[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6DAQZFMX264T62XDS78XYB0":3,"skill-same:01M6DAQZFMX264T62XDS78XYB0":60},{"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":18,"publishedAt":29,"linkOnly":30,"markdownContent":31,"markdownBody":32,"frontMatter":33,"refName":34,"commitSha":35,"skillDirectory":36,"forksCount":14,"repositoryHtmlUrl":37,"repositoryHomepageUrl":6,"ownerHtmlUrl":38,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":39,"install":40,"resources":53},"01M6DAQZFMX264T62XDS78XYB0","tooluniverse-gene-disease-association",null,"Find and compare gene-disease associations across multiple databases (DisGeNET, OpenTargets, Monarch Initiative, OMIM, GenCC, Orphanet, ClinVar). Produces a unified evidence table with confidence levels and cross-database concordance. Use when users ask about gene-disease links, disease genes, genetic basis of disease, or want to compare association evidence across sources.","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-gene-disease-association\u002FSKILL.md",[],[19,20,21,22,23,24,25,26,27,28],"tooluniverse gene disease association","database","table","find","ask","use","evidence","databases","evidence table","across","2026-11-10 10:12:30",false,"---\nname: tooluniverse-gene-disease-association\ndescription: Find and compare gene-disease associations across multiple databases (DisGeNET, OpenTargets, Monarch Initiative, OMIM, GenCC, Orphanet, ClinVar). Produces a unified evidence table with confidence levels and cross-database concordance. Use when users ask about gene-disease links, disease genes, genetic basis of disease, or want to compare association evidence across sources.\n---\n\n# Gene-Disease Association Analysis\n\nSystematically query and compare gene-disease associations across 6+ databases to produce a unified, evidence-graded report. Cross-references DisGeNET scores, OpenTargets evidence, Monarch Initiative cross-species data, OMIM Mendelian mappings, GenCC curated validity, and Orphanet rare disease links.\n\n**IMPORTANT**: Always use English gene names and disease terms in tool calls. Respond in the user's language.\n\n---\n\n## LOOK UP, DON'T GUESS\nWhen uncertain about any scientific fact, SEARCH databases first (PubMed, UniProt, ChEMBL, ClinVar, etc.) rather than reasoning from memory. A database-verified answer is always more reliable than a guess.\n\n---\n\n## Core Principles\n\n1. **Report-first approach** - Create report file FIRST, then populate progressively\n2. **Multi-database triangulation** - Query 4+ sources minimum, cross-validate\n3. **Quantitative scoring** - Report numeric scores from each database\n4. **Concordance analysis** - Count how many databases support each association and reason about independence\n5. **Evidence reasoning** - Assess each association using evidence hierarchy, concordance, and mechanism plausibility\n6. **Mendelian vs complex** - Distinguish monogenic (OMIM\u002FOrphanet) from complex (GWAS\u002FDisGeNET) associations\n7. **Negative results documented** - \"No association found in [database]\" is informative\n\n---\n\n## Workflow Overview\n\n```\nPhase 1: Gene\u002FDisease Identification & ID Resolution\n  Resolve gene symbol to Ensembl ID, HGNC CURIE, MIM number\n  OR resolve disease name to UMLS CUI, EFO ID, MONDO ID, ORPHA code\n      |\nPhase 2: DisGeNET Associations (scored, multi-evidence)\n  Gene-disease association scores with evidence type filtering\n      |\nPhase 3: OpenTargets Associations (integrated evidence)\n  Disease phenotypes and genetic associations from OpenTargets\n      |\nPhase 4: Monarch Initiative (cross-species evidence)\n  