@prefix adms: . @prefix dcat: . @prefix dcatap: . @prefix dct: . @prefix dpv: . @prefix foaf: . @prefix healthdcatap: . @prefix hydra: . @prefix prov: . @prefix rdfs: . @prefix skos: . @prefix vcard: . @prefix xsd: . a hydra:PagedCollection ; hydra:first "https://catalogue.portal.staging.gdi.lu/catalog.ttl?page=1" ; hydra:firstPage "https://catalogue.portal.staging.gdi.lu/catalog.ttl?page=1" ; hydra:itemsPerPage 100 ; hydra:last "https://catalogue.portal.staging.gdi.lu/catalog.ttl?page=1" ; hydra:lastPage "https://catalogue.portal.staging.gdi.lu/catalog.ttl?page=1" ; hydra:totalItems 26 . a dcat:Dataset ; dcatap:applicableLegislation ; healthdcatap:healthCategory ; dct:accessRights ; dct:conformsTo ; dct:creator [ a foaf:Agent ; foaf:name "The Genome of Europe" ] ; dct:description "Example synthetic data used to demonstrate GDI capabilities"@en, ""@nl ; dct:identifier "GOE-LU-LNDS-1" ; dct:issued "2026-04-30T12:11:56.033788"^^xsd:dateTime ; dct:language ; dct:modified "2026-09-10T02:15:04.820098"^^xsd:dateTime ; dct:provenance [ a dct:ProvenanceStatement ; rdfs:label ""@en, ""@nl ] ; dct:publisher [ a foaf:Agent ; foaf:name "LNDS - Luxembourg National Data Service" ] ; dct:title "Genome of Europe Luxembourgish dummy dataset"@en, ""@nl ; dct:type ; adms:versionNotes ""@en, ""@nl ; dcat:contactPoint [ a vcard:Kind ; vcard:fn "LNDS - Luxembourg National Data Service" ; vcard:hasEmail ] ; dcat:distribution ; dcat:keyword "GDI"@en, "Synthetic"@en ; dcat:theme . a dcat:Distribution ; dcatap:applicableLegislation ; dct:description ""@en, ""@nl ; dct:issued "2026-09-10T02:15:04.828200"^^xsd:dateTime ; dct:language ; dct:license ; dct:modified "2026-09-10T02:15:04.823312"^^xsd:dateTime ; dct:rights [ a dct:RightsStatement ; rdfs:label ""@en, ""@nl ] ; dct:title "VCF files"@en, ""@nl ; adms:status ; dcat:accessURL . a dcat:Dataset ; dcatap:applicableLegislation ; healthdcatap:healthCategory ; healthdcatap:numberOfRecords "1"^^xsd:nonNegativeInteger ; healthdcatap:numberOfUniqueIndividuals "4000"^^xsd:nonNegativeInteger ; dct:accessRights ; dct:conformsTo ; dct:creator [ a foaf:Agent ; foaf:name "https://ror.org/04m8m1253" ] ; dct:description "Synthetic test dataset for GDI with individuals from EE, FI, & LV"@en, ""@nl ; dct:identifier "GDI-FI-CSC-001" ; dct:issued "2026-03-04T15:00:16.712338"^^xsd:dateTime ; dct:language ; dct:modified "2026-07-12T16:30:07.192669"^^xsd:dateTime ; dct:provenance [ a dct:ProvenanceStatement ; rdfs:label ""@en, ""@nl ] ; dct:publisher [ a foaf:Agent ; foaf:name "https://ror.org/04m8m1253" ] ; dct:title "Synthetic GDI Finnish Dataset"@en, ""@nl ; dct:type ; adms:versionNotes ""@en, ""@nl ; dcat:theme . a dcat:Dataset ; dcatap:applicableLegislation ; healthdcatap:healthCategory ; healthdcatap:numberOfRecords "20343"^^xsd:nonNegativeInteger ; dct:accessRights ; dct:conformsTo ; dct:creator [ a foaf:Agent ; foaf:name "https://ror.org/04m8m1253" ] ; dct:description "Finnish Dataset produced from legacy data held at THL"@en, ""@nl ; dct:identifier "GDI-FI-CSC-002" ; dct:issued "2026-03-04T15:00:15.614696"^^xsd:dateTime ; dct:language ; dct:modified "2026-07-12T16:30:06.714613"^^xsd:dateTime ; dct:provenance [ a dct:ProvenanceStatement ; rdfs:label ""@en, ""@nl ] ; dct:publisher [ a foaf:Agent ; foaf:name "https://ror.org/03tf0c761" ] ; dct:title "Finnish Legacy Dataset from THL"@en, ""@nl ; adms:versionNotes ""@en, ""@nl ; dcat:theme . a dcat:Dataset ; dct:conformsTo ; dct:creator [ a foaf:Agent ; dct:identifier ; foaf:name "Sen Zhao" ] ; dct:description """SYNTHETIC This dataset contains 10 tumor and normal pairs synthetic WGS data of colorectal cancer that were simulated in a standard format of Illumina paired-end reads. NEAT read simulator (version 3.0, https://github.com/zstephens/neat-genreads) is utilized to synthetize these 10 pairs tumor and normal WGS data. In the procedure of data generation, simulated parameters (i.e., sequencing error statistics, read fragment length distribution and GC% coverage bias) are learned from data models provided by NEAT. The average sequencing depth for tumor and normal samples aims to reach around 110X and 60X, respectively. For generation of synthetic normal WGS data per each sample, a germline variant profile from a real patient is down-sampled randomly, which includes 50% germline variants of such a patient. It is then mixed together with an in silico germline variant profile that is modelled randomly using an average mutation rate (0.001), finally constituting a full germline profile for normal synthetic WGS data. For generation of synthetic tumor WGS data per each sample, a pre-defined somatic short variant profile (SNVs+Indels) learn from a real CRC patient is added to the germline variant profile used for creating normal synthetic WGS data of the same patient, which is utilized to produce simulated sequences. Neither copy number profile nor structural variation profile is introduced into the tumor synthetic WGS data. Tumor content and ploidy are assumed to be 100% and 2."""@en, ""@nl ; dct:identifier "GDI-NO-D-T0001" ; dct:issued "2024-04-30T00:00:00+00:00"^^xsd:dateTime ; dct:modified "2026-06-25T13:33:53+00:00"^^xsd:dateTime ; dct:provenance [ a dct:ProvenanceStatement ; rdfs:label ""@en, ""@nl ] ; dct:publisher [ a foaf:Agent ; dct:identifier ; foaf:name "University of Oslo" ] ; dct:title "SYNTHETIC Norwegian Colorectal Cancer genomic dataset generated in EOSC4Cancer"@en, ""@nl ; adms:versionNotes ""@en, ""@nl ; dcat:contactPoint [ a vcard:Kind ; vcard:fn "Sen Zhao" ; vcard:hasEmail ; vcard:hasUID ] ; dcat:distribution ; dcat:keyword "colorectal_tumor"@en, "ngs"@en, "normal_tumor_pair"@en, "synthetic"@en, "wgs"@en ; dcat:theme . a dcat:Distribution ; dcatap:applicableLegislation ; dct:description ""@en, ""@nl ; dct:format "HTML" ; dct:issued "2026-06-25T13:33:53+00:00"^^xsd:dateTime ; dct:modified "2026-06-25T13:33:53+00:00"^^xsd:dateTime ; dct:rights [ a dct:RightsStatement ; rdfs:label ""@en, ""@nl ] ; dct:title "Distribution for SYNTHETIC Norwegian Colorectal Cancer genomic dataset generated in EOSC4Cancer"@en, ""@nl ; dcat:accessURL ; dcat:downloadURL ; dcat:mediaType "text/html" . a dct:Location . a dcat:Catalog ; dct:language "en" ; dct:modified "2026-09-10T16:15:18.225764"^^xsd:dateTime ; dct:title "CKAN" ; dcat:dataset , , , , , , , , , , , , , , , , , , , , , , , , , ; foaf:homepage . a dcat:Distribution ; dcatap:applicableLegislation ; dct:description ""@en, ""@nl ; dct:issued "2026-07-01T14:15:05.987087"^^xsd:dateTime ; dct:modified "2026-07-01T14:15:05.981800"^^xsd:dateTime ; dct:rights [ a dct:RightsStatement ; rdfs:label ""@en, ""@nl ] ; dct:title "GDI User Portal"@en, ""@nl ; dcat:accessURL . a foaf:Agent ; foaf:name "Latvia" . a foaf:Agent ; foaf:name "Netherlands" . a foaf:Agent ; foaf:name "Czechia" . a rdfs:Resource . a dct:LicenseDocument ; dct:type . a rdfs:Resource . a dct:MediaTypeOrExtent . a rdfs:Resource . a . a . a dcat:Dataset ; dcatap:applicableLegislation ; healthdcatap:healthCategory ; dct:accessRights ; dct:creator [ a foaf:Agent ; foaf:name "GDI Ireland" ] ; dct:description "Allele-frequency dataset derived from 1000 Genomes PGx pilot data, served by the GDI Ireland allele-frequency Beacon (beacon dataset id 1000G-IE-UL-2) and archived in the node Sensitive Data Archive under the same id. Public reference data used for proof-of-concept infrastructure testing."@en, ""@nl ; dct:identifier "GDI-IE-UL-2" ; dct:issued "2026-08-20T18:45:05.213614"^^xsd:dateTime ; dct:language ; dct:modified "2026-09-09T21:30:06.643557"^^xsd:dateTime ; dct:provenance [ a dct:ProvenanceStatement ; rdfs:label ""@en, ""@nl ] ; dct:publisher [ a foaf:Agent ; foaf:name "GDI Ireland" ] ; dct:title "1000 Genomes Data"@en, ""@nl ; adms:identifier [ a adms:Identifier ; skos:notation "nbd24e83e97dc4b1391a8334367e160a6b3" ] ; adms:versionNotes ""@en, ""@nl ; dcat:theme . a dcat:Dataset ; dcatap:applicableLegislation ; healthdcatap:healthCategory ; dct:accessRights ; dct:creator [ a foaf:Agent ; foaf:name "GDI Ireland" ] ; dct:description "Synthetic allele-frequency dataset derived from the Genome of Europe programme, served by the GDI Ireland allele-frequency Beacon (beacon dataset id GoE-IE-UL-1) and archived in the node Sensitive Data Archive under the same id. Aggregate COVID monogenic allele frequencies in GRCh37 and GRCh38 coordinates; synthetic data, no real individuals."@en, ""@nl ; dct:identifier "GOE-IE-UL-1" ; dct:issued "2026-08-20T18:45:04.327756"^^xsd:dateTime ; dct:language ; dct:modified "2026-09-09T21:30:06.143957"^^xsd:dateTime ; dct:provenance [ a dct:ProvenanceStatement ; rdfs:label ""@en, ""@nl ] ; dct:publisher [ a foaf:Agent ; foaf:name "GDI Ireland" ] ; dct:title "Genome of Europe Synthetic Data"@en, ""@nl ; adms:identifier [ a adms:Identifier ; skos:notation "n9815a7f668a24e9e8a3a8f6972d67664b3" ] ; adms:versionNotes ""@en, ""@nl ; dcat:theme . a dcat:Dataset ; dcatap:applicableLegislation ; healthdcatap:healthCategory , ; healthdcatap:numberOfRecords "5000"^^xsd:nonNegativeInteger ; healthdcatap:numberOfUniqueIndividuals "500"^^xsd:nonNegativeInteger ; dct:accessRights ; dct:conformsTo ; dct:creator [ a foaf:Agent ] ; dct:description "Synthetic genomic dataset for testing the GDI starter kit. Contains simulated VCF data with allele frequency information for colorectal cancer cases."@en, ""@nl ; dct:identifier "GDI-BE-DATASET-1" ; dct:issued "2026-03-05T08:05:31.294257"^^xsd:dateTime ; dct:language ; dct:modified "2026-06-09T10:30:05.579958"^^xsd:dateTime ; dct:provenance [ a dct:ProvenanceStatement ; rdfs:label ""@en, ""@nl ] ; dct:publisher [ a foaf:Agent ] ; dct:title "GDI Synthetic Genomics Dataset"@en, ""@nl ; dct:type ; adms:versionNotes ""@en, ""@nl ; dcat:contactPoint [ a vcard:Kind ] ; dcat:distribution ; dcat:keyword "GDI"@en, "colorectal cancer"@en, "genomics"@en, "synthetic data"@en ; dcat:theme ; dpv:hasLegalBasis dpv:Consent . a dcat:Distribution ; dcatap:applicableLegislation ; dct:description "VCF file containing synthetic GWAS and allele frequency data for colorectal cancer cases."@en, ""@nl ; dct:format ; dct:issued "2026-06-09T10:30:05.588057"^^xsd:dateTime ; dct:language ; dct:license ; dct:modified "2026-06-09T10:30:05.583129"^^xsd:dateTime ; dct:rights [ a dct:RightsStatement ; rdfs:label ""@en, ""@nl ] ; dct:title "Synthetic VCF - Colorectal Cancer"@en, ""@nl ; dcat:accessURL ; dcat:byteSize "10485760"^^xsd:nonNegativeInteger ; dcat:mediaType . a dcat:Dataset ; dcatap:applicableLegislation ; healthdcatap:hdab [ a foaf:Agent ; foaf:name "GoE Masaryk University" ] ; healthdcatap:healthCategory ; dct:accessRights ; dct:conformsTo ; dct:creator [ a foaf:Agent ; foaf:name "GoE Masaryk University" ] ; dct:description "Czech GoE Synthetic Aggregated Dataset"@en, ""@nl ; dct:identifier "GOE-CZ-MUNI-00001" ; dct:issued "2026-03-04T15:00:19.704719"^^xsd:dateTime ; dct:language ; dct:modified "2026-09-10T04:15:04.615059"^^xsd:dateTime ; dct:provenance [ a dct:ProvenanceStatement ; rdfs:label ""@en, ""@nl ] ; dct:publisher ; dct:title "Czech GoE Synthetic Aggregated Dataset"@en, ""@nl ; dct:type ; adms:identifier [ a adms:Identifier ; skos:notation "nb8cda937782b4db2b743193ae01a7c49b4" ] ; adms:versionNotes ""@en, ""@nl ; dcat:distribution ; dcat:theme . a dcat:Distribution ; dcatap:applicableLegislation ; dct:description ""@en, ""@nl ; dct:issued "2026-09-10T04:15:04.619861"^^xsd:dateTime ; dct:language ; dct:license ; dct:modified "2026-09-10T04:15:04.618379"^^xsd:dateTime ; dct:rights [ a dct:RightsStatement ; rdfs:label ""@en, ""@nl ] ; dct:title "Czech GoE Synthetic Dataset Distribution"@en, ""@nl ; dcat:accessURL . a dcat:Dataset ; dcatap:applicableLegislation ; healthdcatap:hdab [ a foaf:Agent ; dct:identifier "BfArM-DE" ; vcard:hasEmail ; foaf:homepage ; foaf:name "BfArM-DE" ] ; healthdcatap:healthCategory , , ; dct:accessRights ; dct:conformsTo ; dct:creator [ a foaf:Agent ; dct:identifier "GHGAC49574323578287" ; vcard:hasEmail ; foaf:homepage ; foaf:name "GHGA" ] ; dct:description "Please note: This synthetic data set (with cohort “participants” / ”subjects” marked with FAKE) has no identifiable data and cannot be used to make any inference about cohort data or results. The purpose of this dataset is to aid development of technical implementations for cohort data discovery, harmonization, access, and federated analysis. In support of FAIRness in data sharing, this dataset is made freely available under the Creative Commons Licence (CC-BY). Please ensure this preamble is included with this dataset and that the CINECA project (funding: EC H2020 grant 825775) is acknowledged. This dataset (CINECA_synthetic_cohort_EUROPE_UK1) consists of 2521 samples which have genetic data based on 1000 Genomes data (https://www.nature.com/articles/nature15393), and synthetic subject attributes and phenotypic data derived from UKBiobank (https://journals.plos.org/plosmedicine/article?id=10.1371/journal.pmed.1001779). These data were initially derived using the TOFU tool (https://github.com/spiros/tofu), which generates randomly generated values based on the UKBiobank data dictionary. Categorical values were randomly generated based on the data dictionary, continuous variables generated based on the distribution of values reported by the UK Biobank showcase, and date / time values were random. Additionally we split the phenotypes and attributes into 4 main classes - general, cancer, diabetes mellitus, and cardiac. We assigned the general attributes to all the samples, and the cardiac / diabetes mellitus / cancer attributes to a proportion of the total samples. Once the initial set of phenotypes and attributes were generated, the data data was checked for consistency and where possible dependent attributes were calculated from the independent variables generated by TOFU. For example, BMI was calculated from height and weight data, and age at death generated by date of death and date of birth. These data were then loaded to the development instance of Biosamples (https://www.ebi.ac.uk/biosamples/) which accessioned each of the samples. The genetic data are derived from the 1000 Genomes Phase 3 release (https://www.internationalgenome.org/category/phase-3/). The genotype data consists of a single joint call vcf files with call genotypes for all 2504 samples, plus bed, bim, fam, and nosex files generated via plink for these samples and genotypes. The genotype data has had a variety of errors introduced to mimic real data and as a test for quality control pipelines. These include gender mismatches, ethnic background mislabelling and low call rates for a randomly chosen subset of sample data as well as deviations from Hardy Weinberg equilibrium and low call rates for a random selection of variants. Additionally 40 samples have raw genetic data available in the form of both bam and cram files, including unmapped data. The gender of the samples in the 1000 genomes data has been matched to the synthetic phenotypic data generated for these samples. The genetic data was then linked to the synthetic data in BioSamples, and submitted to EGA."@en, ""@nl ; dct:identifier "GOE-DE-TUB-1" ; dct:issued "2026-03-05T08:05:24.611373"^^xsd:dateTime ; dct:language ; dct:modified "2026-09-10T03:00:05.414817"^^xsd:dateTime ; dct:provenance [ a dct:ProvenanceStatement ; rdfs:label ""@en, ""@nl ] ; dct:publisher [ a foaf:Agent ; dct:identifier "GHGAC49574323578287" ; vcard:hasEmail ; foaf:homepage ; foaf:name "GHGA" ] ; dct:title "CINECA Synthetic Cohort EUROPE UK1 referencing fake samples"@en, ""@nl ; dct:type ; adms:identifier [ a adms:Identifier ; skos:notation "n314f0327efaa49e98898c5a334b3af78b6" ] ; adms:versionNotes ""@en, ""@nl ; dcat:contactPoint [ a vcard:Kind ; vcard:fn "GHGA_DAC" ; vcard:hasEmail ; vcard:hasURL <['https://data.ghga.de/dac/GHGAC49574323578287']> ] ; dcat:distribution ; dcat:keyword "Whole Genomes Sequencing"@en ; dcat:theme ; dpv:hasLegalBasis dpv:Consent . a dcat:Distribution ; dcatap:applicableLegislation ; dct:description "Please note: This synthetic data set (with cohort “participants” / ”subjects” marked with FAKE) has no identifiable data and cannot be used to make any inference about cohort data or results. The purpose of this dataset is to aid development of technical implementations for cohort data discovery, harmonization, access, and federated analysis. In support of FAIRness in data sharing, this dataset is made freely available under the Creative Commons Licence (CC-BY). Please ensure this preamble is included with this dataset and that the CINECA project (funding: EC H2020 grant 825775) is acknowledged. This dataset (CINECA_synthetic_cohort_EUROPE_UK1) consists of 2521 samples which have genetic data based on 1000 Genomes data (https://www.nature.com/articles/nature15393), and synthetic subject attributes and phenotypic data derived from UKBiobank (https://journals.plos.org/plosmedicine/article?id=10.1371/journal.pmed.1001779). These data were initially derived using the TOFU tool (https://github.com/spiros/tofu), which generates randomly generated values based on the UKBiobank data dictionary. Categorical values were randomly generated based on the data dictionary, continuous variables generated based on the distribution of values reported by the UK Biobank showcase, and date / time values were random. Additionally we split the phenotypes and attributes into 4 main classes - general, cancer, diabetes mellitus, and cardiac. We assigned the general attributes to all the samples, and the cardiac / diabetes mellitus / cancer attributes to a proportion of the total samples. Once the initial set of phenotypes and attributes were generated, the data data was checked for consistency and where possible dependent attributes were calculated from the independent variables generated by TOFU. For example, BMI was calculated from height and weight data, and age at death generated by date of death and date of birth. These data were then loaded to the development instance of Biosamples (https://www.ebi.ac.uk/biosamples/) which accessioned each of the samples. The genetic data are derived from the 1000 Genomes Phase 3 release (https://www.internationalgenome.org/category/phase-3/). The genotype data consists of a single joint call vcf files with call genotypes for all 2504 samples, plus bed, bim, fam, and nosex files generated via plink for these samples and genotypes. The genotype data has had a variety of errors introduced to mimic real data and as a test for quality control pipelines. These include gender mismatches, ethnic background mislabelling and low call rates for a randomly chosen subset of sample data as well as deviations from Hardy Weinberg equilibrium and low call rates for a random selection of variants. Additionally 40 samples have raw genetic data available in the form of both bam and cram files, including unmapped data. The gender of the samples in the 1000 genomes data has been matched to the synthetic phenotypic data generated for these samples. The genetic data was then linked to the synthetic data in BioSamples, and submitted to EGA."