{"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-803","ore:describes":{"citation:datasetContact":{"citation:datasetContactName":"Pleiss, Jürgen","citation:datasetContactAffiliation":"Universität Stuttgart"},"citation:keyword":[{"citation:keywordValue":"profile hidden Markov model"},{"citation:keywordValue":"protein sequence"},{"citation:keywordValue":"multiple sequence alignment"},{"citation:keywordValue":"amino acid sequence"}],"author":{"citation:authorName":"Orlando, Marco","citation:authorAffiliation":"University of Milano Bicocca","authorIdentifierScheme":"ORCID","authorIdentifier":"0000-0002-5914-3052"},"citation:dsDescription":{"citation:dsDescriptionValue":"A starting alignment was built if other sequences with a known PDB structure were available, by performing a GH19 domain structure-based alignment generated through the mmaker command implemented in ChimeraX. Other seed sequences in the same superfamily were added to this fixed structural alignment by the use of “--add” flag option available in MAFFT. If no other structures were available rather than the reference, a sequence-based alignment with other seeds was created with MAFFT “L-INS-i” strategy, improved by adding information of up to 600 close homologues obtained from a search in Uniprot non-redundant Uniref50 database using a restrictive E-value threshold of 10-20.\r\nThe obtained alignments were manually cut with respect to the length of the GH19 domain of the reference structure and used to generate the new superfamily-specific profile HMMs."},"grantNumber":[{"citation:grantNumberAgency":"Bundesministerium für Bildung und Forschung","citation:grantNumberValue":"031B0571A"},{"citation:grantNumberAgency":"Deutsche Forschungsgemeinschaft","citation:grantNumberValue":"EXC2075"}],"process:processMethodsPar":{"process:processMethodsParName":"E-value","process:processMethodsParValue":"1E-20"},"publication":{"publicationCitation":"Orlando M, Buchholz PCF, Lotti M, Pleiss J (2020) Large-scale exploration of sequences, substrate specificity and evolution in glycoside hydrolase family 19: the GH19 Engineering Database (submitted)"},"processSoftware":[{"processSoftwareName":"HMMER","processSoftwareVersion":"3.1b2","processSoftwareURL":"http://www.hmmer.org"},{"processSoftwareName":"ChimeraX","processSoftwareCitation":"Goddard TD, Huang CC, Meng EC, Pettersen EF, Couch GS, Morris JH, Ferrin TE (2018) UCSF ChimeraX: Meeting modern challenges in visualization and analysis. Protein Sci 27(1):14-25. https://doi.org/10.1002/pro.3235","processSoftwareVersion":"0.9"},{"processSoftwareName":"MAFFT","processSoftwareCitation":"Katoh K, Standley DM (2013) MAFFT multiple sequence alignment software version 7: improvements in performance and usability. Mol Biol Evol 30(4):772-780. https://doi.org/10.1093/molbev/mst010","processSoftwareVersion":"7.407"}],"title":"Profile hidden Markov models of the Glycoside Hydrolase 19 Engineering Database","citation:depositor":"Buchholz, Patrick C. F.","dateOfDeposit":"2020-05-11","dataSources":["Uniref50 database (Uniprot)\r\nftp://ftp.uniprot.org/pub/databases/uniprot/uniref/uniref50","https://gh19ed.biocatnet.de/"],"subject":"Medicine, Health and Life Sciences","@id":"https://doi.org/10.18419/darus-803","@type":["ore:Aggregation","schema:Dataset"],"schema:version":"1.0","schema:name":"Profile hidden Markov models of the Glycoside Hydrolase 19 Engineering Database","schema:dateModified":"Mon Jun 01 21:16:12 CEST 2020","schema:datePublished":"2020-06-01","schema:license":"http://creativecommons.org/licenses/by/4.0","dvcore:fileTermsOfAccess":{"dvcore:fileRequestAccess":false},"schema:includedInDataCatalog":"DaRUS","schema:isPartOf":{"schema:name":"Glycoside Hydrolase 19 Engineering Database","@id":"https://nfldevdataverse2.rus.uni-stuttgart.de/dataverse/ibtb_GH19ED","schema:description":"Supporting information and original files for bioinformatic investigations using the Glycoside Hydrolase 19 Engineering Database (https://gh19ed.