditor","auditor","coverage","complexity","markers","project","cleanup","unused","code","todo","work","plan","focus","signals","audit","dependency",{"skillNo":151,"name":152,"nameZh":6,"description":153,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":154,"categories":155,"keywords":163,"publishedAt":42},"01M70KPYH9QNHCNME5GJQGE22K","readonly-sql-guard","Make an agent's database access provably read-only. Use when an agent runs caller-supplied SQL against a production\u002FERP\u002Fanalytics database (a \"query\" MCP tool, text-to-SQL, an admin console), or when reviewing DB-access code for write\u002FDDL\u002Fside-effect\u002Ftransaction-escape risks. Checks what a statement CALLS, not just its shape.","https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fdatabase\u002Freadonly-sql-guard\u002FSKILL.md",[156,157,158],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},{"categoryNo":24,"categoryName":25,"taxonomyType":21,"taxonomyTypeDesc":22},{"categoryNo":159,"categoryName":160,"taxonomyType":161,"taxonomyTypeDesc":162},"01JBSEEDCAT000000000000033","数据分析师","PROFESSION","适用职业",[164,165,166,167,168,169,170,41,171,172,173,174,175,176,177,111,178,27,112,34],"readonly","guard","sql guard","sql","readonly sql guard","erp","effect","read-only","db","just","tool","calls","only","MCP","access",{"skillNo":180,"name":181,"nameZh":6,"description":182,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":183,"licenseFileUrl":184,"sourceHtmlUrl":185,"categories":186,"keywords":190,"publishedAt":42},"01M6AFY6F7CC2BBZP1QD6VTNVC","web-artifacts-builder","Suite of tools for creating elaborate, multi-component claude.ai HTML artifacts using modern frontend web technologies (React, Tailwind CSS, shadcn\u002Fui). Use for complex artifacts requiring state management, routing, or shadcn\u002Fui components - not for simple single-file HTML\u002FJSX artifacts.","Apache-2.0","https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Futilities\u002Fweb-artifacts-builder\u002FLICENSE.txt","https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Futilities\u002Fweb-artifacts-builder\u002FSKILL.md",[187],{"categoryNo":188,"categoryName":189,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000009","前端开发",[191,192,193,194,195,196,197,198,199,200,201,202,203,204,205,206,207,208,209,210,211,212,41,213],"artifacts builder","web","web artifacts builder","artifacts","builder","state","routing","state management","component","css","frontend","ui","Tools","file","components","shadcn","react","Tailwind","suite","jsx","html","single-file","ui components",{"skillNo":215,"name":216,"nameZh":6,"description":217,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":183,"licenseFileUrl":218,"sourceHtmlUrl":219,"categories":220,"keywords":225,"publishedAt":42},"01M6AFWF33SFV9Z3SF4PEEE4BF","webapp-testing","Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.","https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fsecurity\u002Fwebapp-testing\u002FLICENSE.txt","https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fsecurity\u002Fwebapp-testing\u002FSKILL.md",[221,224],{"categoryNo":222,"categoryName":223,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000008","测试与质量",{"categoryNo":188,"categoryName":189,"taxonomyType":21,"taxonomyTypeDesc":22},[226,227,228,229,230,192,231,201,202,232,233,234,235,41,236,114,237],"webapp testing","testing","webapp","browser","playwright","applications","debugging","toolkit","logs","screenshots","local","behavior",{"skillNo":239,"name":240,"nameZh":6,"description":241,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":183,"licenseFileUrl":242,"sourceHtmlUrl":243,"categories":244,"keywords":252,"publishedAt":42},"01M6AF67Q67JJJ5V51JR2P52KA","discernment-nudge","After you give a substantive answer or draft that the user may act on — advice or recommendations, drafted artifacts such as goals, plans, pitches, proposals, or emails, estimates or projections, analysis or interpretation of data, factual claims they may rely on, or a multi-step argument — invoke this skill BEFORE finalizing your reply and then, if it applies, append 2-3 short follow-up questions, each tied to something specific in what you just produced, that help the user check key facts, probe the reasoning or assumptions, and notice missing context. Do this at most once per conversation. Skip it when the user asked a trivial how-to or simple lookup, wants a purely educational explanation, asked you only to format, convert, or assemble a file from content they provided, is writing code they will run, is doing creative writing or casual chat, or already asked you to double-check, cite, or review — the skill file explains these boundaries and the exact output format.","https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fproductivity\u002Fdiscernment-nudge\u002FLICENSE.txt","https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fproductivity\u002Fdiscernment-nudge\u002FSKILL.md",[245,248,249],{"categoryNo":246,"categoryName":247,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000018","写作与文案",{"categoryNo":24,"categoryName":25,"taxonomyType":21,"taxonomyTypeDesc":22},{"categoryNo":250,"categoryName":251,"taxonomyType":161,"taxonomyTypeDesc":162},"01JBSEEDCAT000000000000036","内容创作者",[253,254,255,256,257,258,29,259,194,260,204,142,261,262,263,264,265,176,266,112,267,268,269,270,271,120,272],"discernment nudge","nudge","interpretation","help","run","reasoning","writing","lookup","content","review","conversation","short","up","invoke","you","analysis","claims","argument","assemble","recommendations"]