SPARQL example query
◀
▶
◀
▶
115_Number_of_complete_EC_numbers_described_at_protein_level_at_domain_levels_at_component_level: Number of _complete_ EC numbers described at protein level, at domain levels, at component level
PREFIX up:<http://purl.uniprot.org/core/> PREFIX ec:<http://purl.uniprot.org/enzyme/> PREFIX rdfs:<http://www.w3.org/2000/01/rdf-schema#> SELECT (count(distinct ?ecProt) as ?ecNumberInProteinCount) (count(distinct ?ecDomain) as ?ecNumberInDomainCount) (count(distinct ?ecComponent) as ?ecNumberInComponentCount) WHERE { ?protein up:reviewed true . OPTIONAL {?protein up:enzyme ?ecProt . } . OPTIONAL {?protein up:domain/up:enzyme ?ecDomain . } . OPTIONAL {?protein up:component/up:enzyme ?ecComponent . } . }Use116_biosodafrontend_rabit_mouse_orthologs: Rabbit's proteins encoded by genes that are orthologous to Mouse's HBB-Y gene and their cross reference links to Uniprot
PREFIX lscr: <http://purl.org/lscr#> PREFIX orth: <http://purl.org/net/orth#> PREFIX up: <http://purl.uniprot.org/core/> PREFIX obo: <http://purl.obolibrary.org/obo/> PREFIX rdfs: <http://www.w3.org/2000/01/rdf-schema#> SELECT DISTINCT ?PROTEIN_1 ?PROTEIN_2 ?UNIPROT_XREF_1 ?UNIPROT_XREF_2 WHERE { ?taxon_1 up:commonName 'Mouse' . ?taxon_2 up:commonName 'Rabbit' . SERVICE <https://sparql.omabrowser.org/sparql/> { ?cluster a orth:OrthologsCluster . ?cluster orth:hasHomologousMember ?node1 . ?cluster orth:hasHomologousMember ?node2 . ?node2 orth:hasHomologousMember* ?PROTEIN_2 . ?node1 orth:hasHomologousMember* ?PROTEIN_1 . ?PROTEIN_1 a orth:Protein . ?PROTEIN_1 orth:organism/obo:RO_0002162 ?taxon_1 ; rdfs:label 'HBB-Y' ; lscr:xrefUniprot ?UNIPROT_XREF_1 . ?PROTEIN_2 a orth:Protein . ?PROTEIN_2 orth:organism/obo:RO_0002162 ?taxon_2 . ?PROTEIN_2 lscr:xrefUniprot ?UNIPROT_XREF_2 . FILTER ( ?node1 != ?node2 ) } }Use117_biosodafrontend_glioblastoma_orthologs_rat: Which are the proteins associated with glioblastoma and the orthologs expressed in the rat brain?
PREFIX rdfs: <http://www.w3.org/2000/01/rdf-schema#> PREFIX obo: <http://purl.obolibrary.org/obo/> PREFIX orth: <http://purl.org/net/orth#> PREFIX sio: <http://semanticscience.org/resource/> PREFIX taxon: <http://purl.uniprot.org/taxonomy/> PREFIX up: <http://purl.uniprot.org/core/> PREFIX lscr: <http://purl.org/lscr#> PREFIX genex: <http://purl.org/genex#> SELECT DISTINCT ?protein ?orthologous_protein ?gene ?annotation_text WHERE { { SELECT ?protein ?annotation_text WHERE { ?protein a up:Protein ; up:organism taxon:9606 ; up:annotation ?annotation . ?annotation rdfs:comment ?annotation_text . ?annotation a up:Disease_Annotation . FILTER CONTAINS (?annotation_text, "glioblastoma") } } SERVICE <https://sparql.omabrowser.org/sparql/> { SELECT ?orthologous_protein ?protein ?gene WHERE { ?protein_OMA a orth:Protein . ?orthologous_protein a orth:Protein . ?cluster a orth:OrthologsCluster . ?cluster orth:hasHomologousMember ?node1 . ?cluster orth:hasHomologousMember ?node2 . ?node2 orth:hasHomologousMember* ?protein_OMA . ?node1 orth:hasHomologousMember* ?orthologous_protein . ?orthologous_protein orth:organism/obo:RO_0002162 taxon:10116 . # rattus norvegicus ?orthologous_protein sio:SIO_010079 ?gene . ?protein_OMA lscr:xrefUniprot ?protein . FILTER(?node1 != ?node2) } } SERVICE <https://www.bgee.org/sparql/> { ?gene genex:isExpressedIn ?a . ?a rdfs:label "brain" . ?gene orth:organism ?s . ?s obo:RO_0002162 taxon:10116. } }Use118_biosodafrontend_rat_brain_human_cancer: What are the Homo sapiens genes associated with cancer and their orthologs expressed in the Rattus norvegicus brain?