@en, ""@nl ; dct:format ; dct:issued "2026-09-10T03:00:05.420526"^^xsd:dateTime ; dct:language ; dct:license ; dct:modified "2026-09-10T03:00:05.418068"^^xsd:dateTime ; dct:rights [ a dct:RightsStatement ; rdfs:label ""@nl ], ; dct:title "CINECA Synthetic Cohort EUROPE UK1 referencing fake samples"@en, ""@nl ; dcat:accessURL ; dcat:byteSize "6000000"^^xsd:nonNegativeInteger ; dcat:mediaType . a dcat:Dataset ; dcatap:applicableLegislation ; healthdcatap:hdab [ a foaf:Agent ; dct:identifier "4944e954-7769-463f-87ad-f168a27415a3" ; dct:type ; vcard:hasEmail ; foaf:homepage ; foaf:name "University of Maribor"@en ] ; healthdcatap:healthCategory , ; dct:accessRights ; dct:conformsTo ; dct:creator [ a foaf:Agent ; dct:identifier "4944e954-7769-463f-87ad-f168a27415a3" ; vcard:hasEmail ; foaf:homepage ; foaf:name "University of Maribor"@en ] ; dct:description "Slovenian Node: Synthetic population-level dataset generated under the CRG AFBeacon initiative within the Genomics of Europe (GoE) project, used for testing and validation purposes."@en, ""@nl ; dct:identifier "GDI-SI-STAGPOP-0000001" ; dct:issued "2026-04-01T00:00:00+00:00"^^xsd:dateTime ; dct:language ; dct:modified "2026-09-01T00:00:00+00:00"^^xsd:dateTime ; dct:provenance [ a dct:ProvenanceStatement ; rdfs:label ""@en, ""@nl ] ; dct:publisher [ a foaf:Agent ; dct:identifier "502e2534-db18-4932-89a4-e9fa6b16f0ce" ; vcard:hasEmail ; foaf:homepage ; foaf:name "Aleš Čep"@en ] ; dct:title "SVN Synthetic Population-Level Dataset (CRG AFBeacon, GoE)"@en, ""@nl ; dct:type ; adms:versionNotes ""@en, ""@nl ; dcat:distribution ; dcat:keyword "GDI"@en, "GOE"@en, "synthetic data"@en ; dcat:landingPage ; dcat:theme . a dcat:Dataset ; dcatap:applicableLegislation ; healthdcatap:hdab [ a foaf:Agent ; dct:identifier "480f7bfb-21ce-47a2-b0f1-8bf9345a2142" ; dct:type ; vcard:hasEmail ; foaf:homepage ; foaf:name "University Medical Centre Ljubljana"@en ] ; healthdcatap:healthCategory , ; healthdcatap:maxTypicalAge "45"^^xsd:nonNegativeInteger ; healthdcatap:minTypicalAge "45"^^xsd:nonNegativeInteger ; healthdcatap:numberOfRecords "1"^^xsd:nonNegativeInteger ; healthdcatap:numberOfUniqueIndividuals "1"^^xsd:nonNegativeInteger ; dct:accessRights ; dct:conformsTo ; dct:creator [ a foaf:Agent ; dct:identifier "4944e954-7769-463f-87ad-f168a27415a3" ; vcard:hasEmail ; foaf:homepage ; foaf:name "University of Maribor"@en ], [ a foaf:Agent ; dct:identifier "480f7bfb-21ce-47a2-b0f1-8bf9345a2142" ; vcard:hasEmail ; foaf:homepage ; foaf:name "University Medical Centre Ljubljana"@en ], [ a foaf:Agent ; dct:identifier "1d6d7614-33a0-49c4-8b6f-124e3ec18779" ; vcard:hasEmail ; foaf:homepage ; foaf:name "University of Ljubljana"@en ] ; dct:description "The Slovenian Population Reference Dataset is a collection of genomic variant data contributed by participating Slovenian institutions. It is intended to support the development of a population-specific genomic reference for Slovenia, including analyses of allele frequencies, genetic variation, and population-level genomic characteristics. The dataset primarily consists of gVCF files and is designed to enable joint analysis across contributing cohorts."@en, ""@nl ; dct:identifier "GDI-SI-STAGPOP-2026" ; dct:issued "2026-09-10T16:15:08.452484"^^xsd:dateTime ; dct:language ; dct:modified "2026-09-01T00:00:00+00:00"^^xsd:dateTime ; dct:provenance [ a dct:ProvenanceStatement ; rdfs:label ""@en, ""@nl ] ; dct:publisher [ a foaf:Agent ; dct:identifier "4944e954-7769-463f-87ad-f168a27415a3" ; vcard:hasEmail ; foaf:homepage ; foaf:name "University of Maribor"@en ] ; dct:title "Slovenian Population Reference Dataset"@en, ""@nl ; dct:type ; adms:versionNotes ""@en, ""@nl ; dcat:distribution ; dcat:keyword "Slovenian population"@en, "allele frequencies"@en, "genomics"@en, "population genomics"@en ; dcat:landingPage ; dcat:theme ; prov:wasGeneratedBy ; dpv:hasPersonalData . a dcat:Dataset ; dcatap:applicableLegislation ; healthdcatap:healthCategory ; dct:accessRights ; dct:creator [ a foaf:Agent ; dct:identifier "e4c1b197-d455-4196-81dd-e7c5964e084c" ; dct:type foaf:Person ; vcard:hasEmail ; foaf:homepage ; foaf:name "Aleš Čep" ] ; dct:description "The 1+MG COVID dataset is located at CSC's Allas service and it is available via Dylan Spalding (dylan.spalding@csc.fi) by request for the GDI project. In the future, the dataset will be available from CSC's FEGA service (https://research.csc.fi/service/fega/)."@en, ""@nl ; dct:identifier "GDI-SI-UM-2026021200202" ; dct:issued "2026-03-04T15:30:08.107461"^^xsd:dateTime ; dct:language ; dct:modified "2026-03-04T15:30:08.646874"^^xsd:dateTime ; dct:provenance [ a dct:ProvenanceStatement ; rdfs:label ""@en, ""@nl ] ; dct:publisher ; dct:title "1+MG COVID dataset"@en, ""@nl ; dct:type ; adms:versionNotes ""@en, ""@nl ; dcat:contactPoint ; dcat:distribution ; dcat:keyword "COVID"@en, "GDI"@en, "MAP1"@en, "synthetic"@en ; dcat:theme . a dcat:Dataset ; dcatap:applicableLegislation ; healthdcatap:hdab [ a foaf:Agent ; dct:identifier "4944e954-7769-463f-87ad-f168a27415a3" ; dct:type ; vcard:hasEmail ; foaf:homepage ; foaf:name "University of Maribor"@en ] ; healthdcatap:healthCategory , ; dct:accessRights ; dct:conformsTo ; dct:creator [ a foaf:Agent ; dct:identifier "4944e954-7769-463f-87ad-f168a27415a3" ; vcard:hasEmail ; foaf:homepage ; foaf:name "University of Maribor"@en ] ; dct:description "Slovenian Node: The 1+MG COVID GRCh38dataset is located at CSC's Allas service and it is available via Dylan Spalding (dylan.spalding@csc.fi) by request for the GDI project. In the future, the dataset will be available from CSC's FEGA service (https://research.csc.fi/service/fega/)."