TogoMCP

schema_info: title: MediaDive - Microbial Culture Media Database description: | Comprehensive culture media database from DSMZ with 3,289 standardized recipes for bacteria, archaea, fungi, yeast, microalgae, and phages. Includes 1,489 ingredients with chemical cross-references (GMO 41%, CAS 39%, ChEBI 32%), 45,685 strain records (73% with BacDive links), and growth conditions (pH, temperature, oxygen). Hierarchical recipe structure: medium → solution → solution_recipe → ingredient with detailed preparation protocols. endpoint: https://rdfportal.org/primary/sparql base_uri: https://purl.dsmz.de/mediadive/ graphs: - http://rdfportal.org/dataset/mediadive version: mie_version: "1.0" mie_created: "2024-12-08" data_version: "Current" update_frequency: "Regular" license: data_license: "CC BY 4.0" license_url: "https://www.dsmz.de" access: rate_limiting: "Reasonable use" max_query_timeout: "60 seconds" backend: "Virtuoso" shape_expressions: | PREFIX schema: <https://purl.dsmz.de/schema/> PREFIX dct: <http://purl.org/dc/terms/> <MediumShape> { a [ schema:CultureMedium ] ; rdfs:label xsd:string ; schema:belongsToGroup xsd:string ; schema:hasFinalPH xsd:string ? ; schema:hasMinPH xsd:float ? ; schema:hasMaxPH xsd:float ? ; schema:isComplex xsd:boolean } <IngredientShape> { a [ schema:Ingredient ] ; rdfs:label xsd:string ; schema:hasFormula xsd:string ? ; schema:hasCAS xsd:string ? ; schema:hasChEBI xsd:integer ? ; schema:hasPubChem xsd:integer ? ; schema:hasKEGG xsd:string ? ; schema:hasGMO IRI ? } <MediumCompositionShape> { a [ schema:MediumComposition ] ; schema:partOfMedium @<MediumShape> ; schema:containsIngredient @<IngredientShape> ; schema:gramsPerLiter xsd:float ? ; schema:isOptionalIngredient xsd:boolean } <GrowthShape> { a [ schema:GrowthCondition ] ; schema:partOfMedium @<MediumShape> ; schema:relatedToStrain @<StrainShape> ; schema:growthTemperature xsd:integer ; schema:growthPH xsd:float ? ; schema:hasOxygenRequirement xsd:string ? } <StrainShape> { a [ schema:Strain ] ; schema:hasDSMNumber xsd:integer ; schema:hasBacDiveID xsd:integer ? ; schema:hasSpecies xsd:string ; schema:belongsTaxGroup xsd:string } sample_rdf_entries: - title: "Culture Medium" description: "Complete medium with pH and classification." rdf: | mediadive:medium/1118 a schema:CultureMedium ; rdfs:label "MD1-MEDIUM" ; schema:belongsToGroup "MD1-MEDIUM" ; schema:hasFinalPH "7.0-7.2" ; schema:isComplex true . - title: "Ingredient with Cross-References" description: "Chemical ingredient with multiple database identifiers." rdf: | mediadive:ingredient/234 a schema:Ingredient ; rdfs:label "Glucose" ; schema:hasFormula "C6H12O6" ; schema:hasCAS "50-99-7" ; schema:hasChEBI 17234 ; schema:hasPubChem 5793 ; schema:hasKEGG "C00031" . - title: "Growth Conditions" description: "Strain cultivation parameters." rdf: | mediadive:growth/5678 a schema:GrowthCondition ; schema:partOfMedium mediadive:medium/1118 ; schema:relatedToStrain mediadive:strain/12345 ; schema:growthTemperature 37 ; schema:growthPH 7.2 ; schema:hasOxygenRequirement "aerobic" . - title: "Solution Recipe" description: "Ingredient amounts in solution." rdf: | mediadive:solution_recipe/890 a schema:SolutionRecipe ; schema:partOfSolution mediadive:solution/sol123 ; schema:includesIngredient