{"id":"https://openalex.org/W7212226483","doi":"https://doi.org/10.64898/2026.09.09.750348","title":"The StrainDiscoveryDatabase: an open framework for standardized microbial strain data","display_name":"The StrainDiscoveryDatabase: an open framework for standardized microbial strain data","publication_year":2026,"publication_date":"2026-09-10","ids":{"openalex":"https://openalex.org/W7212226483","doi":"https://doi.org/10.64898/2026.09.09.750348"},"language":"en","primary_location":{"id":"doi:10.64898/2026.09.09.750348","doi":"https://doi.org/10.64898/2026.09.09.750348","is_oa":true,"landing_page_url":"https://doi.org/10.64898/2026.09.09.750348","pdf_url":"https://www.biorxiv.org/content/biorxiv/early/2026/09/10/2026.09.09.750348.full.pdf","source":{"id":"https://openalex.org/S4306402567","display_name":"bioRxiv (Cold Spring Harbor Laboratory)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I2750212522","host_organization_name":"Cold Spring Harbor Laboratory","host_organization_lineage":["https://openalex.org/I2750212522"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"bioRxiv","raw_type":"posted-content"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://www.biorxiv.org/content/biorxiv/early/2026/09/10/2026.09.09.750348.full.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5032144349","display_name":"J. Witte","orcid":"https://orcid.org/0009-0005-9790-9097","observed_orcids":["https://orcid.org/0009-0005-9790-9097"]},"institutions":[{"id":"https://openalex.org/I7935750","display_name":"Leibniz Institute DSMZ \u2013 German Collection of Microorganisms and Cell Cultures","ror":"https://ror.org/02tyer376","country_code":"DE","type":"facility","lineage":["https://openalex.org/I315704651","https://openalex.org/I7935750"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Julius F. Witte","raw_affiliation_strings":["Leibniz Institute DSMZ \u2013 German Collection of Microorganisms and Cell Cultures"],"raw_orcid":"https://orcid.org/0009-0005-9790-9097","affiliations":[{"raw_affiliation_string":"Leibniz Institute DSMZ \u2013 German Collection of Microorganisms and Cell Cultures","institution_ids":["https://openalex.org/I7935750"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021981260","display_name":"Artur Lissin","orcid":"https://orcid.org/0009-0007-3729-1533","observed_orcids":["https://orcid.org/0009-0007-3729-1533"]},"institutions":[{"id":"https://openalex.org/I7935750","display_name":"Leibniz Institute DSMZ \u2013 German Collection of Microorganisms and Cell Cultures","ror":"https://ror.org/02tyer376","country_code":"DE","type":"facility","lineage":["https://openalex.org/I315704651","https://openalex.org/I7935750"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Artur Lissin","raw_affiliation_strings":["Leibniz Institute DSMZ \u2013 German Collection of Microorganisms and Cell Cultures"],"raw_orcid":"https://orcid.org/0009-0007-3729-1533","affiliations":[{"raw_affiliation_string":"Leibniz Institute DSMZ \u2013 German Collection of Microorganisms and Cell Cultures","institution_ids":["https://openalex.org/I7935750"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090945520","display_name":"Isabel Schober","orcid":"https://orcid.org/0000-0002-4894-1913","observed_orcids":["https://orcid.org/0000-0002-4894-1913"]},"institutions":[{"id":"https://openalex.org/I7935750","display_name":"Leibniz Institute DSMZ \u2013 German Collection of Microorganisms and Cell Cultures","ror":"https://ror.org/02tyer376","country_code":"DE","type":"facility","lineage":["https://openalex.org/I315704651","https://openalex.org/I7935750"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Isabel Schober","raw_affiliation_strings":["Leibniz Institute DSMZ \u2013 German Collection of Microorganisms and Cell Cultures"],"raw_orcid":"https://orcid.org/0000-0002-4894-1913","affiliations":[{"raw_affiliation_string":"Leibniz