{"dcterms:modified":"2023-12-08","dcterms:creator":"DaRUS","@type":"ore:ResourceMap","@id":"https://nfldevdataverse2.rus.uni-stuttgart.de/api/datasets/export?exporter=OAI_ORE&persistentId=https://doi.org/10.18419/darus-622","ore:describes":{"author":[{"citation:authorName":"Lohoff, Caroline","citation:authorAffiliation":"Universität Stuttgart"},{"citation:authorName":"Buchholz, Patrick C. F.","citation:authorAffiliation":"Universität Stuttgart","authorIdentifierScheme":"ORCID","authorIdentifier":"0000-0001-5967-3777"}],"publication":{"publicationCitation":"Lohoff C., Buchholz P. C. F., Le Roes-Hill M. & Pleiss J. (2020). The Expansin Engineering Database: a navigation and classification tool for expansins and homologues. Proteins: Structure, Function, and Bioinformatics 89:2.","publicationIDType":"doi","publicationIDNumber":"10.1002/prot.26001","publicationURL":"https://doi.org/10.1002/prot.26001"},"process:processMethods":{"processMethodsName":"UCLUST","process:processMethodsPars":"sequence identity threshold","process:processMethodsDescription":"sequence clustering using cluster_fast command from USEARCH"},"citation:datasetContact":{"citation:datasetContactName":"Pleiss, Jürgen","citation:datasetContactAffiliation":"Universität Stuttgart"},"processSoftware":{"processSoftwareName":"USEARCH","processSoftwareCitation":"Edgar, R. C. (2010). Search and clustering orders of magnitude faster than BLAST. Bioinformatics, 26(19), 2460-2461. https://doi.org/10.1093/bioinformatics/btq461","processSoftwareVersion":"11.0.667","processSoftwareURL":"https://www.drive5.com/usearch/"},"citation:keyword":[{"citation:keywordValue":"Protein sequence","citation:keywordVocabulary":"EDAM","citation:keywordVocabularyURI":"http://edamontology.org/data_2976"},{"citation:keywordValue":"Amino acid sequence","citation:keywordVocabulary":"NCIT","citation:keywordVocabularyURI":"http://purl.obolibrary.org/obo/NCIT_C13187"}],"process:processMethodsPar":{"process:processMethodsParName":"sequence identity threshold","process:processMethodsParUnit":"0.8"},"citation:dsDescription":{"citation:dsDescriptionValue":"Query sequences for the individual BLAST searches used to update the Expansin Engineering Database (ExED, https://exed.biocatnet.de/)."},"dateOfDeposit":"2020-01-27","citation:depositor":"Buchholz, Patrick C. F.","subject":"Medicine, Health and Life Sciences","title":"Query sequences for the update of the ExED","alternativeTitle":"Query sequences for the update of the Expansin Engineering Database","dataSources":["Expansin Engineering Database (https://exed.biocatnet.de/)","Protein Database (https://www.ncbi.nlm.nih.gov/protein/)","RCSB Protein Data Bank (https://www.rcsb.org/)","UniProt (https://www.uniprot.org/)"],"@id":"https://doi.org/10.18419/darus-622","@type":["ore:Aggregation","schema:Dataset"],"schema:version":"1.1","schema:name":"Query sequences for the update of the ExED","schema:dateModified":"Mon May 03 09:35:54 CEST 2021","schema:datePublished":"2020-01-30","schema:license":"http://creativecommons.org/licenses/by/4.0","dvcore:fileTermsOfAccess":{"dvcore:fileRequestAccess":false},"schema:includedInDataCatalog":"DaRUS","schema:isPartOf":{"schema:name":"Expansin Engineering Database","@id":"https://nfldevdataverse2.rus.uni-stuttgart.de/dataverse/ibtb_ExED","schema:description":"Supporting information and original files for bioinformatic investigations using the Expansin Engineering Database (https://exed.biocatnet.de/)","schema:isPartOf":{"schema:name":"Bioinformatics","@id":"https://nfldevdataverse2.rus.uni-stuttgart.de/dataverse/ibtb_BI","schema:isPartOf":{"schema:name":"Department of Technical Biochemistry","@id":"https://nfldevdataverse2.rus.uni-stuttgart.de/dataverse/ibtb_TB","schema:isPartOf":{"schema:name":"Institute of Biochemistry and Technical Biochemistry","@id":"https://nfldevdataverse2.rus.uni-stuttgart.de/dataverse/ibtb","schema:isPartOf":{"schema:name":"DaRUS","@id":"https://nfldevdataverse2.rus.uni-stuttgart.de/dataverse/darus","schema:description":"This is the data Repository of the University of Stuttgart."