@en, ""@nl ; dct:identifier "GDI-SI-STAGPOP-0000003" ; dct:issued "2026-04-01T00:00:00+00:00"^^xsd:dateTime ; dct:language ; dct:modified "2026-09-01T00:00:00+00:00"^^xsd:dateTime ; dct:provenance [ a dct:ProvenanceStatement ; rdfs:label ""@en, ""@nl ] ; dct:publisher [ a foaf:Agent ; dct:identifier "502e2534-db18-4932-89a4-e9fa6b16f0ce" ; vcard:hasEmail ; foaf:homepage ; foaf:name "Aleš Čep"@en ] ; dct:title "SVN Synthetic Population-Level COVID dataset (Dylan Spalding, CSC) GRCh38"@en, ""@nl ; dct:type ; adms:versionNotes ""@en, ""@nl ; dcat:distribution , , ; dcat:keyword "GDI"@en, "GOE"@en, "GRCh38"@en, "synthetic data"@en ; dcat:landingPage ; dcat:theme . a dcat:Dataset ; dcatap:applicableLegislation ; healthdcatap:healthCategory ; dct:accessRights ; dct:creator [ a foaf:Agent ; dct:identifier "e4c1b197-d455-4196-81dd-e7c5964e084c" ; dct:type foaf:Person ; vcard:hasEmail ; foaf:homepage ; foaf:name "Aleš Čep" ] ; dct:description "CRG_AFBeacon_GoE_synthetic_dataset"@en, ""@nl ; dct:identifier "GDI-SI-UM-2026021200201" ; dct:issued "2026-03-04T15:30:09.288578"^^xsd:dateTime ; dct:language ; dct:modified "2026-03-04T15:30:09.872457"^^xsd:dateTime ; dct:provenance [ a dct:ProvenanceStatement ; rdfs:label ""@en, ""@nl ] ; dct:publisher ; dct:title "CRG AFBeacon GoE synthetic dataset"@en, ""@nl ; dct:type ; adms:versionNotes ""@en, ""@nl ; dcat:contactPoint ; dcat:distribution ; dcat:keyword "CRG"@en, "GDI"@en, "MAP1"@en, "synthetic"@en ; dcat:theme . a dcat:Dataset ; dcatap:applicableLegislation ; healthdcatap:hdab [ a foaf:Agent ; dct:identifier "4944e954-7769-463f-87ad-f168a27415a3" ; dct:type ; vcard:hasEmail ; foaf:homepage ; foaf:name "University of Maribor"@en ] ; healthdcatap:healthCategory , ; dct:accessRights ; dct:conformsTo ; dct:creator [ a foaf:Agent ; dct:identifier "4944e954-7769-463f-87ad-f168a27415a3" ; vcard:hasEmail ; foaf:homepage ; foaf:name "University of Maribor"@en ] ; dct:description "Slovenian Node: The 1+MG COVID GRCh37 dataset is located at CSC's Allas service and it is available via Dylan Spalding (dylan.spalding@csc.fi) by request for the GDI project. In the future, the dataset will be available from CSC's FEGA service (https://research.csc.fi/service/fega/)."@en, ""@nl ; dct:identifier "GDI-SI-STAGPOP-0000002" ; dct:issued "2026-04-01T00:00:00+00:00"^^xsd:dateTime ; dct:language ; dct:modified "2026-09-01T00:00:00+00:00"^^xsd:dateTime ; dct:provenance [ a dct:ProvenanceStatement ; rdfs:label ""@en, ""@nl ] ; dct:publisher [ a foaf:Agent ; dct:identifier "4944e954-7769-463f-87ad-f168a27415a3" ; vcard:hasEmail ; foaf:homepage ; foaf:name "University of Maribor"@en ] ; dct:title "SVN Synthetic Population-Level COVID dataset (Dylan Spalding, CSC) GRCh37"@en, ""@nl ; dct:type ; adms:versionNotes ""@en, ""@nl ; dcat:distribution ; dcat:keyword "GDI"@en, "GOE"@en, "GRCh37"@en, "synthetic data"@en ; dcat:landingPage ; dcat:theme . a dcat:Distribution ; dcatap:applicableLegislation ; dct:description """"Files for the dataset "SVN Synthetic Population-Level COVID dataset (Dylan Spalding CSC) GRCh37" provided in TXT format.\""""@en, ""@nl ; dct:format ; dct:issued "2026-09-01T00:00:00+00:00"^^xsd:dateTime ; dct:language ; dct:license ; dct:modified "2026-09-01T00:00:00+00:00"^^xsd:dateTime ; dct:rights [ a dct:RightsStatement ; rdfs:label ""@nl ], ; dct:title "SVN Synthetic Population-Level COVID dataset (Dylan Spalding, CSC) GRCh37 - TXT distribution"@en, ""@nl ; dcat:accessURL . a dcat:Distribution ; dcatap:applicableLegislation ; dct:description """"Files for the dataset "SVN Synthetic Population-Level COVID dataset (Dylan Spalding CSC) GRCh38" provided in JSON format.\""""@en, ""@nl ; dct:format ; dct:issued "2026-08-01T00:00:00+00:00"^^xsd:dateTime ; dct:language ; dct:license ; dct:modified "2026-09-01T00:00:00+00:00"^^xsd:dateTime ; dct:rights [ a dct:RightsStatement ; rdfs:label ""@nl ], ; dct:title "SVN Synthetic Population-Level COVID dataset (Dylan Spalding, CSC) GRCh38 - JSON distribution"@en, ""@nl ; dcat:accessURL ; dcat:byteSize "4166"^^xsd:nonNegativeInteger ; dcat:mediaType . a dcat:Distribution ; dcatap:applicableLegislation ; dct:description """"Files for the dataset "SVN Synthetic Population-Level COVID dataset (Dylan Spalding CSC) GRCh38" provided in VCF format.\""""@en, ""@nl ; dct:format ; dct:issued "2026-08-01T00:00:00+00:00"^^xsd:dateTime ; dct:language ; dct:license ; dct:modified "2026-09-01T00:00:00+00:00"^^xsd:dateTime ; dct:rights [ a dct:RightsStatement ; rdfs:label ""@nl ], ; dct:title "SVN Synthetic Population-Level COVID dataset (Dylan Spalding, CSC) GRCh38 - VCF distribution"@en, ""@nl ; dcat:accessURL ; dcat:byteSize "1672"^^xsd:nonNegativeInteger ; dcat:mediaType . a dcat:Distribution ; dcatap:applicableLegislation ; dct:description """"Files for the dataset "SVN Synthetic Population-Level Dataset (CRG AFBeacon GoE)" provided in TXT format.\""""@en, ""@nl ; dct:format ; dct:issued "2026-09-01T00:00:00+00:00"^^xsd:dateTime ; dct:language ; dct:license ; dct:modified "2026-09-01T00:00:00+00:00"^^xsd:dateTime ; dct:rights [ a dct:RightsStatement ; rdfs:label ""@nl ], ; dct:title "SVN Synthetic Population-Level Dataset (CRG AFBeacon, GoE) - TXT distribution"@en, ""@nl ; dcat:accessURL . a dcat:Distribution ; dcatap:applicableLegislation ; dct:description """"Files for the dataset "SVN Synthetic Population-Level COVID dataset (Dylan Spalding CSC) GRCh38" provided in TXT format.\""""@en, ""@nl ; dct:format ; dct:issued "2026-09-01T00:00:00+00:00"^^xsd:dateTime ; dct:language ; dct:license ; dct:modified "2026-09-01T00:00:00+00:00"^^xsd:dateTime ; dct:rights [ a dct:RightsStatement ; rdfs:label ""@nl ], ; dct:title "SVN Synthetic Population-Level COVID dataset (Dylan Spalding, CSC) GRCh38 - TXT distribution"@en, ""@nl ; dcat:accessURL . a dcat:Distribution ; dcatap:applicableLegislation ; dct:description "This distribution provides allele frequency data derived from the CRG_AFBeacon_GoE_synthetic_dataset. The data include population-level allele frequency metrics intended for testing, validation, and demonstration purposes within Beacon-compatible genomic data infrastructures. The dataset is synthetic and does not contain real individual-level genomic data. The distribution supports interoperability and reuse in genomic analysis workflows and pharmacogenomic research contexts."@en, ""@nl ; dct:format ; dct:issued "2026-02-01T00:00:00+00:00"^^xsd:dateTime ; dct:language ; dct:license ; dct:modified "2026-02-01T00:00:00+00:00"^^xsd:dateTime ; dct:rights [ a dct:RightsStatement ; rdfs:label ""@nl ], ; dct:title "Allele Frequency Data Distribution – CRG AFBeacon GoE synthetic dataset"@en, ""@nl ; dcat:accessURL ; dcat:mediaType . a dcat:Distribution ; dcatap:applicableLegislation ; dct:description "This distribution provides allele frequency data derived from the 1+MG COVID dataset. The data include population-level allele frequency metrics intended for testing, validation, and demonstration purposes within Beacon-compatible genomic data infrastructures. The dataset is synthetic and does not contain real individual-level genomic data. The distribution supports interoperability and reuse in genomic analysis workflows and pharmacogenomic research contexts."@en, ""@nl ; dct:format ; dct:issued "2026-02-01T00:00:00+00:00"^^xsd:dateTime ; dct:language ; dct:license ; dct:modified "2026-02-01T00:00:00+00:00"^^xsd:dateTime ; dct:rights [ a dct:RightsStatement ; rdfs:label ""@nl ], ; dct:title "Allele Frequency Data Distribution – 1+MG COVID dataset"@en, ""@nl ; dcat:accessURL ; dcat:mediaType . a dcat:Distribution ; dcatap:applicableLegislation ; dct:description "Files for the dataset \"Slovenian Population Reference Dataset\" provided in TXT format."@en, ""@nl ; dct:format ; dct:issued "2026-09-01T00:00:00+00:00"^^xsd:dateTime ; dct:language ; dct:license ; dct:modified "2026-09-01T00:00:00+00:00"^^xsd:dateTime ; dct:rights [ a dct:RightsStatement ; rdfs:label ""@nl ], ; dct:title "Slovenian Population Reference Dataset - TXT distribution"@en, ""@nl ; dcat:accessURL . a dcat:Dataset ; dcatap:applicableLegislation ; healthdcatap:hdab [ a foaf:Agent ; foaf:name "Miguel Santos" ] ; healthdcatap:healthCategory ; healthdcatap:numberOfUniqueIndividuals "41514"^^xsd:nonNegativeInteger ; dct:accessRights ; dct:conformsTo ; dct:creator [ a foaf:Agent ; foaf:name "CINECA" ] ; dct:description "Synthetic dataset containig CSV and VCF files"@en, ""@nl ; dct:identifier "GDI-PT-BIODATA-1" ; dct:issued "2026-03-16T17:45:04.879798"^^xsd:dateTime ; dct:language ; dct:modified "2026-08-30T00:00:07.531990"^^xsd:dateTime ; dct:provenance [ a dct:ProvenanceStatement ; rdfs:label ""@en, ""@nl ] ; dct:publisher ; dct:title "GDI PT Pop12 sub1 (ITA)"@en, ""@nl ; dct:type ; adms:identifier [ a adms:Identifier ; skos:notation "n44dc59189c1c42c9bc52ee7b266da548b4" ] ; adms:versionNotes ""@en, ""@nl ; dcat:distribution ; dcat:theme . a dcat:Dataset ; dcatap:applicableLegislation ; healthdcatap:hdab [ a foaf:Agent ; foaf:name "Miguel Santos" ] ; healthdcatap:healthCategory ; healthdcatap:numberOfRecords "1"^^xsd:nonNegativeInteger ; healthdcatap:numberOfUniqueIndividuals "4000"^^xsd:nonNegativeInteger ; dct:accessRights ; dct:conformsTo ; dct:creator [ a foaf:Agent ; foaf:name "Hugo Martiniano" ] ; dct:description "GDI Beacon dataset from INSA"@en, ""@nl ; dct:identifier "GDI-PT-INSA-1" ; dct:issued "2026-03-04T15:00:04.843904"^^xsd:dateTime ; dct:language ; dct:modified "2026-08-30T00:00:08.137502"^^xsd:dateTime ; dct:provenance [ a dct:ProvenanceStatement ; rdfs:label ""@en, ""@nl ] ; dct:publisher ; dct:title "GDI PT INSA Beacon dataset 1"@en, ""@nl ; dct:type ; adms:identifier [ a adms:Identifier ; skos:notation "nb59e989d619d4f74bac9e8c047e789c2b4" ] ; adms:versionNotes ""@en, ""@nl ; dcat:theme . a dcat:Distribution ; dcatap:applicableLegislation ; dct:description ""@en, ""@nl ; dct:issued "2026-08-30T00:00:07.536999"^^xsd:dateTime ; dct:language ; dct:license ; dct:modified "2026-08-30T00:00:07.535417"^^xsd:dateTime ; dct:rights [ a dct:RightsStatement ; rdfs:label ""@en, ""@nl ] ; dct:title "Population 12 (ITA), subset 1, Phenotypes of the individuals"@en, ""@nl ; dcat:accessURL . a rdfs:Resource . a dcat:Dataset ; dcatap:applicableLegislation ; healthdcatap:hdab [ a foaf:Agent ; foaf:name "Genomic Data Access Body in Estonia" ] ; healthdcatap:healthCategory , , ; healthdcatap:numberOfRecords "1"^^xsd:nonNegativeInteger ; dct:accessRights ; dct:conformsTo ; dct:creator [ a foaf:Agent ; foaf:name "Estonian Biobank" ] ; dct:description "Example GoE synthetic data from https://raw.githubusercontent.com/GenomicDataInfrastructure/starter-kit-synthetic-data/refs/heads/main/example_GoE_data/GRCh38/COVID.monogneic.aggregate.AFs.GRCh38.vcf"@en, ""@nl ; dct:identifier "GDI-EE-ESTBB-20260626320416" ; dct:issued "2026-06-26T12:04:16+00:00"^^xsd:dateTime ; dct:language ; dct:modified "2026-06-26T12:04:16+00:00"^^xsd:dateTime ; dct:provenance [ a dct:ProvenanceStatement ; rdfs:label ""@en, ""@nl ] ; dct:publisher [ a foaf:Agent ; foaf:name "Estonian Biobank" ] ; dct:title "Tiny GoE synthetic data"@en, ""@nl ; adms:versionNotes ""@en, ""@nl ; dcat:distribution , ; dcat:keyword "Estonia"@en, "GoE"@en, "aggregate"@en, "synthetic"@en, "test"@en ; dcat:theme . a dcat:Dataset ; healthdcatap:maxTypicalAge "100"^^xsd:nonNegativeInteger ; healthdcatap:minTypicalAge "1"^^xsd:nonNegativeInteger ; healthdcatap:numberOfRecords "10"^^xsd:nonNegativeInteger ; healthdcatap:numberOfUniqueIndividuals "4"^^xsd:nonNegativeInteger ; healthdcatap:populationCoverage "This test dataset covers no real population."@en ; dct:accessRights ; dct:creator [ a foaf:Agent ; dct:identifier ; vcard:hasEmail ; foaf:homepage ; foaf:name "BSC" ] ; dct:description """The synthetic genomes have been created trying to mimic real cancer data of 4 patients (Named 185, 186, 187, and 188). Mutations are based on real CRC patients from the PCAWG dataset. For each patient, two tumor samples at different time points and one healthy sample have been simulated. The cancer intra-tumor heterogeneity and evolution in the patients is depicted by simulating reads from tumor subclones separately and then mixing them according to their clonal proportions in each sample. For rapid use and transfer, only selected chromosomes have been generated for each patient. For Beacon queries, the following url can be used https://gdi-beacon-prototype.azurewebsites.net/api/datasets/EGAD50000000276"""@en, ""@nl ; dct:identifier "EGAD50000000276" ; dct:issued "2025-01-29T11:11:11+00:00"^^xsd:dateTime ; dct:language ; dct:modified "2025-01-29T13:36:10+00:00"^^xsd:dateTime ; dct:provenance [ a dct:ProvenanceStatement ; rdfs:label ""@en, ""@nl ] ; dct:publisher [ a foaf:Agent ; dct:identifier ; vcard:hasEmail ; foaf:homepage ; foaf:name "Health-RI" ] ; dct:title "EOSC4Cancer Longitudinal Synthetic Colorectal Cancer Genomic data developed at BSC"@en, ""@nl ; adms:versionNotes ""@en, ""@nl ; dcat:contactPoint [ a vcard:Kind ; vcard:fn "Servicedesk Health-RI" ; vcard:hasEmail ; vcard:hasUID ] ; dcat:distribution ; dcat:keyword "Cancer"@en, "Colorectal Cancer"@en, "Genomics"@en, "Synthetic Data"@en ; dcat:theme . a dcat:Dataset ; dcatap:applicableLegislation ; healthdcatap:healthCategory , ; dct:accessRights ; dct:conformsTo ; dct:creator [ a foaf:Agent ; foaf:name "Hans-Christian van der Werf " ] ; dct:description "The 1+MG COVID dataset is located at CSC's Allas service and it is available via Dylan Spalding (dylan.spalding@csc.fi) by request for the GDI project. In the future, the dataset will be available from CSC's FEGA service (https://research.csc.fi/service/fega/)."