{"id":58132,"identifier":"FK2/YQDFT4","persistentUrl":"https://doi.org/10.60507/FK2/YQDFT4","protocol":"doi","authority":"10.60507","separator":"/","publisher":"bonndata","publicationDate":"2026-08-25","storageIdentifier":"file://10.60507/FK2/YQDFT4","metadataLanguage":"en","datasetType":"dataset","datasetVersion":{"id":818,"datasetId":58132,"datasetPersistentId":"doi:10.60507/FK2/YQDFT4","datasetType":"dataset","storageIdentifier":"file://10.60507/FK2/YQDFT4","versionNumber":1,"internalVersionNumber":8,"versionMinorNumber":0,"versionState":"RELEASED","latestVersionPublishingState":"RELEASED","lastUpdateTime":"2026-08-25T13:22:42Z","releaseTime":"2026-08-25T13:22:42Z","createTime":"2026-08-21T14:08:41Z","publicationDate":"2026-08-25","citationDate":"2026-08-25","license":{"name":"CC BY 4.0","uri":"http://creativecommons.org/licenses/by/4.0","iconUri":"https://licensebuttons.net/l/by/4.0/88x31.png"},"fileAccessRequest":true,"metadataBlocks":{"citation":{"displayName":"Citation Metadata","name":"citation","fields":[{"typeName":"title","multiple":false,"typeClass":"primitive","value":"Theobroma cacao: Genome Sequences and Annotations"},{"typeName":"author","multiple":true,"typeClass":"compound","value":[{"authorName":{"typeName":"authorName","multiple":false,"typeClass":"primitive","value":"Marín Recinos, María Fernanda"},"authorAffiliation":{"typeName":"authorAffiliation","multiple":false,"typeClass":"primitive","value":"University of Bonn"},"authorIdentifierScheme":{"typeName":"authorIdentifierScheme","multiple":false,"typeClass":"controlledVocabulary","value":"ORCID"},"authorIdentifier":{"typeName":"authorIdentifier","multiple":false,"typeClass":"primitive","value":"https://orcid.org/0000-0001-5575-1264","expandedvalue":{"personName":"Marín Recinos, María Fernanda","@id":"https://orcid.org/0000-0001-5575-1264","scheme":"ORCID","@type":"https://schema.org/Person"}}},{"authorName":{"typeName":"authorName","multiple":false,"typeClass":"primitive","value":"Ajayi, Blessing"},"authorIdentifierScheme":{"typeName":"authorIdentifierScheme","multiple":false,"typeClass":"controlledVocabulary","value":"ORCID"},"authorIdentifier":{"typeName":"authorIdentifier","multiple":false,"typeClass":"primitive","value":"https://orcid.org/0009-0005-4753-8769","expandedvalue":{"personName":"Ajayi, Blessing","@id":"https://orcid.org/0009-0005-4753-8769","scheme":"ORCID","@type":"https://schema.org/Person"}}},{"authorName":{"typeName":"authorName","multiple":false,"typeClass":"primitive","value":"Wolff, Katharina"},"authorAffiliation":{"typeName":"authorAffiliation","multiple":false,"typeClass":"primitive","value":"University of Bonn"},"authorIdentifierScheme":{"typeName":"authorIdentifierScheme","multiple":false,"typeClass":"controlledVocabulary","value":"ORCID"},"authorIdentifier":{"typeName":"authorIdentifier","multiple":false,"typeClass":"primitive","value":"https://orcid.org/0000-0002-3616-0482","expandedvalue":{"personName":"Wolff, Katharina","@id":"https://orcid.org/0000-0002-3616-0482","scheme":"ORCID","@type":"https://schema.org/Person"}}},{"authorName":{"typeName":"authorName","multiple":false,"typeClass":"primitive","value":"Choudhary, Nancy"},"authorAffiliation":{"typeName":"authorAffiliation","multiple":false,"typeClass":"primitive","value":"University of Bonn"},"authorIdentifierScheme":{"typeName":"authorIdentifierScheme","multiple":false,"typeClass":"controlledVocabulary","value":"ORCID"},"authorIdentifier":{"typeName":"authorIdentifier","multiple":false,"typeClass":"primitive","value":"https://orcid.org/0000-0002-2562-7905","expandedvalue":{"personName":"Choudhary, Nancy","@id":"https://orcid.org/0000-0002-2562-7905","scheme":"ORCID","@type":"https://schema.org/Person"}}},{"authorName":{"typeName":"authorName","multiple":false,"typeClass":"primitive","value":"Vieira