PREFIX up:<http://purl.uniprot.org/core/> PREFIX taxon:<http://purl.uniprot.org/taxonomy/> PREFIX rdfs:<http://www.w3.org/2000/01/rdf-schema#> PREFIX orth:<http://purl.org/net/orth#> PREFIX dcterms:<http://purl.org/dc/terms/> PREFIX obo:<http://purl.obolibrary.org/obo/> PREFIX lscr:<http://purl.org/lscr#> PREFIX genex:<http://purl.org/genex#> PREFIX sio: <http://semanticscience.org/resource/> SELECT ?gene ?orthologous_protein2 WHERE { { SELECT ?protein1 WHERE { ?protein1 a up:Protein; up:organism/up:scientificName 'Homo sapiens' ; up:annotation ?annotation . ?annotation rdfs:comment ?annotation_text. ?annotation a up:Disease_Annotation . FILTER CONTAINS (?annotation_text, "cancer") } } SERVICE <https://sparql.omabrowser.org/sparql/> { SELECT ?orthologous_protein2 ?protein1 ?gene WHERE { ?protein_OMA a orth:Protein . ?orthologous_protein2 a orth:Protein . ?cluster a orth:OrthologsCluster . ?cluster orth:hasHomologousMember ?node1 . ?cluster orth:hasHomologousMember ?node2 . ?node2 orth:hasHomologousMember* ?protein_OMA . ?node1 orth:hasHomologousMember* ?orthologous_protein2 .?orthologous_protein2 orth:organism/obo:RO_0002162/up:scientificName 'Rattus norvegicus' . ?orthologous_protein2 sio:SIO_010079 ?gene . ?protein_OMA lscr:xrefUniprot ?protein1 . FILTER(?node1 != ?node2) } } SERVICE <https://www.bgee.org/sparql/> { ?gene genex:isExpressedIn ?anatEntity . ?anatEntity rdfs:label 'brain' . ?gene orth:organism ?org . ?org obo:RO_0002162 taxon:10116 . } }Use119_uniref_distinct_ec_in_seed: Distinct Enzymes in UniRef50 seed entries
PREFIX up:<http://purl.uniprot.org/core/> SELECT (COUNT(DISTINCT ?enzyme) AS ?distinctEnzymesInUniRef50Seed) WHERE { GRAPH <http://sparql.uniprot.org/uniprot>{ ?protein ( up:enzyme | up:domain/up:enzyme | up:component/up:enzyme ) ?enzyme . } GRAPH <http://sparql.uniprot.org/uniref>{ ?protein up:seedFor ?cluster . ?cluster up:identity 0.5 . } }Use120_for_taxon_find_reference_proteomes: For a ncbi taxon identifier as a digit find it's reference proteome(s) if they exist
PREFIX up:<http://purl.uniprot.org/core/> PREFIX taxon:<http://purl.uniprot.org/taxonomy/> SELECT ?taxon ?reference_proteome WHERE { VALUES (?taxid) { (623) # Shigella flexneri (633) # Yersinia pseudotuberculosis } # Convert the digit to a correct IRI BIND(IRI(CONCAT(STR(taxon:), ?taxid)) AS ?taxon) ?taxon up:scientificName ?taxonName . OPTIONAL { ?reference_proteome a up:Reference_Proteome . ?reference_proteome up:organism ?taxon . } }Use121_proteins_and_diseases_linked: List all UniProtKB proteins and the diseases are annotated to be related.
