{"dcterms:modified":"2026-08-27","dcterms:creator":"bonndata","@type":"ore:ResourceMap","schema:additionalType":"Dataverse OREMap Format v1.0.1","dvcore:generatedBy":{"@type":"schema:SoftwareApplication","schema:name":"Dataverse","schema:version":"6.7.1 build 1955-8e18f64","schema:url":"https://github.com/iqss/dataverse"},"@id":"https://bonndata.uni-bonn.de/catalog/datasets/10.60507/FK2/ZNVSLA/exportformat/oai-ore.json","ore:describes":{"citation:freeKeyword":[{"citation:freeKeywordValue":"flavonoids"},{"citation:freeKeywordValue":"pigmentation"},{"citation:freeKeywordValue":"gene loss"},{"citation:freeKeywordValue":"phylogenomics"},{"citation:freeKeywordValue":"carotenoids"},{"citation:freeKeywordValue":"comparative genomics"},{"citation:freeKeywordValue":"Cucurbitaceae"}],"author":[{"citation:authorName":"Choudhary, Nancy","citation:authorAffiliation":"IZMB, University of Bonn","authorIdentifierScheme":"ORCID","authorIdentifier":{"personName":"Choudhary, Nancy","@id":"https://orcid.org/0000-0002-2562-7905","scheme":"ORCID","@type":"https://schema.org/Person"}},{"citation:authorName":"Hagedorn, Marie","citation:authorAffiliation":"IZMB, University of Bonn","authorIdentifierScheme":"ORCID","authorIdentifier":{"personName":"Hagedorn, Marie","@id":"https://orcid.org/0009-0009-1312-0531","scheme":"ORCID","@type":"https://schema.org/Person"}},{"citation:authorName":"Pucker, Boas","citation:authorAffiliation":"IZMB, University of Bonn","authorIdentifierScheme":"ORCID","authorIdentifier":{"personName":"Pucker, Boas","@id":"https://orcid.org/0000-0002-3321-7471","scheme":"ORCID","@type":"https://schema.org/Person"}}],"publication":{"publicationCitation":"Nancy Choudhary, Marie Hagedorn, Boas Pucker (2025). Out of the blue: Family-wide loss of anthocyanin biosynthesis in Cucurbitaceae","publicationIDType":"doi","publicationURL":"https://doi.org/10.1101/2025.10.06.680802","publicationRelationType":"IsSupplementTo"},"citation:datasetContact":{"citation:datasetContactName":"Choudhary, Nancy","citation:datasetContactAffiliation":"University of Bonn","citation:datasetContactEmail":"nchoudha@uni-bonn.de"},"citation:dsDescription":{"citation:dsDescriptionValue":"This dataset contains supplementary data supporting the manuscript \"Out of the blue: Family-wide loss of anthocyanin biosynthesis in Cucurbitaceae\".  In this large-scale phylogenomics study, we discovered the systemic absence of anthocyanin and proanthocyanidin biosynthesis genes in the Cucurbitaceae family. The structural genes DFR, ANS, arGST, LAR, and ANR, along with the anthocyanin-related regulatory MYB genes were absent in the family, confirmed via synteny and phylogenetic analysis. The dataset includes details about the sources of datasets used in the study, structural annotation details, detailed taxonomic classification results for all datasets, details about genes used for species and gene phylogenies, coding sequences used for individual anthocyanin biosynthesis gene trees (in FASTA format), sources used for flower and fruit colour mapping, structural annotation files, and gene expression data.","citation:dsDescriptionDate":"2025-12-15"},"contributor":{"citation:contributorType":"Supervisor","citation:contributorName":"Boas Pucker"},"citation:dateOfCollection":{"citation:dateOfCollectionStart":"2024-12-26","citation:dateOfCollectionEnd":"2025-07-31"},"dateOfDeposit":"2025-12-15","title":"Supplementary data supporting the study: \"Out of the blue: Family-wide loss of anthocyanin biosynthesis in