Institute DSMZ \u2013 German Collection of Microorganisms and Cell Cultures","institution_ids":["https://openalex.org/I7935750"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034175020","display_name":"Christian Ebeling","orcid":"https://orcid.org/0000-0002-7560-6846","observed_orcids":["https://orcid.org/0000-0002-7560-6846"]},"institutions":[{"id":"https://openalex.org/I7935750","display_name":"Leibniz Institute DSMZ \u2013 German Collection of Microorganisms and Cell Cultures","ror":"https://ror.org/02tyer376","country_code":"DE","type":"facility","lineage":["https://openalex.org/I315704651","https://openalex.org/I7935750"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Christian Ebeling","raw_affiliation_strings":["Leibniz Institute DSMZ \u2013 German Collection of Microorganisms and Cell Cultures"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Leibniz Institute DSMZ \u2013 German Collection of Microorganisms and Cell Cultures","institution_ids":["https://openalex.org/I7935750"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5140878049","display_name":"Helko L\u00fcken","orcid":"https://orcid.org/0009-0005-0674-1859","observed_orcids":["https://orcid.org/0009-0005-0674-1859"]},"institutions":[{"id":"https://openalex.org/I7935750","display_name":"Leibniz Institute DSMZ \u2013 German Collection of Microorganisms and Cell Cultures","ror":"https://ror.org/02tyer376","country_code":"DE","type":"facility","lineage":["https://openalex.org/I315704651","https://openalex.org/I7935750"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Helko L\u00fcken","raw_affiliation_strings":["Leibniz Institute DSMZ \u2013 German Collection of Microorganisms and Cell Cultures"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Leibniz Institute DSMZ \u2013 German Collection of Microorganisms and Cell Cultures","institution_ids":["https://openalex.org/I7935750"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022180345","display_name":"Julia Koblitz","orcid":"https://orcid.org/0000-0002-7260-2129","observed_orcids":["https://orcid.org/0000-0002-7260-2129"]},"institutions":[{"id":"https://openalex.org/I7935750","display_name":"Leibniz Institute DSMZ \u2013 German Collection of Microorganisms and Cell Cultures","ror":"https://ror.org/02tyer376","country_code":"DE","type":"facility","lineage":["https://openalex.org/I315704651","https://openalex.org/I7935750"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Julia Koblitz","raw_affiliation_strings":["Leibniz Institute DSMZ \u2013 German Collection of Microorganisms and Cell Cultures"],"raw_orcid":"https://orcid.org/0000-0002-7260-2129","affiliations":[{"raw_affiliation_string":"Leibniz Institute DSMZ \u2013 German Collection of Microorganisms and Cell Cultures","institution_ids":["https://openalex.org/I7935750"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062022007","display_name":"Andrey M. Yurkov","orcid":"https://orcid.org/0000-0002-1072-5166","observed_orcids":["https://orcid.org/0000-0002-1072-5166"]},"institutions":[{"id":"https://openalex.org/I7935750","display_name":"Leibniz Institute DSMZ \u2013 German Collection of Microorganisms and Cell Cultures","ror":"https://ror.org/02tyer376","country_code":"DE","type":"facility","lineage":["https://openalex.org/I315704651","https://openalex.org/I7935750"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Andrey Yurkov","raw_affiliation_strings":["Leibniz Institute DSMZ \u2013 German Collection of Microorganisms and Cell Cultures"],"raw_orcid":"https://orcid.org/0000-0002-1072-5166","affiliations":[{"raw_affiliation_string":"Leibniz Institute DSMZ \u2013 German Collection of Microorganisms and Cell Cultures","institution_ids":["https://openalex.org/I7935750"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066331469","display_name":"Boyke