PREFIX up: <http://purl.uniprot.org/core/> SELECT ?protein ?disease WHERE { ?protein a up:Protein ; up:annotation ?annotation . ?annotation a up:Disease_Annotation ; up:disease ?disease . ?disease a up:Disease . }Use122_enzymes_transporting_lipids_in_reviewed_human: List all UniProtKB SwissProt entries, facilitation the transport of lipids.
PREFIX up: <http://purl.uniprot.org/core/> PREFIX rh: <http://rdf.rhea-db.org/> PREFIX CHEBI: <http://purl.obolibrary.org/obo/CHEBI_> PREFIX rdfs: <http://www.w3.org/2000/01/rdf-schema#> PREFIX taxon: <http://purl.uniprot.org/taxonomy/> SELECT ?protein ?chebi WHERE { GRAPH <https://sparql.rhea-db.org/rhea> { ?rhea rh:isTransport true . ?rhea rh:side/rh:contains/rh:compound ?compound . ?compound (rh:chebi|(rh:reactivePart/rh:chebi)|rh:underlyingChebi) ?chebi . } # CHEBI:18059 is the class for all Lipids ?chebi rdfs:subClassOf* CHEBI:18059 . # Select human reviewed entries from Swiss-Prot ?protein up:reviewed true ; up:organism taxon:9606 . # Link protein to catalytic activity, then to Rhea reaction ?protein up:annotation ?annotation . ?annotation up:catalyticActivity ?catalytic_activity . ?catalytic_activity up:catalyzedReaction ?rhea . }Use123_list_EC_numbers_not_linked_to_UniProt_entries: list = EC numbers not linked to UniProt entries
PREFIX up:<http://purl.uniprot.org/core/> PREFIX ec:<http://purl.uniprot.org/enzyme/> PREFIX rdfs:<http://www.w3.org/2000/01/rdf-schema#> SELECT (COUNT(DISTINCT ?ecNumber) AS ?ecCount) WHERE { ?ecNumber rdfs:subClassOf up:Enzyme . FILTER (NOT EXISTS {?ecNumber up:obsolete true .} ) FILTER (!regex(?ecNumber,'-')) . FILTER (NOT EXISTS { ?protein up:enzyme ?ecNumber . ?protein up:reviewed true . }) FILTER (NOT EXISTS { ?protein up:domain/up:enzyme ?ecNumber . ?protein up:reviewed true . }) FILTER (NOT EXISTS { ?protein up:reviewed true . ?protein up:component/up:enzyme ?ecNumber . }) }Use124_list_protein_components_ec: list = protein - components -ec
PREFIX up:<http://purl.uniprot.org/core/> PREFIX ec:<http://purl.uniprot.org/enzyme/> PREFIX rdfs:<http://www.w3.org/2000/01/rdf-schema#> SELECT DISTINCT ?enzyme WHERE { ?protein up:reviewed true . ?protein up:mnemonic ?mnemonic . ?protein up:domain ?domain . ?domain up:enzyme ?enzyme . }Use125_CORDIS_EURIO_cited_project_results_in_uniprot: Use the CORDIS EURIO Knowledge Graph in combination with UniProt to find the count of outputs(DOIs) of their funded projects cited in UniProt.