Gene-disease associations integrating OMIM, ClinVar, model organisms\n      |\nPhase 5: Mendelian Disease Evidence (curated)\n  OMIM gene-disease map, GenCC validity classifications, Orphanet rare diseases\n      |\nPhase 6: Variant-Disease Associations (optional, if gene query)\n  DisGeNET variant-disease links, ClinVar pathogenic variants\n      |\nPhase 7: Evidence Synthesis\n  Unified table, concordance scoring, confidence levels, final report\n```\n\n---\n\n## Phase 1: Gene\u002FDisease Identification & ID Resolution\n\n```python\nfrom tooluniverse import ToolUniverse\ntu = ToolUniverse()\ntu.load_tools()\n\n# Gene query: resolve IDs\ngene_info = tu.tools.MyGene_query_genes(query=f\"symbol:{gene_symbol}\", species=\"human\",\n    fields=\"symbol,ensembl.gene,entrezgene,name\", size=5)  # -> ensembl_id\nmonarch_search = tu.tools.MonarchV3_search(query=gene_symbol, category=\"biolink:Gene\", limit=5)  # -> HGNC CURIE\nomim_result = tu.tools.OMIM_search(query=gene_symbol, limit=5)  # -> MIM number\ngene_summary = tu.tools.Harmonizome_get_gene(gene_symbol=gene_symbol)\n\n# Disease query: resolve IDs\nmonarch_disease = tu.tools.MonarchV3_search(query=disease_name, category=\"biolink:Disease\", limit=5)  # -> MONDO CURIE\nmappings = tu.tools.MonarchV3_get_mappings(entity_id=mondo_id, limit=20)  # -> OMIM, ICD10, SNOMED, Orphanet\n```\n\n---\n\n## Phase 2: DisGeNET Associations\n\n> **API KEY REQUIRED**: DisGeNET tools require `DISGENET_API_KEY` environment variable. Without it, all DisGeNET calls will fail. Register at https:\u002F\u002Fwww.disgenet.org\u002Fapi\u002F#\u002FAuthorization for a free academic key.\n> **Fallback if no key**: Skip this phase and rely on OpenTargets (Phase 3) + Monarch (Phase 4) which are free and cover much of the same data.\n\n```python\n# Gene -> diseases\ndisgenet_diseases = tu.tools.DisGeNET_search_gene(gene=gene_symbol, limit=20)\ndisgenet_gda = tu.tools.DisGeNET_get_gda(gene=gene_symbol, source=\"CURATED\", min_score=0.3, limit=25)\n\n# Disease -> genes (accepts name or UMLS CUI like \"C0006142\")\ndisgenet_genes = tu.tools.DisGeNET_search_disease(disease=disease_name, limit=20)\ndisgenet_ranked = tu.tools.DisGeNET_get_disease_genes(disease=disease_name, min_score=0.3, limit=50)\n```\n\n**Interpreting DisGeNET scores**: Higher scores reflect more evidence sources and stronger curation. Rather than memorizing cutoffs, ask: is this score driven by curated sources or text-mining? Use `source=\"CURATED\"` to distinguish.\n\n---\n\n## Phase 3: OpenTargets Associations\n\n```python\not_diseases = tu.tools.OpenTargets_get_diseases_phenotypes_by_target_ensembl(ensemblId=ensembl_id)\not_evidence = tu.tools.OpenTargets_target_disease_evidence(ensemblId=ensembl_id, efoId=efo_id)\n# Both require pre-resolved Ensembl\u002FEFO IDs. Use OpenTargets_multi_entity_search to discover IDs.\n```\n\n---\n\n## Phase 4: Monarch Initiative Associations\n\n```python\n# Gene -> diseases (integrates OMIM, ClinVar, Orphanet, model organisms)\nmonarch_diseases = tu.tools.MonarchV3_get_associations(\n    subject=hgnc_curie, category=\"biolink:CausalGeneToDiseaseAssociation\", limit=20)\n# Disease -> genes\nmonarch_genes = tu.tools.MonarchV3_get_associations(\n    subject=mondo_id, category=\"biolink:CorrelatedGeneToDiseaseAssociation\", limit=20)\nhistopheno = tu.tools.MonarchV3_get_histopheno(entity_id=mondo_id)  # phenotypes by body system\nentity = tu.tools.MonarchV3_get_entity(entity_id=hgnc_curie)  # details, synonyms, xrefs\n```\n\n---\n\n## Phase 5: Mendelian Disease Evidence\n\n> **API KEY REQUIRED**: OMIM tools require `OMIM_API_KEY`. Register at https:\u002F\u002Fomim.org\u002Fapi for academic access.