Bunk","orcid":"https://orcid.org/0000-0002-8420-8161","observed_orcids":["https://orcid.org/0000-0002-8420-8161"]},"institutions":[{"id":"https://openalex.org/I7935750","display_name":"Leibniz Institute DSMZ \u2013 German Collection of Microorganisms and Cell Cultures","ror":"https://ror.org/02tyer376","country_code":"DE","type":"facility","lineage":["https://openalex.org/I315704651","https://openalex.org/I7935750"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Boyke Bunk","raw_affiliation_strings":["Leibniz Institute DSMZ \u2013 German Collection of Microorganisms and Cell Cultures"],"raw_orcid":"https://orcid.org/0000-0002-8420-8161","affiliations":[{"raw_affiliation_string":"Leibniz Institute DSMZ \u2013 German Collection of Microorganisms and Cell Cultures","institution_ids":["https://openalex.org/I7935750"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024646865","display_name":"Jos\u00e9 L\u00f3pez-Coronado","orcid":"https://orcid.org/0000-0001-7442-8091","observed_orcids":["https://orcid.org/0000-0001-7442-8091"]},"institutions":[{"id":"https://openalex.org/I16097986","display_name":"Universitat de Val\u00e8ncia","ror":"https://ror.org/043nxc105","country_code":"ES","type":"education","lineage":["https://openalex.org/I16097986"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Jos\u00e9 Miguel L\u00f3pez-Coronado","raw_affiliation_strings":["Microbial Resource Research Infrastructure-Spanish node (MIRRI-ES)","Spanish Type Culture Collection-University of Valencia (CECT-UVEG)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microbial Resource Research Infrastructure-Spanish node (MIRRI-ES)","institution_ids":[]},{"raw_affiliation_string":"Spanish Type Culture Collection-University of Valencia (CECT-UVEG)","institution_ids":["https://openalex.org/I16097986"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5140900497","display_name":"Adrian Vaello","orcid":"https://orcid.org/0009-0004-0398-1403","observed_orcids":["https://orcid.org/0009-0004-0398-1403"]},"institutions":[{"id":"https://openalex.org/I16097986","display_name":"Universitat de Val\u00e8ncia","ror":"https://ror.org/043nxc105","country_code":"ES","type":"education","lineage":["https://openalex.org/I16097986"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Adrian Vaello","raw_affiliation_strings":["Microbial Resource Research Infrastructure-Spanish node (MIRRI-ES)","Spanish Type Culture Collection-University of Valencia (CECT-UVEG)"],"raw_orcid":"https://orcid.org/0009-0004-0398-1403","affiliations":[{"raw_affiliation_string":"Microbial Resource Research Infrastructure-Spanish node (MIRRI-ES)","institution_ids":[]},{"raw_affiliation_string":"Spanish Type Culture Collection-University of Valencia (CECT-UVEG)","institution_ids":["https://openalex.org/I16097986"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057608650","display_name":"Aurora Zuzuarregui","orcid":"https://orcid.org/0000-0003-2980-8321","observed_orcids":["https://orcid.org/0000-0003-2980-8321"]},"institutions":[{"id":"https://openalex.org/I16097986","display_name":"Universitat de Val\u00e8ncia","ror":"https://ror.org/043nxc105","country_code":"ES","type":"education","lineage":["https://openalex.org/I16097986"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Aurora Zuzuarregui","raw_affiliation_strings":["Microbial Resource Research Infrastructure-Spanish node (MIRRI-ES)","Spanish Type Culture Collection-University of Valencia (CECT-UVEG)"],"raw_orcid":"https://orcid.org/0000-0003-2980-8321","affiliations":[{"raw_affiliation_string":"Microbial Resource Research Infrastructure-Spanish node (MIRRI-ES)","institution_ids":[]},{"raw_affiliation_string":"Spanish Type Culture Collection-University of Valencia (CECT-UVEG)","institution_ids":["https://openalex.org/I16097986"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034121124","display_name":"Rosa Aznar","orcid":"https://orcid.org/0000-0002-8761-8887","observed_orcids":["https://orcid.org/0000-0002-8761-8887"]},"institutions":[{"id":"https://openalex.org/I16097986","display_name":"Universitat de Val\u00e8ncia","ror":"https://ror.org/043nxc105","country_code":"ES","type":"education","lineage":["https://openalex.org/I16097986"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Rosa Aznar","raw_affiliation_strings":["Microbial Resource Research Infrastructure-Spanish node (MIRRI-ES)","Spanish Type Culture Collection-University of Valencia (CECT-UVEG)"],"raw_orcid":"https://orcid.org/0000-0002-8761-8887","affiliations":[{"raw_affiliation_string":"Microbial Resource Research Infrastructure-Spanish node (MIRRI-ES)","institution_ids":[]},{"raw_affiliation_string":"Spanish Type Culture Collection-University of Valencia (CECT-UVEG)","institution_ids":["https://openalex.org/I16097986"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5140917238","display_name":"Agust\u00edn Garc\u00eda Do\u00f1ate","orcid":"https://orcid.org/0009-0002-2159-965X","observed_orcids":["https://orcid.org/0009-0002-2159-965X"]},"institutions":[{"id":"https://openalex.org/I16097986","display_name":"Universitat de Val\u00e8ncia","ror":"https://ror.org/043nxc105","country_code":"ES","type":"education","lineage":["https://openalex.org/I16097986"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Agustin Garc\u00eda-Do\u00f1ate","raw_affiliation_strings":["Microbial Resource Research Infrastructure-Spanish node (MIRRI-ES)","Spanish Type Culture Collection-University of Valencia (CECT-UVEG)"],"raw_orcid":"https://orcid.org/0009-0002-2159-965X","affiliations":[{"raw_affiliation_string":"Microbial Resource Research Infrastructure-Spanish node (MIRRI-ES)","institution_ids":[]},{"raw_affiliation_string":"Spanish Type Culture Collection-University of Valencia (CECT-UVEG)","institution_ids":["https://openalex.org/I16097986"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059706632","display_name":"Ana M. P. Melo","orcid":"https://orcid.org/0000-0003-0695-3817","observed_orcids":["https://orcid.org/0000-0003-0695-3817"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ana M. P. Melo","raw_affiliation_strings":["MIRRI-ERIC"],"raw_orcid":"https://orcid.org/0000-0003-0695-3817","affiliations":[{"raw_affiliation_string":"MIRRI-ERIC","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011455287","display_name":"G.J.M. Verkley","orcid":"https://orcid.org/0000-0001-6575-2439","observed_orcids":["https://orcid.org/0000-0001-6575-2439"]},"institutions":[{"id":"https://openalex.org/I4210113371","display_name":"Westerdijk Fungal Biodiversity Institute","ror":"https://ror.org/030a5r161","country_code":"NL","type":"facility","lineage":["https://openalex.org/I1322597698","https://openalex.org/I4210113371"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Gerard Verkleij","raw_affiliation_strings":["Westerdijk Fungal Biodiversity Institute (WI-KNAW)"],"raw_orcid":"https://orcid.org/0000-0001-6575-2439","affiliations":[{"raw_affiliation_string":"Westerdijk Fungal Biodiversity Institute (WI-KNAW)","institution_ids":["https://openalex.org/I4210113371"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102928197","display_name":"Ronald P. de Vries","orcid":"https://orcid.org/0000-0002-4363-1123","observed_orcids":["https://orcid.org/0000-0002-4363-1123"]},"institutions":[{"id":"https://openalex.org/I4210113371","display_name":"Westerdijk Fungal Biodiversity Institute","ror":"https://ror.org/030a5r161","country_code":"NL","type":"facility","lineage":["https://openalex.org/I1322597698","https://openalex.org/I4210113371"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Ronald P. de Vries","raw_affiliation_strings":["Westerdijk Fungal Biodiversity Institute (WI-KNAW)"],"raw_orcid":"https://orcid.org/0000-0002-4363-1123","affiliations":[{"raw_affiliation_string":"Westerdijk Fungal Biodiversity Institute (WI-KNAW)","institution_ids":["https://openalex.org/I4210113371"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101955637","display_name":"Vincent Robert","orcid":"https://orcid.org/0000-0002-9370-4677","observed_orcids":["https://orcid.org/0000-0002-9370-4677"]},"institutions":[{"id":"https://openalex.org/I4210113371","display_name":"Westerdijk Fungal Biodiversity Institute","ror":"https://ror.org/030a5r161","country_code":"NL","type":"facility","lineage":["https://openalex.org/I1322597698","https://openalex.org/I4210113371"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Vincent Robert","raw_affiliation_strings":["Westerdijk Fungal Biodiversity Institute (WI-KNAW)"],"raw_orcid":"https://orcid.org/0000-0002-9370-4677","affiliations":[{"raw_affiliation_string":"Westerdijk Fungal Biodiversity Institute (WI-KNAW)","institution_ids":["https://openalex.org/I4210113371"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032002807","display_name":"Wieland Meyer","orcid":"https://orcid.org/0000-0001-9933-8340","observed_orcids":["https://orcid.org/0000-0001-9933-8340"]},"institutions":[{"id":"https://openalex.org/I4210113371","display_name":"Westerdijk Fungal Biodiversity Institute","ror":"https://ror.org/030a5r161","country_code":"NL","type":"facility","lineage":["https://openalex.org/I1322597698","https://openalex.org/I4210113371"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Wieland Meyer","raw_affiliation_strings":["Westerdijk Fungal Biodiversity Institute (WI-KNAW)"],"raw_orcid":"https://orcid.org/0000-0001-9933-8340","affiliations":[{"raw_affiliation_string":"Westerdijk Fungal Biodiversity Institute (WI-KNAW)","institution_ids":["https://openalex.org/I4210113371"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041682758","display_name":"J\u00f6rg Overmann","orcid":"https://orcid.org/0000-0003-3909-7201","observed_orcids":["https://orcid.org/0000-0003-3909-7201"]},"institutions":[{"id":"https://openalex.org/I4210165730","display_name":"Bavarian Natural History Collections","ror":"https://ror.org/05th1v540","country_code":"DE","type":"facility","lineage":["https://openalex.org/I4210165730"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"J\u00f6rg Overmann","raw_affiliation_strings":["SNSB- Staatliche Naturwissenschaftliche Sammlungen Bayerns"],"raw_orcid":"https://orcid.org/0000-0003-3909-7201","affiliations":[{"raw_affiliation_string":"SNSB- Staatliche Naturwissenschaftliche Sammlungen Bayerns","institution_ids":["https://openalex.org/I4210165730"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5007508762","display_name":"L.C. Reimer","orcid":"https://orcid.org/0000-0002-7805-0660","observed_orcids":["https://orcid.org/0000-0002-7805-0660"]},"institutions":[{"id":"https://openalex.org/I7935750","display_name":"Leibniz Institute DSMZ \u2013 German Collection of Microorganisms and Cell Cultures","ror":"https://ror.org/02tyer376","country_code":"DE","type":"facility","lineage":["https://openalex.org/I315704651","https://openalex.org/I7935750"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Lorenz C. Reimer","raw_affiliation_strings":["Leibniz Institute DSMZ \u2013 German Collection of Microorganisms and Cell Cultures"],"raw_orcid":"https://orcid.org/0000-0002-7805-0660","affiliations":[{"raw_affiliation_string":"Leibniz Institute DSMZ \u2013 German Collection of Microorganisms and Cell Cultures","institution_ids":["https://openalex.org/I7935750"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5007508762"],"corresponding_institution_ids":["https://openalex.org/I7935750"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"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/T11937","display_name":"Research Data Management Practices","score":0.9702000021934509,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T11937","display_name":"Research Data Management