MCP Server Proto-OKN

[ { "name": "biobricks-aopwiki", "display_name": "Biobricks Aopwiki", "named_graph_uri": "https://purl.org/okn/frink/kg/biobricks-aopwiki", "endpoint_url": "https://frink.apps.renci.org/biobricks-aopwiki/sparql", "domain_tags": [ "toxicology", "biology", "health" ], "description_summary": "The BioBricks AOP-Wiki knowledge graph serves toxicologists, regulatory scientists, and environmental health researchers by providing structured representations of Adverse Outcome Pathways (AOPs) that link molecular initiating events to adverse health outcomes. This knowledge graph contains 493 AOPs, 1,469 key events, and 2,060 key event relationships, totaling 184,303 triples that capture the mechanistic understanding of chemical toxicity pathways. The dataset integrates chemical entities (including CHEMINF molecular descriptors), biological processes (GO terms), and organism/organ/cell-type contexts, with extensive cross-references to ChEBI, ChEMBL, PubChem, KEGG, and Wikidata through 13,692 exact matches and additional identifier mappings. Licensed under CC-BY-SA-1.0 with regular updates (last modified November 2024), the graph is derived from the collaborative AOP-Wiki project and is accessible via a SPARQL endpoint through FRINK, enabling federated queries for chemical hazard assessment and predictive toxicology applications.", "entity_types": { "classes": [ "Adverse Outcome Pathway (AOP)", "Key Event (KE)", "Key Event Relationship (KER)", "Biological Process", "Organ Context", "Cell Type Context", "Chemical Identifier", "Chemical Information", "CAS Registry Number", "InChI", "InChIKey", "PubChem Compound ID", "ChEBI Identifier", "SMILES", "Taxonomic Classification", "Gene Identifier", "Protein Identifier", "Pathway Identifier", "Disease or Disorder" ], "predicates": [ "Has Molecular Initiating Event", "Has Key Event", "Has Adverse Outcome", "Has Key Event Relationship", "Has Upstream Key Event", "Has Downstream Key Event", "Has Chemical Entity", "Has Evidence", "Label", "Title", "Description", "Creator", "Identifier", "Created", "Modified" ], "has_edge_properties": false }, "identifier_namespaces": [ "CAS", "ChEBI", "ChEMBL", "PubChem", "InChIKey" ], "example_queries": [ "What adverse outcome pathways involve estrogen receptor activation?" ] }, { "name": "biobricks-ice", "display_name": "Biobricks Ice", "named_graph_uri": "https://purl.org/okn/frink/kg/biobricks-ice", "endpoint_url": "https://frink.apps.renci.org/biobricks-ice/sparql", "domain_tags": [ "toxicology", "chemistry", "biology" ], "description_summary": "BioBricks ICE (Integrated Chemical Environment) is an open knowledge graph that serves toxicologists, computational chemists, and environmental health researchers by integrating chemical safety and bioassay data from the EPA's NICEATM ICE database. The graph contains 27.4 million triples describing 206,543 chemical entities linked to over 3 million bioassay measurements across 2,063 standardized assays. Core entities include chemical substances (identified via EPA DSSTox IDs), bioassays (BAO ontology), assay measurements, and mechanistic targets with gene and UMLS identifiers. The graph employs established vocabularies including the BioAssay Ontology (BAO), Chemical Information Ontology (CHEMINF), Semanticscience Integrated Ontology (SIO), and Relation Ontology (RO). External linkages to EPA CompTox Dashboard, NCBI Gene, and UMLS enable cross-database queries. Licensed as public domain (CC0-1.0), the graph supports federation with other toxicology and biomedical knowledge graphs.", "entity_types": { "classes": [ "Bioassay Result", "Chemical Entity", "Chemical Identifier", "Database Entry", "Bioassay", "Chemical Structure Descriptor", "Chemical Information", "Biological Target", "Gene Identifier", "Assay Design" ], "predicates": [ "May Inform On", "Source", "Participates In", "Has Participant", "Type", "Assay Source", "UMLS Concept", "In Vitro Assay Format", "Assay Tissue", "Through Mechanistic Target", "Label", "Has Identifier", "Has Specified Output", "NCI Mechanistic Target", "Assay Species", "Has Assay Component", "Entrez Gene ID", "Has Unit", "Is About", "Has Value", "Has Exposure" ], "has_edge_properties": false }, "identifier_namespaces": [ "DTXSID", "NCBI_Gene", "InChIKey", "CAS" ], "example_queries": [ "What bioassays are available for a specific chemical?", "What is the toxicity profile of bisphenol A?" ] }, { "name": "biobricks-mesh", "display_name": "Biobricks Mesh", "named_graph_uri": "https://purl.org/okn/frink/kg/biobricks-mesh", "endpoint_url": "https://frink.apps.renci.org/biobricks-mesh/sparql", "domain_tags": [ "biology", "health", "vocabulary" ], "description_summary": "BioBricks MeSH is an open knowledge graph providing the complete Medical Subject Headings (MeSH) controlled vocabulary from the U.S. National Library of Medicine in RDF format for biomedical researchers, data scientists, and information professionals. The graph contains over 18.1 million triples representing 2.4 million biomedical entities organized into 862,579 terms, 464,362 concepts, and 249,243 chemical substance records alongside 66,110 organisms, 29,940 topical descriptors, and 6,750 diseases. The hierarchical structure is maintained through 80,096 tree numbers with parent-child relationships and complex concept mappings. Entities are richly labeled with standard rdfs:label properties (achieving 98%+ coverage across major classes) and include temporal metadata with the latest revisions dating to January 2023. Licensed as public domain (CC0-1.0), the dataset is available through a SPARQL endpoint at FRINK, enabling direct federated queries with other biomedical knowledge graphs that reference MeSH identifiers.", "entity_types": { "classes": [ "Descriptor (Main Heading)", "Qualifier (Subheading)", "Supplementary Concept Record", "Topical Descriptor", "Publication Type", "Geographical Descriptor", "Concept", "Term", "Anatomy [A]", "Organisms [B]", "Diseases [C]", "Chemicals and Drugs [D]", "Analytical, Diagnostic and Therapeutic Techniques and Equipment [E]", "Psychiatry and Psychology [F]", "Phenomena and Processes [G]", "Disciplines and Occupations [H]", "Anthropology, Education, Sociology and Social Phenomena [I]", "Technology, Industry, Agriculture [J]", "Humanities [K]", "Information Science [L]", "Named Groups [M]", "Health Care [N]", "Publication Characteristics [V]", "Geographicals [Z]", "Asthma", "Diabetes Mellitus", "Hypertension", "Carcinoma", "COVID-19", "Acetaminophen", "Anti-Bacterial Agents", "Body Mass Index", "Magnetic Resonance Imaging", "Pregnancy", "diagnosis", "therapeutic use", "adverse effects", "epidemiology", "genetics", "prevention & control" ], "predicates": [ "Label", "Preferred Concept", "Has Concept", "Has Term", "Preferred Term", "Broader Descriptor", "Narrower Descriptor", "Tree Number", "Allowable Qualifier", "Pharmacological Action", "Scope Note", "Broader", "Narrower" ], "has_edge_properties": false }, "identifier_namespaces": [ "MeSH" ], "example_queries": [] }, { "name": "biobricks-pubchem-annotations", "display_name": "Biobricks Pubchem Annotations", "named_graph_uri": "https://purl.org/okn/frink/kg/biobricks-pubchem-annotations", "endpoint_url": "https://frink.apps.renci.org/biobricks-pubchem-annotations/sparql", "domain_tags": [ "chemistry", "toxicology", "pharmacology" ], "description_summary": "BioBricks PubChem Annotations is an open knowledge graph providing structured access to chemical annotations originally sourced from PubChem's Annotations subset, targeting researchers in cheminformatics, toxicology, and environmental health. The graph contains over 10.7 million annotations (87.4 million triples total) describing chemical compounds through text-based annotations including regulatory data, physical properties, biological activities, and hazard information. Each annotation follows the W3C Web Annotation Data Model, linking PubChem compound identifiers to textual annotation bodies covering topics from state-level contaminant limits to chemical synthesis methods. The knowledge graph interoperates with the broader PubChem RDF ecosystem through shared compound URIs in the namespace. Annotations derive from multiple heterogeneous sources with varying licenses, documented in PubChem's