\n> **Fallback if no key**: Use Monarch Initiative (`biolink:CausalGeneToDiseaseAssociation` from Phase 4) which includes OMIM data without requiring a key. Also use GenCC (below) which is fully open.\n\n```python\n# OMIM: Mendelian gene-disease mapping (use gene MIM number, not phenotype MIM)\nomim_entry = tu.tools.OMIM_get_entry(mim_number=mim_number)\nomim_gene_map = tu.tools.OMIM_get_gene_map(mim_number=mim_number)\nomim_clinical = tu.tools.OMIM_get_clinical_synopsis(mim_number=phenotype_mim)\n\n# GenCC: curated validity (Definitive\u002FStrong\u002FModerate\u002FLimited\u002FDisputed\u002FRefuted)\ngencc_result = tu.tools.GenCC_search_gene(gene_symbol=gene_symbol)  # handles gene renames\ngencc_disease = tu.tools.GenCC_search_disease(disease=\"Marfan syndrome\")  # word-tokenized matching\ngencc_classifications = tu.tools.GenCC_get_classifications(gene_symbol=\"BRCA1\", disease=\"breast cancer\")\n\n# Orphanet: rare disease associations (filter results by exact gene.symbol match)\norphanet_result = tu.tools.Orphanet_get_gene_diseases(gene_name=gene_symbol)\n```\n\n---\n\n## Phase 6: Variant-Disease Associations (Optional)\n\nRun when the query is gene-based and variant-level evidence adds value.\n\n```python\nvda_result = tu.tools.DisGeNET_get_vda(gene=gene_symbol, limit=25)  # variant-disease links\nclinvar_result = tu.tools.ClinVar_search_variants(gene=gene_symbol, max_results=20)\nclinvar_detail = tu.tools.ClinVar_get_variant_details(variant_id=\"12345\")  # detailed variant info\n```\n\n---\n\n## Phase 7: Evidence Synthesis\n\n### Unified Association Table\n\nCompile all results into a single table per gene-disease pair:\n\n```markdown\n## Gene-Disease Associations for BRCA1\n\n| Disease | DisGeNET Score | OpenTargets Score | Monarch | OMIM | GenCC | Orphanet | Sources |\n|---------|---------------|-------------------|---------|------|-------|----------|---------|\n| Breast cancer | 0.82 | 0.95 | Yes | #114480 | Definitive | ORPHA:227535 | 6\u002F6 |\n| Ovarian cancer | 0.78 | 0.91 | Yes | #604370 | Definitive | ORPHA:213500 | 6\u002F6 |\n| Pancreatic cancer | 0.35 | 0.42 | Yes | - | Moderate | - | 3\u002F6 |\n| Fanconi anemia | 0.45 | 0.38 | Yes | #605724 | Strong | ORPHA:84 | 5\u002F6 |\n```\n\n### Reasoning Strategies for Evidence Evaluation\n\n**Evidence strength reasoning**: A gene-disease association supported by multiple independent lines of evidence (genetic, functional, model organism) is stronger than one supported by a single study. Ask: how many independent sources support this link? Do they converge on the same mechanism?\n\n**Genetic evidence hierarchy**: Mendelian segregation (gene mutation causes disease in family) > GWAS (statistical association in population) > candidate gene study (hypothesis-driven). The first proves causation. The second shows correlation. The third is hypothesis. OMIM\u002FGenCC \"Definitive\" entries represent the top of this hierarchy; DisGeNET text-mining hits represent the bottom.\n\n**Cross-database concordance**: If DisGeNET, OpenTargets, AND OMIM all link gene X to disease Y, that's strong concordance. If only one database shows the link, check why -- is it a single study indexed by that database? Concordance across databases does not equal independent evidence if they all cite the same primary study. Count the number of databases supporting each association, but reason about whether they represent truly independent evidence.