{"id":14637,"identifier":"FK2/ZNVSLA","persistentUrl":"https://doi.org/10.60507/FK2/ZNVSLA","protocol":"doi","authority":"10.60507","separator":"/","publisher":"bonndata","publicationDate":"2025-12-18","storageIdentifier":"file://10.60507/FK2/ZNVSLA","metadataLanguage":"en","datasetType":"dataset","datasetVersion":{"id":527,"datasetId":14637,"datasetPersistentId":"doi:10.60507/FK2/ZNVSLA","datasetType":"dataset","storageIdentifier":"file://10.60507/FK2/ZNVSLA","versionNumber":1,"internalVersionNumber":26,"versionMinorNumber":0,"versionState":"RELEASED","latestVersionPublishingState":"RELEASED","productionDate":"2025-12-15","lastUpdateTime":"2025-12-18T14:00:01Z","releaseTime":"2025-12-18T14:00:01Z","createTime":"2025-12-01T13:22:29Z","publicationDate":"2025-12-18","citationDate":"2025-12-18","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":"Supplementary data supporting the study: \"Out of the blue: Family-wide loss of anthocyanin biosynthesis in Cucurbitaceae\""},{"typeName":"author","multiple":true,"typeClass":"compound","value":[{"authorName":{"typeName":"authorName","multiple":false,"typeClass":"primitive","value":"Choudhary, Nancy"},"authorAffiliation":{"typeName":"authorAffiliation","multiple":false,"typeClass":"primitive","value":"IZMB, 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":"Hagedorn, Marie"},"authorAffiliation":{"typeName":"authorAffiliation","multiple":false,"typeClass":"primitive","value":"IZMB, University of Bonn"},"authorIdentifierScheme":{"typeName":"authorIdentifierScheme","multiple":false,"typeClass":"controlledVocabulary","value":"ORCID"},"authorIdentifier":{"typeName":"authorIdentifier","multiple":false,"typeClass":"primitive","value":"https://orcid.org/0009-0009-1312-0531","expandedvalue":{"personName":"Hagedorn, Marie","@id":"https://orcid.org/0009-0009-1312-0531","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":"IZMB, University of Bonn"},"authorIdentifierScheme":{"typeName":"authorIdentifierScheme","multiple":false,"typeClass":"controlledVocabulary","value":"ORCID"},"authorIdentifier":{"typeName":"authorIdentifier","multiple":false,"typeClass":"primitive","value":"https://orcid.org/0000-0002-3321-7471","expandedvalue":{"personName":"Pucker, Boas","@id":"https://orcid.org/0000-0002-3321-7471","scheme":"ORCID","@type":"https://schema.org/Person"}}}]},{"typeName":"datasetContact","multiple":true,"typeClass":"compound","value":[{"datasetContactName":{"typeName":"datasetContactName","multiple":false,"typeClass":"primitive","value":"Choudhary, Nancy"},"datasetContactAffiliation":{"typeName":"datasetContactAffiliation","multiple":false,"typeClass":"primitive","value":"University of Bonn"},"datasetContactEmail":{"typeName":"datasetContactEmail","multiple":false,"typeClass":"primitive","value":"nchoudha@uni-bonn.de"}}]},{"typeName":"dsDescription","multiple":true,"typeClass":"compound","value":[{"dsDescriptionValue":{"typeName":"dsDescriptionValue","multiple":false,"typeClass":"primitive","value":"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."},"dsDescriptionDate":{"typeName":"dsDescriptionDate","multiple":false,"typeClass":"primitive","value":"2025-12-15"}}]},{"typeName":"subject","multiple":true,"typeClass":"controlledVocabulary","value":["Medicine, Health and Life Sciences"]},{"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":"flavonoids"}},{"freeKeywordValue":{"typeName":"freeKeywordValue","multiple":false,"typeClass":"primitive","value":"pigmentation"}},{"freeKeywordValue":{"typeName":"freeKeywordValue","multiple":false,"typeClass":"primitive","value":"gene loss"}},{"freeKeywordValue":{"typeName":"freeKeywordValue","multiple":false,"typeClass":"primitive","value":"phylogenomics"}},{"freeKeywordValue":{"typeName":"freeKeywordValue","multiple":false,"typeClass":"primitive","value":"carotenoids"}},{"freeKeywordValue":{"typeName":"freeKeywordValue","multiple":false,"typeClass":"primitive","value":"comparative