source metadata.", "entity_types": { "classes": [ "Annotation", "PubChem Compound", "PubChem Substance", "Textual Body", "Chemical Property Annotation", "Biological Activity Annotation", "Toxicology Data Annotation", "Pharmacology Data Annotation", "Literature Reference Annotation", "Patent Data Annotation", "Synonym Annotation", "Annotation ANID1", "Annotation ANID10", "Annotation ANID100" ], "predicates": [ "Has Body", "Has Target", "Type", "Value", "Format", "Subject", "Chemical Name", "Molecular Formula", "InChI", "SMILES", "Has Attribute", "Has Value" ], "has_edge_properties": false }, "identifier_namespaces": [ "PubChem", "InChI", "InChIKey", "SMILES" ], "example_queries": [] }, { "name": "biobricks-tox21", "display_name": "Biobricks Tox21", "named_graph_uri": "https://purl.org/okn/frink/kg/biobricks-tox21", "endpoint_url": "https://frink.apps.renci.org/biobricks-tox21/sparql", "domain_tags": [ "toxicology", "chemistry" ], "description_summary": "BioBricks Tox21 is an open knowledge graph that transforms the Tox21 quantitative high-throughput screening (qHTS) 10K library data into structured, machine-readable RDF format. The source dataset contains over 120 million chemical assay data points across 70+ distinct assays for evaluating potential toxicity of approximately 10,000 diverse chemicals. This knowledge graph represents 8,947 chemical entities with ~27,000 triples, primarily using Chemical Information Ontology (CHEMINF) classes to describe compounds. Each chemical is identified using standardized CAS Registry Numbers through identifiers.org URIs and linked to its Tox21 source data. Developed by Insilica LLC as part of the NSF-funded BioBricks-OKG project (Award #2333728), the graph aims to harmonize chemical safety data for researchers, regulatory agencies, and pharmaceutical companies. The dataset is released under CC0-1.0 (Public Domain) license .", "entity_types": { "classes": [ "Chemical Identifier" ], "predicates": [ "Label", "Source", "Type" ], "has_edge_properties": false }, "identifier_namespaces": [ "CAS" ], "example_queries": [ "What chemicals have been tested in Tox21 assays?" ] }, { "name": "biobricks-toxcast", "display_name": "Biobricks Toxcast", "named_graph_uri": "https://purl.org/okn/frink/kg/biobricks-toxcast", "endpoint_url": "https://frink.apps.renci.org/biobricks-toxcast/sparql", "domain_tags": [ "toxicology", "chemistry" ], "description_summary": "BioBricks ToxCast is an open knowledge graph for computational toxicology researchers, regulatory scientists, and environmental health professionals seeking standardized access to EPA ToxCast high-throughput screening data. The graph contains 3.34 million bioassay screening results linking 9,542 chemical entities to 2,205 distinct assay endpoints, enabling systematic exploration of chemical-bioactivity relationships across diverse toxicological targets. Each chemical is identified by both EPA DSSTox Substance Identifiers (DTXSID) and InChIKeys, supporting cross-reference to external chemical databases. The knowledge graph employs standardized vocabularies including the BioAssay Ontology (BAO), Chemical Information Ontology (CHEMINF), and Biolink, ensuring semantic interoperability with other toxicology and biomedical knowledge graphs. Data is derived from EPA's public domain ToxCast database and released under CC0-1.0. Users can query the graph via SPARQL at the FRINK infrastructure endpoint to integrate ToxCast screening data with complementary datasets for compound prioritization, adverse outcome pathway analysis, and mechanism-based risk assessment.", "entity_types": { "classes": [ "Chemical Entity", "Chemical Identifier", "Bioassay", "Chemical Structure Descriptor", "Chemical Information", "Biological Target", "Assay Design" ], "predicates": [ "Label", "Source", "Has Identifier", "Participates In", "Assay ID", "Has Participant", "Type", "Has Specified Output", "Has Assay Component", "Is About", "Has Value" ], "has_edge_properties": false }, "identifier_namespaces": [ "DTXSID", "InChIKey", "CAS" ], "example_queries": [ "What high-throughput screening results exist for PFAS chemicals?" ] }, { "name": "biohealth", "display_name": "Biohealth", "named_graph_uri": "https://purl.org/okn/frink/kg/biohealth", "endpoint_url": "https://frink.apps.renci.org/biohealth/sparql", "domain_tags": [ "biology", "health", "social_determinants" ], "description_summary": "Bio-Health KG is a comprehensive health knowledge graph developed by the University of Virginia under NSF funding (Award #2333740) that integrates biomedical facts with Social Determinants of Health (SDoH) data to address healthcare disparities. The graph contains over 110 million triples representing 250,976 biomedical entities interconnected through 18.3 million biomedical relationships. It continuously updates from streams of scientific literature (primarily PubMed) and Electronic Health Records (including MIMIC clinical data), enabling real-time integration of emerging research findings. Core semantic relationships leverage the Biolink vocabulary with predicates including location_of, affects, treats, coexists_with, and causes, while custom schema extensions capture clinical processes and measurements. The knowledge graph employs reified statements (RDF reification) for comprehensive provenance tracking. The project aims to uncover associations between social determinants and health outcomes to improve healthcare equity.", "entity_types": { "classes": [], "predicates": [], "has_edge_properties": false }, "identifier_namespaces": [ "MONDO", "MeSH", "UMLS" ], "example_queries": [ "What social determinants are associated with diabetes?" ] }, { "name": "climatemodelskg", "display_name": "Climatemodelskg", "named_graph_uri": "https://purl.org/okn/frink/kg/climatemodelskg", "endpoint_url": "https://frink.apps.renci.org/climatemodelskg/sparql", "domain_tags": [ "climate", "environment", "geospatial" ], "description_summary": "The Climate Models Knowledge Graph integrates structured information about climate models, experiments, and research outputs to support climate science evaluation and development. Built for climate researchers, model developers, and policy analysts, it contains 1.4 million triples describing 55,890 entities across 48 classes. The graph centers on climate model documentation, linking 394 Sources (GCMs, RCMs) to 481 Experiments conducted by 132 Institutes, producing 2,907 climate Variables measured across extensive geographic coverage including 30,062 Cities, 252 Countries, and 3,893 subdivisions. Regional climate models cover approximately 400,000 geographic locations. Entities connect to GeoNames identifiers enabling geospatial integration, while the custom ontology () structures relationships between models, physical schemes, metrics, and results. The knowledge graph supports CMIP6-related research and regional climate modeling studies.", "entity_types": { "classes": [ "Activity", "City", "Continent", "Country_Subdivision", "Country", "Domain", "Ensemble", "Experiment", "ExperimentFamily", "Field", "Forcing", "Frequency", "GridLabel", "Innovation", "Institute", "Instrument", "Keyword", "Member", "Method", "Metric", "MIPEra", "Model", "Natural_Hazard", "NaturalHazardType", "No_Country_Region", "ObservationalDataset", "Ocean_Circulation", "Paper", "PhysicalFeature", "PhysicalScheme", "Platform", "Problem", "Project", "RCM", "Realm", "Resolution", "Result", "SimulationType", "Source", "SourceComponent", "SourceType", "SubExperiment", "Task", "Teleconnection", "Variable", "Water_Bodies", "Weather_Event" ], "predicates": [ "APPLIES_TO_REALM", "ASSOCIATED_WITH_MEMBER", "BELONGS_TO_MIP_ERA", "CORRESPONDS_TO", "COVERS_DOMAIN", "COVERS_REGION", "DRIVEN_BY_SOURCE", "FOCUSES_ON_REALM", "GENERATED_BY_ACTIVITY", "HAS_METRIC", "HAS_PHYSICAL_FEATURE", "HAS_SIMULATION_TYPE", "HAS_SOURCE_COMPONENT", "HAS_SPATIAL_RESOLUTION", "HAS_SUB_EXPERIMENT", "HAS_SUBSEQUENT_VERSION", "IN_CONTINENT", "IN_COUNTRY", "INCLUDES_ENSEMBLE_MEMBER", "INCLUDES_EXPERIMENT", "INHERITED_FROM", "IS_OF_TYPE", "METHOD_EXPERIMENTS_ON_OBSERVATIONAL_DATASET", "METHOD_HAS_INNOVATION", "METHOD_HAS_RESULT", "METHOD_SOLVES_PROBLEM", "METHOD_USES_METRIC", "METHOD_USES_MODEL", "METHOD_WORKS_ON_TASK", "MODEL_EXPERIMENTS_ON_OBSERVATIONAL_DATASET", "MODEL_HAS_RESULT", "MODEL_SOLVES_PROBLEM", "MODEL_USES_METRIC", "MODEL_WORKS_FOR_TASK", "PAPER_APPLIES_METHOD", "PAPER_BELONGS_TO_FIELD", "PAPER_EXPERIMENTS_ON_OBSERVATIONAL_DATASET", "PAPER_HAS_INNOVATION", "PAPER_HAS_KEYWORD", "PAPER_HAS_MODEL", "PAPER_HAS_RESULT", "PAPER_MENTIONS", "PAPER_SOLVES_PROBLEM", "PAPER_USES_METRIC", "PAPER_WORKS_ON_TASK", "PART_OF_ENSEMBLE", "PART_OF_PROJECT", "PARTICIPATED_IN", "PERFORMED_BY_INSTITUTE", "PRODUCED_BY_INSTITUTE", "PRODUCES_VARIABLE", "RESULT_HAS_METRIC", "SAMPLED_AT_FREQUENCY", "TASK_EXPERIMENTS_ON_OBSERVATIONAL_DATASET", "TASK_FACES_PROBLEM", "TASK_USES_METRIC", "USED_IN_EXPERIMENT", "USES_FORCING", "USES_PHYSICAL_SCHEME" ], "has_edge_properties": false }, "identifier_namespaces": [ "GeoNames" ], "example_queries": [ "What climate models cover a specific region?" ] }, { "name": "dreamkg", "display_name": "Dreamkg", "named_graph_uri": "https://purl.org/okn/frink/kg/dreamkg", "endpoint_url": "https://frink.apps.renci.org/dreamkg/sparql", "domain_tags": [ "social_services", "homelessness" ], "description_summary": "DREAM-KG (Dynamic, REsponsive, Adaptive, and Multifaceted Knowledge Graph) is an Open Knowledge Network addressing homelessness for case workers, service providers, law enforcement, nonprofits, and people experiencing homelessness. The graph integrates 87 social service organizations with their locations, contact information, and 87 distinct service offerings, structured using Schema.org vocabulary for interoperability. It contains 32,460 triples across 1,764 entities, primarily modeling service availability (609 opening hours specifications), service categories (157 CategoryCodes), and target audiences (81 audience types). Data is extensively linked to Aunt Bertha's social services directory (1,392 external references) and employs W3C PROV ontology for provenance tracking of all entities through transformation activities. Services are geocoded with latitude/longitude, categorized by populations served (abuse survivors, adults, teens, African American communities).", "entity_types": { "classes": [ "AdministrativeArea", "Audience", "CategoryCode", "ContactPoint", "OpeningHoursSpecification", "Organization", "Place", "Service", "ServiceChannel", "TextObject", "WebPage", "Activity", "Collection", "Entity" ], "predicates": [ "address", "areaServed", "audienceType", "availableChannel", "category", "closes", "codeValue", "conditionsOfAccess", "containedInPlace", "dayOfWeek", "description", "disambiguatingDescription", "hasMap", "hoursAvailable", "identifier", "inCodeSet", "latitude", "longitude", "name", "opens", "provider", "sameAs", "serviceLocation", "servicePhone", "serviceUrl", "telephone", "text", "type", "generated", "hadMember", "influenced", "wasDerivedFrom", "wasGeneratedBy", "wasInfluencedBy" ], "has_edge_properties": false }, "identifier_namespaces": [], "example_queries": [ "What social services are available for homeless individuals?" ] }, { "name": "fiokg", "display_name": "Fiokg", "named_graph_uri": "https://purl.org/okn/frink/kg/fiokg", "endpoint_url": "https://frink.apps.renci.org/fiokg/sparql", "domain_tags": [ "environment", "regulatory", "industry" ], "description_summary": "The FIO KG is a core component of the SAWGraph (Safe Agricultural Products and Water Graph) project, an NSF-funded Proto-OKN initiative to monitor and trace PFAS and other contaminants in the nation's food and water systems. This knowledge graph integrates comprehensive facility and industry classification data for the coterminous United States from EPA's Facility Registry Service (FRS), which provides an integrated source of environmental information about over 826,000 regulated facilities across air, water, and waste programs. The graph contains 2.6 million entities and over 10 million triples, structuring data around facilities, environmental records (monitoring, permits, enforcement), and NAICS industry codes. Each facility is spatially indexed using S2 cells (Level 13) and linked to environmental interest types, compliance systems, and temporal tracking records. The dataset employs standard vocabularies including Dublin Core, PROV-O, GeoSPARQL, and Schema.org, with strong external links to Data Commons (218K) and STKO-KWG geospatial resources (1.5M). Updated through July 2025, the graph supports SPARQL queries via the FRINK platform for environmental compliance research, contaminant pathway analysis, and facility-industry profiling.", "entity_types": { "classes": [ "Agency", "Agriculture", "Commerce", "Congress", "Defense", "Energy", "Health and Human Services", "Homeland Security", "Housing and Urban Development", "Interior", "Judicial", "Justice", "Labor", "State", "Transportation", "Treasury", "Veterans Affairs", "AIR PROGRAMS", "ANIMAL OPERATIONS", "ASSISTANCE AND SUPPORT PROGRAMS", "CHEMICAL RELEASE PROGRAMS", "CHEMICAL STORAGE PROGRAMS", "COASTAL AND OCEAN PROGRAMS", "Compliance Interest", "Compliance Record", "Compliance System", "DRINKING WATER PROGRAMS", "EPA PFAS Facility", "ECOLOGY OPERATIONS", "ELECTRONIC PERMIT SYSTEM", "Enforcement or Compliance record", "Enforcement Interest", "Enforcement System", "Enforcement Tracking Record", "Environmental Interest By Program", "Environmental Interest By Record Type", "Environmental Interest Type", "FRS Facility", "FACILITY/SITE IDENTIFICATION", "Facility Type", "Grant System", "GROUND WATER PROGRAMS", "HAZARDOUS WASTE PROGRAMS", "HEALTH AND SAFETY PROGRAMS", "Legacy System", "LEGAL/ENFORCEMENT ACTIVITIES", "Monitoring Record", "Permit Interest", "Permit or license record", "Permit System", "PESTICIDES PROGRAMS", "Program Information System", "Project Record", "Project System", "RADIATION PROTECTION PROGRAMS", "Facility Record", "Registration Record", "Registry Interest", "Registry System", "REMEDIATION AND REDEVELOPMENT PROGRAMS", "Reporting Interest", "Reporting Record", "Reporting System", "Risk Interest", "Risk Plan Record", "Site Interest", "Site Record", "Site System", "SOLID WASTE PROGRAMS", "State System", "State Tracking Record", "Station System", "Facility Supplemental Record", "Tribal System", "Tribal Tracking Record", "UNDERGROUND STORAGE TANK PROGRAMS", "WASTE WATER PROGRAMS", "WATER RESOURCES PROGRAMS", "Facility", "Industry", "Organization", "NAICS Industry", "NAICS Industry Code", "NAICS Industry Group", "NAICS Industry Sector", "NAICS Industry Subsector" ], "predicates": [ "from System", "in program type", "has FRS Id", "has monitoring record", "has record", "has supplemental record", "of facility type", "of program category", "of Primary Industry", "of Secondary Industry", "part Of", "replaced By", "has Facility", "of industry", "of Year", "owned By", "same code", "subcode of", "year deprecated" ], "has_edge_properties": false }, "identifier_namespaces": [ "NAICS", "S2Cell", "FIPS" ], "example_queries": [ "What regulated facilities exist in a county?" ] }, { "name": "gene-expression-atlas-okn", "display_name": "Gene Expression Atlas Okn", "named_graph_uri": "https://purl.org/okn/frink/kg/gene-expression-atlas-okn", "endpoint_url": "https://frink.apps.renci.org/gene-expression-atlas-okn/sparql", "domain_tags": [ "genomics", "biology", "health" ], "description_summary": "The Gene Expression Atlas Open Knowledge Network (gene-expression-atlas-okn) is a semantic knowledge graph containing selected studies from the EMBL-EBI Gene Expression Atlas, a curated database of gene expression experiments. This knowledge graph integrates 243 studies encompassing 797 assays that profile expression patterns across 152,879 genes. The data captures differential gene expression measurements with statistical metrics (log2 fold changes, adjusted p-values) linked to diverse biological contexts including anatomical entities, cell types, diseases, developmental life stages, and biological sex categories.