PREFIX xsd: <http://www.w3.org/2001/XMLSchema#> PREFIX dcterms: <http://purl.org/dc/terms/> PREFIX up: <http://purl.uniprot.org/core/> PREFIX eurio: <http://data.europa.eu/s66#> PREFIX patent: <http://purl.uniprot.org/EPO/> PREFIX pubmed: <http://purl.uniprot.org/pubmed/> SELECT (IRI(CONCAT('https://cordis.europa.eu/project/id/', SAMPLE(?identifier))) AS ?id) (SAMPLE(?project_title) AS ?project_titles) (COUNT(DISTINCT ?doi_string) AS ?doisInSwissProt) (COUNT(DISTINCT ?protein) AS ?entriesInSwissProt) WHERE { SERVICE <https://cordis.europa.eu/datalab/sparql> { ?project a eurio:Project ; eurio:identifier ?identifier ; eurio:title ?project_title ; eurio:hasResult ?result . ?result eurio:doi ?doi . } #EURIO use literals of type xsd:anyURI to represent DOIs #without the leading doi: indicator BIND(CONCAT("doi:", STR(?doi)) AS ?doi_string) ?citation a up:Journal_Citation ; dcterms:identifier ?doi_string . ?protein up:citation ?citation . BIND(xsd:int(?identifier) AS ?intid) } GROUP BY ?project ORDER BY DESC(?intid)Use126_count_venom_related_proteins: Count the number of entries that are annotated to be related to venomous activity in selected taxonomic groups
PREFIX rdfs: <http://www.w3.org/2000/01/rdf-schema#> PREFIX taxon: <http://purl.uniprot.org/taxonomy/> PREFIX up: <http://purl.uniprot.org/core/> PREFIX location: <http://purl.uniprot.org/locations/> SELECT (COUNT(DISTINCT ?protein) AS ?proteins) ?grouping ?groupingScientificName WHERE { VALUES ?grouping { taxon:6103 #sea anemones taxon:8570 #snakes taxon:6855 #scorpions taxon:6893 #Araneae taxon:50557 #Insecta taxon:37797 #Conoidea } ?grouping up:scientificName ?groupingScientificName . ?taxon rdfs:subClassOf ?grouping. ?protein up:organism ?taxon . { ?protein up:annotation ?tsa . ?tsa a up:Tissue_Specificity_Annotation ; rdfs:comment ?tsac . FILTER(REGEX(?tsac, 'venom', 'i')) } UNION { ?protein up:annotation ?scla . # location:177 is nematocyst ?scla a up:Subcellular_Location_Annotation ; up:locatedIn/up:cellularComponent location:177 . } } GROUP BY ?grouping ?groupingScientificName ORDER BY ?proteinsUse127_uniprot_human_reviewed_to_chebi: UniProt entries use ChEBI in the following annotations: Ligands, Cofactors and Enzymatic Activity. This query shows how these can all be retrieved in one go, to make a UniProt to ChEBI mapping. The example query is made smaller by retrieving only human entries in Swiss-Prot.
PREFIX uniprotkb: <http://purl.uniprot.org/uniprot/> PREFIX taxon: <http://purl.uniprot.org/taxonomy/> PREFIX rh: <http://rdf.rhea-db.org/> PREFIX owl: <http://www.w3.org/2002/07/owl#> PREFIX CHEBI: <http://purl.obolibrary.org/obo/CHEBI_> PREFIX up: <http://purl.uniprot.org/core/> PREFIX rdfs: <http://www.w3.org/2000/01/rdf-schema#> SELECT (SUBSTR(STR(?protein), STRLEN(STR(uniprotkb:))+1) AS ?proteinAc) (GROUP_CONCAT(DISTINCT ?chebiId; separator=',') AS ?chebis) WHERE { ?protein up:reviewed true ; up:organism taxon:9606 . { ?protein up:annotation ?ligandAnnotation . ?ligandAnnotation up:ligand/rdfs:subClassOf ?chebi } UNION { ?protein up:annotation ?cofactorAnnotation . ?cofactorAnnotation up:cofactor ?chebi . } UNION { ?protein up:annotation ?catalyticActivityAnnotation . ?catalyticActivityAnnotation a up:Catalytic_Activity_Annotation ; up:catalyticActivity ?catalyticActivity . ?catalyticActivity up:catalyzedReaction ?rhea . ?rhea rh:side/rh:contains/rh:compound ?compound . ?compound (rh:chebi|(rh:reactivePart/rh:chebi)|rh:underlyingChebi) ?chebi . } GRAPH <http://sparql.uniprot.org/chebi> { ?chebi a owl:Class . } BIND((CONCAT('chebi:',SUBSTR(STR(?chebi), STRLEN(STR(CHEBI:))+1))) AS ?chebiId) } GROUP BY ?proteinUse128_distinct_rhea_in_different_taxons_grouped_by_eco: Count of unique Rhea reactions/Evidence code pairs annotated in different taxa in Swiss-Prot