\n\n**Mechanism reasoning**: Knowing the gene's function helps evaluate the association. A gene encoding a liver enzyme being linked to liver disease is mechanistically plausible. The same gene being linked to a psychiatric disorder needs stronger evidence because the mechanism is less obvious. Use Harmonizome gene summaries and Monarch phenotype profiles to assess mechanistic plausibility.\n\n---\n\n## Common Patterns\n\n- **Gene-centric**: MyGene ID resolution -> DisGeNET\u002FOpenTargets\u002FMonarch\u002FOMIM\u002FGenCC\u002FOrphanet -> unified table ranked by concordance\n- **Disease-centric**: MonarchV3 disease search -> DisGeNET disease genes -> Monarch\u002FOMIM -> unified gene table ranked by evidence\n- **Gene-disease pair**: Resolve both IDs -> query all databases for the specific pair -> deep evidence summary with variant-level data\n- **Mendelian discovery**: OMIM_search -> OMIM_get_gene_map -> GenCC per gene -> Orphanet -> filter by curated validity\n- **Cross-species**: Monarch associations (HP\u002FMP\u002FZP phenotypes) + DisGeNET ANIMAL_MODELS source -> model organism evidence\n- **Gene renames**: GenCC handles renames automatically via `_gene_matches()`. Other tools require current HGNC symbol from MyGene_query_genes.\n\n---\n\n## Troubleshooting\n\n- **DisGeNET returns empty**: Check DISGENET_API_KEY. Try UMLS CUI instead of disease name.\n- **OMIM returns no gene map**: Use the gene MIM number, not the phenotype MIM number.\n- **Monarch returns no associations**: Verify CURIE format (HGNC:1100 not HGNC:BRCA1). Use MonarchV3_search first.\n- **OpenTargets returns no diseases**: Verify Ensembl ID via MyGene_query_genes with `fields=\"ensembl.gene\"`.\n- **GenCC returns empty**: Not all genes have classifications. Check for gene renames.\n- **GenCC disease search misses**: Simplify query (e.g., \"breast cancer\" not \"hereditary breast and ovarian cancer syndrome\").\n- **Gene rename misses in non-GenCC tools**: Only GenCC handles renames automatically. Use MyGene_query_genes to confirm the current canonical symbol.\n\n---\n\n## Resources\n\nFor comprehensive disease reports: [tooluniverse-disease-research](..\u002Ftooluniverse-disease-research\u002FSKILL.md)\nFor rare disease diagnosis: [tooluniverse-rare-disease-diagnosis](..\u002Ftooluniverse-rare-disease-diagnosis\u002FSKILL.md)\nFor variant interpretation: [tooluniverse-variant-interpretation](..\u002Ftooluniverse-variant-interpretation\u002FSKILL.md)\nFor drug-target validation: [tooluniverse-drug-target-validation](..\u002Ftooluniverse-drug-target-validation\u002FSKILL.md)\n","# Gene-Disease Association Analysis\n\nSystematically query and compare gene-disease associations across 6+ databases to produce a unified, evidence-graded report. Cross-references DisGeNET scores, OpenTargets evidence, Monarch Initiative cross-species data, OMIM Mendelian mappings, GenCC curated validity, and Orphanet rare disease links.\n\n**IMPORTANT**: Always use English gene names and disease terms in tool calls. Respond in the user's language.\n\n---\n\n## LOOK UP, DON'T GUESS\nWhen uncertain about any scientific fact, SEARCH databases first (PubMed, UniProt, ChEMBL, ClinVar, etc.) rather than reasoning from memory. A database-verified answer is always more reliable than a guess.