\n\nBuilt using Biolink Model ontology standards, the knowledge graph connects genes to biological processes, molecular pathways, and protein domains through expression associations. Each study includes comprehensive metadata such as experimental factors, technology platforms, PubMed references, and contrast comparisons between test and reference groups. This structured representation enables systematic exploration of how gene expression varies across tissues, diseases, developmental stages, and experimental conditions, supporting integrative genomics research and cross-study meta-analyses.", "entity_types": { "classes": [ "AnatomicalEntity", "Assay", "Association", "Attribute", "BiologicalProcess", "BiologicalSex", "Cell", "Disease", "Gene", "GeneExpressionMixin", "LifeStage", "Pathway", "PopulationOfIndividualOrganisms", "ProteinDomain", "Study" ], "predicates": [ "has_attribute", "has_input", "has_output", "participates_in", "studies", "subject", "object", "predicate", "in_taxon" ], "has_edge_properties": true }, "identifier_namespaces": [ "NCBI_Gene", "Ensembl", "GeneSymbol", "UBERON", "CL", "GO" ], "example_queries": [ "What genes are differentially expressed in breast cancer?", "What tissues show high expression of BRCA1?" ], "aliases": [ "gene-expression-altlas-okn" ] }, { "name": "geoconnex", "display_name": "Geoconnex", "named_graph_uri": "https://purl.org/okn/frink/kg/geoconnex", "endpoint_url": "https://frink.apps.renci.org/geoconnex/sparql", "domain_tags": [ "hydrology", "geospatial", "environment" ], "description_summary": "Geoconnex is an open, community-contribution knowledge graph designed to link hydrologic features across the United States, making water data easily discoverable, accessible, and usable for researchers, agencies, and water managers. The graph contains over 19.2 million triples describing 1.6 million hydrologic locations including monitoring sites, dams, watersheds, stream networks, and water bodies, with extensive geospatial coverage through 763,000 point geometries and 320,000 polygon features. Built on persistent identifiers and published in accordance with Spatial Data on the Web best practices, Geoconnex harvests JSON-LD metadata from water data providers using common ontologies including schema.org for general metadata, HY-Features for hydrology, and SOSA/SSN for sensor observations. The system enables federation across organizational boundaries by maintaining persistent URIs at that prevent link rot while allowing data publishers to update their resources.", "entity_types": { "classes": [ "Aquifer System", "Aquifer Unit", "Hydrogeologic Unit", "Water Well", "VoID Dataset", "Link Set", "Linkset", "Entry Point", "List Item", "News Article", "Organization", "Person", "Search Action", "Web Page", "Web Site", "Geometry Collection", "Line String", "Point", "Polygon", "Observation Collection", "Feature Catalog", "Feature Link Set", "Data Download", "Geographic Coordinates", "Geographic Shape", "Property Value", "Catchment (Application Schema)", "Catchment Divide", "Hydrometric Feature (Application Schema)", "Catchment", "Catchment Aggregate", "Dendritic Catchment", "Flow Path", "Hydrologic Network", "Hydrologic Nexus", "Hydrologic Location", "Hydrometric Feature", "Hydrometric Network", "Hydrologic Location (Schema)", "Atmosphere", "Canal", "Ditch", "Diversion", "Estuary", "Ocean", "Shore", "Sinkhole", "Stream", "Subsurface" ], "predicates": [ "groundwater aquifer system", "contains", "conforms to", "format", "property", "target", "as WKT", "coordinate reference system", "has geometry", "has feature of interest", "connected to", "about", "content URL", "description", "distribution", "encoding format", "geographic location", "geo intersects", "geo within", "identifier", "is based on", "latitude", "line", "location", "longitude", "measurement method", "measurement technique", "name", "polygon", "property ID", "provider", "publisher", "same as", "subject of", "superseded by", "temporal coverage", "unit text", "URL", "value", "variable measured", "catchment realization", "contributing catchment", "encompassing catchment", "exorheic drainage", "hydrometric network", "inflow", "lower catchment", "network station", "nexus realization", "outflow", "realized catchment", "realized nexus", "receiving catchment", "upper catchment", "distance description", "distance from referent", "hydrologic location type", "indirect position", "containing catchment", "distance expression", "interpolative", "linear element", "referenced position", "length", "width", "mouth of watercourse", "origin of watercourse" ], "has_edge_properties": false }, "identifier_namespaces": [ "Geoconnex" ], "example_queries": [ "What monitoring sites exist in a watershed?" ] }, { "name": "hydrologykg", "display_name": "Hydrologykg", "named_graph_uri": "https://purl.org/okn/frink/kg/hydrologykg", "endpoint_url": "https://frink.apps.renci.org/hydrologykg/sparql", "domain_tags": [ "hydrology", "environment", "water_quality" ], "description_summary": "The SAWGraph Hydrology KG is part of the Safe Agricultural Products and Water Graph (SAWGraph) is an NSF-funded Proto-OKN Theme 1 initiative designed for environmental regulators, water safety officials, and PFAS researchers. This knowledge graph integrates surface water features including stream reaches and watersheds, groundwater features like aquifers, and hydrological connectivity data to support contaminant tracing and water quality analysis. The graph connects to geoconnex and KnowWhereGraph to provide geospatial relations, with locations spatially integrated via S2 cells and administrative regions using FIPS codes and ZIP codes. It enables users to trace pollutant pathways, identify upstream contamination sources, assess downstream impacts from point sources, and determine which water wells are hydrologically connected to contaminated sites. Built on open-source hydrological datasets including the National Hydrography Dataset.", "entity_types": { "classes": [ "Groundwater Aquifer", "Aquifer Water Feature", "Subsurface Water Feature", "Surface Water Feature", "Water Feature", "Water Feature Representation", "Flow Path Length", "Quantity Kind", "Quantity Value", "Unit", "Well Depth in Feet (IL)", "Well Purpose", "Well Yield", "Maine Geological Survey Well", "Well Depth in Feet", "Well Overburden Thickness in Feet", "Well Type", "Well Use", "Maine MGS aquifer ID", "Maine SAW aquifer system ID", "PWS Service Area", "PWS Service Area Type", "PWS Source Water Type", "PWS Sub-Feature", "PWS Sub-Feature Activity", "PWS Sub-Feature Type", "Public Water System", "Community Water System", "Groundwater-Based Public Water System", "Non-Community Water System", "Non-Transient Non-Community Water System", "Surface Water-Based Public Water System", "Transient Non-Community Water System", "PWS name", "Cell", "Region", "Road Segment", "S2 Cell", "S2 Cell Level 13", "ZIP Code Area", "Feature", "Geometry", "Spatial Object", "Multi-Polygon", "Polygon", "Canal", "Catchment", "Catchment Realization", "Elementary Flow Path", "Estuary", "Flow Path", "Hydrologic Feature", "Impoundment", "Lagoon", "Lake", "Main Stem", "River", "Water Body" ], "predicates": [ "groundwater aquifer system", "groundwater aquifer system part", "has COMID", "has feature code", "has feature type", "has flow path length", "has reach code", "source", "contributor", "date created", "creator", "description", "date modified", "publisher", "title", "connected to", "spatially related to", "has quantity kind", "has unit", "numeric value", "quantity value", "unit", "Illinois State Geological Survey Well", "has ISWS ID", "has owner", "well depth (IL)", "well purpose", "well yield", "Illinois SAW aquifer ID", "Illinois SAW aquifer system ID", "has use", "of well type", "well depth", "well overburden", "aquifer type", "Combined Distribution System", "buys from", "deactivation date", "first report", "has activity", "has method", "has ownership", "has part", "has permanent source", "has source", "in combined system", "last report", "part of", "population served", "primary source type", "sells to", "service area", "service area type", "service connections", "source for", "Administrative Region", "Administrative Region Level 0", "Administrative Region Level 1", "Administrative Region Level 2", "Administrative Region Level 3", "Administrative Region Level 4", "Administrative Region Level 5", "Administrative Region Level 6", "Statistical Area", "administrative part of", "spatially contains", "spatially crosses", "spatially equals", "spatially overlaps", "spatially touches", "spatially within", "spatial relation", "as WKT", "default geometry", "has default geometry", "has geometry", "domain