}}}}},"ore:aggregates":[{"schema:description":"Seed (query) sequences for the initial setup of the ExED. Protein sequences are given in FASTA format. Headers correspond to sequence identifiers in the style of UniprotKB.","schema:name":"Update_1_Seed_sequences_Hfams_1-25.fasta","dvcore:restricted":false,"schema:version":1,"dvcore:datasetVersionId":299,"@id":"doi:10.18419/darus-622/3","schema:sameAs":"https://nfldevdataverse2.rus.uni-stuttgart.de/api/access/datafile/:persistentId?persistentId=doi:10.18419/darus-622/3","@type":"ore:AggregatedResource","schema:fileFormat":"application/octet-stream","dvcore:filesize":8914,"dvcore:storageIdentifier":"s3://fokus-dv-prod-1:16ff175af84-7e84e6617c57","dvcore:rootDataFileId":-1,"dvcore:checksum":{"@type":"MD5","@value":"4f5de838715758c51a8cf33de96da0e8"}},{"schema:description":"Seed (query) sequences for the first update of the ExED (USEARCH centroid sequences). Protein sequences are given in FASTA format with one line per sequence. Headers correspond to sequence identifiers of the Expansin Engineering Database.","schema:name":"Update_2_Centroids_USEARCH.fasta","dvcore:restricted":false,"schema:version":1,"dvcore:datasetVersionId":299,"@id":"doi:10.18419/darus-622/1","schema:sameAs":"https://nfldevdataverse2.rus.uni-stuttgart.de/api/access/datafile/:persistentId?persistentId=doi:10.18419/darus-622/1","@type":"ore:AggregatedResource","schema:fileFormat":"application/octet-stream","dvcore:filesize":6619,"dvcore:storageIdentifier":"s3://fokus-dv-prod-1:16ff13e54bb-c236891cc8bd","dvcore:rootDataFileId":-1,"dvcore:checksum":{"@type":"MD5","@value":"5ae0036abf33f3585e5629a8337b7039"}},{"schema:description":"Tabular file with headers: sequence identifier from the Expansin Engineering Database (1st column) and NCBI accession.version (2nd column). This file lists the sequence accessions used in the first update of the ExED.","schema:name":"Update_2_Centroids_USEARCH.csv","dvcore:restricted":false,"schema:version":1,"dvcore:datasetVersionId":299,"@id":"doi:10.18419/darus-622/2","schema:sameAs":"https://nfldevdataverse2.rus.uni-stuttgart.de/api/access/datafile/:persistentId?persistentId=doi:10.18419/darus-622/2&format=original","@type":"ore:AggregatedResource","schema:fileFormat":"text/csv","dvcore:filesize":471,"dvcore:storageIdentifier":"s3://fokus-dv-prod-1:16ff1736594-bf75198ec29a","dvcore:currentIngestedName":"Update_2_Centroids_USEARCH.tab","dvcore:UNF":"UNF:6:eFcDsa8udm3F11lB7M2q6w==","dvcore:rootDataFileId":-1,"dvcore:checksum":{"@type":"MD5","@value":"b7bb4f4ac61adf7e13764a72e2a3af02"}}],"schema:hasPart":["doi:10.18419/darus-622/3","doi:10.18419/darus-622/1","doi:10.18419/darus-622/2"]},"@context":{"alternativeTitle":"http://purl.org/dc/terms/alternative","author":"http://purl.org/dc/terms/creator","authorIdentifier":"http://purl.org/spar/datacite/AgentIdentifier","authorIdentifierScheme":"http://purl.org/spar/datacite/AgentIdentifierScheme","citation":"https://dataverse.org/schema/citation/","dataSources":"https://www.w3.org/TR/prov-o/#wasDerivedFrom","dateOfDeposit":"http://purl.org/dc/terms/dateSubmitted","dcterms":"http://purl.org/dc/terms/","dvcore":"https://dataverse.org/schema/core#","ore":"http://www.openarchives.org/ore/terms/","process":"https://nfldevdataverse2.rus.uni-stuttgart.de/schema/process#","processMethodsName":"https://schema.org/measurementTechnique","processSoftware":"https://schema.org/SoftwareApplication","processSoftwareCitation":"https://schema.org/citation","processSoftwareName":"https://schema.org/name","processSoftwareURL":"https://schema.org/downloadUrl","processSoftwareVersion":"https://schema.org/version","publication":"http://purl.org/dc/terms/isReferencedBy","publicationCitation":"http://purl.org/dc/terms/bibliographicCitation","publicationIDNumber":"http://purl.org/spar/datacite/ResourceIdentifier","publicationIDType":"http://purl.org/spar/datacite/ResourceIdentifierScheme","publicationURL":"https://schema.org/distribution","schema":"http://schema.org/","subject":"http://purl.org/dc/terms/subject","title":"http://purl.org/dc/terms/title"}}