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":"Profile hidden Markov model in HMMER format for the chitinase superfamily","schema:name":"CHITs.hmm","dvcore:restricted":false,"schema:version":2,"dvcore:datasetVersionId":376,"@id":"doi:10.18419/darus-803/6","schema:sameAs":"https://nfldevdataverse2.rus.uni-stuttgart.de/api/access/datafile/:persistentId?persistentId=doi:10.18419/darus-803/6","@type":"ore:AggregatedResource","schema:fileFormat":"application/octet-stream","dvcore:filesize":113564,"dvcore:storageIdentifier":"s3://fokus-dv-prod-1:17202b00fca-a1fa63f7cc4b","dvcore:rootDataFileId":-1,"dvcore:checksum":{"@type":"MD5","@value":"9c4c77ebc1b7f7a3c4c4f9bf713aa7fe"}},{"schema:description":"Profile hidden Markov model in HMMER format for the endolysin superfamily","schema:name":"ELYSs.hmm","dvcore:restricted":false,"schema:version":2,"dvcore:datasetVersionId":376,"@id":"doi:10.18419/darus-803/2","schema:sameAs":"https://nfldevdataverse2.rus.uni-stuttgart.de/api/access/datafile/:persistentId?persistentId=doi:10.18419/darus-803/2","@type":"ore:AggregatedResource","schema:fileFormat":"application/octet-stream","dvcore:filesize":83322,"dvcore:storageIdentifier":"s3://fokus-dv-prod-1:17202b0129f-28f8232542d5","dvcore:rootDataFileId":-1,"dvcore:checksum":{"@type":"MD5","@value":"61d6a4adfde821f447d18458a00e7667"}},{"schema:description":"Clustal alignment for the profile hidden Markov model of the chitinase superfamily\r\n\t","schema:name":"Reference_alignment_CHITs.aln","dvcore:restricted":false,"schema:version":2,"dvcore:datasetVersionId":376,"@id":"doi:10.18419/darus-803/1","schema:sameAs":"https://nfldevdataverse2.rus.uni-stuttgart.de/api/access/datafile/:persistentId?persistentId=doi:10.18419/darus-803/1","@type":"ore:AggregatedResource","schema:fileFormat":"application/octet-stream","dvcore:filesize":16272,"dvcore:storageIdentifier":"s3://fokus-dv-prod-1:17202b01482-b0f4b40f7595","dvcore:rootDataFileId":-1,"dvcore:checksum":{"@type":"MD5","@value":"1de23a931f1988e2e26fa21ca210605c"}},{"schema:description":"Stockholm alignment for the profile hidden Markov model of the chitinase superfamily","schema:name":"Reference_alignment_CHITs.stockholm","dvcore:restricted":false,"schema:version":2,"dvcore:datasetVersionId":376,"@id":"doi:10.18419/darus-803/3","schema:sameAs":"https://nfldevdataverse2.rus.uni-stuttgart.de/api/access/datafile/:persistentId?persistentId=doi:10.18419/darus-803/3","@type":"ore:AggregatedResource","schema:fileFormat":"application/octet-stream","dvcore:filesize":18605,"dvcore:storageIdentifier":"s3://fokus-dv-prod-1:17202b0164f-63b777b39aeb","dvcore:rootDataFileId":-1,"dvcore:checksum":{"@type":"MD5","@value":"116056d1f562c17e3a2b0ebe8714d0fe"}},{"schema:description":"Clustal alignment for the profile hidden Markov model of the endolysin superfamily","schema:name":"Reference_alignment_ELYSs.aln","dvcore:restricted":false,"schema:version":2,"dvcore:datasetVersionId":376,"@id":"doi:10.18419/darus-803/4","schema:sameAs":"https://nfldevdataverse2.rus.uni-stuttgart.de/api/access/datafile/:persistentId?persistentId=doi:10.18419/darus-803/4","@type":"ore:AggregatedResource","schema:fileFormat":"application/octet-stream","dvcore:filesize":403941,"dvcore:storageIdentifier":"s3://fokus-dv-prod-1:17202b0191d-084a4f5111b3","dvcore:rootDataFileId":-1,"dvcore:checksum":{"@type":"MD5","@value":"b30ebdc0bf4ad0af8b50c15f6339b5e7"}},{"schema:description":"Stockholm alignment for the profile hidden Markov model of the endolysin superfamily","schema:name":"Reference_alignment_ELYSs.stockholm","dvcore:restricted":false,"schema:version":2,"dvcore:datasetVersionId":376,"@id":"doi:10.18419/darus-803/5","schema:sameAs":"https://nfldevdataverse2.rus.uni-stuttgart.de/api/access/datafile/:persistentId?persistentId=doi:10.18419/darus-803/5","@type":"ore:AggregatedResource","schema:fileFormat":"application/octet-stream","dvcore:filesize":429406,"dvcore:storageIdentifier":"s3://fokus-dv-prod-1:17202b01bbf-5b80fd35d28b","dvcore:rootDataFileId":-1,"dvcore:checksum":{"@type":"MD5","@value":"88e1f79860f29df5626599bd48cfcff3"}}],"schema:hasPart":["doi:10.18419/darus-803/6","doi:10.18419/darus-803/2","doi:10.18419/darus-803/1","doi:10.18419/darus-803/3","doi:10.18419/darus-803/4","doi:10.18419/darus-803/5"]},"@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/","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#","grantNumber":"https://schema.org/sponsor","ore":"http://www.openarchives.org/ore/terms/","process":"https://nfldevdataverse2.rus.uni-stuttgart.de/schema/process#","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","schema":"http://schema.org/","subject":"http://purl.org/dc/terms/subject","title":"http://purl.org/dc/terms/title"}}