{"id":"https://openalex.org/W7213654166","doi":"https://doi.org/10.64898/2026.09.14.751540","title":"BGC Atlas v2: biosynthetic gene clusters with taxonomic and environmental context at scale","display_name":"BGC Atlas v2: biosynthetic gene clusters with taxonomic and environmental context at scale","publication_year":2026,"publication_date":"2026-09-18","ids":{"openalex":"https://openalex.org/W7213654166","doi":"https://doi.org/10.64898/2026.09.14.751540"},"language":"en","primary_location":{"id":"doi:10.64898/2026.09.14.751540","doi":"https://doi.org/10.64898/2026.09.14.751540","is_oa":true,"landing_page_url":"https://doi.org/10.64898/2026.09.14.751540","pdf_url":"https://www.biorxiv.org/content/biorxiv/early/2026/09/18/2026.09.14.751540.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":"submittedVersion","is_accepted":false,"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/2026/09/18/2026.09.14.751540.full.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5001761525","display_name":"Caner Ba\u011fc\u0131","orcid":"https://orcid.org/0000-0003-4428-9515","observed_orcids":["https://orcid.org/0000-0003-4428-9515"]},"institutions":[{"id":"https://openalex.org/I4210115305","display_name":"German Center for Infection Research","ror":"https://ror.org/028s4q594","country_code":"DE","type":"facility","lineage":["https://openalex.org/I4210115305","https://openalex.org/I4405256427"]},{"id":"https://openalex.org/I8087733","display_name":"University of T\u00fcbingen","ror":"https://ror.org/03a1kwz48","country_code":"DE","type":"education","lineage":["https://openalex.org/I8087733"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Caner Ba\u011fc\u0131","raw_affiliation_strings":["German Center for Infection Research (DZIF), Partner Site T\u00fcbingen, 72076 T\u00fcbingen, Germany","Interfaculty Institute for Biomedical Informatics (IBMI), University of T\u00fcbingen, Auf der Morgenstelle 24, 72076 T\u00fcbingen, Germany","Interfaculty Institute of Microbiology and Infection Medicine (IMIT), Translational Genome Mining for Natural Products, University of T\u00fcbingen, 72076 T\u00fcbingen, Germany"],"raw_orcid":"https://orcid.org/0000-0003-4428-9515","affiliations":[{"raw_affiliation_string":"German Center for Infection Research (DZIF), Partner Site T\u00fcbingen, 72076 T\u00fcbingen, Germany","institution_ids":["https://openalex.org/I4210115305"]},{"raw_affiliation_string":"Interfaculty Institute for Biomedical Informatics (IBMI), University of T\u00fcbingen, Auf der Morgenstelle 24, 72076 T\u00fcbingen, Germany","institution_ids":["https://openalex.org/I8087733"]},{"raw_affiliation_string":"Interfaculty Institute of Microbiology and Infection Medicine (IMIT), Translational Genome Mining for Natural Products, University of T\u00fcbingen, 72076 T\u00fcbingen, Germany","institution_ids":["https://openalex.org/I8087733"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5152197540","display_name":"Alec Talamas-Tanner","orcid":"https://orcid.org/0009-0004-6175-5041","observed_orcids":["https://orcid.org/0009-0004-6175-5041"]},"institutions":[{"id":"https://openalex.org/I4210115305","display_name":"German Center for Infection Research","ror":"https://ror.org/028s4q594","country_code":"DE","type":"facility","lineage":["https://openalex.org/I4210115305","https://openalex.org/I4405256427"]},{"id":"https://openalex.org/I8087733","display_name":"University of T\u00fcbingen","ror":"https://ror.org/03a1kwz48","country_code":"DE","type":"education","lineage":["https://openalex.org/I8087733"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Alec Talamas-Tanner","raw_affiliation_strings":["German Center for Infection Research (DZIF), Partner Site T\u00fcbingen, 72076 T\u00fcbingen, Germany","Interfaculty