PREFIX rdf: <http://www.w3.org/1999/02/22-rdf-syntax-ns#> PREFIX up: <http://purl.uniprot.org/core/> PREFIX taxon: <http://purl.uniprot.org/taxonomy/> PREFIX rdfs: <http://www.w3.org/2000/01/rdf-schema#> SELECT (COUNT(DISTINCT ?rhea) as ?uniqueRheaCount) ?taxon ?taxonName ?eco WHERE { #Select taxa VALUES (?taxon) { (taxon:9606) # Homo sapiens (taxon:7742) # Vertebrata (taxon:33208) # Metazoa (taxon:33090) # Viridiplantae (taxon:4751) # Fungi (taxon:2) # Bacteria (taxon:2157) # Archaea (taxon:10239) # Viruses } ?taxon up:scientificName ?taxonName . GRAPH <http://sparql.uniprot.org/taxonomy>{ ?subc rdfs:subClassOf ?taxon . } GRAPH <http://sparql.uniprot.org/uniprot>{ { ?protein up:organism ?subc . } UNION { # Only useful in the Homo sapiens case ?protein up:organism ?taxon . } ?protein up:reviewed true . ?protein up:annotation ?annot . ?annot up:catalyticActivity ?caa . ?caa up:catalyzedReaction ?rhea . [] rdf:subject ?annot ; rdf:object ?caa ; up:attribution/up:evidence ?eco } } GROUP BY ?taxon ?taxonName ?eco ORDER BY ?taxonName ?ecoUse129_taxon_rhea_annotation_count: List Taxa Identifiers and the number of annotated Rhea reactions in each that have experimental evidence.
PREFIX taxon: <http://purl.uniprot.org/taxonomy/> PREFIX rdf: <http://www.w3.org/1999/02/22-rdf-syntax-ns#> PREFIX ECO: <http://purl.obolibrary.org/obo/ECO_> PREFIX up: <http://purl.uniprot.org/core/> SELECT ?taxon (COUNT(?rhea) AS ?experimentalRheaAnnotated) WHERE { GRAPH <http://sparql.uniprot.org/uniprot> { ?protein up:organism ?taxon ; up:annotation ?catalyticActivityAnnotation . ?catalyticActivityAnnotation up:catalyticActivity ?catalyticActivity . ?catalyticActivity up:catalyzedReaction ?rhea . [] rdf:subject ?catalyticActivityAnnotation ; rdf:object ?catalyticActivity ; up:attribution ?attr . ?attr up:evidence ECO:0000269 . } } GROUP BY ?taxonUse130_taxon_any_rhea_annotation_count: List Taxa Identifiers and the number of annotated Rhea reactions for each
PREFIX rdf: <http://www.w3.org/1999/02/22-rdf-syntax-ns#> PREFIX up: <http://purl.uniprot.org/core/> SELECT ?taxon (COUNT(?rhea) AS ?rheaAnnotated) WHERE { GRAPH <http://sparql.uniprot.org/uniprot> { ?protein up:organism ?taxon ; up:annotation ?catalyticActivityAnnotation . ?catalyticActivityAnnotation up:catalyticActivity ?catalyticActivity . ?catalyticActivity up:catalyzedReaction ?rhea . } } GROUP BY ?taxonUse131_count_panther_experimental_rhea: Count the number of PANTHER families that have an experimentally confirmed catalytic activity
PREFIX ECO: <http://purl.obolibrary.org/obo/ECO_> PREFIX rdf: <http://www.w3.org/1999/02/22-rdf-syntax-ns#> PREFIX up: <http://purl.uniprot.org/core/> PREFIX rdfs:<http://www.w3.org/2000/01/rdf-schema#> SELECT (COUNT(DISTINCT ?pantherFamily) AS ?pantherFamiliesWithExperimentalCatalyticActivity) WHERE { # Protein has a catalytic activity annotation with a Rhea reaction ?protein up:annotation ?ann . ?ann up:catalyticActivity ?ca . ?ca up:catalyzedReaction ?rhea . # The catalyticActivity statement has experimental evidence and a citation ?reif rdf:subject ?ann ; rdf:predicate up:catalyticActivity ; rdf:object ?ca ; up:attribution ?attr . ?attr up:evidence ECO:0000269 . # Protein is linked to a PANTHER family cross-reference ?protein rdfs:seeAlso ?pantherFamily . ?pantherFamily up:database <http://purl.uniprot.org/database/PANTHER> . }Use131_count_panther_experimental_rhea: Count the number of PANTHER families that have an experimentally confirmed catalytic activity
