Last active
April 12, 2024 19:04
-
-
Save lindenb/5c49056d3bc6cd386b964f1cd93fa789 to your computer and use it in GitHub Desktop.
https://www.biostars.org/p/9592523/ Can you suggest a protein that has two chainst but only 50 total number of atoms?
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
PREFIX xsd: <http://www.w3.org/2001/XMLSchema#> | |
PREFIX wikibase: <http://wikiba.se/ontology#> | |
PREFIX wdt: <http://www.wikidata.org/prop/direct/> | |
PREFIX wd: <http://www.wikidata.org/entity/> | |
PREFIX vg: <http://biohackathon.org/resource/vg#> | |
PREFIX up: <http://purl.uniprot.org/core/> | |
PREFIX uniprotkb: <http://purl.uniprot.org/uniprot/> | |
PREFIX uberon: <http://purl.obolibrary.org/obo/uo#> | |
PREFIX taxon: <http://purl.uniprot.org/taxonomy/> | |
PREFIX sp: <http://spinrdf.org/sp#> | |
PREFIX skos: <http://www.w3.org/2004/02/skos/core#> | |
PREFIX sio: <http://semanticscience.org/resource/> | |
PREFIX sh: <http://www.w3.org/ns/shacl#> | |
PREFIX sd: <http://www.w3.org/ns/sparql-service-description#> | |
PREFIX schema: <http://schema.org/> | |
PREFIX sachem: <http://bioinfo.uochb.cas.cz/rdf/v1.0/sachem#> | |
PREFIX rh: <http://rdf.rhea-db.org/> | |
PREFIX pubmed: <http://rdf.ncbi.nlm.nih.gov/pubmed/> | |
PREFIX ps: <http://www.wikidata.org/prop/statement/> | |
PREFIX pq: <http://www.wikidata.org/prop/qualifier/> | |
PREFIX patent: <http://data.epo.org/linked-data/def/patent/> | |
PREFIX p: <http://www.wikidata.org/prop/> | |
PREFIX owl: <http://www.w3.org/2002/07/owl#> | |
PREFIX orthodbGroup: <http://purl.orthodb.org/odbgroup/> | |
PREFIX orthodb: <http://purl.orthodb.org/> | |
PREFIX orth: <http://purl.org/net/orth#> | |
PREFIX oboInOwl: <http://www.geneontology.org/formats/oboInOwl#> | |
PREFIX obo: <http://purl.obolibrary.org/obo/> | |
PREFIX np: <http://nextprot.org/rdf#> | |
PREFIX nextprot_cv: <http://nextprot.org/rdf/terminology/> | |
PREFIX nextprot: <http://nextprot.org/rdf/entry/> | |
PREFIX mnx: <https://rdf.metanetx.org/schema/> | |
PREFIX mnet: <https://rdf.metanetx.org/mnet/> | |
PREFIX mesh: <http://id.nlm.nih.gov/mesh/> | |
PREFIX lscr: <http://purl.org/lscr#> | |
PREFIX lipidmaps: <https://www.lipidmaps.org/rdf/> | |
PREFIX keywords: <http://purl.uniprot.org/keywords/> | |
PREFIX insdcschema: <http://ddbj.nig.ac.jp/ontologies/nucleotide/> | |
PREFIX insdc: <http://identifiers.org/insdc/> | |
PREFIX identifiers: <http://identifiers.org/> | |
PREFIX glyconnect: <https://purl.org/glyconnect/> | |
PREFIX glycan: <http://purl.jp/bio/12/glyco/glycan#> | |
PREFIX genex: <http://purl.org/genex#> | |
PREFIX foaf: <http://xmlns.com/foaf/0.1/> | |
PREFIX faldo: <http://biohackathon.org/resource/faldo#> | |
PREFIX eunisSpecies: <http://eunis.eea.europa.eu/rdf/species-schema.rdf#> | |
PREFIX ensembltranscript: <http://rdf.ebi.ac.uk/resource/ensembl.transcript/> | |
PREFIX ensemblterms: <http://rdf.ebi.ac.uk/terms/ensembl/> | |
PREFIX ensemblprotein: <http://rdf.ebi.ac.uk/resource/ensembl.protein/> | |
PREFIX ensemblexon: <http://rdf.ebi.ac.uk/resource/ensembl.exon/> | |
PREFIX ensembl: <http://rdf.ebi.ac.uk/resource/ensembl/> | |
PREFIX ec: <http://purl.uniprot.org/enzyme/> | |
PREFIX dcterms: <http://purl.org/dc/terms/> | |
PREFIX dc: <http://purl.org/dc/terms/> | |
PREFIX chebislash: <http://purl.obolibrary.org/obo/chebi/> | |
PREFIX chebihash: <http://purl.obolibrary.org/obo/chebi#> | |
PREFIX cco: <http://rdf.ebi.ac.uk/terms/chembl#> | |
PREFIX busco: <http://busco.ezlab.org/schema#> | |
PREFIX bibo: <http://purl.org/ontology/bibo/> | |
PREFIX allie: <http://allie.dbcls.jp/> | |
PREFIX SWISSLIPID: <https://swisslipids.org/rdf/SLM_> | |
PREFIX GO: <http://purl.obolibrary.org/obo/GO_> | |
PREFIX ECO: <http://purl.obolibrary.org/obo/ECO_> | |
PREFIX CHEBI: <http://purl.obolibrary.org/obo/CHEBI_> | |
PREFIX rdfs: <http://www.w3.org/2000/01/rdf-schema#> | |
PREFIX rdf: <http://www.w3.org/1999/02/22-rdf-syntax-ns#> | |
SELECT distinct ?prot ?protName (COUNT(DISTINCT ?chain) as ?n_chains) | |
WHERE | |
{ | |
?prot <http://purl.uniprot.org/core/mnemonic> ?protName . | |
?prot <http://purl.uniprot.org/core/annotation> ?chain . | |
?prot a <http://purl.uniprot.org/core/Protein> . | |
?chain a <http://purl.uniprot.org/core/Peptide_Annotation> . | |
?prot <http://purl.uniprot.org/core/sequence> ?sequence . | |
?chain rdfs:comment ?chainTitle . | |
?sequence rdf:value ?pep . | |
FILTER( strlen(str(?pep)) > 60 ) . | |
FILTER( regex(str(?chainTitle),"chain" ) ) . | |
} | |
GROUP BY ?prot ?protName | |
HAVING( (COUNT(DISTINCT ?chain))=2) | |
ORDER by ?prot ?n_chains |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment