{"id":"https://openalex.org/W4236715722","doi":"https://doi.org/10.7287/peerj.preprints.26951v1","title":"20 GB in 10 minutes: A case for linking major biodiversity databases using an open socio-technical infrastructure and a pragmatic, cross-institutional collaboration","display_name":"20 GB in 10 minutes: A case for linking major biodiversity databases using an open socio-technical infrastructure and a pragmatic, cross-institutional collaboration","publication_year":2018,"publication_date":"2018-05-22","ids":{"openalex":"https://openalex.org/W4236715722","doi":"https://doi.org/10.7287/peerj.preprints.26951v1"},"language":"en","primary_location":{"id":"doi:10.7287/peerj.preprints.26951v1","is_oa":true,"landing_page_url":"https://doi.org/10.7287/peerj.preprints.26951v1","pdf_url":"https://peerj.com/preprints/26951.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":null,"raw_type":"posted-content"},"type":"preprint","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://peerj.com/preprints/26951.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5028696519","display_name":"Anne Thessen","orcid":"https://orcid.org/0000-0002-2908-3327"},"institutions":[{"id":"https://openalex.org/I4210147267","display_name":"Ronin Institute","ror":"https://ror.org/04awze035","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I4210147267"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Anne E Thessen","raw_affiliation_strings":["Ronin Institute for Independent Scholarship, Montclair, New Jersey, USA"],"affiliations":[{"raw_affiliation_string":"Ronin Institute for Independent Scholarship, Montclair, New Jersey, USA","institution_ids":["https://openalex.org/I4210147267"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036204270","display_name":"Jorrit H. Poelen","orcid":"https://orcid.org/0000-0003-3138-4118"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jorrit H Poelen","raw_affiliation_strings":["Self-employed, Oakland, California, USA"],"affiliations":[{"raw_affiliation_string":"Self-employed, Oakland, California, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021610285","display_name":"Matthew Collins","orcid":"https://orcid.org/0000-0001-6462-8639"},"institutions":[{"id":"https://openalex.org/I33213144","display_name":"University of Florida","ror":"https://ror.org/02y3ad647","country_code":"US","type":"education","lineage":["https://openalex.org/I33213144"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Matthew Collins","raw_affiliation_strings":["University of Florida, Gainsville, Florida, USA"],"affiliations":[{"raw_affiliation_string":"University of Florida, Gainsville, Florida, USA","institution_ids":["https://openalex.org/I33213144"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5020378268","display_name":"Jennifer Hammock","orcid":"https://orcid.org/0000-0002-9943-2342"},"institutions":[{"id":"https://openalex.org/I1341618623","display_name":"National Museum of Natural History","ror":"https://ror.org/00cz47042","country_code":"US","type":"archive","lineage":["https://openalex.org/I103187081","https://openalex.org/I1341618623"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jen Hammock","raw_affiliation_strings":["National Museum of Natural History, Washington DC, USA"],"affiliations":[{"raw_affiliation_string":"National Museum of Natural History, Washington DC, USA","institution_ids":["https://openalex.org/I1341618623"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5028696519"],"corresponding_institution_ids":["https://openalex.org/I4210147267"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.33473585,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"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/T10215","display_name":"Semantic Web and Ontologies","score":0.9926000237464905,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10215","display_name":"Semantic Web and Ontologies","score":0.9926000237464905,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10895","display_name":"Species Distribution and Climate Change","score":0.9896000027656555,"subfield":{"id":"https://openalex.org/subfields/2302","display_name":"Ecological Modeling"},"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":0.9746000170707703,"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/identifier","display_name":"Identifier","score":0.816420316696167},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7444308400154114},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.6472716927528381},{"id":"https://openalex.org/keywords/interoperability","display_name":"Interoperability","score":0.5858989357948303},{"id":"https://openalex.org/keywords/biological-database","display_name":"Biological database","score":0.5316126346588135},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.4829108715057373},{"id":"https://openalex.org/keywords/ontology","display_name":"Ontology","score":0.4328341782093048},{"id":"https://openalex.org/keywords/graph-database","display_name":"Graph database","score":0.4177580773830414},{"id":"https://openalex.org/keywords/metadata","display_name":"Metadata","score":0.41189610958099365},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.3941795527935028},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3283706307411194},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.1988123059272766}],"concepts":[{"id":"https://openalex.org/C154504017","wikidata":"https://www.wikidata.org/wiki/Q853614","display_name":"Identifier","level":2,"score":0.816420316696167},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7444308400154114},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.6472716927528381},{"id":"https://openalex.org/C20136886","wikidata":"https://www.wikidata.org/wiki/Q749647","display_name":"Interoperability","level":2,"score":0.5858989357948303},{"id":"https://openalex.org/C20901353","wikidata":"https://www.wikidata.org/wiki/Q4117139","display_name":"Biological