Institute for Biomedical Informatics (IBMI), University of T\u00fcbingen, Auf der Morgenstelle 24, 72076 T\u00fcbingen, Germany","Interfaculty Institute of Microbiology and Infection Medicine (IMIT), Translational Genome Mining for Natural Products, University of T\u00fcbingen, 72076 T\u00fcbingen, Germany"],"raw_orcid":"https://orcid.org/0009-0004-6175-5041","affiliations":[{"raw_affiliation_string":"German Center for Infection Research (DZIF), Partner Site T\u00fcbingen, 72076 T\u00fcbingen, Germany","institution_ids":["https://openalex.org/I4210115305"]},{"raw_affiliation_string":"Interfaculty Institute for Biomedical Informatics (IBMI), University of T\u00fcbingen, Auf der Morgenstelle 24, 72076 T\u00fcbingen, Germany","institution_ids":["https://openalex.org/I8087733"]},{"raw_affiliation_string":"Interfaculty Institute of Microbiology and Infection Medicine (IMIT), Translational Genome Mining for Natural Products, University of T\u00fcbingen, 72076 T\u00fcbingen, Germany","institution_ids":["https://openalex.org/I8087733"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5058692862","display_name":"Nadine Ziemert","orcid":"https://orcid.org/0000-0002-7264-1857","observed_orcids":["https://orcid.org/0000-0002-7264-1857"]},"institutions":[{"id":"https://openalex.org/I4210115305","display_name":"German Center for Infection Research","ror":"https://ror.org/028s4q594","country_code":"DE","type":"facility","lineage":["https://openalex.org/I4210115305","https://openalex.org/I4405256427"]},{"id":"https://openalex.org/I8087733","display_name":"University of T\u00fcbingen","ror":"https://ror.org/03a1kwz48","country_code":"DE","type":"education","lineage":["https://openalex.org/I8087733"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Nadine Ziemert","raw_affiliation_strings":["German Center for Infection Research (DZIF), Partner Site T\u00fcbingen, 72076 T\u00fcbingen, Germany","Interfaculty Institute for Biomedical Informatics (IBMI), University of T\u00fcbingen, Auf der Morgenstelle 24, 72076 T\u00fcbingen, Germany","Interfaculty Institute of Microbiology and Infection Medicine (IMIT), Translational Genome Mining for Natural Products, University of T\u00fcbingen, 72076 T\u00fcbingen, Germany"],"raw_orcid":"https://orcid.org/0000-0002-7264-1857","affiliations":[{"raw_affiliation_string":"German Center for Infection Research (DZIF), Partner Site T\u00fcbingen, 72076 T\u00fcbingen, Germany","institution_ids":["https://openalex.org/I4210115305"]},{"raw_affiliation_string":"Interfaculty Institute for Biomedical Informatics (IBMI), University of T\u00fcbingen, Auf der Morgenstelle 24, 72076 T\u00fcbingen, Germany","institution_ids":["https://openalex.org/I8087733"]},{"raw_affiliation_string":"Interfaculty Institute of Microbiology and Infection Medicine (IMIT), Translational Genome Mining for Natural Products, University of T\u00fcbingen, 72076 T\u00fcbingen, Germany","institution_ids":["https://openalex.org/I8087733"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5058692862"],"corresponding_institution_ids":["https://openalex.org/I4210115305","https://openalex.org/I8087733"],"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/T10252","display_name":"Microbial Natural Products and Biosynthesis","score":0.9994999766349792,"subfield":{"id":"https://openalex.org/subfields/2402","display_name":"Applied Microbiology and Biotechnology"},"field":{"id":"https://openalex.org/fields/24","display_name":"Immunology and Microbiology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},"topics":[{"id":"https://openalex.org/T10252","display_name":"Microbial Natural Products and Biosynthesis","score":0.9994999766349792,"subfield":{"id":"https://openalex.org/subfields/2402","display_name":"Applied