genomics"}},{"freeKeywordValue":{"typeName":"freeKeywordValue","multiple":false,"typeClass":"primitive","value":"Cucurbitaceae"}}]},{"typeName":"publication","multiple":true,"typeClass":"compound","value":[{"publicationRelationType":{"typeName":"publicationRelationType","multiple":false,"typeClass":"controlledVocabulary","value":"IsSupplementTo"},"publicationCitation":{"typeName":"publicationCitation","multiple":false,"typeClass":"primitive","value":"Nancy Choudhary, Marie Hagedorn, Boas Pucker (2025). Out of the blue: Family-wide loss of anthocyanin biosynthesis in Cucurbitaceae"},"publicationIDType":{"typeName":"publicationIDType","multiple":false,"typeClass":"controlledVocabulary","value":"doi"},"publicationURL":{"typeName":"publicationURL","multiple":false,"typeClass":"primitive","value":"https://doi.org/10.1101/2025.10.06.680802"}}]},{"typeName":"language","multiple":true,"typeClass":"controlledVocabulary","value":["English"]},{"typeName":"productionDate","multiple":false,"typeClass":"primitive","value":"2025-12-15"},{"typeName":"productionPlace","multiple":false,"typeClass":"primitive","value":"Bonn"},{"typeName":"contributor","multiple":true,"typeClass":"compound","value":[{"contributorType":{"typeName":"contributorType","multiple":false,"typeClass":"controlledVocabulary","value":"Supervisor"},"contributorName":{"typeName":"contributorName","multiple":false,"typeClass":"primitive","value":"Boas Pucker"}}]},{"typeName":"depositor","multiple":false,"typeClass":"primitive","value":"Choudhary, Nancy"},{"typeName":"dateOfDeposit","multiple":false,"typeClass":"primitive","value":"2025-12-15"},{"typeName":"dateOfCollection","multiple":true,"typeClass":"compound","value":[{"dateOfCollectionStart":{"typeName":"dateOfCollectionStart","multiple":false,"typeClass":"primitive","value":"2024-12-26"},"dateOfCollectionEnd":{"typeName":"dateOfCollectionEnd","multiple":false,"typeClass":"primitive","value":"2025-07-31"}}]},{"typeName":"software","multiple":true,"typeClass":"compound","value":[{"softwareName":{"typeName":"softwareName","multiple":false,"typeClass":"primitive","value":"GeMoMa"},"softwareVersion":{"typeName":"softwareVersion","multiple":false,"typeClass":"primitive","value":"1.9"}},{"softwareName":{"typeName":"softwareName","multiple":false,"typeClass":"primitive","value":"BUSCO"},"softwareVersion":{"typeName":"softwareVersion","multiple":false,"typeClass":"primitive","value":"5.8.1"}},{"softwareName":{"typeName":"softwareName","multiple":false,"typeClass":"primitive","value":"Kraken"},"softwareVersion":{"typeName":"softwareVersion","multiple":false,"typeClass":"primitive","value":"2.1.3"}},{"softwareName":{"typeName":"softwareName","multiple":false,"typeClass":"primitive","value":"Bracken"},"softwareVersion":{"typeName":"softwareVersion","multiple":false,"typeClass":"primitive","value":"2.9"}},{"softwareName":{"typeName":"softwareName","multiple":false,"typeClass":"primitive","value":"kallisto"},"softwareVersion":{"typeName":"softwareVersion","multiple":false,"typeClass":"primitive","value":"0.44"}},{"softwareName":{"typeName":"softwareName","multiple":false,"typeClass":"primitive","value":"Python"},"softwareVersion":{"typeName":"softwareVersion","multiple":false,"typeClass":"primitive","value":"3.11.8"}}]}]},"codeMeta20":{"displayName":"Software Metadata (CodeMeta v2.0)","name":"codeMeta20","fields":[]}},"files":[{"description":"List of BUSCO genes from eudictoyledons_odb12 lineage used for coalescence and concatenation-based species phylogeny","label":"BUSCO_genes_for_species_phylogeny.csv","restricted":false,"version":1,"datasetVersionId":527,"dataFile":{"id":14799,"persistentId":"doi:10.60507/FK2/ZNVSLA/CY5FUG","pidURL":"https://doi.org/10.60507/FK2/ZNVSLA/CY5FUG","filename":"BUSCO_genes_for_species_phylogeny.csv","contentType":"text/csv","friendlyType":"Comma Separated