Salgado de Oliveira, Julie Anne"},"authorAffiliation":{"typeName":"authorAffiliation","multiple":false,"typeClass":"primitive","value":"University of Bonn"},"authorIdentifierScheme":{"typeName":"authorIdentifierScheme","multiple":false,"typeClass":"controlledVocabulary","value":"ORCID"},"authorIdentifier":{"typeName":"authorIdentifier","multiple":false,"typeClass":"primitive","value":"https://orcid.org/0000-0001-9930-6373","expandedvalue":{"personName":"Vieira Salgado de Oliveira, Julie Anne","@id":"https://orcid.org/0000-0001-9930-6373","scheme":"ORCID","@type":"https://schema.org/Person"}}},{"authorName":{"typeName":"authorName","multiple":false,"typeClass":"primitive","value":"Pucker, Boas"},"authorAffiliation":{"typeName":"authorAffiliation","multiple":false,"typeClass":"primitive","value":"University of Bonn"},"authorIdentifierScheme":{"typeName":"authorIdentifierScheme","multiple":false,"typeClass":"controlledVocabulary","value":"ORCID"},"authorIdentifier":{"typeName":"authorIdentifier","multiple":false,"typeClass":"primitive","value":"0000-0002-3321-7471"}}]},{"typeName":"datasetContact","multiple":true,"typeClass":"compound","value":[{"datasetContactAffiliation":{"typeName":"datasetContactAffiliation","multiple":false,"typeClass":"primitive","value":"University of Bonn"},"datasetContactEmail":{"typeName":"datasetContactEmail","multiple":false,"typeClass":"primitive","value":"marmarin@uni-bonn.de"}}]},{"typeName":"dsDescription","multiple":true,"typeClass":"compound","value":[{"dsDescriptionValue":{"typeName":"dsDescriptionValue","multiple":false,"typeClass":"primitive","value":"The genomes of two Theobroma cacao plants were sequenced with Nanopore long reads. The genome sequence was assembled with hifiasm and the gene models were predicted by GeMoMa. The functional annotation was predicted based on sequence similarity to well characterized Arabidopsis thaliana sequences."}}]},{"typeName":"subject","multiple":true,"typeClass":"controlledVocabulary","value":["Agricultural Sciences","Medicine, Health and Life Sciences","Other"]},{"typeName":"subjectRefinement","multiple":true,"typeClass":"compound","value":[{"subjectRefinementValue":{"typeName":"subjectRefinementValue","multiple":false,"typeClass":"primitive","value":"Plant Sciences [202]"}}]},{"typeName":"freeKeyword","multiple":true,"typeClass":"compound","value":[{"freeKeywordValue":{"typeName":"freeKeywordValue","multiple":false,"typeClass":"primitive","value":"Theobroma cacao"}},{"freeKeywordValue":{"typeName":"freeKeywordValue","multiple":false,"typeClass":"primitive","value":"genome sequence"}},{"freeKeywordValue":{"typeName":"freeKeywordValue","multiple":false,"typeClass":"primitive","value":"Genome annotation"}},{"freeKeywordValue":{"typeName":"freeKeywordValue","multiple":false,"typeClass":"primitive","value":"Long read sequence"}}]},{"typeName":"publication","multiple":true,"typeClass":"compound","value":[{"publicationRelationType":{"typeName":"publicationRelationType","multiple":false,"typeClass":"controlledVocabulary","value":"IsCitedBy"},"publicationCitation":{"typeName":"publicationCitation","multiple":false,"typeClass":"primitive","value":"Cacao genome sequence reveals insights into the flavonoid biosynthesis\nMaria Fernanda Marin Recinos, Sarah Winnier, Kiersten Lagerhausen, Blessing Ajayi, Katharina Wolff, Ronja Friedhoff, Chiara Marie Dassow, Nancy Choudhary, Boas Pucker\nbioRxiv 2024.11.23.624982;"},"publicationIDType":{"typeName":"publicationIDType","multiple":false,"typeClass":"controlledVocabulary","value":"doi"},"publicationURL":{"typeName":"publicationURL","multiple":false,"typeClass":"primitive","value":"https://doi.org/10.1101/2024.11.23.624982"}}]},{"typeName":"language","multiple":true,"typeClass":"controlledVocabulary","value":["English"]},{"typeName":"depositor","multiple":false,"typeClass":"primitive","value":"Marin