Microbiology and Biotechnology"},"field":{"id":"https://openalex.org/fields/24","display_name":"Immunology and Microbiology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T10015","display_name":"Genomics and Phylogenetic Studies","score":9.999999747378752e-05,"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/T12673","display_name":"Microbial Metabolism and Applications","score":0.0,"subfield":{"id":"https://openalex.org/subfields/1305","display_name":"Biotechnology"},"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/biosynthetic-gene-clusters","display_name":"biosynthetic gene clusters","score":0.9990000128746033},{"id":"https://openalex.org/keywords/secondary-metabolites","display_name":"secondary metabolites","score":0.9070000052452087},{"id":"https://openalex.org/keywords/natural-products","display_name":"natural products","score":0.7039999961853027},{"id":"https://openalex.org/keywords/metagenome-assembled-genomes","display_name":"metagenome-assembled genomes","score":0.9120000004768372},{"id":"https://openalex.org/keywords/metagenomic-assembly","display_name":"metagenome assembly","score":0.7519999742507935},{"id":"https://openalex.org/keywords/taxonomic-classification","display_name":"taxonomic classification","score":0.5370000004768372},{"id":"https://openalex.org/keywords/environmental-metadata","display_name":"environmental metadata","score":0.9210000038146973},{"id":"https://openalex.org/keywords/protein-sequence-search","display_name":"protein sequence search","score":0.5239999890327454},{"id":"https://openalex.org/keywords/microbial-interactions","display_name":"microbial interactions","score":0.527999997138977}],"concepts":[{"id":"https://openalex.org/C15151743","wikidata":"https://www.wikidata.org/wiki/Q903778","display_name":"Metagenomics","level":3,"score":0.9057999849319458},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.7002000212669373},{"id":"https://openalex.org/C2776673561","wikidata":"https://www.wikidata.org/wiki/Q655357","display_name":"Atlas (anatomy)","level":2,"score":0.6191999912261963},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5715000033378601},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.5450000166893005},{"id":"https://openalex.org/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","level":1,"score":0.5311999917030334},{"id":"https://openalex.org/C141231307","wikidata":"https://www.wikidata.org/wiki/Q7020","display_name":"Genome","level":3,"score":0.45170000195503235},{"id":"https://openalex.org/C189592816","wikidata":"https://www.wikidata.org/wiki/Q427626","display_name":"Taxonomic rank","level":3,"score":0.4083999991416931},{"id":"https://openalex.org/C130217890","wikidata":"https://www.wikidata.org/wiki/Q47041","display_name":"Biodiversity","level":2,"score":0.398499995470047},{"id":"https://openalex.org/C71640776","wikidata":"https://www.wikidata.org/wiki/Q16521","display_name":"Taxon","level":2,"score":0.35030001401901245},{"id":"https://openalex.org/C90132467","wikidata":"https://www.wikidata.org/wiki/Q171184","display_name":"Phylogenetics","level":3,"score":0.3456000089645386},{"id":"https://openalex.org/C189206191","wikidata":"https://www.wikidata.org/wiki/Q222046","display_name":"Genomics","level":4,"score":0.33180001378059387},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.3244999945163727},{"id":"https://openalex.org/C193252679","wikidata":"https://www.wikidata.org/wiki/Q242125","display_name":"Phylogenetic tree","level":3,"score":0.31459999084472656},{"id":"https://openalex.org/C2781316041","wikidata":"https://www.wikidata.org/wiki/Q1230584","display_name":"Diversity (politics)","level":2,"score":0.3138999938964844},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.3050000071525574},{"id":"https://openalex.org/C143121216","wikidata":"https://www.wikidata.org/wiki/Q1330402","display_name":"Microbiome","level":2,"score":0.29670000076293945},{"id":"https://openalex.org/C18903297","wikidata":"https://www.wikidata.org/wiki/Q7150","display_name":"Ecology","level":1,"score":0.29159998893737793},{"id":"https://openalex.org/C2779188883","wikidata":"https://www.wikidata.org/wiki/Q82446","display_name":"Global Map","level":3,"score":0.27959999442100525},{"id":"https://openalex.org/C69562835","wikidata":"https://www.wikidata.org/wiki/Q3054637","display_name":"Microbial ecology","level":3,"score":0.2791999876499176},{"id":"https://openalex.org/C25147867","wikidata":"https://www.wikidata.org/wiki/Q36039","display_name":"Beta diversity","level":3,"score":0.2728999853134155},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.258899986743927},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.25450000166893005}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.64898/2026.09.14.751540","doi":"https://doi.org/10.64898/2026.09.14.751540","is_oa":true,"landing_page_url":"https://doi.org/10.64898/2026.09.14.751540","pdf_url":"https://www.biorxiv.org/content/biorxiv/early/2026/09/18/2026.09.14.751540.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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"bioRxiv","raw_type":"posted-content"}],"best_oa_location":{"id":"doi:10.64898/2026.09.14.751540","doi":"https://doi.org/10.64898/2026.09.14.751540","is_oa":true,"landing_page_url":"https://doi.org/10.64898/2026.09.14.751540","pdf_url":"https://www.biorxiv.org/content/biorxiv/early/2026/09/18/2026.09.14.751540.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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"bioRxiv","raw_type":"posted-content"},"sustainable_development_goals":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G5691959603","display_name":"HPC Forschungscluster","funder_award_id":"455787709","funder_id":"https://openalex.org/F4320320879","funder_display_name":"Deutsche Forschungsgemeinschaft"},{"id":"https://openalex.org/G6314704487","display_name":null,"funder_award_id":"0072511-00","funder_id":"https://openalex.org/F4320320882","funder_display_name":"Volkswagen Foundation"},{"id":"https://openalex.org/G9000385856","display_name":null,"funder_award_id":"09.726","funder_id":"https://openalex.org/F4320311052","funder_display_name":"Deutsches Zentrum f\u00fcr Infektionsforschung"},{"id":"https://openalex.org/G9000396911","display_name":"A Machine Learning-Driven Pipeline for Predicting and Producing Novel Antibiotics","funder_award_id":"0072511","funder_id":"https://openalex.org/F4320320882","funder_display_name":"Volkswagen Foundation"}],"funders":[{"id":"https://openalex.org/F4320311052","display_name":"Deutsches Zentrum f\u00fcr Infektionsforschung","ror":"https://ror.org/028s4q594"},{"id":"https://openalex.org/F4320320879","display_name":"Deutsche Forschungsgemeinschaft","ror":"https://ror.org/018mejw64"},{"id":"https://openalex.org/F4320320882","display_name":"Volkswagen Foundation","ror":"https://ror.org/03bsmfz84"},{"id":"https://openalex.org/F4320321112","display_name":"Eberhard Karls Universit\u00e4t