\n\n---\n\n## Core Principles\n\n1. **Report-first approach** - Create report file FIRST, then populate progressively\n2. **Multi-database triangulation** - Query 4+ sources minimum, cross-validate\n3. **Quantitative scoring** - Report numeric scores from each database\n4. **Concordance analysis** - Count how many databases support each association and reason about independence\n5. **Evidence reasoning** - Assess each association using evidence hierarchy, concordance, and mechanism plausibility\n6. **Mendelian vs complex** - Distinguish monogenic (OMIM\u002FOrphanet) from complex (GWAS\u002FDisGeNET) associations\n7. **Negative results documented** - \"No association found in [database]\" is informative\n\n---\n\n## Workflow Overview\n\n```\nPhase 1: Gene\u002FDisease Identification & ID Resolution\n  Resolve gene symbol to Ensembl ID, HGNC CURIE, MIM number\n  OR resolve disease name to UMLS CUI, EFO ID, MONDO ID, ORPHA code\n      |\nPhase 2: DisGeNET Associations (scored, multi-evidence)\n  Gene-disease association scores with evidence type filtering\n      |\nPhase 3: OpenTargets Associations (integrated evidence)\n  Disease phenotypes and genetic associations from OpenTargets\n      |\nPhase 4: Monarch Initiative (cross-species evidence)\n  Gene-disease associations integrating OMIM, ClinVar, model organisms\n      |\nPhase 5: Mendelian Disease Evidence (curated)\n  OMIM gene-disease map, GenCC validity classifications, Orphanet rare diseases\n      |\nPhase 6: Variant-Disease Associations (optional, if gene query)\n  DisGeNET variant-disease links, ClinVar pathogenic variants\n      |\nPhase 7: Evidence Synthesis\n  Unified table, concordance scoring, confidence levels, final report\n```\n\n---\n\n## Phase 1: Gene\u002FDisease Identification & ID Resolution\n\n```python\nfrom tooluniverse import ToolUniverse\ntu = ToolUniverse()\ntu.load_tools()\n\n# Gene query: resolve IDs\ngene_info = tu.tools.MyGene_query_genes(query=f\"symbol:{gene_symbol}\", species=\"human\",\n    fields=\"symbol,ensembl.gene,entrezgene,name\", size=5)  # -> ensembl_id\nmonarch_search = tu.tools.MonarchV3_search(query=gene_symbol, category=\"biolink:Gene\", limit=5)  # -> HGNC CURIE\nomim_result = tu.tools.OMIM_search(query=gene_symbol, limit=5)  # -> MIM number\ngene_summary = tu.tools.Harmonizome_get_gene(gene_symbol=gene_symbol)\n\n# Disease query: resolve IDs\nmonarch_disease = tu.tools.MonarchV3_search(query=disease_name, category=\"biolink:Disease\", limit=5)  # -> MONDO CURIE\nmappings = tu.tools.MonarchV3_get_mappings(entity_id=mondo_id, limit=20)  # -> OMIM, ICD10, SNOMED, Orphanet\n```\n\n---\n\n## Phase 2: DisGeNET Associations\n\n> **API KEY REQUIRED**: DisGeNET tools require `DISGENET_API_KEY` environment variable. Without it, all DisGeNET calls will fail. Register at https:\u002F\u002Fwww.disgenet.org\u002Fapi\u002F#\u002FAuthorization for a free academic key.\n> **Fallback if no key**: Skip this phase and rely on OpenTargets (Phase 3) + Monarch (Phase 4) which are free and cover much of the same data.\n\n```python\n# Gene -> diseases\ndisgenet_diseases = tu.tools.DisGeNET_search_gene(gene=gene_symbol, limit=20)\ndisgenet_gda = tu.tools.DisGeNET_get_gda(gene=gene_symbol, source=\"CURATED\", min_score=0.3, limit=25)\n\n# Disease -> genes (accepts name or UMLS CUI like \"C0006142\")\ndisgenet_genes = tu.tools.DisGeNET_search_disease(disease=disease_name, limit=20)\ndisgenet_ranked = tu.tools.DisGeNET_get_disease_genes(disease=disease_name, min_score=0.3, limit=50)\n```\n\n**Interpreting DisGeNET scores**: Higher scores reflect more evidence sources and stronger curation. Rather than memorizing cutoffs, ask: is this score driven by curated sources or text-mining? Use `source=\"CURATED\"` to distinguish.\n\n---\n\n## Phase 3: OpenTargets Associations\n\n```python\not_diseases = tu.tools.OpenTargets_get_diseases_phenotypes_by_target_ensembl(ensemblId=ensembl_id)\not_evidence = tu.tools.OpenTargets_target_disease_evidence(ensemblId=ensembl_id, efoId=efo_id)\n# Both require pre-resolved Ensembl\u002FEFO IDs. Use OpenTargets_multi_entity_search to discover IDs.