includes", "name", "range includes", "downstream flow path", "downstream flow path (transitive closure)", "encompassing catchment", "realized catchment", "upstream flow path", "upstream water body" ], "has_edge_properties": false }, "identifier_namespaces": [ "NHDPlus_COMID", "FIPS", "S2Cell" ], "example_queries": [ "What is the hydrological connectivity between surface water features?" ] }, { "name": "nasa-gesdisc-kg", "display_name": "Nasa Gesdisc Kg", "named_graph_uri": "https://purl.org/okn/frink/kg/nasa-gesdisc-kg", "endpoint_url": "https://frink.apps.renci.org/nasa-gesdisc-kg/sparql", "domain_tags": [ "climate", "earth_science", "geospatial" ], "description_summary": "", "entity_types": { "classes": [ "DataCenter", "Dataset", "Instrument", "Platform", "Project", "Publication", "ScienceKeyword" ], "predicates": [ "date", "identifier", "subject", "label", "year", "CITES", "cmrId", "daac", "globalId", "HAS_APPLIEDRESEARCHAREA", "HAS_DATASET", "HAS_INSTRUMENT", "HAS_PLATFORM", "HAS_SCIENCEKEYWORD", "HAS_SUBCATEGORY", "landingPageUrl", "nwCorner_crs", "nwCorner_latitude", "nwCorner_longitude", "OF_PROJECT", "pagerank_publication_dataset", "seCorner_crs", "seCorner_latitude", "seCorner_longitude", "temporalFrequency", "Type", "url", "USES_DATASET", "abstract", "title" ], "has_edge_properties": false }, "identifier_namespaces": [], "example_queries": [] }, { "name": "nde", "display_name": "Nde", "named_graph_uri": "https://purl.org/okn/frink/kg/nde", "endpoint_url": "https://frink.apps.renci.org/nde/sparql", "domain_tags": [ "infectious_disease", "health", "data_discovery" ], "description_summary": "The NIAID Data Ecosystem (NDE) Knowledge Graph provides structured metadata for infectious and immune-mediated disease (IID) research resources. Developed by the National Institute of Allergy and Infectious Diseases in collaboration with Scripps Research, this knowledge graph powers the NIAID Data Ecosystem Discovery Portal (https://data.niaid.nih.gov), which aggregates millions of datasets from over 70 sources including NIAID-funded repositories and globally-relevant IID repositories.\n\nThe knowledge graph organizes metadata using Schema.org vocabulary, enabling unified search across diverse biomedical data types including -omics data, clinical studies, epidemiological data, pathogen-host interactions, flow cytometry, and imaging datasets. It connects datasets to their authors, funding sources, research projects, publications, and key disease and pathogen terms, facilitating discovery of resources related to COVID-19, HIV, malaria, tuberculosis, and other infectious diseases. By harmonizing heterogeneous metadata formats and providing both user-friendly search interfaces and programmatic API access, the NDE knowledge graph accelerates IID research and maximizes the impact of publicly-funded scientific data.", "entity_types": { "classes": [ "DataCatalog", "DataDownload", "Dataset", "DefinedTerm", "MonetaryGrant", "Organization", "Person", "ResearchProject", "ScholarlyArticle", "Class" ], "predicates": [ "abstract", "affiliation", "alternateName", "archivedAt", "author", "date", "dateCreated", "dateModified", "datePublished", "description", "endDate", "familyName", "funder", "funding", "givenName", "healthCondition", "identifier", "includedInDataCatalog", "infectiousAgent", "name", "parentOrganization", "sameAs", "species", "startDate", "url", "versionDate", "domain", "range" ], "has_edge_properties": false }, "identifier_namespaces": [ "PubMed" ], "example_queries": [] }, { "name": "nikg", "display_name": "Nikg", "named_graph_uri": "https://purl.org/okn/frink/kg/nikg", "endpoint_url": "https://frink.apps.renci.org/nikg/sparql", "domain_tags": [ "public_safety", "urban_planning", "geospatial" ], "description_summary": "The Neighborhood Information Knowledge Graph (NIKG) is a knowledge graph warehouse designed for researchers, urban planners, and public health officials analyzing neighborhood-level data. It integrates incident records (particularly crime and safety events), census tract boundaries, and geospatial location data from Philadelphia and potentially other urban areas. The graph contains structured entities including Incidents with attributes such as officer involvement, fatality status, offender demographics (race, sex, age), and precise geospatial coordinates represented as WKT geometries via GeoSPARQL. NIKG links to standard geospatial vocabularies (OGC GeoSPARQL, sf:Point) and employs Philadelphia metadata schemas for domain-specific properties.", "entity_types": { "classes": [ "Point", "Class", "Block Group", "Census Tract", "Incident", "Location" ], "predicates": [ "asWKT", "hasGeometry", "age_of", "happened_at", "is_fatal", "OffenderDeceased", "OffenderInjured", "OffenderRace", "OffenderSex", "OfficerInvolved" ], "has_edge_properties": false }, "identifier_namespaces": [ "FIPS" ], "example_queries": [ "What incidents occurred in specific neighborhoods?" ] }, { "name": "ruralkg", "display_name": "Ruralkg", "named_graph_uri": "https://purl.org/okn/frink/kg/ruralkg", "endpoint_url": "https://frink.apps.renci.org/ruralkg/sparql", "domain_tags": [ "rural_health", "health", "criminal_justice" ], "description_summary": "The Rural Resilience Knowledge Graph (RuralKG) is a cross-domain semantic resource designed for researchers, policymakers, and public health professionals studying health disparities and justice outcomes in rural America. It integrates substance abuse data from the National Survey on Drug Use and Health (NSDUH), criminal justice incidents from the National Incident-Based Reporting System (NIBRS), mental health treatment provider locations, and geospatial administrative boundaries spanning 56 states/territories, 3,253 counties, and 31,120 cities. Each county is linked to USDA Rural-Urban Continuum Codes (RUCC) to facilitate rural-urban comparative analyses. The graph contains 815,852 triples describing 67,191 entities across 16 classes, with rich connections between treatment providers (9,037) and 176 mental health services. RuralKG uses a native ontology (sail.ua.edu/ruralkg) and provides standard SPARQL access for federated querying, supporting interdisciplinary research on rural health equity, substance abuse patterns, and justice system interactions.", "entity_types": { "classes": [ "City", "County", "State", "County Status", "RUCC", "Substance", "Substance Related Incident", "Mental Health Service", "Mental Health Service Category", "Treatment Provider", "NIBRS", "NIBRS Answer", "NSDUH", "NSDUH Answer", "Class", "Ontology" ], "predicates": [ "Created", "Creator", "Description", "Has Version", "Title", "Abbreviation", "Contains Place", "FIPS", "Latitude", "Longitude", "Name", "Primary County", "Ranking", "Has Variable", "Census County", "Code", "Has RUCC", "Population", "Year", "Concept Type", "Domain Category", "From Dataset", "Hierarchy Level", "Identifier", "Address", "Alias", "Contains Service", "In City", "Phone", "Provides Service", "Zipcode", "Answer Code", "Answer Content", "Content", "Generated Description", "Has Answer", "Comment", "Is Defined By", "Label", "Subclass Of" ], "has_edge_properties": false }, "identifier_namespaces": [ "FIPS", "RUCC" ], "example_queries": [ "What substance abuse treatment providers are in rural counties?", "What is the relationship between rurality and mental health services?" ] }, { "name": "sawgraph", "display_name": "Sawgraph", "named_graph_uri": "https://purl.org/okn/frink/kg/sawgraph", "endpoint_url": "https://frink.apps.renci.org/sawgraph/sparql", "domain_tags": [ "food_safety", "water_quality", "PFAS", "environment" ], "description_summary": "SAWGraph (Safe Agricultural Products and Water Graph) is a specialized knowledge graph designed for environmental health researchers, regulatory agencies, and public health officials to track per- and polyfluoroalkyl substances (PFAS) and other contaminants in food and water systems. The graph integrates contamination measurements from Maine's EGAD drinking water monitoring program and the national Water Quality Portal, linking observations to food products (FOODON taxonomy including meat, dairy, produce, and seafood), geographic locations (administrative regions), and taxonomic entities (NCBITaxon organisms). SAWGraph employs the