{"id":"https://openalex.org/W7165405256","doi":"https://doi.org/10.5281/zenodo.20653199","title":"Supporting data for: Global Environmental Genomics Reveals Vast Uncultivated Protist Diversity and Taxonomic Blind Spots","display_name":"Supporting data for: Global Environmental Genomics Reveals Vast Uncultivated Protist Diversity and Taxonomic Blind Spots","publication_year":2026,"publication_date":"2026-06-13","ids":{"openalex":"https://openalex.org/W7165405256","doi":"https://doi.org/10.5281/zenodo.20653199"},"language":"en","primary_location":{"id":"doi:10.5281/zenodo.20653199","doi":"https://doi.org/10.5281/zenodo.20653199","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.20653199","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Dataset"},"volume":null,"type":"dataset","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.5281/zenodo.20653199","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5114012877","display_name":"Miguel F. Romero","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I196679689","display_name":"Joint Genome Institute","ror":"https://ror.org/04xm1d337","country_code":"US","type":"facility","lineage":["https://openalex.org/I1330989302","https://openalex.org/I148283060","https://openalex.org/I196679689","https://openalex.org/I39565521"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Romero Gutierrez, Miguel Fernando","raw_affiliation_strings":["DOE Joint Genome Institute"],"raw_orcid":"https://orcid.org/0000-0002-3799-717X","affiliations":[{"raw_affiliation_string":"DOE Joint Genome Institute","institution_ids":["https://openalex.org/I196679689"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025611353","display_name":"Arianna I. Krinos","orcid":"https://orcid.org/0000-0001-9767-8392","observed_orcids":["https://orcid.org/0000-0001-9767-8392"]},"institutions":[{"id":"https://openalex.org/I196679689","display_name":"Joint Genome Institute","ror":"https://ror.org/04xm1d337","country_code":"US","type":"facility","lineage":["https://openalex.org/I1330989302","https://openalex.org/I148283060","https://openalex.org/I196679689","https://openalex.org/I39565521"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Krinos, Arianna I.","raw_affiliation_strings":["Joint Genome Institute"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Joint Genome Institute","institution_ids":["https://openalex.org/I196679689"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088850798","display_name":"Xyrus X. Maurer\u2010Alcal\u00e1","orcid":"https://orcid.org/0000-0002-7499-9369","observed_orcids":["https://orcid.org/0000-0002-7499-9369"]},"institutions":[{"id":"https://openalex.org/I1338124936","display_name":"American Museum of Natural History","ror":"https://ror.org/03thb3e06","country_code":"US","type":"archive","lineage":["https://openalex.org/I1338124936"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Maurer-Alcala, Xyrus","raw_affiliation_strings":["American Museum of Natural History"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"American Museum of Natural History","institution_ids":["https://openalex.org/I1338124936"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5138993979","display_name":"John A. Burns","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I2800663845","display_name":"Bigelow Laboratory for Ocean Sciences","ror":"https://ror.org/03v2r6x37","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I2800663845"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Burns, John A.","raw_affiliation_strings":["Bigelow Laboratory for Ocean Sciences"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Bigelow Laboratory for Ocean Sciences","institution_ids":["https://openalex.org/I2800663845"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016018436","display_name":"Ram\u016bnas Stepanauskas","orcid":"https://orcid.org/0000-0003-4458-3108","observed_orcids":["https://orcid.org/0000-0003-4458-3108"]},"institutions":[{"id":"https://openalex.org/I2800663845","display_name":"Bigelow Laboratory for Ocean Sciences","ror":"https://ror.org/03v2r6x37","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I2800663845"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Stepanauskas, Ramunas","raw_affiliation_strings":["Bigelow Laboratory for Ocean Sciences"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Bigelow Laboratory for Ocean Sciences","institution_ids":["https://openalex.org/I2800663845"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006298901","display_name":"Tanja Woyke","orcid":"https://orcid.org/0000-0002-9485-5637","observed_orcids":["https://orcid.org/0000-0002-9485-5637"]},"institutions":[{"id":"https://openalex.org/I196679689","display_name":"Joint Genome Institute","ror":"https://ror.org/04xm1d337","country_code":"US","type":"facility","lineage":["https://openalex.org/I1330989302","https://openalex.org/I148283060","https://openalex.org/I196679689","https://openalex.org/I39565521"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Woyke, Tanja","raw_affiliation_strings":["Joint