Cucurbitaceae\"","citation:depositor":"Choudhary, Nancy","language":"English","citation:productionPlace":"Bonn","citation:productionDate":"2025-12-15","subject":"Medicine, Health and Life Sciences","software":[{"citation:softwareName":"GeMoMa","citation:softwareVersion":"1.9"},{"citation:softwareName":"BUSCO","citation:softwareVersion":"5.8.1"},{"citation:softwareName":"Kraken","citation:softwareVersion":"2.1.3"},{"citation:softwareName":"Bracken","citation:softwareVersion":"2.9"},{"citation:softwareName":"kallisto","citation:softwareVersion":"0.44"},{"citation:softwareName":"Python","citation:softwareVersion":"3.11.8"}],"citation:subjectRefinement":{"subjectRefinementValue":"Plant Sciences [202]"},"@id":"https://doi.org/10.60507/FK2/ZNVSLA","@type":["ore:Aggregation","schema:Dataset"],"schema:version":"1.0","schema:name":"Supplementary data supporting the study: \"Out of the blue: Family-wide loss of anthocyanin biosynthesis in Cucurbitaceae\"","schema:dateModified":"Thu Dec 18 15:00:01 CET 2025","schema:datePublished":"2025-12-18","schema:creativeWorkStatus":"RELEASED","schema:license":"http://creativecommons.org/licenses/by/4.0","dvcore:fileTermsOfAccess":{"dvcore:fileRequestAccess":true},"schema:includedInDataCatalog":"bonndata","schema:isPartOf":{"schema:name":"Plant Biotechnology and Bioinformatics","@id":"https://bonndata.uni-bonn.de/dataverse/pbb","schema:description":"We address biological questions by combining molecular biology and computational methods. Our focus is on the genetic basis of plant specialized metabolism and the evolution of biosynthetic capabilities. To elucidate biosynthetic networks, we combine data from our own sequencing with public datasets. Bioinformatics tools are developed to answer specific questions through the analysis of large datasets, often employing methods of artificial intelligence. We investigate the regulation of biosynthetic networks through transcriptomics. Phylogenetic analyses assist in selecting candidate genes for specific molecular functions. Identified genes and biosynthetic pathways serve as a basis for experiments using synthetic biology methods. The results from the various approaches culminate in biotechnological applications.","schema:isPartOf":{"schema:name":"bonndata","@id":"https://bonndata.uni-bonn.de/dataverse/bonndata-root","schema:description":"<h3>bonndata is the institutional, cross-disciplinary research data repository for the publication of research data for all researchers at the University of Bonn.\n<br> bonndata is provided by the <a href=\"https://www.hrz.uni-bonn.de/de\">University IT and Data Center </a> and maintained by the <a href=\"https://www.forschungsdaten.uni-bonn.de/de\">Research Data Service Center</a>.\n<br><hr>\nReady to get started with bonndata? \n<br>\nHave a look at our <a href=\"https://confluence.team.uni-bonn.de/x/-1dqBg\">User Guide</a> to get to know the bonndata workflow, tips and tricks!\n<br><hr>\nQuestions? Need assistance? \n<br>\nGet in touch: <b> researchdata@uni-bonn.de</h3>\n<br><hr>"}},"schema:inLanguage":"en","ore:aggregates":[{"schema:description":"List of BUSCO genes from eudictoyledons_odb12 lineage used for coalescence and concatenation-based species phylogeny","schema:name":"BUSCO_genes_for_species_phylogeny.csv","dvcore:restricted":false,"schema:version":1,"dvcore:datasetVersionId":527,"@id":"doi:10.60507/FK2/ZNVSLA/CY5FUG","schema:sameAs":"https://bonndata.uni-bonn.de/catalog/downloads/14799/BUSCO_genes_for_species_phylogeny.csv","@type":"ore:AggregatedResource","schema:fileFormat":"text/csv","dvcore:filesize":51652,"dvcore:storageIdentifier":"file://19b21f7386c-7909b845c585","dvcore:rootDataFileId":-1,"dvcore:checksum":{"@type":"MD5","@value":"6349019a3d9a25b2d52db69957243d10"}},{"schema:description":"List