\n```\n\n---\n\n## Phase 4: Monarch Initiative Associations\n\n```python\n# Gene -> diseases (integrates OMIM, ClinVar, Orphanet, model organisms)\nmonarch_diseases = tu.tools.MonarchV3_get_associations(\n    subject=hgnc_curie, category=\"biolink:CausalGeneToDiseaseAssociation\", limit=20)\n# Disease -> genes\nmonarch_genes = tu.tools.MonarchV3_get_associations(\n    subject=mondo_id, category=\"biolink:CorrelatedGeneToDiseaseAssociation\", limit=20)\nhistopheno = tu.tools.MonarchV3_get_histopheno(entity_id=mondo_id)  # phenotypes by body system\nentity = tu.tools.MonarchV3_get_entity(entity_id=hgnc_curie)  # details, synonyms, xrefs\n```\n\n---\n\n## Phase 5: Mendelian Disease Evidence\n\n> **API KEY REQUIRED**: OMIM tools require `OMIM_API_KEY`. Register at https:\u002F\u002Fomim.org\u002Fapi for academic access.\n> **Fallback if no key**: Use Monarch Initiative (`biolink:CausalGeneToDiseaseAssociation` from Phase 4) which includes OMIM data without requiring a key. Also use GenCC (below) which is fully open.\n\n```python\n# OMIM: Mendelian gene-disease mapping (use gene MIM number, not phenotype MIM)\nomim_entry = tu.tools.OMIM_get_entry(mim_number=mim_number)\nomim_gene_map = tu.tools.OMIM_get_gene_map(mim_number=mim_number)\nomim_clinical = tu.tools.OMIM_get_clinical_synopsis(mim_number=phenotype_mim)\n\n# GenCC: curated validity (Definitive\u002FStrong\u002FModerate\u002FLimited\u002FDisputed\u002FRefuted)\ngencc_result = tu.tools.GenCC_search_gene(gene_symbol=gene_symbol)  # handles gene renames\ngencc_disease = tu.tools.GenCC_search_disease(disease=\"Marfan syndrome\")  # word-tokenized matching\ngencc_classifications = tu.tools.GenCC_get_classifications(gene_symbol=\"BRCA1\", disease=\"breast cancer\")\n\n# Orphanet: rare disease associations (filter results by exact gene.symbol match)\norphanet_result = tu.tools.Orphanet_get_gene_diseases(gene_name=gene_symbol)\n```\n\n---\n\n## Phase 6: Variant-Disease Associations (Optional)\n\nRun when the query is gene-based and variant-level evidence adds value.\n\n```python\nvda_result = tu.tools.DisGeNET_get_vda(gene=gene_symbol, limit=25)  # variant-disease links\nclinvar_result = tu.tools.ClinVar_search_variants(gene=gene_symbol, max_results=20)\nclinvar_detail = tu.tools.ClinVar_get_variant_details(variant_id=\"12345\")  # detailed variant info\n```\n\n---\n\n## Phase 7: Evidence Synthesis\n\n### Unified Association Table\n\nCompile all results into a single table per gene-disease pair:\n\n```markdown\n## Gene-Disease Associations for BRCA1\n\n| Disease | DisGeNET Score | OpenTargets Score | Monarch | OMIM | GenCC | Orphanet | Sources |\n|---------|---------------|-------------------|---------|------|-------|----------|---------|\n| Breast cancer | 0.82 | 0.95 | Yes | #114480 | Definitive | ORPHA:227535 | 6\u002F6 |\n| Ovarian cancer | 0.78 | 0.91 | Yes | #604370 | Definitive | ORPHA:213500 | 6\u002F6 |\n| Pancreatic cancer | 0.35 | 0.42 | Yes | - | Moderate | - | 3\u002F6 |\n| Fanconi anemia | 0.45 | 0.38 | Yes | #605724 | Strong | ORPHA:84 | 5\u002F6 |\n```\n\n### Reasoning Strategies for Evidence Evaluation\n\n**Evidence strength reasoning**: A gene-disease association supported by multiple independent lines of evidence (genetic, functional, model organism) is stronger than one supported by a single study. Ask: how many independent sources support this link? Do they converge on the same mechanism?\n\n**Genetic evidence hierarchy**: Mendelian segregation (gene mutation causes disease in family) > GWAS (statistical association in population) > candidate gene study (hypothesis-driven). The first proves causation. The second shows correlation. The third is hypothesis. OMIM\u002FGenCC \"Definitive\" entries represent the top of this hierarchy; DisGeNET text-mining hits represent the bottom.