{"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-2054","ore:describes":{"citation:keyword":[{"citation:keywordValue":"Alignment","citation:keywordVocabulary":"EDAM","citation:keywordVocabularyURI":"http://edamontology.org/operation_2928"},{"citation:keywordValue":"Network"},{"citation:keywordValue":"Amino Acid Sequence","citation:keywordVocabulary":"NCIT","citation:keywordVocabularyURI":"http://purl.obolibrary.org/obo/NCIT_C13187"},{"citation:keywordValue":"Graph"},{"citation:keywordValue":"Protein Sequence","citation:keywordVocabulary":"EDAM","citation:keywordVocabularyURI":"http://edamontology.org/data_2976"},{"citation:keywordValue":"Sequence Clustering","citation:keywordVocabulary":"EDAM","citation:keywordVocabularyURI":"http://edamontology.org/operation_0291"}],"process:processMethodsPar":[{"process:processMethodsParName":"substitution matrix","process:processMethodsParSymbol":"BLOSUM62"},{"process:processMethodsParName":"word length (CD-Hit)","process:processMethodsParValue":"5"},{"process:processMethodsParName":"identity threshold (CD-HIT)","process:processMethodsParValue":"0.9"},{"process:processMethodsParName":"gap opening penalty","process:processMethodsParValue":"10"},{"process:processMethodsParName":"gap extension penalty","process:processMethodsParValue":"0.5"}],"process:processMethods":[{"processMethodsName":"Needleman-Wunsch alignment","process:processMethodsPars":"gap opening penalty, gap extension penalty, substitution matrix"},{"processMethodsName":"CD-HIT","process:processMethodsPars":"sequence identity threshold, word length","process:processMethodsDescription":"sequence clustering"}],"processSoftware":[{"processSoftwareName":"CD-HIT","processSoftwareCitation":"Li, W., & Godzik, A. (2006). Cd-hit: A fast program for clustering and comparing large sets of protein or nucleotide sequences. Bioinformatics. 22(13):1658-1659. DOI: 10.1093/bioinformatics/btl158","processSoftwareVersion":"4.7","processSoftwareURL":"http://weizhongli-lab.org/cd-hit/"},{"processSoftwareName":"EMBOSS","processSoftwareCitation":"Rice, P., Longden, L., & Bleasby, A. (2000). EMBOSS: The European Molecular Biology Open Software Suite. Trends in Genetics. 16(6):276-277. DOI: 10.1016/S0168-9525(00)02024-2","processSoftwareVersion":"6.6.0","processSoftwareURL":"http://emboss.sourceforge.net/"},{"processSoftwareName":"NetworkX","processSoftwareCitation":"Hagberg, A. A., Schult, D. A., & Swart, P. J. (2008). Exploring network structure, dynamics, and function using NetworkX. 7th Python in Science Conference (SciPy 2008). http://conference.scipy.org/proceedings/scipy2008/paper_2data Repository of the University of Stuttgart."}}}}},"ore:aggregates":[{"schema:description":"Protein sequence network for PETase homologues. Edges were selected at a threshold of 55% pairwise sequence identity.","schema:name":"PET_local_08_55sim.graphml","dvcore:restricted":false,"schema:version":2,"dvcore:datasetVersionId":2208,"@id":"doi:10.18419/darus-2054/3","schema:sameAs":"https://nfldevdataverse2.rus.uni-stuttgart.de/api/access/datafile/:persistentId?persistentId=doi:10.18419/darus-2054/3","@type":"ore:AggregatedResource","schema:fileFormat":"text/xml-graphml","dvcore:filesize":6035615,"dvcore:storageIdentifier":"s3://fokus-dv-prod-1:17a53064bc8-4469e7d9f99e","dvcore:rootDataFileId":-1,"dvcore:checksum":{"@type":"MD5","@value":"abddf6c05feb40d68c3c5cbed3f21d2b"}},{"schema:description":"Protein sequence network for PURase homologues from LED superfamily 11. Edges were selected at a threshold of 60% pairwise sequence identity.","schema:name":"Sfam11_09_60sim.graphml","dvcore:restricted":false,"schema:version":2,"dvcore:datasetVersionId":2208,"@id":"doi:10.18419/darus-2054/2","schema:sameAs":"https://nfldevdataverse2.rus.uni-stuttgart.de/api/access/datafile/:persistentId?persistentId=doi:10.18419/darus-2054/2","@type":"ore:AggregatedResource","schema:fileFormat":"text/xml-graphml","dvcore:filesize":570547,"dvcore:storageIdentifier":"s3://fokus-dv-prod-1:17a5306523d-640b5f94bab5","dvcore:rootDataFileId":-1,"dvcore:checksum":{"@type":"MD5","@value":"7cd626f025e5d7a0a253281649894b7f"}},{"schema:description":"Protein sequence network for PURase homologues from LED superfamily 13. Edges were selected at a threshold of 60% pairwise sequence identity.","schema:name":"Sfam13_09_60sim.graphml","dvcore:restricted":false,"schema:version":2,"dvcore:datasetVersionId":2208,"@id":"doi:10.18419/darus-2054/1","schema:sameAs":"https://nfldevdataverse2.rus.uni-stuttgart.de/api/access/datafile/:persistentId?persistentId=doi:10.18419/darus-2054/1","@type":"ore:AggregatedResource","schema:fileFormat":"text/xml-graphml","dvcore:filesize":16586,"dvcore:storageIdentifier":"s3://fokus-dv-prod-1:17a530652eb-f40f783c70c4","dvcore:rootDataFileId":-1,"dvcore:checksum":{"@type":"MD5","@value":"e93342540254b2c25b2826343947b22b"}}],"schema:hasPart":["doi:10.18419/darus-2054/3","doi:10.18419/darus-2054/2","doi:10.18419/darus-2054/1"]},"@context":{"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/","dateOfDeposit":"http://purl.org/dc/terms/dateSubmitted","dcterms":"http://purl.org/dc/terms/","dvcore":"https://dataverse.org/schema/core#","language":"http://purl.org/dc/terms/language","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","schema":"http://schema.org/","subject":"http://purl.org/dc/terms/subject","title":"http://purl.org/dc/terms/title"}}