Contaminoso ontology (COSO) for standardized contamination modeling, connecting to external identifiers via ComptoxAI substance links and CAS numbers. Observations include measurement values, detection limits, lab qualifiers, and validation levels. The knowledge graph is updated with emerging contaminant data to support food safety assessments and regulatory compliance tracking.", "entity_types": { "classes": [ "Aggregate Contaminant Measurement", "Analysis Method", "Contaminant Absolute Quantity Kind", "Contaminant Concentration Quantity Kind", "Contaminant Measurement", "Contaminant Observation", "Contaminant Relative Measurement", "Contaminant Relative Quantity Kind", "Contaminant Sample Observation", "Contaminant Volume Quantity Kind", "Contamination Property", "Detect Quantity Value", "Detection Limit", "Feature", "Material Sample", "Non-Detect Quantity Value", "Observation Annotation", "Point", "Quantitation Limit", "Quantity Value", "Result Qualifier", "Sample Annotation", "Sample Material Type", "Sample Point", "Sampled Feature", "Single Contaminant Measurement", "Substance", "Substance Collection", "Feature Of Interest", "Observation", "Procedure", "Result", "Sample" ], "predicates": [ "analyzed sample", "cas number", "from sample point", "has any feature of interest", "has feature of interest", "has result", "measurement unit", "measurement value", "observation annotation", "observed at point", "observed at sample point", "observed time", "of substance", "point from feature", "result annotation", "sample annotation", "sample of material type", "substance identifier", "is sample of", "observed property", "used procedure" ], "has_edge_properties": false }, "identifier_namespaces": [ "CAS" ], "example_queries": [ "Where have PFAS been detected in drinking water?", "What food products contain contaminants?" ] }, { "name": "scales", "display_name": "Scales", "named_graph_uri": "https://purl.org/okn/frink/kg/scales", "endpoint_url": "https://frink.apps.renci.org/scales/sparql", "domain_tags": [ "criminal_justice", "legal" ], "description_summary": "SCALES (Systematic Content Analysis of Litigation Events) is an open knowledge network designed to democratize access to criminal and civil court records across the United States. The knowledge graph contains over 523 million triples describing 96.5 million entities spanning more than 4.1 million cases, including 2.4 million criminal cases and 1.8 million civil cases. The graph integrates data from federal district courts as well as state and local court systems, linking entities such as parties, attorneys, law firms, judges, charges, sentences, arrests, and bookings across cases. Built on the National Information Exchange Model (NIEM) Justice Domain standard, SCALES employs standardized vocabularies to enable systematic analysis of justice system functioning, reveal inequities, and support evidence-based policy making. The platform addresses the critical lack of nationally-accessible and linked criminal justice data.", "entity_types": { "classes": [ "Arrest", "Arrest Charge", "Attorney", "Booking", "Booking Facility", "Case Defendant Party", "Case Defense Attorney", "Case Initiating Attorney", "Case Initiating Party", "Case Judge", "Charge", "Court", "Judge", "Law Enforcement Official", "Register Action", "Register Of Actions", "Release", "Sentence", "Sentence Term", "Person", "Civil Case", "Criminal Case", "Firm", "Party" ], "predicates": [ "NIBRS report category code", "offense UCR code", "county code", "arrest official", "attorney", "bond amount", "bond type", "booking facility", "booking release", "case", "case charge", "case court", "case defendant party", "case defense attorney", "case initiating attorney", "case initiating party", "case judge", "case official role text", "charge booking", "charge disposition", "charge disposition category text", "charge sentence", "charge sequence ID", "charge severity level code", "charge subject", "charge text", "court category code", "court name", "drug category code", "judicial official category text", "participant role category text", "person charge", "person sex code", "register action date", "register action description text", "sentence", "sentence description text", "sentence term", "statute keyword text", "subject booking", "term duration", "activity date", "address postal code", "administrative ID", "case docket ID", "case general category text", "case sub category text", "contact mailing address", "court postal code", "end date", "entity name", "facility name", "jurisdiction text", "locale census block ID", "organization name", "person full name", "person ID", "person race text", "person sex text", "start date", "status description text", "birth year", "booking case", "docket entry", "docket table", "firm", "ontology label", "party", "appointed by party", "assigned to defendant", "has charge type", "has commission date", "has extra info", "has FJC node ID", "has highest offense level opening", "has highest offense level terminated", "has IFP judge attribution", "has IFP label", "has member case", "has reference to other entry", "has related case", "has UVA judge dir ID", "is in circuit", "is instance of entity" ], "has_edge_properties": false }, "identifier_namespaces": [], "example_queries": [ "How many criminal cases were filed in federal court?" ] }, { "name": "securechainkg", "display_name": "Securechainkg", "named_graph_uri": "https://purl.org/okn/frink/kg/securechainkg", "endpoint_url": "https://frink.apps.renci.org/securechainkg/sparql", "domain_tags": [ "software_security", "supply_chain" ], "description_summary": "SecureChain KG is a large-scale knowledge graph that maps software components and vulnerabilities across multiple programming languages to strengthen software supply chain security. Built for developers, security analysts, and policymakers, it contains 9.8 million entities capturing 803,769 software packages, 8.6 million software versions, 259,806 vulnerabilities, and 53,378 hardware components with their versions, interconnected through 73.5 million triples. The ontology models dependencies between software versions and other components through properties like sc:dependsOn, which help assess potential risks and identify vulnerabilities, with links to licenses ensuring compliance across the supply chain. Dominated by PyPI (603K packages) and Cargo (180K packages) ecosystems, SecureChain primarily covers Python and Rust software. Continuously updated through neural knowledge acquisition pipelines that extract information from documentation, CVEs, bug reports, and online discussions, it provides a real-time view of software supply chain risks.", "entity_types": { "classes": [ "Hardware", "Hardware Version", "License", "Software", "Software Version", "Vulnerability", "Vulnerability Type", "Person", "Manufacturer", "Material Product" ], "predicates": [ "has Hardware Version", "has Software Version", "vulnerable To", "vulnerability Type", "depends On", "manufacturer", "contributor", "license", "ecosystem", "version Name", "cpe23", "identifier", "name", "url", "programming Language" ], "has_edge_properties": false }, "identifier_namespaces": [ "CVE", "CPE" ], "example_queries": [ "What vulnerabilities affect a Python package?" ] }, { "name": "sockg", "display_name": "Sockg", "named_graph_uri": "https://purl.org/okn/frink/kg/sockg", "endpoint_url": "https://frink.apps.renci.org/sockg/sparql", "domain_tags": [ "agriculture", "soil_science", "climate" ], "description_summary": "The Soil Organic Carbon Knowledge Graph (SOCKG) serves agricultural researchers, carbon market operators, and climate scientists by consolidating fragmented soil carbon datasets into a unified semantic framework. SOCKG contains detailed agricultural experimental data including tillage events, crop rotations, fertilizer amendments, soil measurements (chemical and biological samples), weather observations, and greenhouse gas flux measurements across multiple sites and treatments. The graph models agricultural management practices (planting, grazing, irrigation, residue management) and their relationships to soil organic carbon dynamics using a custom ontology (idir.uta.edu/sockg-ontology). SOCKG links to external vocabularies including Schema.org for