mediadive:ingredient/234 ; schema:ingredientAmount 10.0 ; schema:ingredientUnit "g" ; schema:gramsPerLiter 10.0 . - title: "Microbial Strain" description: "Strain with taxonomic data and BacDive link." rdf: | mediadive:strain/12345 a schema:Strain ; schema:hasDSMNumber 12345 ; schema:hasBacDiveID 167744 ; schema:hasSpecies "Desulfotomaculum antarcticum" ; schema:belongsTaxGroup "Bacteria" . sparql_query_examples: - title: "Search Media by Keyword" description: "Find culture media by label/group keywords using bif:contains." question: "Which media are for marine organisms?" complexity: "basic" sparql: | PREFIX schema: <https://purl.dsmz.de/schema/> SELECT ?medium ?label ?group FROM <http://rdfportal.org/dataset/mediadive> WHERE { ?medium a schema:CultureMedium ; rdfs:label ?label ; schema:belongsToGroup ?group . ?label bif:contains "'marine'" } ORDER BY ?label LIMIT 30 - title: "Retrieve Medium Properties" description: "Get functional properties and growth characteristics." question: "What are the properties of specific media?" complexity: "basic" sparql: | PREFIX schema: <https://purl.dsmz.de/schema/> SELECT ?medium ?label ?ph ?isComplex ?docLink FROM <http://rdfportal.org/dataset/mediadive> WHERE { VALUES ?medium { <https://purl.dsmz.de/mediadive/medium/1118> } ?medium a schema:CultureMedium ; rdfs:label ?label ; schema:isComplex ?isComplex . OPTIONAL { ?medium schema:hasFinalPH ?ph } OPTIONAL { ?medium schema:hasLinkToSource ?docLink } } - title: "Search by pH Range" description: "Find media within specific pH ranges." question: "Which media have pH between 6.5 and 7.5?" complexity: "intermediate" sparql: | PREFIX schema: <https://purl.dsmz.de/schema/> SELECT ?medium ?label ?minPH ?maxPH FROM <http://rdfportal.org/dataset/mediadive> WHERE { ?medium a schema:CultureMedium ; rdfs:label ?label ; schema:hasMinPH ?minPH ; schema:hasMaxPH ?maxPH . FILTER(?minPH >= 6.5 && ?maxPH <= 7.5) } ORDER BY ?minPH LIMIT 20 - title: "Growth by Temperature" description: "Find thermophilic organism conditions." question: "What growth conditions exist above 45°C?" complexity: "intermediate" sparql: | PREFIX schema: <https://purl.dsmz.de/schema/> SELECT ?medium ?strain ?temp ?ph ?oxygen FROM <http://rdfportal.org/dataset/mediadive> WHERE { ?growth a schema:GrowthCondition ; schema:partOfMedium ?medium ; schema:relatedToStrain ?strain ; schema:growthTemperature ?temp . OPTIONAL { ?growth schema:growthPH ?ph } OPTIONAL { ?growth schema:hasOxygenRequirement ?oxygen } FILTER(?temp > 45) } ORDER BY DESC(?temp) LIMIT 20 - title: "Medium Composition" description: "Get complete ingredient list with concentrations." question: "What are the ingredients in a specific medium?" complexity: "intermediate" sparql: | PREFIX schema: <https://purl.dsmz.de/schema/> SELECT ?medium ?mediumLabel ?ingredient ?ingredientLabel ?gPerL FROM <http://rdfportal.org/dataset/mediadive> WHERE { ?composition a schema:MediumComposition ; schema:partOfMedium ?medium ; schema:containsIngredient ?ingredient ; schema:gramsPerLiter ?gPerL . ?medium rdfs:label ?mediumLabel . ?ingredient rdfs:label ?ingredientLabel . FILTER(?medium = <https://purl.dsmz.de/mediadive/medium/1118>) } ORDER BY DESC(?gPerL) - title: "Ingredient Cross-References" description: "Link ingredients to chemical databases." question: "Which ingredients have ChEBI and KEGG?" complexity: "advanced" sparql: | PREFIX schema: <https://purl.dsmz.de/schema/> SELECT ?ingredient ?label ?chebi ?kegg ?pubchem ?cas FROM <http://rdfportal.org/dataset/mediadive> WHERE { ?ingredient a schema:Ingredient ; rdfs:label ?label . OPTIONAL { ?ingredient schema:hasChEBI ?chebi } OPTIONAL { ?ingredient schema:hasKEGG ?kegg } OPTIONAL { ?ingredient schema:hasPubChem ?pubchem } OPTIONAL { ?ingredient schema:hasCAS ?cas } FILTER(BOUND(?chebi) && BOUND(?kegg)) } ORDER BY ?label LIMIT 30 - title: "Strain-Medium Compatibility" description: "Map strains to compatible media with growth indicators." question: "Which media support specific bacterial strains?" complexity: "advanced" sparql: | PREFIX schema: <https://purl.dsmz.de/schema/> SELECT ?strain ?species ?medium ?mediumLabel ?temp FROM <http://rdfportal.org/dataset/mediadive> WHERE { ?growth a schema:GrowthCondition ; schema:relatedToStrain ?strain ; schema:partOfMedium ?medium ; schema:growthTemperature ?temp ; schema:hasGrowthIndicator true . ?strain schema:hasSpecies ?species . ?medium rdfs:label ?mediumLabel . } ORDER BY ?species ?medium LIMIT 40 cross_references: - pattern: "schema:has[Database] properties" description: "Ingredients link to chemical databases via dedicated properties." databases: chemical_identifiers: ["GMO (41%)", "CAS (39%)"] metabolic: ["ChEBI (32%)", "PubChem (18%)", "KEGG (13%)", "MetaCyc (7%)"] regional: ["ZVG (15%)"] sparql: | SELECT ?ingredient ?cas ?chebi ?kegg ?gmo FROM <http://rdfportal.org/dataset/mediadive> WHERE { ?ingredient a schema:Ingredient . OPTIONAL { ?ingredient schema:hasCAS ?cas } OPTIONAL { ?ingredient schema:hasChEBI ?chebi } OPTIONAL { ?ingredient schema:hasKEGG ?kegg } OPTIONAL { ?ingredient schema:hasGMO ?gmo } FILTER(BOUND(?cas) || BOUND(?chebi)) } LIMIT 50 - pattern: "schema:hasBacDiveID" description: "Strains link to BacDive for phenotypic data." databases: microbial: ["BacDive (73% of 45,685 strains)"] sparql: | SELECT ?strain ?dsmNumber ?bacDiveID ?species FROM <http://rdfportal.org/dataset/mediadive> WHERE { ?strain a schema:Strain ; schema:hasDSMNumber ?dsmNumber ; schema:hasBacDiveID ?bacDiveID ; schema:hasSpecies ?species . } LIMIT 30 - pattern: "schema:hasLinkToSource" description: "Media link to DSMZ PDF documentation." databases: documentation: ["DSMZ PDFs (99% of 3,289 media)"] sparql: | SELECT ?medium ?label ?pdfLink FROM <http://rdfportal.org/dataset/mediadive> WHERE { ?medium a schema:CultureMedium ; rdfs:label ?label ; schema:hasLinkToSource ?pdfLink . } LIMIT 30 architectural_notes: schema_design: - "Medium as central hub: compositions, solutions, growth conditions, steps" - "Hierarchical recipe: medium → solution → solution_recipe → ingredient" - "Strain-medium via growth conditions for cultivation compatibility" performance: - "Use bif:contains for label/group/species keyword searches" - "pH/temperature numeric filtering efficient" - "Composition queries can be large - filter by specific medium" - "Use OPTIONAL for partial cross-reference coverage" data_integration: - "GMO highest coverage (41%) for metabolic context" - "CAS Registry (39%) for chemical identification" - "BacDive (73%) for microbial phenotypes" - "DSMZ PDFs (99%) for authoritative