@en, ""@nl ; dct:identifier "GDI-NL-HRI-00001" ; dct:issued "2026-03-17T17:45:06.405384"^^xsd:dateTime ; dct:language ; dct:modified "2026-09-10T02:00:20.610044"^^xsd:dateTime ; dct:provenance [ a dct:ProvenanceStatement ; rdfs:label ""@en, ""@nl ] ; dct:publisher ; dct:title "1+MG COVID dataset"@en, ""@nl ; dct:type ; adms:versionNotes ""@en, ""@nl ; dcat:distribution ; dcat:theme . a dcat:Dataset ; dcatap:applicableLegislation ; healthdcatap:healthCategory ; dct:accessRights ; dct:conformsTo ; dct:creator [ a foaf:Agent ; dct:identifier ; vcard:hasEmail ; foaf:homepage ; foaf:name "Erasmus MC" ] ; dct:description "All variants detected by whole exome sequencing of 2628 Dutch healthy elderly individuals"@en, ""@nl ; dct:identifier "GOE-NL-ERS-0001" ; dct:issued "2026-03-05T08:05:22.009282"^^xsd:dateTime ; dct:language ; dct:modified "2026-09-10T02:00:18.827744"^^xsd:dateTime ; dct:provenance [ a dct:ProvenanceStatement ; rdfs:label ""@en, ""@nl ] ; dct:publisher [ a foaf:Agent ; dct:identifier ; vcard:hasEmail ; foaf:homepage ; foaf:name "Erasmus MC" ] ; dct:title "Exome Sequencing"@en, ""@nl ; adms:identifier [ a adms:Identifier ; skos:notation "na3b8f31df7424c66b81d2f96e2663599b4" ] ; adms:versionNotes ""@en, ""@nl ; dcat:contactPoint [ a vcard:Kind ; vcard:fn "Jeroen van Rooij" ; vcard:hasEmail ] ; dcat:distribution ; dcat:keyword "Cohort Study"@en ; dcat:theme . a dcat:Distribution ; dcatap:applicableLegislation ; dct:description ""@en, ""@nl ; dct:issued "2026-09-10T02:00:20.614461"^^xsd:dateTime ; dct:language ; dct:license ; dct:modified "2026-09-10T02:00:20.613039"^^xsd:dateTime ; dct:rights [ a dct:RightsStatement ; rdfs:label ""@en, ""@nl ] ; dct:title "1+MG COVID dataset"@en, ""@nl ; dcat:accessURL . a dcat:Distribution ; dcatap:applicableLegislation ; dct:description "All variants detected by whole exome sequencing of 2628 Dutch healthy elderly individuals"@en, ""@nl ; dct:format ; dct:issued "2026-09-10T02:00:18.833743"^^xsd:dateTime ; dct:language ; dct:license ; dct:modified "2026-09-10T02:00:18.831078"^^xsd:dateTime ; dct:rights [ a dct:RightsStatement ; rdfs:label ""@nl ], ; dct:title "Allele Frequencies of 2628 Exome Sequenced Samples."@en, ""@nl ; dcat:accessURL ; dcat:byteSize "6000000"^^xsd:nonNegativeInteger ; dcat:downloadURL ; dcat:mediaType "text/vcard" . a dcat:Distribution ; dct:description "VCF file containing GWAS and allele frequency lookup data of synthetic Colorectal cancer cases."@en, ""@nl ; dct:format ; dct:issued "2026-09-10T02:00:22.414388"^^xsd:dateTime ; dct:language ; dct:license ; dct:modified "2026-09-10T02:00:22.409619"^^xsd:dateTime ; dct:rights [ a dct:RightsStatement ; rdfs:label ""@nl ], ; dct:title "Example VCF from BSC"@en, ""@nl ; dcat:accessURL ; dcat:byteSize "1024"^^xsd:nonNegativeInteger ; dcat:mediaType . a dcat:Dataset ; dcatap:applicableLegislation ; healthdcatap:hdab [ a foaf:Agent ; dct:identifier "HDAB-BG" ; vcard:hasEmail ; foaf:homepage ; foaf:name "Health Data Access Body - Bulgaria" ] ; healthdcatap:healthCategory , , ; healthdcatap:numberOfRecords "571"^^xsd:nonNegativeInteger ; healthdcatap:numberOfUniqueIndividuals "20"^^xsd:nonNegativeInteger ; dct:accessRights ; dct:conformsTo ; dct:creator [ a foaf:Agent ; dct:identifier "GOE-BG-MMC-1" ; vcard:hasEmail ; foaf:homepage ; foaf:name "Genome of Europe - BG node" ] ; dct:description "GoE/GDI - Bulgaria MMC Dataset 1 - This is an example synthetic dataset for the staging environment of GDI."@en, ""@nl ; dct:identifier "GOE-BG-MUS-1" ; dct:issued "2026-03-05T08:05:30.222454"^^xsd:dateTime ; dct:language ; dct:modified "2026-08-31T02:45:05.680358"^^xsd:dateTime ; dct:provenance [ a dct:ProvenanceStatement ; rdfs:label ""@en, ""@nl ] ; dct:publisher [ a foaf:Agent ; dct:identifier "MUS-BG" ; vcard:hasEmail ; foaf:homepage ; foaf:name "Molecular Medicine Center - MU Sofia" ] ; dct:title "Genome of Europe Bulgaria Dummy dataset"@en, ""@nl ; dct:type ; adms:versionNotes ""@en, ""@nl ; dcat:contactPoint [ a vcard:Kind ; vcard:fn "MMC - BG" ; vcard:hasEmail ; vcard:hasURL <['https://www.mmcbg.org/']> ] ; dcat:distribution ; dcat:keyword "GDI"@en, "Genome of Europe"@en, "Synthetic"@en ; dcat:theme ; dpv:hasLegalBasis dpv:Consent . a dcat:Distribution ; dcatap:applicableLegislation ; dct:description "VCF file containing GWAS and allele frequency lookup data of synthetic cases. This is the default file downloaded from CRG_AFBeacon_GoE_synthetic_dataset_split-multiallelic-GTmasked-variantQC-sampleQC-ploidy_fixed-AF_recalc.vcf.gz"@en, ""@nl ; dct:format ; dct:issued "2026-08-31T02:45:05.688327"^^xsd:dateTime ; dct:language ; dct:license ; dct:modified "2026-08-31T02:45:05.683804"^^xsd:dateTime ; dct:rights [ a dct:RightsStatement ; rdfs:label ""@en, ""@nl ] ; dct:title "Example VCF for Bulgarian Aggregated Allele Frequency"@en, ""@nl ; dcat:accessURL ; dcat:byteSize "148000"^^xsd:nonNegativeInteger ; dcat:mediaType . a rdfs:Resource . a dcat:Dataset ; dcatap:applicableLegislation ; healthdcatap:hdab [ a foaf:Agent ; foaf:name "Latvian Biomedical Research and Study Centre; Aivars Cīrulis; Genome of Europe - LV Node" ] ; healthdcatap:healthCategory ; healthdcatap:numberOfRecords "56156"^^xsd:nonNegativeInteger ; healthdcatap:numberOfUniqueIndividuals "3000"^^xsd:nonNegativeInteger ; dct:accessRights ; dct:conformsTo ; dct:creator [ a foaf:Agent ; foaf:name "LBMC" ] ; dct:description "Synthetic aggregated allele frequencies representing 3000 individuals from Latvian population by sex and country of birth."