organizations and people, Dublin Core for bibliographic metadata, GeoSPARQL for spatial data, QUDT for units and measurements, and the USDA National Agricultural Library Thesaurus (NALT).", "entity_types": { "classes": [ "Bibliographic Resource", "Book", "Quantity Value", "Unit", "Administrative Region Level 0", "Administrative Region Level 1", "Administrative Region Level 2", "Administrative Region", "Region", "S2 Cell Level 13", "Feature", "Geometry", "Spatial Object", "Class", "Datatype", "OWL Class", "Datatype Property", "Object Property", "Ontology", "Abstract", "Active Ingredient", "Amendment", "Amendment Placement", "Amendment Type", "Animal Class", "Animal Species", "Biomass Analysis", "Biomass Carbohydrate", "Biomass Energy", "Biomass Mineral", "Book Chapter", "Broadleaf or Grass", "Chamber Placement", "Cover Crop", "Crop Related Measurement", "Cultivar", "Cutting Height", "Equipment", "Erosion Measurement", "Experimental Unit", "Fertilizer Amendment", "Funding Source", "Gas Nutrient Loss", "GHG Flux", "Grazing Management", "Grazing Plants", "Grazing Rate", "Growth Stage", "Growth Stage Management", "Growth Stage Related Measurement", "Harvested Fraction", "Harvest Fraction", "Irrigation", "Journal Article", "Location", "Losses or Deposition", "Measurable Entity", "Measurement", "Nutrient Efficiency", "Other Events", "Parameter", "Pesticide Placement", "Pesticide Target", "Plant Fraction", "Plant Fraction Related Measurement", "Planting Management", "Planting Method", "Popular Article", "Possibly Simulated Measurement", "Proceedings", "Project", "Project Scenario", "Quality Measurement", "Report", "Residue Management", "Residue Measurement", "Residue Removal", "Rotation", "Sample", "Simulation Model", "Site", "Soil Biological Sample", "Soil Chemical Sample", "Soil Cover", "Soil Physical Sample", "Soil Sample", "Species Mix", "Start Stop Interval", "Surface or Leaching", "Thesis", "Tillage", "Tillage Event", "Tillage Management", "Tillage Method", "Timing", "Treatment", "Water Quality Area", "Water Quality Concentration", "Weather Observation", "Wind Erosion Area", "Yield Nutrient Uptake", "Soil organic carbon", "Occupation", "Organization", "Person" ], "predicates": [ "bibliographic Citation", "creator", "date", "description", "identifier", "is Part Of", "issued", "title", "topological connection (spatial contact) (sawgraph)", "has Unit", "numeric Value", "quantity Value", "standard Uncertainty", "sfContains (kwg)", "sfWithin (kwg)", "CAS Number", "as WKT", "has Geometry", "comment", "domain", "label", "range", "sub Class Of", "sub Property Of", "disjoint With", "equivalent Property", "inverse Of", "bad Value Flag", "cites", "corresponding Author", "end Date", "from Project", "from Unit", "funded By", "has Amendment Type", "has Animal Class", "has Animal Species", "has Broadleaf or Grass", "has Chamber Placement", "has Crop", "has Cultivar", "has Grazing Rate", "has Growth Stage", "has Harvested Fraction", "has Losses or Deposition", "has Measurement", "has Other Events", "has Pesticide Active Ingredient", "has Pesticide Target", "has Plant Fraction", "has Project Scenario", "has Rotation", "has Species Mix", "has Surface or Leaching", "has Tillage", "has Tillage Event", "has Timing", "has Treatment", "inferred", "irrigation", "is Interpolated", "lower Depth", "of", "organic Management", "start Date", "tile Drainage", "treatment Has Amendment", "treatment Has Grazing Management", "treatment Has Growth Stage Management", "treatment Has Planting Management", "treatment Has Residue Management", "treatment Has Tillage Management", "unit Has Amendment", "unit Has Grazing Management", "unit Has Growth Stage Management", "unit Has Planting Management", "unit Has Residue Management", "unit Has Tillage Management", "unit URL", "upper Depth", "uses Cover Crop", "uses Equipment", "uses Fertilizer Amendment", "uses Irrigation", "uses Model", "uses Planting Method", "uses Residue Removal", "uses Tillage Method", "uses Treatment", "weather At", "with Cutting Height", "with Pesticide Placement", "with Placement", "with Start Stop Interval", "additional Name", "affiliation", "email", "family Name", "given Name", "has Occupation", "honorific Suffix", "is Primary Contact", "postal Code", "role", "telephone", "work Location" ], "has_edge_properties": false }, "identifier_namespaces": [], "example_queries": [ "What soil carbon measurements exist for different tillage practices?" ] }, { "name": "spatialkg", "display_name": "Spatialkg", "named_graph_uri": "https://purl.org/okn/frink/kg/spatialkg", "endpoint_url": "https://frink.apps.renci.org/spatialkg/sparql", "domain_tags": [ "geospatial", "administrative_boundaries" ], "description_summary": "The SAWGraph Spatial KG is a large-scale geospatial knowledge graph developed by the SAWGraph project for researchers and practitioners working with place-based data and spatial analytics. The graph contains 756.9 million triples describing 16.8 million spatial entities, primarily organized around GeoSPARQL-compliant spatial objects including 7.4 million S2 cells (Level 13 discretization) and hierarchical administrative regions across three levels (102 countries/Level 1, 6,228 Level 2, 35,458 Level 3 units). The knowledge graph leverages the STKO-KWG ontology and implements OGC GeoSPARQL standards, enabling interoperability with other geospatial datasets through standardized vocabularies (owl:, geosparql:, rdf:, rdfs:). Funded by NSF award #2333782, the dataset supports spatial reasoning, place-based linkage, and geographic data integration.", "entity_types": { "classes": [ "Administrative Region", "Administrative Region Level 0", "Administrative Region Level 1", "Administrative Region Level 2", "Administrative Region Level 3", "Administrative Region Level 4", "Administrative Region Level 5", "Administrative Region Level 6", "Cell", "Place", "Point of Interest", "Region", "Road Segment", "S2 Cell", "S2 Cell Level 0", "S2 Cell Level 1", "S2 Cell Level 10", "S2 Cell Level 11", "S2 Cell Level 12", "S2 Cell Level 13", "S2 Cell Level 14", "S2 Cell Level 15", "S2 Cell Level 2", "S2 Cell Level 3", "S2 Cell Level 4", "S2 Cell Level 5", "S2 Cell Level 6", "S2 Cell Level 7", "S2 Cell Level 8", "S2 Cell Level 9", "Statistical Area", "ZIP Code Area", "Feature", "Geometry", "Spatial Object" ], "predicates": [ "source", "contributor", "date created", "creator", "description", "date modified", "publisher", "title", "connected to", "spatially related to", "administrative part of", "as Well-Known Text", "cell identifier", "has default geometry", "has end time", "has FIPS code", "has geometry", "has start time", "has temporal extent", "spatially contains", "spatially crosses", "spatially disjoint", "spatially equals", "spatially intersects", "spatially overlaps", "spatially touches", "spatially within", "spatial relation", "as WKT", "default geometry", "has metric area" ], "has_edge_properties": false }, "identifier_namespaces": [ "S2Cell", "FIPS" ], "example_queries": [ "What administrative regions contain a specific location?" ] }, { "name": "spoke-genelab", "display_name": "Spoke Genelab", "named_graph_uri": "https://purl.org/okn/frink/kg/spoke-genelab", "endpoint_url": "https://frink.apps.renci.org/spoke-genelab/sparql", "domain_tags": [ "genomics", "space_biology", "biology" ], "description_summary": "", "entity_types": { "classes": [ "Assay", "Anatomy", "CellType", "Gene", "Study", "MethylationRegion", "Mission" ], "predicates": [ "CONDUCTED_MIcS", "INVESTIGATED_ASiA", "INVESTIGATED_ASiCT", "IS_ORTHOLOG_MGiG", "MEASURED_DIFFERENTIAL_EXPRESSION_ASmMG", "MEASURED_DIFFERENTIAL_METHYLATION_ASmMR", "METHYLATED_IN_MGmMR", "PERFORMED_SpAS" ], "has_edge_properties": true }, "identifier_namespaces": [ "NCBI_Gene", "GeneSymbol", "UBERON", "CL" ], "example_queries": [ "What genes are differentially expressed in spaceflight experiments?", "What are the mouse orthologs of human disease genes?", "What methylation changes occur in spaceflight studies?" ] }, { "name": "spoke-okn", "display_name": "Spoke Okn", "named_graph_uri": "https://purl.org/okn/frink/kg/spoke-okn", "endpoint_url": "https://frink.apps.renci.org/spoke-okn/sparql", "domain_tags": [ "biology", "health", "chemistry", "environment", "geospatial" ], "description_summary": "", "entity_types": { "classes": [ "Social Determinants of Health", "Administrative Area", "Chemical Entity", "Disease", "Environmental Feature", "Gene", "Organism Taxon" ], "predicates": [ "Source", "Geographic Coordinates", "Database Reference", "Type", "Comment", "Label", "See Also", "Is Subtype Of (SDoH)", "Is Subtype Of (Disease)", "Is Subtype Of (Compound)", "Is Subtype Of (Environment)", "Part Of (Location)", "Part Of (Compound)", "Found In (Compound in Location)", "Found In (Environment in Location)", "Isolated In (Organism in Location)", "Disease Prevalence in Location", "SDoH Prevalence in Location", "Disease Mortality in Location", "Associates (Disease with Gene)", "Associates (SDoH with Disease)", "Treats (Compound treats Disease)", "Contraindicates (Compound contraindicated for Disease)", "Interacts (Compound with Compound)", "Upregulates (Compound increases Gene)", "Downregulates (Compound decreases Gene)", "Expressed In (Gene expressed in Disease)", "Responds To (Organism responds to Compound)", "Resistant To (mutantGene resistant to Compound)", "Response To (mutantGene response to Compound)", "Adverse Response To (mutantGene adverse response to Compound)", "Positive Marker (Gene marker for Disease)", "Negative Marker (Gene marker against Disease)", "Resembles (Disease resembles Disease)", "Has Role (Compound has biological role)" ], "has_edge_properties": true }, "identifier_namespaces": [ "Ensembl", "DOID", "ChEBI", "InChIKey", "FIPS" ], "example_queries": [ "What drugs treat rheumatoid arthritis?", "What genes are associated with Crohn's disease?", "What is the prevalence of diabetes in California counties?", "What compounds are found in water supplies in Texas?" ], "aliases": [ "spoke" ] }, { "name": "sudokn", "display_name": "Sudokn", "named_graph_uri": "https://purl.org/okn/frink/kg/sudokn", "endpoint_url": "https://frink.apps.renci.org/sudokn/sparql", "domain_tags": [ "manufacturing", "supply_chain" ], "description_summary": "SUDOKN (Supply and Demand Open Knowledge Network) is a specialized knowledge graph connecting publicly available manufacturing capability data for Small and Medium-Sized Manufacturers (SMMs) across the United States. The graph contains detailed information about manufacturing organizations, their process capabilities (machining, welding, coating, finishing, 3D printing), material processing expertise (metals, plastics, composites), quality certifications (ISO 9000/9001, AS9100/9102), and industry alignments (aerospace, automotive, electronics, food processing). Each manufacturer is geolocated with postal addresses, coordinates, and regional identifiers, and linked to NAICS industry classifications. SUDOKN leverages the Industrial Ontologies Foundry (IOF) core ontologies for semantic interoperability, enabling federation with other manufacturing and supply chain knowledge graphs. The dataset supports supplier discovery, capability matching, and supply chain risk analysis.", "entity_types": { "classes": [ "City", "State", "Country", "County", "Business Description", "Certificate", "Postal Address", "Email Address", "Web Address", "Address Line", "US Postal Code", "Two Dimensional Cartesian Spatial Coordinate Datum", "NAICS Classifier", "Product Category Classifier", "Ownership Status Classifier", "Special Business Status Classifier", "Classifier", "Manufacturing Process Capability", "Material Processing Capability", "Quality Management Capability", "Machining Capability", "Welding Capability", "Casting Capability", "Coating Capability", "Fabricating Capability", "Forming Capability", "Joining Capability", "CNC Machining Capability", "Additive Manufacturing Capability", "Aluminum Processing Capability", "Steel Processing Capability", "Stainless Steel Processing Capability", "Plastic Processing Capability", "Copper Processing Capability", "ISO9001 Certificate", "AS9100 Certificate", "ITAR Certificate", "Aerospace Industry", "Automotive Industry", "Defense Industry", "Medical Devices Industry", "Semiconductor Industry", "Minority Owned", "Women Owned", "Veteran Owned", "Small Disadvantaged Business", "Manufacturer", "Organization", "Material Product", "Capability", "Geospatial Location", "Geospatial Site", "Industry" ], "predicates": [ "attests to", "classified by product category", "has address part", "has business description", "has certificate", "has email address", "has geospatial location", "has management capability", "has material capability", "has NAICS classifier", "has ownership status classifier", "has primary NAICS classifier", "has process capability", "has secondary NAICS classifier", "has special business status classifier", "has web address", "located in city", "located in country", "located in county", "located in state", "manufactures", "supplies to industry" ], "has_edge_properties": false }, "identifier_namespaces": [ "NAICS" ], "example_queries": [ "What manufacturers have specific process capabilities?" ] }, { "name": "ufokn", "display_name": "Ufokn", "named_graph_uri": "https://purl.org/okn/frink/kg/ufokn", "endpoint_url": "https://frink.apps.renci.org/ufokn/sparql", "domain_tags": [ "urban_flooding", "infrastructure", "emergency_response" ], "description_summary": "The Urban Flooding Open Knowledge Network (UF-OKN) is a geospatial knowledge graph infrastructure that integrates urban built environment data with real-time and historical hydrologic forecasts to enable flood risk assessment and emergency response. UF-OKN contains structured representations of urban infrastructure (buildings, roads, stormwater networks, power stations) derived from OpenStreetMap, linked to hydrologic features (rivers, streams) and operational forecast models including NOAA's National Water Model and local models like HEC-RAS and SWMM. The knowledge graph introduces \"Risk-Points\u2122\"\u2014locations where built and natural environments interact with potential flood impacts\u2014providing 24-year historical analysis coverage across the continental United States. UF-OKN uses schema.org vocabularies (Place, GeoShape, GeoCoordinates, Observation, PropertyValue) and STKO spatial ontologies (S2Cell) to enable SPARQL queries connecting infrastructure vulnerability to forecast conditions. The knowledge graph supports developers building custom flood information applications, emergency management systems, and risk analysis tools for planning and real-time response.", "entity_types": { "classes": [ "GeoCoordinates", "GeoShape", "Observation", "Place", "PropertyValue", "S2Cell" ], "predicates": [ "asWKT", "additionalType", "description", "elevation", "geo", "identifier", "latitude", "longitude", "measuredProperty", "name", "observationAbout", "observationDate", "propertyID", "unitCode", "unitText", "value", "variableMeasured" ], "has_edge_properties": false }, "identifier_namespaces": [ "S2Cell" ], "example_queries": [] }, { "name": "wildlifekn", "display_name": "Wildlifekn", "named_graph_uri": "https://purl.org/okn/frink/kg/wildlifekn", "endpoint_url": "https://frink.apps.renci.org/wildlifekn/sparql", "domain_tags": [ "wildlife", "biodiversity", "conservation" ], "description_summary": "Wildlife-KN is a comprehensive knowledge network designed for wildlife researchers, conservation managers, and policymakers addressing biodiversity challenges under climate change. The graph integrates data on wildlife species, habitat characteristics, environmental variables, geographic distributions, and climate projections to enable cross-domain analysis of how changing conditions affect wildlife populations and ecosystems. Built to support interdisciplinary inquiry, Wildlife-KN links biological observations with geospatial, temporal, and climatological data, facilitating queries about species vulnerability, habitat suitability shifts, and conservation prioritization. The knowledge graph employs standard semantic web vocabularies (RDFS, SKOS, Schema.org, GeoSPARQL) and cross-links to authoritative biodiversity databases, enabling federation with other OKN Theme-1 resources.", "entity_types": { "classes": [ "Amphibian Name", "Bird Name", "Location" ], "predicates": [ "Date", "Label", "Subject Of", "Observed At", "Observed Times" ], "has_edge_properties": false }, "identifier_namespaces": [], "example_queries": [] } ]