Genome Institute"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Joint Genome Institute","institution_ids":["https://openalex.org/I196679689"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5064963970","display_name":"Frederik Schulz","orcid":"https://orcid.org/0000-0002-4932-4677","observed_orcids":["https://orcid.org/0000-0002-4932-4677"]},"institutions":[{"id":"https://openalex.org/I196679689","display_name":"Joint Genome Institute","ror":"https://ror.org/04xm1d337","country_code":"US","type":"facility","lineage":["https://openalex.org/I1330989302","https://openalex.org/I148283060","https://openalex.org/I196679689","https://openalex.org/I39565521"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Schulz, Frederik","raw_affiliation_strings":["Joint Genome Institute"],"raw_orcid":"https://orcid.org/0000-0002-4932-4677","affiliations":[{"raw_affiliation_string":"Joint Genome Institute","institution_ids":["https://openalex.org/I196679689"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11879","display_name":"Protist diversity and phylogeny","score":0.9980000257492065,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},"topics":[{"id":"https://openalex.org/T11879","display_name":"Protist diversity and phylogeny","score":0.9980000257492065,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T11791","display_name":"Microbial Community Ecology and Physiology","score":0.0013000000035390258,"subfield":{"id":"https://openalex.org/subfields/2303","display_name":"Ecology"},"field":{"id":"https://openalex.org/fields/23","display_name":"Environmental Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.0003000000142492354,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/protist-diversity","display_name":"protist diversity","score":0.8389999866485596},{"id":"https://openalex.org/keywords/18s-rrna","display_name":"18S rRNA","score":0.9129999876022339},{"id":"https://openalex.org/keywords/single-amplified-genomes","display_name":"single amplified genomes","score":0.6949999928474426},{"id":"https://openalex.org/keywords/metagenomics","display_name":"metagenomics","score":0.5680000185966492},{"id":"https://openalex.org/keywords/16s-rrna","display_name":"16S rRNA","score":0.6389999985694885},{"id":"https://openalex.org/keywords/marine-protists","display_name":"marine protists","score":0.6290000081062317},{"id":"https://openalex.org/keywords/freshwater-protists","display_name":"freshwater protists","score":0.9980000257492065},{"id":"https://openalex.org/keywords/phylogenomics","display_name":"phylogenomics","score":0.5239999890327454},{"id":"https://openalex.org/keywords/otu-clustering","display_name":"OTU clustering","score":0.3619999885559082},{"id":"https://openalex.org/keywords/single-cell-genomics","display_name":"single-cell genomics","score":0.3319999873638153}],"concepts":[{"id":"https://openalex.org/C47698986","wikidata":"https://www.wikidata.org/wiki/Q10018973","display_name":"18S ribosomal RNA","level":4,"score":0.8396000266075134},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.6833999752998352},{"id":"https://openalex.org/C67905577","wikidata":"https://www.wikidata.org/wiki/Q215980","display_name":"Ribosomal RNA","level":3,"score":0.6409000158309937},{"id":"https://openalex.org/C2779825944","wikidata":"https://www.wikidata.org/wiki/Q7097792","display_name":"Operational taxonomic unit","level":4,"score":0.5873000025749207},{"id":"https://openalex.org/C42062724","wikidata":"https://www.wikidata.org/wiki/Q1209205","display_name":"16S ribosomal RNA","level":3,"score":0.5148000121116638},{"id":"https://openalex.org/C2778330419","wikidata":"https://www.wikidata.org/wiki/Q10892","display_name":"Protist","level":3,"score":0.46389999985694885},{"id":"https://openalex.org/C155794727","wikidata":"https://www.wikidata.org/wiki/Q2306414","display_name":"Internal transcribed spacer","level":4,"score":0.4205999970436096},{"id":"https://openalex.org/C113174947","wikidata":"https://www.wikidata.org/wiki/Q2859736","display_name":"Tree (set theory)","level":2,"score":0.36890000104904175},{"id":"https://openalex.org/C45235069","wikidata":"https://www.wikidata.org/wiki/Q278425","display_name":"Table (database)","level":2,"score":0.34310001134872437},{"id":"https://openalex.org/C18903297","wikidata":"https://www.wikidata.org/wiki/Q7150","display_name":"Ecology","level":1,"score":0.3271999955177307},{"id":"https://openalex.org/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","level":1,"score":0.3199000060558319},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.2946000099182129},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.2786000072956085},{"id":"https://openalex.org/C30968088","wikidata":"https://www.wikidata.org/wiki/Q1230601","display_name":"Diversity