PREFIX ECO: <http://purl.obolibrary.org/obo/ECO_> PREFIX rdf: <http://www.w3.org/1999/02/22-rdf-syntax-ns#> PREFIX up: <http://purl.uniprot.org/core/> PREFIX rdfs:<http://www.w3.org/2000/01/rdf-schema#> SELECT (COUNT(DISTINCT ?pantherFamily) AS ?pantherFamiliesWithExperimentalCatalyticActivity) WHERE { # Protein has a catalytic activity annotation with a Rhea reaction ?protein up:annotation ?ann . ?ann up:catalyticActivity ?ca . ?ca up:catalyzedReaction ?rhea . # The catalyticActivity statement has experimental evidence and a citation ?reif rdf:subject ?ann ; rdf:predicate up:catalyticActivity ; rdf:object ?ca ; up:attribution ?attr . ?attr up:evidence ECO:0000269 . # Protein is linked to a PANTHER family cross-reference ?protein rdfs:seeAlso ?pantherFamily . ?pantherFamily up:database <http://purl.uniprot.org/database/PANTHER> . }Use132_experimental_Rhea_per_PANTHER: Count the number of times a Rhea reaction was experimentally annotated in a PANTHER family
PREFIX ECO: <http://purl.obolibrary.org/obo/ECO_> PREFIX rdf: <http://www.w3.org/1999/02/22-rdf-syntax-ns#> PREFIX up: <http://purl.uniprot.org/core/> PREFIX rdfs:<http://www.w3.org/2000/01/rdf-schema#> SELECT ?pantherFamily (COUNT(?rhea) AS ?experimentalRhea) WHERE { # Protein has a catalytic activity annotation with a Rhea reaction ?protein up:annotation ?ann . ?ann up:catalyticActivity ?ca . ?ca up:catalyzedReaction ?rhea . # The catalyticActivity statement has experimental evidence and a citation ?reif rdf:subject ?ann ; rdf:predicate up:catalyticActivity ; rdf:object ?ca ; up:attribution ?attr . ?attr up:evidence ECO:0000269 . # Protein is linked to a PANTHER family cross-reference ?protein rdfs:seeAlso ?pantherFamily . ?pantherFamily up:database <http://purl.uniprot.org/database/PANTHER> . } GROUP BY ?pantherFamily ORDER BY DESC(?experimentalRhea)Use133_mapping_panther_rhea_uniprot_eco: Generate a mapping table for PANTHER family - Rhea - UniProt Protein - ECO code
PREFIX rdf: <http://www.w3.org/1999/02/22-rdf-syntax-ns#> PREFIX up: <http://purl.uniprot.org/core/> PREFIX rdfs:<http://www.w3.org/2000/01/rdf-schema#> SELECT ?pantherFamily ?rhea ?protein ?eco WHERE { # Protein has a catalytic activity annotation with a Rhea reaction ?protein up:annotation ?ann . ?ann up:catalyticActivity ?ca . ?ca up:catalyzedReaction ?rhea . # The catalyticActivity statement has experimental evidence and a citation ?reif rdf:subject ?ann ; rdf:predicate up:catalyticActivity ; rdf:object ?ca ; up:attribution ?attr . ?attr up:evidence ?eco . # Protein is linked to a PANTHER family cross-reference ?protein rdfs:seeAlso ?pantherFamily . ?pantherFamily up:database <http://purl.uniprot.org/database/PANTHER> . }Use135_plazi_proteome: Connect a taxonomic treatment collected by Plazi in their synospecies system. We connect by what is called the dwc:id-ENA property which is encoded as a xsd:string which is the naked identifier of an NCBI taxon concept. Which in UniProt is encoded as an IRI starting with `http://purl.uniprot.org/taxonomy/'. After converting the taxon identifier we can query for Proteomes in UniProt for that taxon.