Practices","score":0.9702000021934509,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.01489999983459711,"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/T11986","display_name":"Scientific Computing and Data Management","score":0.00419999985024333,"subfield":{"id":"https://openalex.org/subfields/1802","display_name":"Information Systems and Management"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/microbial-strain-data","display_name":"microbial strain data","score":0.9369999766349792},{"id":"https://openalex.org/keywords/data-harmonization","display_name":"data harmonization","score":0.7480000257492065},{"id":"https://openalex.org/keywords/data-deduplication","display_name":"data deduplication","score":0.8349999785423279},{"id":"https://openalex.org/keywords/culture-collection","display_name":"culture collection","score":0.7609999775886536},{"id":"https://openalex.org/keywords/fair-principles","display_name":"FAIR principles","score":0.796999990940094},{"id":"https://openalex.org/keywords/machine-learning-training-data","display_name":"machine learning training data","score":0.6380000114440918}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7017999887466431},{"id":"https://openalex.org/C32587265","wikidata":"https://www.wikidata.org/wiki/Q1182260","display_name":"Data deduplication","level":2,"score":0.6779999732971191},{"id":"https://openalex.org/C154504017","wikidata":"https://www.wikidata.org/wiki/Q853614","display_name":"Identifier","level":2,"score":0.6026999950408936},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4514000117778778},{"id":"https://openalex.org/C174348530","wikidata":"https://www.wikidata.org/wiki/Q188635","display_name":"Bridging (networking)","level":2,"score":0.45010000467300415},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.4198000133037567},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.4088999927043915},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.3882000148296356},{"id":"https://openalex.org/C93518851","wikidata":"https://www.wikidata.org/wiki/Q180160","display_name":"Metadata","level":2,"score":0.3797999918460846},{"id":"https://openalex.org/C19443361","wikidata":"https://www.wikidata.org/wiki/Q5282533","display_name":"Disparate system","level":2,"score":0.36880001425743103},{"id":"https://openalex.org/C20136886","wikidata":"https://www.wikidata.org/wiki/Q749647","display_name":"Interoperability","level":2,"score":0.35899999737739563},{"id":"https://openalex.org/C115901376","wikidata":"https://www.wikidata.org/wiki/Q184199","display_name":"Automation","level":2,"score":0.33980000019073486},{"id":"https://openalex.org/C201797286","wikidata":"https://www.wikidata.org/wiki/Q4914986","display_name":"Biological data","level":2,"score":0.3321000039577484},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3319999873638153},{"id":"https://openalex.org/C13926793","wikidata":"https://www.wikidata.org/wiki/Q3507155","display_name":"Group method of data handling","level":2,"score":0.31700000166893005},{"id":"https://openalex.org/C91632574","wikidata":"https://www.wikidata.org/wiki/Q15088675","display_name":"Data curation","level":2,"score":0.31679999828338623},{"id":"https://openalex.org/C5655090","wikidata":"https://www.wikidata.org/wiki/Q192588","display_name":"Relational database","level":2,"score":0.3151000142097473},{"id":"https://openalex.org/C72634772","wikidata":"https://www.wikidata.org/wiki/Q386824","display_name":"Data integration","level":2,"score":0.31189998984336853},{"id":"https://openalex.org/C116409475","wikidata":"https://www.wikidata.org/wiki/Q1385056","display_name":"External Data Representation","level":2,"score":0.30820000171661377},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.2946999967098236},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.2930000126361847},{"id":"https://openalex.org/C206345919","wikidata":"https://www.wikidata.org/wiki/Q20380951","display_name":"Resource (disambiguation)","level":2,"score":0.2863999903202057},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.2858000099658966},{"id":"https://openalex.org/C79974875","wikidata":"https://www.wikidata.org/wiki/Q483639","display_name":"Cloud computing","level":2,"score":0.28540000319480896},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.2842000126838684},{"id":"https://openalex.org/C70061542","wikidata":"https://www.wikidata.org/wiki/Q989016","display_name":"Distributed database","level":2,"score":0.28299999237060547},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.27649998664855957},{"id":"https://openalex.org/C99613125","wikidata":"https://www.wikidata.org/wiki/Q165194","display_name":"Application programming interface","level":2,"score":0.2718000113964081},{"id":"https://openalex.org/C2780416260","wikidata":"https://www.wikidata.org/wiki/Q2063","display_name":"JSON","level":2,"score":0.27149999141693115},{"id":"https://openalex.org/C20901353","wikidata":"https://www.wikidata.org/wiki/Q4117139","display_name":"Biological database","level":2,"score":0.27059999108314514},{"id":"https://openalex.org/C2779965156","wikidata":"https://www.wikidata.org/wiki/Q5227350","display_name":"Data sharing","level":3,"score":0.2669999897480011},{"id":"https://openalex.org/C33762810","wikidata":"https://www.wikidata.org/wiki/Q461671","display_name":"Data integrity","level":2,"score":0.26080000400543213}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.64898/2026.09.09.750348","doi":"https://doi.org/10.64898/2026.09.09.750348","is_oa":true,"landing_page_url":"https://doi.org/10.64898/2026.09.09.750348","pdf_url":"https://www.biorxiv.org/content/biorxiv/early/2026/09/10/2026.09.09.750348.full.pdf","source":{"id":"https://openalex.org/S4306402567","display_name":"bioRxiv (Cold Spring Harbor Laboratory)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I2750212522","host_organization_name":"Cold Spring Harbor Laboratory","host_organization_lineage":["https://openalex.org/I2750212522"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"bioRxiv","raw_type":"posted-content"}],"best_oa_location":{"id":"doi:10.64898/2026.09.09.750348","doi":"https://doi.org/10.64898/2026.09.09.750348","is_oa":true,"landing_page_url":"https://doi.org/10.64898/2026.09.09.750348","pdf_url":"https://www.biorxiv.org/content/biorxiv/early/2026/09/10/2026.09.09.750348.full.pdf","source":{"id":"https://openalex.org/S4306402567","display_name":"bioRxiv (Cold Spring Harbor Laboratory)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I2750212522","host_organization_name":"Cold Spring Harbor Laboratory","host_organization_lineage":["https://openalex.org/I2750212522"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"bioRxiv","raw_type":"posted-content"},"sustainable_development_goals":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G3618239412","display_name":"NFDI4Microbiota  Nationale Forschungsdateninfrastruktur f\u00fcr MikrobiotaForschung","funder_award_id":"460129525","funder_id":"https://openalex.org/F4320320879","funder_display_name":"Deutsche Forschungsgemeinschaft"},{"id":"https://openalex.org/G402113476","display_name":"RI services to promote deep digitalization of Industrial Biotechnology - towards smart biomanufacturing","funder_award_id":"101094287","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"},{"id":"https://openalex.org/G7710879285","display_name":null,"funder_award_id":"NFDI4Microbiota","funder_id":"https://openalex.org/F4320320879","funder_display_name":"Deutsche Forschungsgemeinschaft"}],"funders":[{"id":"https://openalex.org/F4320320300","display_name":"European Commission","ror":"https://ror.org/00k4n6c32"},{"id":"https://openalex.org/F4320320879","display_name":"Deutsche