index","level":3,"score":0.2526000142097473}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.5281/zenodo.20653199","doi":"https://doi.org/10.5281/zenodo.20653199","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.20653199","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Dataset"},{"id":"doi:10.5281/zenodo.20653200","doi":"https://doi.org/10.5281/zenodo.20653200","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.20653200","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Dataset"},{"id":"doi:10.5281/zenodo.21776524","doi":"https://doi.org/10.5281/zenodo.21776524","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.21776524","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Dataset"}],"best_oa_location":{"id":"doi:10.5281/zenodo.20653199","doi":"https://doi.org/10.5281/zenodo.20653199","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.20653199","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Dataset"},"sustainable_development_goals":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G42916606","display_name":null,"funder_award_id":"DE AC02 05CH11231","funder_id":"https://openalex.org/F4320306084","funder_display_name":"U.S. Department of Energy"}],"funders":[{"id":"https://openalex.org/F4320306084","display_name":"U.S. Department of Energy","ror":"https://ror.org/01bj3aw27"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4408882575","https://openalex.org/W748031565","https://openalex.org/W6924832822","https://openalex.org/W6958407940","https://openalex.org/W4394511275","https://openalex.org/W4283642636","https://openalex.org/W4394085436","https://openalex.org/W6929638801","https://openalex.org/W4393469819","https://openalex.org/W6906608546"],"abstract_inverted_index":{"File":[0],"description:":[1],"18S_cluster.tsv":[2],"(173.60":[3],"MB)":[4,22,37,67,79,207,224,241,255,331,349,374],"-":[5,23,38,49,68,80,91,107,127,146,163,180,194,208,225,242,256,270,287,304,318,332,350,365,375,384],"Table":[6,24,333,351],"with":[7,25,60,93,109,334,352],"annotations":[8,26,335,353],"and":[9,27,113,152,169,214,231,276,293,336,354],"metrics":[10,28,337,355],"at":[11,17,29,338,344,356],"the":[12,30,61,83,133,339,357,378],"18S":[13,31,42,52,150,167,184,198,212,229,246,260,274,291,308,322,369],"rRNA":[14,32,43,53,151,154,168,171,185,199,213,216,230,233,247,261,275,278,292,295,309,323,341,359,370],"OTU":[15,54,155,172,186,200,217,234,248,262,279,296,310,324,342],"level":[16,343],"85%":[18,345],"identity.":[19,346],"18S_sequence.tsv":[20],"(787.57":[21],"sequence":[33,360],"level.":[34,361],"eukcensus_2025_18S.fna":[35],"(616.19":[36],"Fasta":[39,366],"file":[40,367],"of":[41,368],"sequences.":[44,371],"rarefied-diversity.tsv":[45],"(12.41":[46],"MB":[47],")":[48],"Sample":[50],"by":[51],"count":[55],"table":[56,70],"rarefied":[57],"using":[58],"rrarefy":[59],"R":[62],"vegan":[63],"package.":[64],"eukcensus_2025_img_metadata.tsv":[65],"(18.08":[66],"Metadata":[69],"for":[71,82,149,166,183,197,211,228,245,259,273,290,307,321,377,386],"IMG/M":[72],"derived":[73],"environmental":[74,94,110],"sequencing":[75],"samples.":[76],"eukcensus_2025_sag_assemblies.tar.gz":[77],"(146.03":[78],"Assemblies":[81],"Single":[84],"cell":[85,388],"Amplified":[86],"Genomes.":[87],"F1_tree.nwk.txt":[88],"(56.29":[89],"KB)":[90,106,126,145,162,179,193,269,286,303,317,383],"Tree":[92,108],"representative":[95,111,115],"clusters":[96,112],"shown":[97,117,136],"in":[98,101,118,121,132,137,140,157,174,188,202,219,236,250,264,281,298,312,326],"Figure":[99,119,138],"1":[100],"newick":[102,122,141],"format.":[103,123,142],"F3A_tree.nwk.txt":[104],"(190.81":[105],"orphan":[114],"sequences":[116],"3A":[120],"F3D_tree.nwk.txt":[124],"(7.42":[125],"Phylogenomic":[128],"tree":[129,135],"including":[130,390],"SAGs":[131],"eukaryotic":[134],"3D":[139],"marine-correlations-coeff.tsv":[143],"(868.62":[144],"Correlation":[147,181,209,243,271,305],"coefficients":[148,182,210,244,272,306],"16S":[153,170,215,232,277,294,340,358],"pairs":[156,173,187,201,218,235,249,263,280,297,311,325],"marine":[158,175,189,203],"environments.":[159,176,190,204,221,238,252,266,283,300,314,328],"marine-correlations-pvalues.tsv":[160],"(930.37":[161],"Adjusted":[164,195,226,257,288,319],"p-values":[165,196,227,258,289,320],"marine-eukcorrelations-coeff.tsv":[177],"(582.72":[178],"marine-eukcorrelations-pvalues.tsv":[191],"(620.31":[192],"freshw-correlations-coeff.tsv":[205],"(3.00":[206],"freshwater":[220,237,251,265],"freshw-correlations-pvalues.tsv":[222],"(3.23":[223],"freshw-eukcorrelations-coeff.tsv":[239],"(9.15":[240],"freshw-eukcorrelations-pvalues.tsv":[253],"(9.56":[254],"soil-correlations-coeff.tsv":[267],"(547.88":[268],"soil":[282,299,313,327],"soil-correlations-pvalues.tsv":[284],"(586.42":[285],"soil-eukcorrelations-coeff.tsv":[301],"(146.94":[302],"soil-eukcorrelations-pvalues.tsv":[315],"(157.01":[316],"16S_cluster.tsv":[329],"(38.39":[330],"16S_sequence.tsv":[347],"(689.23":[348],"eukcensus_2025_16S.fna":[362],"(1.78":[363],"GB)":[364],"eukcensus_ssuextract.tar.gz":[372],"(30.54":[373],"Code":[376],"ssuextract":[379],"software.":[380],"SAG_data_SRA.tsv":[381],"(10.5":[382],"Information":[385],"single":[387],"sorts":[389],"SRA":[391],"ID.":[392]},"counts_by_year":[],"updated_date":"2026-10-28T10:33:24.094632","created_date":"2026-06-20T00:00:00"}