PREFIX up: <http://purl.uniprot.org/core/> PREFIX trt: <http://plazi.org/vocab/treatment#> PREFIX dwc: <http://rs.tdwg.org/dwc/terms/> PREFIX dwcFP: <http://filteredpush.org/ontologies/oa/dwcFP#> SELECT ?proteome ?ncbiTaxon ?treatment WHERE { { SERVICE <https://lindas.admin.ch/query> { ?tc a dwcFP:TaxonConcept ; dwc:ID-ENA ?ena . ?treatment trt:augmentsTaxonConcept|trt:definesTaxonConcept ?tc ; dwc:basisOfRecord ?mc . ?mc trt:gbifOccurrenceId ?occ . } } BIND(IRI(CONCAT('http://purl.uniprot.org/taxonomy/', ?ena)) AS ?ncbiTaxon) ?proteome a up:Proteome ; up:organism ?ncbiTaxon }Use136_self_interacting_reviewed_human_proteins: Find reviewed human proteins that are annotated as self-interacting, i.e. known to form homodimers or homo-oligomers
PREFIX up: <http://purl.uniprot.org/core/> PREFIX taxon: <http://purl.uniprot.org/taxonomy/> SELECT DISTINCT ?protein WHERE { ?protein a up:Protein ; up:organism taxon:9606 ; up:reviewed true ; up:interaction ?interaction . ?interaction a up:Self_Interaction . }Use137_interaction_partners_and_evidence_count: Find the interaction partners of human tumor suppressor TP53 (P04637) and the number of experiments supporting each interaction
PREFIX up: <http://purl.uniprot.org/core/> PREFIX uniprotkb: <http://purl.uniprot.org/uniprot/> PREFIX owl: <http://www.w3.org/2002/07/owl#> SELECT DISTINCT ?partnerProtein ?experiments WHERE { uniprotkb:P04637 up:interaction ?interaction . ?interaction a up:Non_Self_Interaction ; up:participant ?partner ; up:experiments ?experiments . # up:participant identifies the interacting molecule by its IntAct # identifier; owl:sameAs links that identifier back to the UniProt # protein it corresponds to. ?partner owl:sameAs ?partnerProtein . FILTER(?partnerProtein != uniprotkb:P04637) } ORDER BY DESC(?experiments)Use138_unique_taxons_having_an_experimental_chebi: Count distinct taxons linked to ChEBI in different ways via experimental annotations in UniProt
PREFIX ECO: <http://purl.obolibrary.org/obo/ECO_> PREFIX rdf: <http://www.w3.org/1999/02/22-rdf-syntax-ns#> PREFIX rh: <http://rdf.rhea-db.org/> PREFIX rdfs: <http://www.w3.org/2000/01/rdf-schema#> PREFIX owl: <http://www.w3.org/2002/07/owl#> PREFIX up: <http://purl.uniprot.org/core/> SELECT (COUNT(DISTINCT ?taxon) AS ?taxonsLinkedToChebi) (COUNT(DISTINCT ?ligandTaxon) AS ?taxonsLinkedToChebiViaLigand) (COUNT(DISTINCT ?cofactorTaxon) AS ?taxonsLinkedToChebiViaCofactor) (COUNT(DISTINCT ?catalyticTaxon) AS ?taxonsLinkedToChebiViaCatalytic) WHERE { { GRAPH <http://sparql.uniprot.org/uniprot> { ?protein up:annotation ?ligandAnnotation . ?ligandAnnotation up:ligand/rdfs:subClassOf ?chebi . ?reif rdf:subject ?protein ; rdf:object ?ligandAnnotation . } } UNION { GRAPH <http://sparql.uniprot.org/uniprot> { ?protein up:annotation ?cofactorAnnotation . ?cofactorAnnotation up:cofactor ?chebi . ?reif rdf:subject ?cofactorAnnotation ; rdf:object ?chebi . } } UNION { GRAPH <http://sparql.uniprot.org/uniprot> { ?protein up:annotation ?catalyticActivityAnnotation . ?catalyticActivityAnnotation a up:Catalytic_Activity_Annotation ; up:catalyticActivity ?catalyticActivity . ?catalyticActivity up:catalyzedReaction ?rhea . ?reif rdf:subject ?catalyticActivityAnnotation ; rdf:object ?catalyticActivity . } GRAPH <https://sparql.rhea-db.org/rhea> { ?rhea rh:side/rh:contains/rh:compound ?compound . ?compound (rh:chebi|(rh:reactivePart/rh:chebi)|rh:underlyingChebi) ?chebi . } } GRAPH <http://sparql.uniprot.org/uniprot> { ?reif up:attribution ?attr . ?attr up:evidence ECO:0000269 . ?protein up:organism ?taxon . BIND(IF(BOUND(?ligandAnnotation),?taxon, ?_) AS ?ligandTaxon) BIND(IF(BOUND(?cofactorAnnotation),?taxon, ?_) AS ?cofactorTaxon) BIND(IF(BOUND(?catalyticActivityAnnotation),?taxon, ?_) AS ?catalyticTaxon) } GRAPH <http://sparql.uniprot.org/chebi> { ?chebi a owl:Class . } }Use139_glycosylation_sites_on_human_proteins: Find glycosylation sites on reviewed human proteins, together with the modified residue position and the kind of glycosylation (e.g. N-linked, O-linked, C-linked)
PREFIX up: <http://purl.uniprot.org/core/> PREFIX taxon: <http://purl.uniprot.org/taxonomy/> PREFIX faldo: <http://biohackathon.org/resource/faldo#> PREFIX rdfs: <http://www.w3.org/2000/01/rdf-schema#> SELECT ?protein ?position ?glycosylationType WHERE { ?protein a up:Protein ; up:organism taxon:9606 ; up:reviewed true ; up:annotation ?annotation . ?annotation a up:Glycosylation_Annotation ; rdfs:comment ?glycosylationType ; up:range ?range . ?range faldo:begin/faldo:position ?position . }Use140_disulfide_bonds_and_interchain_links: Find the disulfide bonds of human insulin (P01308), the pair of residue positions each one connects, and whether it links two different chains (e.g. the A and B chains of mature insulin) rather than two residues within the same chain
PREFIX up: <http://purl.uniprot.org/core/> PREFIX uniprotkb: <http://purl.uniprot.org/uniprot/> PREFIX faldo: <http://biohackathon.org/resource/faldo#> PREFIX rdfs: <http://www.w3.org/2000/01/rdf-schema#> SELECT ?annotation (GROUP_CONCAT(STR(?position); separator="-") AS ?positions) (SAMPLE(?rawComment) AS ?interchainNote) WHERE { uniprotkb:P01308 up:annotation ?annotation . ?annotation a up:Disulfide_Bond_Annotation ; up:range ?range . # Each disulfide bond annotation has one up:range per residue it # connects; a plain xsd:int position must be coerced with STR() before # GROUP_CONCAT can aggregate it. ?range faldo:begin/faldo:position ?position . # Absence of a comment means the bond is intra-chain; a comment # mentioning "Interchain" means it links two separate chains. OPTIONAL { ?annotation rdfs:comment ?rawComment } } GROUP BY ?annotationUse