@en, ""@nl ; dct:identifier "GOE-LV-LBMC-1" ; dct:isReferencedBy ; dct:issued "2026-03-04T15:30:10.755277"^^xsd:dateTime ; dct:language ; dct:modified "2026-05-31T07:15:07.330517"^^xsd:dateTime ; dct:provenance [ a dct:ProvenanceStatement ; rdfs:label ""@en, ""@nl ] ; dct:publisher ; dct:title "Synthetic Genome of Europe Latvian Genome Reference Project (LGRP) Allele Frequencies Dataset"@en, ""@nl ; dct:type ; adms:versionNotes ""@en, ""@nl ; dcat:distribution ; dcat:theme ; dpv:hasLegalBasis "dpv:Consent" . a dcat:Distribution ; dcatap:applicableLegislation ; dct:description ""@en, ""@nl ; dct:issued "2026-05-31T07:15:07.334813"^^xsd:dateTime ; dct:language ; dct:license ; dct:modified "2026-05-31T07:15:07.333414"^^xsd:dateTime ; dct:rights [ a dct:RightsStatement ; rdfs:label ""@en, ""@nl ] ; dct:title "Staging GoE LV Beacon "@en, ""@nl ; dcat:accessURL . a dcat:Dataset ; dcatap:applicableLegislation ; healthdcatap:healthCategory ; dct:accessRights ; dct:conformsTo ; dct:creator [ a foaf:Agent ; dct:identifier ; foaf:name "EGA" ] ; dct:description """ This is a subset of the GDI MS8 synthetic dataset (COVID pop13_1) containing aggregated allele frequency (AF) statistics for variants on chr21 across 42,312 samples. It has been extended to include aggregated AF statistics stratified by sex and ancestry populations in alignment with GoE requirements (by CRG, ES)."""@en, ""@nl ; dct:identifier "GOE-ES-CRG-1" ; dct:issued "2024-11-05T18:22:29+00:00"^^xsd:dateTime ; dct:language ; dct:modified "2026-01-30T17:28:57+00:00"^^xsd:dateTime ; dct:provenance [ a dct:ProvenanceStatement ; rdfs:label ""@en, ""@nl ] ; dct:publisher [ a foaf:Agent ; dct:identifier ; foaf:name "EGA" ] ; dct:title "CRG_AFBeacon_GoE_synthetic_dataset"@en, ""@nl ; dct:type ; adms:versionNotes ""@en, ""@nl ; dcat:contactPoint [ a vcard:Kind ; vcard:fn "Contact for Beacon team at EGA, CRG" ; vcard:hasEmail ] ; dcat:distribution ; dcat:keyword "COVID"@en, "COVID-19"@en, "EGA"@en, "GDI"@en, "GoE"@en, "synthetic"@en ; dcat:theme . a dcat:Distribution ; dcatap:applicableLegislation ; dct:description ""@en, ""@nl ; dct:format "ZIP" ; dct:issued "2026-09-10T16:15:12.838737"^^xsd:dateTime ; dct:modified "2026-09-10T16:15:12.832521"^^xsd:dateTime ; dct:rights [ a dct:RightsStatement ; rdfs:label ""@en, ""@nl ] ; dct:title "ZIP package containing synthetic VCF data"@en, ""@nl ; dcat:accessURL ; dcat:downloadURL ; dcat:mediaType "application/zip" . a dcat:Dataset ; dcatap:applicableLegislation ; healthdcatap:hdab ; healthdcatap:healthCategory ; dct:accessRights ; dct:conformsTo ; dct:creator [ a foaf:Agent ; dct:identifier ; foaf:name "EGA" ] ; dct:description """ This dataset contains the pheno-clinical and genomic information of 42046 individuals from COVID Population 11 Finland, Subgroup 2. 2010 are affected by Phenotype 1, 2010 are affected by Phenotype 2, 188 are affected by Phenotype 1 and 2, and 37838 are control. The dataset also contains the information about the smoking habits of each individual."""@en, ""@nl ; dct:identifier "GDI-ES-EGA-00000000955" ; dct:issued "2024-11-05T18:22:29+00:00"^^xsd:dateTime ; dct:language ; dct:modified "2026-01-30T17:28:57+00:00"^^xsd:dateTime ; dct:provenance [ a dct:ProvenanceStatement ; rdfs:label ""@en, ""@nl ] ; dct:publisher [ a foaf:Agent ; dct:identifier ; foaf:name "EGA" ] ; dct:spatial ; dct:title "GDI synthetic dataset (Population 11 Finland, Subgroup 2)"@en, ""@nl ; dct:type ; adms:versionNotes ""@en, ""@nl ; dcat:contactPoint [ a vcard:Kind ; vcard:fn "EGAC00001000514" ; vcard:hasEmail ; vcard:hasUID ] ; dcat:distribution ; dcat:keyword "COVID"@en, "COVID-19"@en, "EGA"@en, "GDI"@en, "synthetic"@en ; dcat:theme . a dcat:Distribution ; dcatap:applicableLegislation ; dct:description ""@en, ""@nl ; dct:issued "2026-09-10T16:15:15.750475"^^xsd:dateTime ; dct:modified "2026-09-10T16:15:15.744328"^^xsd:dateTime ; dct:rights [ a dct:RightsStatement ; rdfs:label ""@en, ""@nl ] ; dct:title "Files containing synthetic data"@en, ""@nl ; dcat:accessURL . a rdfs:Resource . a rdfs:Resource . a rdfs:Resource . a prov:Activity . a rdfs:Resource . a rdfs:Resource . a rdfs:Resource . a dct:MediaTypeOrExtent . a rdfs:Resource . a rdfs:Resource . a dcat:Dataset ; dct:creator [ a foaf:Agent ; dct:identifier ; foaf:name "National Bioinformatics Infrastructure Sweden" ] ; dct:description "This is the first part of the split 11 of the synthetic data dedicated for the GDI MS8"@en, ""@nl ; dct:identifier "GDID-12345678-11se" ; dct:issued "2024-07-07T11:11:11+00:00"^^xsd:dateTime ; dct:language ; dct:modified "2024-06-04T13:36:10+00:00"^^xsd:dateTime ; dct:provenance [ a dct:ProvenanceStatement ; rdfs:label ""@en, ""@nl ] ; dct:publisher [ a foaf:Agent ; dct:identifier ; foaf:name "National Bioinformatics Infrastructure Sweden" ] ; dct:title "COVID-19 GWAS and Allele Frequency Lookup Dataset for GDI MS 8"@en, ""@nl ; adms:versionNotes ""@en, ""@nl ; dcat:contactPoint [ a vcard:Kind ; vcard:fn "Data Access Committee of NBIS" ; vcard:hasEmail ; vcard:hasUID ] ; dcat:distribution ; dcat:keyword "COVID19"@en, "Smokers"@en ; dcat:theme . a dcat:Distribution ; dct:description "VCF file containing GWAS and allele frequency lookup data of synthetic COVID-19.cases and controls for GDI MS8 demonstration."@en, ""@nl ; dct:issued "2026-09-10T00:00:09.056182"^^xsd:dateTime ; dct:language ; dct:license ; dct:modified "2026-09-10T00:00:09.052652"^^xsd:dateTime ; dct:rights [ a dct:RightsStatement ; rdfs:label ""@en, ""@nl ] ; dct:title "GWAS and Allele Frequency Lookup Data Distribution for GDI MS8"@en, ""@nl ; dcat:accessURL ; dcat:mediaType . a dct:RightsStatement . a rdfs:Resource . a . a rdfs:Resource . a dct:RightsStatement . a foaf:Agent ; foaf:name "Portugal" . a foaf:Agent ; dct:identifier "EGAC00001000514" ; foaf:name "EGA Data Access Committee EGAC00001000514" . a dct:RightsStatement, rdfs:Resource . a rdfs:Resource . a rdfs:Resource . a vcard:Kind . a foaf:Agent . a dct:MediaTypeOrExtent . a dct:RightsStatement . a dct:LinguisticSystem . a dct:LicenseDocument ; dct:type . a foaf:Document . a dct:MediaTypeOrExtent . a dct:MediaTypeOrExtent . a dct:MediaType . a dct:MediaType . a dct:LicenseDocument ; dct:type . a rdfs:Resource . a . a . a dct:LicenseDocument, dct:RightsStatement ; dct:type . a dct:Standard . a dct:RightsStatement . a . a dct:LinguisticSystem .