Forschungsgemeinschaft","ror":"https://ror.org/018mejw64"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7212226483.pdf","grobid_xml":"https://content.openalex.org/works/W7212226483.grobid-xml"},"referenced_works_count":7,"referenced_works":["https://openalex.org/W2302501749","https://openalex.org/W4403924738","https://openalex.org/W4411114967","https://openalex.org/W4414509376","https://openalex.org/W6893164595","https://openalex.org/W6968400156","https://openalex.org/W7127159303"],"related_works":["https://openalex.org/W4414509376","https://openalex.org/W6929789373","https://openalex.org/W7082163075","https://openalex.org/W6949637002","https://openalex.org/W6911232586"],"abstract_inverted_index":{"Abstract":[0],"The":[1,87,180],"vast":[2],"amount":[3],"of":[4,19,26,47,53,130,149,175,239],"existing":[5,100,242],"data":[6,49,81,95,101,120,200],"on":[7,92,99,105,244],"microbial":[8,36,85,245],"strains":[9],"holds":[10],"immense":[11],"potential":[12],"to":[13,154,197,211,223,247],"revolutionize":[14],"bioindustry":[15],"through":[16],"the":[17,24,44,48,51,69,106,125,131,138,147,150,160,170,198,215,237,240],"application":[18],"Artificial":[20],"Intelligence":[21],"(AI).":[22],"However,":[23],"training":[25],"robust":[27],"predictive":[28],"AI":[29],"models":[30],"requires":[31],"large-scale,":[32],"unified,":[33],"and":[34,50,118,146,163,173,207,231],"non-redundant":[35],"datasets,":[37],"which":[38],"is":[39,103,186],"currently":[40],"severely":[41],"hindered":[42],"by":[43],"deep":[45],"fragmentation":[46],"existence":[52],"synonymous":[54,157],"strain":[55,158,226],"identifiers":[56],"in":[57,188,194],"different":[58],"culture":[59],"collections.":[60],"To":[61],"overcome":[62],"these":[63],"infrastructural":[64],"bottlenecks,":[65],"we":[66],"have":[67],"established":[68],"StrainDiscoveryDatabase":[70],"(SDD),":[71],"a":[72,189,218],"comprehensive,":[73],"machine-readable":[74],"dataset":[75,185],"encompassing":[76],"over":[77],"6.2":[78],"million":[79],"harmonized":[80],"points":[82],"for":[83],"256,889":[84],"strains.":[86],"SDD":[88,216],"does":[89],"not":[90],"rely":[91],"its":[93,164],"own":[94],"repository,":[96],"but":[97],"rather":[98],"that":[102],"retrieved":[104,123],"fly":[107],"from":[108,177],"highly":[109,190],"curated":[110],"databases.":[111],"Through":[112],"an":[113],"automated":[114],"pipeline":[115],"phenotypic,":[116],"genotypic,":[117],"contextual":[119],"are":[121,167],"systematically":[122],"via":[124],"Application":[126],"Programming":[127],"Interfaces":[128],"(APIs)":[129],"Bacterial":[132],"Diversity":[133],"database":[134,162,205],"(Bac":[135],"Dive":[136],"),":[137],"Microbial":[139],"Resource":[140],"Research":[141],"Infrastructure":[142],"Information":[143],"System":[144],"(MIRRI-IS)":[145],"catalogue":[148],"DSMZ.":[151],"In":[152],"order":[153],"reliably":[155],"resolve":[156],"identifiers,":[159],"StrainInfo":[161],"identification":[165],"tools":[166],"employed,":[168],"enabling":[169],"accurate":[171],"deduplication":[172],"unification":[174],"records":[176],"disparate":[178],"sources.":[179],"resulting":[181],"aggregated,":[182],"globally":[183],"unique":[184],"provided":[187],"standardized":[191],"JSON":[192],"format":[193],"strict":[195],"adherence":[196],"FAIR":[199],"principles.":[201],"By":[202],"bridging":[203],"isolated":[204],"silos":[206],"linking":[208],"distributed":[209],"knowledge":[210,243],"discrete":[212],"biological":[213],"entities,":[214],"provides":[217],"high-quality,":[219],"foundational":[220],"resource":[221],"designed":[222],"accelerate":[224],"trait-based":[225],"discovery,":[227],"large-scale":[228],"comparative":[229],"analysis,":[230],"machine":[232],"learning":[233],"applications,":[234],"thereby":[235],"supporting":[236],"translation":[238],"extensive":[241],"traits":[246],"bioindustrial":[248],"applications.":[249]},"counts_by_year":[],"updated_date":"2026-10-28T10:33:24.094632","created_date":"2026-09-12T00:00:00"}