of reference sequences used for phylogenetic trees","schema:name":"Bait_sequences_gene_trees.csv","dvcore:restricted":false,"schema:version":1,"dvcore:datasetVersionId":527,"@id":"doi:10.60507/FK2/ZNVSLA/R8I60C","schema:sameAs":"https://bonndata.uni-bonn.de/catalog/downloads/14801/Bait_sequences_gene_trees.csv","@type":"ore:AggregatedResource","schema:fileFormat":"text/csv","dvcore:filesize":49864,"dvcore:storageIdentifier":"file://19b21f731e3-90aff7cf0560","dvcore:rootDataFileId":-1,"dvcore:checksum":{"@type":"MD5","@value":"5e1581a14a019d45774fe557a1e12a8d"}},{"schema:description":"Coding sequences used for constructing individual gene phylogenetic trees in FASTA format. ","schema:name":"Coding_seq_gene_trees_dataset.tar.gz","dvcore:restricted":false,"schema:version":1,"dvcore:datasetVersionId":527,"@id":"doi:10.60507/FK2/ZNVSLA/QKHYGA","schema:sameAs":"https://bonndata.uni-bonn.de/catalog/downloads/14802/Coding_seq_gene_trees_dataset.tar.gz","@type":"ore:AggregatedResource","schema:fileFormat":"application/gzip","dvcore:filesize":6056086,"dvcore:storageIdentifier":"file://19b21f6fe35-5c0af3177050","dvcore:rootDataFileId":-1,"dvcore:checksum":{"@type":"MD5","@value":"76582297191abb036adfb1cd7d07c96c"}},{"schema:description":"Sources of genomic and transcriptomic datasets used in the study","schema:name":"Dataset_sources.csv","dvcore:restricted":false,"schema:version":2,"dvcore:datasetVersionId":527,"@id":"doi:10.60507/FK2/ZNVSLA/UCO4IK","schema:sameAs":"https://bonndata.uni-bonn.de/catalog/downloads/14877/Dataset_sources.csv","@type":"ore:AggregatedResource","schema:fileFormat":"text/csv","dvcore:filesize":37277,"dvcore:storageIdentifier":"file://19b31a121d3-a08f019b45c6","dvcore:rootDataFileId":-1,"dvcore:checksum":{"@type":"MD5","@value":"3e5fd89ec0b5c62d0b40ec9e8097a8ff"}},{"schema:description":"Gene expression data of selected datasets used for expression analysis. File names are based on the plant species name. Each sub-folder contains the reference sequence (*.cds.fa & *.pep.fa), and a count table with the expression data (*.tpms.txt).","schema:name":"Expression_datasets.tar.gz","dvcore:restricted":false,"schema:version":1,"dvcore:datasetVersionId":527,"@id":"doi:10.60507/FK2/ZNVSLA/S3I0KS","schema:sameAs":"https://bonndata.uni-bonn.de/catalog/downloads/14804/Expression_datasets.tar.gz","@type":"ore:AggregatedResource","schema:fileFormat":"application/gzip","dvcore:filesize":1227781722,"dvcore:storageIdentifier":"file://19b21fc73c6-290a0e9d48cc","dvcore:rootDataFileId":-1,"dvcore:checksum":{"@type":"MD5","@value":"1fa4521900ba3fbab3d589936a2c3849"}},{"schema:description":"Links to websites used as reference for mapping fruit and flower colours used in Figure 2. ","schema:name":"Fruit_flower_colour_sources.csv","dvcore:restricted":false,"schema:version":1,"dvcore:datasetVersionId":527,"@id":"doi:10.60507/FK2/ZNVSLA/QU4ISS","schema:sameAs":"https://bonndata.uni-bonn.de/catalog/downloads/14797/Fruit_flower_colour_sources.csv","@type":"ore:AggregatedResource","schema:fileFormat":"text/csv","dvcore:filesize":13899,"dvcore:storageIdentifier":"file://19b21f73dd9-8bcd13193585","dvcore:rootDataFileId":-1,"dvcore:checksum":{"@type":"MD5","@value":"0d2e5292f31213e8b98d08d54fde165b"}},{"schema:description":"Structural annotation of various datasets generated in the study using GeMoMa v1.9. Each subfolder contains the structural annotations in GFF3 (.gff3) format, predicted coding sequences as FASTA file (.cds.fa), and the predicted polypeptide