\n\n**Cross-database concordance**: If DisGeNET, OpenTargets, AND OMIM all link gene X to disease Y, that's strong concordance. If only one database shows the link, check why -- is it a single study indexed by that database? Concordance across databases does not equal independent evidence if they all cite the same primary study. Count the number of databases supporting each association, but reason about whether they represent truly independent evidence.\n\n**Mechanism reasoning**: Knowing the gene's function helps evaluate the association. A gene encoding a liver enzyme being linked to liver disease is mechanistically plausible. The same gene being linked to a psychiatric disorder needs stronger evidence because the mechanism is less obvious. Use Harmonizome gene summaries and Monarch phenotype profiles to assess mechanistic plausibility.\n\n---\n\n## Common Patterns\n\n- **Gene-centric**: MyGene ID resolution -> DisGeNET\u002FOpenTargets\u002FMonarch\u002FOMIM\u002FGenCC\u002FOrphanet -> unified table ranked by concordance\n- **Disease-centric**: MonarchV3 disease search -> DisGeNET disease genes -> Monarch\u002FOMIM -> unified gene table ranked by evidence\n- **Gene-disease pair**: Resolve both IDs -> query all databases for the specific pair -> deep evidence summary with variant-level data\n- **Mendelian discovery**: OMIM_search -> OMIM_get_gene_map -> GenCC per gene -> Orphanet -> filter by curated validity\n- **Cross-species**: Monarch associations (HP\u002FMP\u002FZP phenotypes) + DisGeNET ANIMAL_MODELS source -> model organism evidence\n- **Gene renames**: GenCC handles renames automatically via `_gene_matches()`. Other tools require current HGNC symbol from MyGene_query_genes.\n\n---\n\n## Troubleshooting\n\n- **DisGeNET returns empty**: Check DISGENET_API_KEY. Try UMLS CUI instead of disease name.\n- **OMIM returns no gene map**: Use the gene MIM number, not the phenotype MIM number.\n- **Monarch returns no associations**: Verify CURIE format (HGNC:1100 not HGNC:BRCA1). Use MonarchV3_search first.\n- **OpenTargets returns no diseases**: Verify Ensembl ID via MyGene_query_genes with `fields=\"ensembl.gene\"`.\n- **GenCC returns empty**: Not all genes have classifications. Check for gene renames.\n- **GenCC disease search misses**: Simplify query (e.g., \"breast cancer\" not \"hereditary breast and ovarian cancer syndrome\").\n- **Gene rename misses in non-GenCC tools**: Only GenCC handles renames automatically. Use MyGene_query_genes to confirm the current canonical symbol.\n\n---\n\n## Resources\n\nFor comprehensive disease reports: [tooluniverse-disease-research](..\u002Ftooluniverse-disease-research\u002FSKILL.md)\nFor rare disease diagnosis: [tooluniverse-rare-disease-diagnosis](..\u002Ftooluniverse-rare-disease-diagnosis\u002FSKILL.md)\nFor variant interpretation: [tooluniverse-variant-interpretation](..\u002Ftooluniverse-variant-interpretation\u002FSKILL.md)\nFor drug-target validation: [tooluniverse-drug-target-validation](..