protocols" data_quality: - "pH: string ranges (hasFinalPH) + numeric min/max" - "Cross-reference coverage varies by database" - "Use isOptionalIngredient flag for flexibility" data_statistics: total_media: 3289 total_ingredients: 1489 total_strains: 45685 coverage: ingredients_gmo: "41%" ingredients_cas: "39%" ingredients_chebi: "32%" strains_bacdive: "73%" media_pdf_links: "99%" cardinality: avg_compositions_per_medium: 21.9 avg_solution_recipes_per_solution: 7.2 performance_characteristics: - "Temperature/pH numeric filtering efficient" - "Use bif:contains for keyword searches" - "Composition queries need medium filters" - "LIMIT 30-50 recommended" anti_patterns: - title: "FILTER Instead of bif:contains" problem: "Using FILTER CONTAINS for keyword searches is inefficient." wrong_sparql: | SELECT ?medium ?label WHERE { ?medium a schema:CultureMedium ; rdfs:label ?label . FILTER(CONTAINS(LCASE(?label), "marine")) } correct_sparql: | SELECT ?medium ?label WHERE { ?medium a schema:CultureMedium ; rdfs:label ?label . ?label bif:contains "'marine'" } explanation: "Use bif:contains for full-text search - faster and supports boolean operators." - title: "Missing OPTIONAL for Partial Coverage" problem: "Requiring all cross-references filters out most ingredients." wrong_sparql: | SELECT ?ingredient ?chebi ?kegg ?pubchem WHERE { ?ingredient a schema:Ingredient ; schema:hasChEBI ?chebi ; schema:hasKEGG ?kegg ; schema:hasPubChem ?pubchem . } correct_sparql: | SELECT ?ingredient ?chebi ?kegg ?pubchem WHERE { ?ingredient a schema:Ingredient . OPTIONAL { ?ingredient schema:hasChEBI ?chebi } OPTIONAL { ?ingredient schema:hasKEGG ?kegg } OPTIONAL { ?ingredient schema:hasPubChem ?pubchem } FILTER(BOUND(?chebi) || BOUND(?kegg)) } explanation: "Use OPTIONAL for properties with partial coverage, then filter for at least one." - title: "Unbounded Composition Queries" problem: "Composition queries without medium filter return too many rows." wrong_sparql: | SELECT ?composition ?medium ?ingredient ?gPerL WHERE { ?composition schema:partOfMedium ?medium ; schema:containsIngredient ?ingredient ; schema:gramsPerLiter ?gPerL . } correct_sparql: | SELECT ?composition ?medium ?ingredient ?gPerL WHERE { ?composition schema:partOfMedium ?medium ; schema:containsIngredient ?ingredient ; schema:gramsPerLiter ?gPerL . FILTER(?medium = <https://purl.dsmz.de/mediadive/medium/1118>) } LIMIT 50 explanation: "Filter by specific medium or use LIMIT to avoid timeouts." common_errors: - error: "Keyword search failures" causes: - "Using FILTER CONTAINS instead of bif:contains" - "Not wrapping keywords in single quotes" solutions: - "Use bif:contains for full-text search" - "Format: ?label bif:contains \"'keyword'\"" - "Boolean: ?label bif:contains \"'keyword1' OR 'keyword2'\"" - error: "Empty cross-reference results" causes: - "Requiring all databases (AND logic)" - "Not using OPTIONAL for partial coverage" solutions: - "Use OPTIONAL for each database property" - "Filter with OR: FILTER(BOUND(?chebi) || BOUND(?kegg))" - "Coverage: GMO 41%, CAS 39%, ChEBI 32%" - error: "Query timeout on compositions" causes: - "No medium filter with 72K+ compositions" - "Missing LIMIT clause" solutions: - "Filter by specific medium first" - "Use LIMIT 50-100" - "Avg 21.9 compositions per medium"