Values","filesize":51652,"description":"List of BUSCO genes from eudictoyledons_odb12 lineage used for coalescence and concatenation-based species phylogeny","storageIdentifier":"file://19b21f7386c-7909b845c585","rootDataFileId":-1,"md5":"6349019a3d9a25b2d52db69957243d10","checksum":{"type":"MD5","value":"6349019a3d9a25b2d52db69957243d10"},"tabularData":false,"creationDate":"2025-12-15","publicationDate":"2025-12-18","fileAccessRequest":true}},{"description":"List of reference sequences used for phylogenetic trees","label":"Bait_sequences_gene_trees.csv","restricted":false,"version":1,"datasetVersionId":527,"dataFile":{"id":14801,"persistentId":"doi:10.60507/FK2/ZNVSLA/R8I60C","pidURL":"https://doi.org/10.60507/FK2/ZNVSLA/R8I60C","filename":"Bait_sequences_gene_trees.csv","contentType":"text/csv","friendlyType":"Comma Separated Values","filesize":49864,"description":"List of reference sequences used for phylogenetic trees","storageIdentifier":"file://19b21f731e3-90aff7cf0560","rootDataFileId":-1,"md5":"5e1581a14a019d45774fe557a1e12a8d","checksum":{"type":"MD5","value":"5e1581a14a019d45774fe557a1e12a8d"},"tabularData":false,"creationDate":"2025-12-15","publicationDate":"2025-12-18","fileAccessRequest":true}},{"description":"Coding sequences used for constructing individual gene phylogenetic trees in FASTA format. ","label":"Coding_seq_gene_trees_dataset.tar.gz","restricted":false,"version":1,"datasetVersionId":527,"dataFile":{"id":14802,"persistentId":"doi:10.60507/FK2/ZNVSLA/QKHYGA","pidURL":"https://doi.org/10.60507/FK2/ZNVSLA/QKHYGA","filename":"Coding_seq_gene_trees_dataset.tar.gz","contentType":"application/gzip","friendlyType":"Gzip Archive","filesize":6056086,"description":"Coding sequences used for constructing individual gene phylogenetic trees in FASTA format. ","storageIdentifier":"file://19b21f6fe35-5c0af3177050","rootDataFileId":-1,"md5":"76582297191abb036adfb1cd7d07c96c","checksum":{"type":"MD5","value":"76582297191abb036adfb1cd7d07c96c"},"tabularData":false,"creationDate":"2025-12-15","publicationDate":"2025-12-18","fileAccessRequest":true}},{"description":"Sources of genomic and transcriptomic datasets used in the study","label":"Dataset_sources.csv","restricted":false,"version":2,"datasetVersionId":527,"dataFile":{"id":14877,"persistentId":"doi:10.60507/FK2/ZNVSLA/UCO4IK","pidURL":"https://doi.org/10.60507/FK2/ZNVSLA/UCO4IK","filename":"Dataset_sources.csv","contentType":"text/csv","friendlyType":"Comma Separated Values","filesize":37277,"description":"Sources of genomic and transcriptomic datasets used in the study","storageIdentifier":"file://19b31a121d3-a08f019b45c6","rootDataFileId":-1,"md5":"3e5fd89ec0b5c62d0b40ec9e8097a8ff","checksum":{"type":"MD5","value":"3e5fd89ec0b5c62d0b40ec9e8097a8ff"},"tabularData":false,"creationDate":"2025-12-18","publicationDate":"2025-12-18","fileAccessRequest":true}},{"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).","label":"Expression_datasets.tar.gz","restricted":false,"version":1,"datasetVersionId":527,"dataFile":{"id":14804,"persistentId":"doi:10.60507/FK2/ZNVSLA/S3I0KS","pidURL":"https://doi.org/10.60507/FK2/ZNVSLA/S3I0KS","filename":"Expression_datasets.tar.gz","contentType":"application/gzip","friendlyType":"Gzip Archive","filesize":1227781722,"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).","storageIdentifier":"file://19b21fc73c6-290a0e9d48cc","rootDataFileId":-1,"md5":"1fa4521900ba3fbab3d589936a2c3849","checksum":{"type":"MD5","value":"1fa4521900ba3fbab3d589936a2c3849"},"tabularData":false,"creationDate":"2025-12-15","publicationDate":"2025-12-18","fileAccessRequest":true}},{"description":"Links to websites used as reference for mapping fruit and flower colours used in Figure 2. ","label":"Fruit_flower_colour_sources.csv","restricted":false,"version":1,"datasetVersionId":527,"dataFile":{"id":14797,"persistentId":"doi:10.60507/FK2/ZNVSLA/QU4ISS","pidURL":"https://doi.org/10.60507/FK2/ZNVSLA/QU4ISS","filename":"Fruit_flower_colour_sources.csv","contentType":"text/csv","friendlyType":"Comma