database","level":2,"score":0.5316126346588135},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.4829108715057373},{"id":"https://openalex.org/C25810664","wikidata":"https://www.wikidata.org/wiki/Q44325","display_name":"Ontology","level":2,"score":0.4328341782093048},{"id":"https://openalex.org/C176225458","wikidata":"https://www.wikidata.org/wiki/Q595971","display_name":"Graph database","level":3,"score":0.4177580773830414},{"id":"https://openalex.org/C93518851","wikidata":"https://www.wikidata.org/wiki/Q180160","display_name":"Metadata","level":2,"score":0.41189610958099365},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.3941795527935028},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3283706307411194},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.1988123059272766},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.0},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.7287/peerj.preprints.26951v1","is_oa":true,"landing_page_url":"https://doi.org/10.7287/peerj.preprints.26951v1","pdf_url":"https://peerj.com/preprints/26951.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":null,"raw_type":"posted-content"}],"best_oa_location":{"id":"doi:10.7287/peerj.preprints.26951v1","is_oa":true,"landing_page_url":"https://doi.org/10.7287/peerj.preprints.26951v1","pdf_url":"https://peerj.com/preprints/26951.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":null,"raw_type":"posted-content"},"sustainable_development_goals":[{"display_name":"Industry, innovation and infrastructure","score":0.6200000047683716,"id":"https://metadata.un.org/sdg/9"}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4236715722.pdf","grobid_xml":"https://content.openalex.org/works/W4236715722.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2392768766","https://openalex.org/W2058118494","https://openalex.org/W2095118173","https://openalex.org/W2382021449","https://openalex.org/W2605630948","https://openalex.org/W4283723149","https://openalex.org/W2887168851","https://openalex.org/W2496792076","https://openalex.org/W2560036845","https://openalex.org/W31445736"],"abstract_inverted_index":{"Biodiversity":[0,170],"information":[1],"is":[2,29,85,132,177],"made":[3,184],"available":[4],"through":[5],"numerous":[6],"databases":[7,23,49,160],"that":[8,98,325],"each":[9,33,241],"have":[10],"their":[11],"own":[12,37],"data":[13,18,21,121],"models,":[14],"web":[15],"services,":[16],"and":[17,46,61,71,115,125,128,167,195,209,229,265,276,286,289],"types.":[19],"Combining":[20],"across":[22,159],"leads":[24],"to":[25,134,211,240,269,273,309],"new":[26],"insights,":[27],"but":[28],"not":[30],"easy":[31],"because":[32],"database":[34,172],"uses":[35],"its":[36],"system":[38],"of":[39,44,68,78,104,186,193,202,218,236,255,257,280],"identifiers.":[40],"In":[41],"the":[42,76,91,112,153,168,298,307],"absence":[43],"stable":[45],"interoperable":[47],"identifiers,":[48],"are":[50,130,326],"often":[51],"linked":[52,210,232],"using":[53],"taxonomic":[54],"names.":[55],"This":[56,144,243],"labor":[57],"intensive,":[58],"error":[59],"prone,":[60],"lengthy":[62],"process":[63,279],"relies":[64],"on":[65,138,224,297],"accessible":[66,327],"versions":[67],"nomenclatural":[69],"authorities":[70],"fuzzy-matching":[72],"algorithms.":[73],"To":[74],"approach":[75],"challenge":[77],"linking":[79,158,165],"diverse":[80,102,315],"data,":[81],"more":[82],"than":[83],"technology":[84],"needed.":[86],"New":[87],"social":[88],"collaborations":[89],"like":[90],"Global":[92,169],"Unified":[93],"Open":[94,270,283],"Data":[95],"Architecture":[96],"(GUODA)":[97],"combine":[99],"skills":[100],"from":[101,107,111,123,205,328],"groups":[103],"computer":[105],"engineers":[106],"iDigBio,":[108],"server":[109],"resources":[110,324],"Advanced":[113],"Computing":[114],"Information":[116],"Systems":[117],"(ACIS)":[118],"Lab,":[119],"global-scale":[120],"presentation":[122],"EOL,":[124],"independent":[126],"developers":[127],"researchers":[129],"what":[131],"needed":[133],"make":[135],"concrete":[136],"progress":[137],"finding":[139],"relationships":[140],"between":[141],"biodiversity":[142,237,311],"datasets.":[143],"paper":[145],"will":[146],"discuss":[147],"a":[148,162,178,225,302,329,337],"technical":[149],"solution":[150],"developed":[151],"by":[152,233,313],"GUODA":[154,175,299,305],"collaboration":[155,338],"for":[156],"faster":[157],"with":[161,190,320],"use":[163],"case":[164],"Wikidata":[166,206,228,249,264],"Interactions":[171],"(GloBI).":[173],"The":[174,278],"infrastructure":[176],"12-node,":[179],"high":[180,321],"performance":[181,322],"computing":[182,323],"cluster":[183],"up":[185],"about":[187,214],"192":[188],"threads":[189],"12":[191],"TB":[192],"storage":[194],"288":[196],"GB":[197],"memory.":[198],"Using":[199],"GUODA,":[200],"20GB":[201],"compressed":[203],"JSON":[204],"was":[207,293],"processed":[208],"GloBI":[212,230,266,287],"in":[213,246,251,262,295,335],"10-11":[215],"minutes.":[216],"Instead":[217],"comparing":[219,234],"name":[220,260],"strings":[221],"or":[222,331],"relying":[223],"single":[226],"identifier,":[227],"were":[231,267],"graphs":[235],"identifiers":[238],"external":[239],"system.":[242],"method":[244],"resulted":[245],"adding":[247],"119,957":[248],"links":[250,261],"GloBI,":[252],"an":[253],"increase":[254],"13.7%":[256],"all":[258],"outgoing":[259],"GloBI.":[263],"compared":[268],"Tree":[271,284],"Taxonomy":[272,285],"examine":[274],"consistency":[275,291],"coverage.":[277],"parsing":[281],"Wikidata,":[282],"archives":[288],"calculating":[290],"metrics":[292],"done":[294],"minutes":[296],"platform.":[300],"As":[301],"model":[303],"collaboration,":[304],"has":[306],"potential":[308],"revolutionize":[310],"science":[312],"bringing":[314],"technically":[316],"minded":[317],"people":[318],"together":[319],"laptop":[330],"desktop.":[332],"However,":[333],"participating":[334],"such":[336],"still":[339],"requires":[340],"basic":[341],"programming":[342],"skills.":[343]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