Recinos, Maria"},{"typeName":"dateOfDeposit","multiple":false,"typeClass":"primitive","value":"2026-08-21"}]}},"files":[{"label":"README_Tcacao.md","restricted":false,"version":1,"datasetVersionId":818,"dataFile":{"id":58144,"persistentId":"doi:10.60507/FK2/YQDFT4/QICWZH","pidURL":"https://doi.org/10.60507/FK2/YQDFT4/QICWZH","filename":"README_Tcacao.md","contentType":"text/markdown","friendlyType":"Markdown Text","filesize":9037,"storageIdentifier":"file://1a024ae0d9b-d3005ff78e91","rootDataFileId":-1,"md5":"3ac82eef484de1d85bb01001e73da34e","checksum":{"type":"MD5","value":"3ac82eef484de1d85bb01001e73da34e"},"tabularData":false,"creationDate":"2026-08-21","publicationDate":"2026-08-25","fileAccessRequest":true}},{"label":"Tcacao_BONN1.v01.asm.fasta.gz","restricted":false,"version":1,"datasetVersionId":818,"dataFile":{"id":58140,"persistentId":"doi:10.60507/FK2/YQDFT4/JUKXXQ","pidURL":"https://doi.org/10.60507/FK2/YQDFT4/JUKXXQ","filename":"Tcacao_BONN1.v01.asm.fasta.gz","contentType":"application/gzip","friendlyType":"Gzip Archive","filesize":102227370,"storageIdentifier":"file://1a024a39936-45b7d066ec60","rootDataFileId":-1,"md5":"b8e60a60cf1f53425372f4c62dfcde48","checksum":{"type":"MD5","value":"b8e60a60cf1f53425372f4c62dfcde48"},"tabularData":false,"creationDate":"2026-08-21","publicationDate":"2026-08-25","fileAccessRequest":true}},{"label":"Tcacao_BONN1.v01.v01.cds.fasta","restricted":false,"version":1,"datasetVersionId":818,"dataFile":{"id":58133,"persistentId":"doi:10.60507/FK2/YQDFT4/CGLHHH","pidURL":"https://doi.org/10.60507/FK2/YQDFT4/CGLHHH","filename":"Tcacao_BONN1.v01.v01.cds.fasta","contentType":"application/octet-stream","friendlyType":"Unknown","filesize":72715236,"storageIdentifier":"file://1a024a53ae1-60cb72496d5a","rootDataFileId":-1,"md5":"f9d3deb72ac5c9aafc1d52230b1dcac0","checksum":{"type":"MD5","value":"f9d3deb72ac5c9aafc1d52230b1dcac0"},"tabularData":false,"creationDate":"2026-08-21","publicationDate":"2026-08-25","fileAccessRequest":true}},{"label":"Tcacao_BONN1.v01.v01.gff","restricted":false,"version":1,"datasetVersionId":818,"dataFile":{"id":58138,"persistentId":"doi:10.60507/FK2/YQDFT4/Q8ZVHI","pidURL":"https://doi.org/10.60507/FK2/YQDFT4/Q8ZVHI","filename":"Tcacao_BONN1.v01.v01.gff","contentType":"application/octet-stream","friendlyType":"Unknown","filesize":57219328,"storageIdentifier":"file://1a024a4a1ea-1c97f82f1d85","rootDataFileId":-1,"md5":"7f1741c1ef48820737c1a86ce08204ef","checksum":{"type":"MD5","value":"7f1741c1ef48820737c1a86ce08204ef"},"tabularData":false,"creationDate":"2026-08-21","publicationDate":"2026-08-25","fileAccessRequest":true}},{"label":"Tcacao_BONN1.v01.v01.pep.fasta","restricted":false,"version":1,"datasetVersionId":818,"dataFile":{"id":58139,"persistentId":"doi:10.60507/FK2/YQDFT4/16FBNK","pidURL":"https://doi.org/10.60507/FK2/YQDFT4/16FBNK","filename":"Tcacao_BONN1.v01.v01.pep.fasta","contentType":"application/octet-stream","friendlyType":"Unknown","filesize":24834670,"storageIdentifier":"file://1a024a65022-9f65d721b410","rootDataFileId":-1,"md5":"e59dd3d0d981aae785229f94373cbcd7","checksum":{"type":"MD5","value":"e59dd3d0d981aae785229f94373cbcd7"},"tabularData":false,"creationDate":"2026-08-21","publicationDate":"2026-08-25","fileAccessRequest":true}},{"label":"Tcacao_BONN1_annot.v01.v01.txt","restricted":false,"version":1,"datasetVersionId":818,"dataFile":{"id":58137,"persistentId":"doi:10.60507/FK2/YQDFT4/6UAUBC","pidURL":"https://doi.org/10.60507/FK2/YQDFT4/6UAUBC","filename":"Tcacao_BONN1_annot.v01.v01.txt","contentType":"text/plain","friendlyType":"Plain