Separated Values","filesize":13899,"description":"Links to websites used as reference for mapping fruit and flower colours used in Figure 2. ","storageIdentifier":"file://19b21f73dd9-8bcd13193585","rootDataFileId":-1,"md5":"0d2e5292f31213e8b98d08d54fde165b","checksum":{"type":"MD5","value":"0d2e5292f31213e8b98d08d54fde165b"},"tabularData":false,"creationDate":"2025-12-15","publicationDate":"2025-12-18","fileAccessRequest":true}},{"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.","label":"Gene_Annotation_dataset.tar.gz","restricted":false,"version":1,"datasetVersionId":527,"dataFile":{"id":14803,"persistentId":"doi:10.60507/FK2/ZNVSLA/LBADVE","pidURL":"https://doi.org/10.60507/FK2/ZNVSLA/LBADVE","filename":"Gene_Annotation_dataset.tar.gz","contentType":"application/gzip","friendlyType":"Gzip Archive","filesize":2192069456,"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.","storageIdentifier":"file://19b22096429-8af51054c646","rootDataFileId":-1,"md5":"7b79b7bf905e7e72c5b234a3968b2971","checksum":{"type":"MD5","value":"7b79b7bf905e7e72c5b234a3968b2971"},"tabularData":false,"creationDate":"2025-12-15","publicationDate":"2025-12-18","fileAccessRequest":true}},{"description":"Statistics of gene annotation of 82 species and re-annotation of 7 species","label":"Gene_annotation_stats.csv","restricted":false,"version":1,"datasetVersionId":527,"dataFile":{"id":14798,"persistentId":"doi:10.60507/FK2/ZNVSLA/3ATXUD","pidURL":"https://doi.org/10.60507/FK2/ZNVSLA/3ATXUD","filename":"Gene_annotation_stats.csv","contentType":"text/csv","friendlyType":"Comma Separated Values","filesize":7705,"description":"Statistics of gene annotation of 82 species and re-annotation of 7 species","storageIdentifier":"file://19b21f73e20-a7a140022e4d","rootDataFileId":-1,"md5":"8b6e314c149aa413049e66e977c863cb","checksum":{"type":"MD5","value":"8b6e314c149aa413049e66e977c863cb"},"tabularData":false,"creationDate":"2025-12-15","publicationDate":"2025-12-18","fileAccessRequest":true}},{"description":"Detailed results of Kraken and Bracken classification of all datasets","label":"Kraken_classification.csv","restricted":false,"version":1,"datasetVersionId":527,"dataFile":{"id":14795,"persistentId":"doi:10.60507/FK2/ZNVSLA/9LWPEX","pidURL":"https://doi.org/10.60507/FK2/ZNVSLA/9LWPEX","filename":"Kraken_classification.csv","contentType":"text/csv","friendlyType":"Comma Separated Values","filesize":35465,"description":"Detailed results of Kraken and Bracken classification of all datasets","storageIdentifier":"file://19b21f73e56-9dad89e3b981","rootDataFileId":-1,"md5":"d03c4330afa93ae046f183653f66d1c6","checksum":{"type":"MD5","value":"d03c4330afa93ae046f183653f66d1c6"},"tabularData":false,"creationDate":"2025-12-15","publicationDate":"2025-12-18","fileAccessRequest":true}},{"description":"README file describing the datasets and files overview","label":"README.txt","restricted":false,"version":2,"datasetVersionId":527,"dataFile":{"id":14878,"persistentId":"doi:10.60507/FK2/ZNVSLA/P3PHNX","pidURL":"https://doi.org/10.60507/FK2/ZNVSLA/P3PHNX","filename":"README.txt","contentType":"text/plain","friendlyType":"Plain Text","filesize":17406,"description":"README file describing the datasets and files overview","storageIdentifier":"file://19b31a1218d-eabeb0d83dc4","rootDataFileId":-1,"md5":"09efa63aa55dec812e8d28aa1037efac","checksum":{"type":"MD5","value":"09efa63aa55dec812e8d28aa1037efac"},"tabularData":false,"creationDate":"2025-12-18","publicationDate":"2025-12-18","fileAccessRequest":true}}],"citation":"Choudhary, Nancy; Hagedorn, Marie; Pucker, Boas, 2025, \"Supplementary data supporting the study: \"Out of the blue: Family-wide loss of anthocyanin biosynthesis in Cucurbitaceae\"\", https://doi.org/10.60507/FK2/ZNVSLA, bonndata, V1"}}