sequences as FASTA file (.pep.fa) for the corresponding dataset. File names are based on the plant species name.","schema:name":"Gene_Annotation_dataset.tar.gz","dvcore:restricted":false,"schema:version":1,"dvcore:datasetVersionId":527,"@id":"doi:10.60507/FK2/ZNVSLA/LBADVE","schema:sameAs":"https://bonndata.uni-bonn.de/catalog/downloads/14803/Gene_Annotation_dataset.tar.gz","@type":"ore:AggregatedResource","schema:fileFormat":"application/gzip","dvcore:filesize":2192069456,"dvcore:storageIdentifier":"file://19b22096429-8af51054c646","dvcore:rootDataFileId":-1,"dvcore:checksum":{"@type":"MD5","@value":"7b79b7bf905e7e72c5b234a3968b2971"}},{"schema:description":"Statistics of gene annotation of 82 species and re-annotation of 7 species","schema:name":"Gene_annotation_stats.csv","dvcore:restricted":false,"schema:version":1,"dvcore:datasetVersionId":527,"@id":"doi:10.60507/FK2/ZNVSLA/3ATXUD","schema:sameAs":"https://bonndata.uni-bonn.de/catalog/downloads/14798/Gene_annotation_stats.csv","@type":"ore:AggregatedResource","schema:fileFormat":"text/csv","dvcore:filesize":7705,"dvcore:storageIdentifier":"file://19b21f73e20-a7a140022e4d","dvcore:rootDataFileId":-1,"dvcore:checksum":{"@type":"MD5","@value":"8b6e314c149aa413049e66e977c863cb"}},{"schema:description":"Detailed results of Kraken and Bracken classification of all datasets","schema:name":"Kraken_classification.csv","dvcore:restricted":false,"schema:version":1,"dvcore:datasetVersionId":527,"@id":"doi:10.60507/FK2/ZNVSLA/9LWPEX","schema:sameAs":"https://bonndata.uni-bonn.de/catalog/downloads/14795/Kraken_classification.csv","@type":"ore:AggregatedResource","schema:fileFormat":"text/csv","dvcore:filesize":35465,"dvcore:storageIdentifier":"file://19b21f73e56-9dad89e3b981","dvcore:rootDataFileId":-1,"dvcore:checksum":{"@type":"MD5","@value":"d03c4330afa93ae046f183653f66d1c6"}},{"schema:description":"README file describing the datasets and files overview","schema:name":"README.txt","dvcore:restricted":false,"schema:version":2,"dvcore:datasetVersionId":527,"@id":"doi:10.60507/FK2/ZNVSLA/P3PHNX","schema:sameAs":"https://bonndata.uni-bonn.de/catalog/downloads/14878/README.txt","@type":"ore:AggregatedResource","schema:fileFormat":"text/plain","dvcore:filesize":17406,"dvcore:storageIdentifier":"file://19b31a1218d-eabeb0d83dc4","dvcore:rootDataFileId":-1,"dvcore:checksum":{"@type":"MD5","@value":"09efa63aa55dec812e8d28aa1037efac"}}],"schema:hasPart":["doi:10.60507/FK2/ZNVSLA/CY5FUG","doi:10.60507/FK2/ZNVSLA/R8I60C","doi:10.60507/FK2/ZNVSLA/QKHYGA","doi:10.60507/FK2/ZNVSLA/UCO4IK","doi:10.60507/FK2/ZNVSLA/S3I0KS","doi:10.60507/FK2/ZNVSLA/QU4ISS","doi:10.60507/FK2/ZNVSLA/LBADVE","doi:10.60507/FK2/ZNVSLA/3ATXUD","doi:10.60507/FK2/ZNVSLA/9LWPEX","doi:10.60507/FK2/ZNVSLA/P3PHNX"]},"@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/","contributor":"http://purl.org/dc/terms/contributor","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/","personName":"https://schema.org/name","publication":"http://purl.org/dc/terms/isReferencedBy","publicationCitation":"http://purl.org/dc/terms/bibliographicCitation","publicationIDType":"http://purl.org/spar/datacite/ResourceIdentifierScheme","publicationRelationType":"http://datacite.org/schema/kernel-4/simpleTypes#relationType","publicationURL":"https://schema.org/distribution","schema":"http://schema.org/","scheme":"http://www.w3.org/2004/02/skos/core#inScheme","software":"https://www.w3.org/TR/prov-o/#wasGeneratedBy","subject":"http://purl.org/dc/terms/subject","subjectRefinementValue":"http://purl.org/dc/terms/subject","title":"http://purl.org/dc/terms/title"}}