\u002Ftooluniverse-drug-target-validation\u002FSKILL.md)\n",{"name":5,"description":7},"main","a298c929b6cbd662e1fce54302ce520d5ceea1a5",".agents\u002Flibrary\u002Fskills\u002Ftooluniverse-gene-disease-association","https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain","https:\u002F\u002Fgithub.com\u002FPrekzursil","2026-11-02 14:30:57",{"source":8,"skillName":5,"commands":41,"prompt":51,"zipAvailable":52},[42,45,48],{"tool":43,"command":44},"npx","npx skills add Prekzursil\u002Fagent-skills-toolchain --skill tooluniverse-gene-disease-association",{"tool":46,"command":47},"bunx","bunx skills add Prekzursil\u002Fagent-skills-toolchain --skill tooluniverse-gene-disease-association",{"tool":49,"command":50},"pnpm","pnpm dlx skills add Prekzursil\u002Fagent-skills-toolchain --skill tooluniverse-gene-disease-association","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002F.agents\u002Flibrary\u002Fskills\u002Ftooluniverse-gene-disease-association\u002FSKILL.md",true,[54],{"path":55,"resourceType":56,"resourceTypeDesc":57,"sizeBytes":58,"sourceHtmlUrl":59},"resources\u002Fimplementation-playbook.md","REFERENCE","参考文档",20936,"https:\u002F\u002Fgithub.com\u002Fsapsapshen\u002Fai-memory-router\u002Fblob\u002Fmain\u002Fskills-store\u002Fglobal\u002Fstride-analysis-patterns\u002Fresources\u002Fimplementation-playbook.md",[61,82,113,140,154,170],{"skillNo":62,"name":63,"nameZh":6,"description":64,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":65,"categories":66,"keywords":67,"publishedAt":29},"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",[],[68,69,70,71,72,73,74,75,76,24,77,78,79,80,81],"clarify requirements","clarify","requirements","risk","options","task","prompts","goal","scanning","context","repo","injection","execution","file",{"skillNo":83,"name":84,"nameZh":6,"description":85,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":86,"categories":87,"keywords":93,"publishedAt":29},"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",[88],{"categoryNo":89,"categoryName":90,"taxonomyType":91,"taxonomyTypeDesc":92},"01JBSEEDCAT000000000000023","Skill与智能体开发","SCENARIO","使用场景",[94,95,96,97,98,99,100,101,102,103,104,105,106,107,24,108,109,110,111,112],"openmm md","how","decision","pick","linux","analyze","tool","stack","open","NVIDIA","gpu","license","workflow","windows","free","molecular dynamics","local","do","MCP",{"skillNo":114,"name":115,"nameZh":6,"description":116,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":117,"categories":118,"keywords":125,"publishedAt":29},"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",[119,122],{"categoryNo":120,"categoryName":121,"taxonomyType":91,"taxonomyTypeDesc":92},"01JBSEEDCAT000000000000003","演示文稿",{"categoryNo":123,"categoryName":124,"taxonomyType":91,"taxonomyTypeDesc":92},"01JBSEEDCAT000000000000008","测试与质量",[126,127,128,129,130,131,132,133,134,135,95,136,137,138,139],"review","visual","visual review","pages","web","false","iteration","take","check","slides","ui","screenshot","playwright","screenshots",{"skillNo":141,"name":142,"nameZh":6,"description":143,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":144,"categories":145,"keywords":146,"publishedAt":29},"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",[],[142,147,148,149,150,151,152,153],"setup","report","project","installation","project setup","issues","state",{"skillNo":155,"name":156,"nameZh":6,"description":157,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":158,"categories":159,"keywords":161,"publishedAt":29},"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",[160],{"categoryNo":89,"categoryName":90,"taxonomyType":91,"taxonomyTypeDesc":92},[156,162,73,163,164,165,24,166,167,168,169],"start issue","issue","ready","work on issue","user","work","work on","development",{"skillNo":171,"name":147,"nameZh":6,"description":172,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":173,"categories":174,"keywords":175,"publishedAt":29},"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",[],[147,149,110,176,151,177],"files","interactive"]