Text","filesize":2700143,"storageIdentifier":"file://1a024a687d0-ea3997013fb7","rootDataFileId":-1,"md5":"905fdff8fc90e1cd9d3b170e54655daf","checksum":{"type":"MD5","value":"905fdff8fc90e1cd9d3b170e54655daf"},"tabularData":false,"creationDate":"2026-08-21","publicationDate":"2026-08-25","fileAccessRequest":true}},{"label":"Tcacao_BRAU1.v01.asm.fasta.gz","restricted":false,"version":1,"datasetVersionId":818,"dataFile":{"id":58141,"persistentId":"doi:10.60507/FK2/YQDFT4/R569Q2","pidURL":"https://doi.org/10.60507/FK2/YQDFT4/R569Q2","filename":"Tcacao_BRAU1.v01.asm.fasta.gz","contentType":"application/gzip","friendlyType":"Gzip Archive","filesize":102043785,"storageIdentifier":"file://1a0249cdea3-193b373c0976","rootDataFileId":-1,"md5":"3e59f3738ada1217880895c27a946200","checksum":{"type":"MD5","value":"3e59f3738ada1217880895c27a946200"},"tabularData":false,"creationDate":"2026-08-21","publicationDate":"2026-08-25","fileAccessRequest":true}},{"label":"Tcacao_BRAU1.v01.v01.cds.fasta","restricted":false,"version":1,"datasetVersionId":818,"dataFile":{"id":58143,"persistentId":"doi:10.60507/FK2/YQDFT4/ECBQBM","pidURL":"https://doi.org/10.60507/FK2/YQDFT4/ECBQBM","filename":"Tcacao_BRAU1.v01.v01.cds.fasta","contentType":"application/octet-stream","friendlyType":"Unknown","filesize":97064527,"storageIdentifier":"file://1a0249ef473-e517ac040cf6","rootDataFileId":-1,"md5":"51c19a868da3bb91e26eae130d1fae7f","checksum":{"type":"MD5","value":"51c19a868da3bb91e26eae130d1fae7f"},"tabularData":false,"creationDate":"2026-08-21","publicationDate":"2026-08-25","fileAccessRequest":true}},{"label":"Tcacao_BRAU1.v01.v01.gff","restricted":false,"version":1,"datasetVersionId":818,"dataFile":{"id":58135,"persistentId":"doi:10.60507/FK2/YQDFT4/XPSSUU","pidURL":"https://doi.org/10.60507/FK2/YQDFT4/XPSSUU","filename":"Tcacao_BRAU1.v01.v01.gff","contentType":"application/octet-stream","friendlyType":"Unknown","filesize":78030303,"storageIdentifier":"file://1a0249e1042-0cebba4c3bda","rootDataFileId":-1,"md5":"95c6db60500df280d49884a2acf47998","checksum":{"type":"MD5","value":"95c6db60500df280d49884a2acf47998"},"tabularData":false,"creationDate":"2026-08-21","publicationDate":"2026-08-25","fileAccessRequest":true}},{"label":"Tcacao_BRAU1.v01.v01.pep.fasta","restricted":false,"version":1,"datasetVersionId":818,"dataFile":{"id":58134,"persistentId":"doi:10.60507/FK2/YQDFT4/E1P0WO","pidURL":"https://doi.org/10.60507/FK2/YQDFT4/E1P0WO","filename":"Tcacao_BRAU1.v01.v01.pep.fasta","contentType":"application/octet-stream","friendlyType":"Unknown","filesize":33061999,"storageIdentifier":"file://1a0249f1ed2-d4d5d4d64c66","rootDataFileId":-1,"md5":"0d1fcd8883545019af52251a3c79e4c1","checksum":{"type":"MD5","value":"0d1fcd8883545019af52251a3c79e4c1"},"tabularData":false,"creationDate":"2026-08-21","publicationDate":"2026-08-25","fileAccessRequest":true}},{"label":"Tcacao_BRAU1_annot.v01.v01.txt","restricted":false,"version":1,"datasetVersionId":818,"dataFile":{"id":58142,"persistentId":"doi:10.60507/FK2/YQDFT4/R3KQGP","pidURL":"https://doi.org/10.60507/FK2/YQDFT4/R3KQGP","filename":"Tcacao_BRAU1_annot.v01.v01.txt","contentType":"text/plain","friendlyType":"Plain Text","filesize":3495719,"storageIdentifier":"file://1a024a0d154-d73f28c33d36","rootDataFileId":-1,"md5":"bf3f7dbe1a9c6e40bff4b81d6e1430e0","checksum":{"type":"MD5","value":"bf3f7dbe1a9c6e40bff4b81d6e1430e0"},"tabularData":false,"creationDate":"2026-08-21","publicationDate":"2026-08-25","fileAccessRequest":true}}],"citation":"Marín Recinos, María Fernanda; Ajayi, Blessing; Wolff, Katharina; Choudhary, Nancy; Vieira Salgado de Oliveira, Julie Anne; Pucker, Boas, 2026, \"Theobroma cacao: Genome Sequences and Annotations\", https://doi.org/10.60507/FK2/YQDFT4, bonndata, V1"}}