T\u00fcbingen","ror":"https://ror.org/03a1kwz48"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7213654166.pdf","grobid_xml":"https://content.openalex.org/works/W7213654166.grobid-xml"},"referenced_works_count":41,"referenced_works":["https://openalex.org/W2011084061","https://openalex.org/W2028158620","https://openalex.org/W2521644033","https://openalex.org/W2953008890","https://openalex.org/W3011366455","https://openalex.org/W3019706413","https://openalex.org/W3021868763","https://openalex.org/W3096951695","https://openalex.org/W3104596207","https://openalex.org/W3137047737","https://openalex.org/W3143063265","https://openalex.org/W3165511231","https://openalex.org/W3205017888","https://openalex.org/W4225416490","https://openalex.org/W4283262943","https://openalex.org/W4310957810","https://openalex.org/W4388000969","https://openalex.org/W4388592083","https://openalex.org/W4391878823","https://openalex.org/W4403924741","https://openalex.org/W4405220977","https://openalex.org/W4406731845","https://openalex.org/W4407092397","https://openalex.org/W4409781688","https://openalex.org/W4411079183","https://openalex.org/W4412640188","https://openalex.org/W4415469270","https://openalex.org/W4415513318","https://openalex.org/W4415614933","https://openalex.org/W4415739021","https://openalex.org/W4416956300","https://openalex.org/W4416985723","https://openalex.org/W4417398509","https://openalex.org/W6887511650","https://openalex.org/W7124441413","https://openalex.org/W7125601577","https://openalex.org/W7130517564","https://openalex.org/W7171388573","https://openalex.org/W7203719083","https://openalex.org/W7203904780","https://openalex.org/W7206163306"],"related_works":["https://openalex.org/W4403924741","https://openalex.org/W3197817645","https://openalex.org/W2982582384","https://openalex.org/W3121081543","https://openalex.org/W2558253576","https://openalex.org/W6977023436","https://openalex.org/W2915392951","https://openalex.org/W3121296743","https://openalex.org/W4416759958","https://openalex.org/W4309066510"],"abstract_inverted_index":{"Abstract":[0],"Genomic":[1],"and":[2,28,36,72,95,107,129,132,145,158,166,174],"metagenomic":[3,99],"studies":[4],"have":[5,9],"revealed":[6],"that":[7],"microbes":[8],"the":[10,83],"capacity":[11],"to":[12,58,88,101,154],"produce":[13],"an":[14],"enormous":[15],"diversity":[16,63,148,171],"of":[17,34,46,168],"secondary":[18],"metabolites.":[19],"These":[20],"compounds":[21],"play":[22],"important":[23],"roles":[24],"in":[25],"microbial":[26],"interactions":[27],"are":[29],"also":[30,140],"a":[31,43],"major":[32],"source":[33],"medicines":[35],"other":[37],"useful":[38],"natural":[39],"products,":[40],"yet":[41],"only":[42],"small":[44],"fraction":[45],"this":[47,60],"biosynthetic":[48,66,147,170],"potential":[49],"has":[50],"been":[51],"experimentally":[52],"characterized.":[53],"BGC":[54,78,160,176],"Atlas":[55,79,161,177],"was":[56],"developed":[57],"explore":[59],"largely":[61],"uncharacterized":[62],"by":[64],"placing":[65],"gene":[67],"clusters":[68],"(BGCs)":[69],"into":[70],"genomic":[71],"environmental":[73,121,128],"context.":[74],"Here,":[75],"we":[76],"present":[77],"v2,":[80],"which":[81],"expands":[82],"collection":[84],"more":[85,89],"than":[86,90],"eightfold":[87],"16":[91],"million":[92],"predicted":[93],"BGCs":[94],"extends":[96],"it":[97],"from":[98],"assemblies":[100],"metagenome-assembled":[102],"genomes":[103,106],"(MAGs),":[104],"single-amplified":[105],"isolate":[108],"genomes.":[109],"The":[110],"new":[111],"release":[112],"provides":[113],"taxonomic":[114],"assignments":[115],"for":[116],"nearly":[117],"all":[118],"BGCs,":[119],"harmonized":[120],"metadata,":[122],"nested":[123],"searches":[124,134],"across":[125,172],"biosynthetic,":[126],"taxonomic,":[127],"geographic":[130],"properties,":[131],"protein-sequence":[133],"against":[135],"BGC-encoded":[136],"genes.":[137],"Its":[138],"scale":[139],"reveals":[141],"how":[142],"much":[143],"bacterial":[144],"archaeal":[146],"remains":[149],"unexplored.":[150],"By":[151],"connecting":[152],"pathways":[153],"related":[155],"families,":[156],"organisms":[157],"environments,":[159],"v2":[162,178],"supports":[163],"natural-product":[164],"discovery":[165],"investigations":[167],"prokaryotic":[169],"taxa":[173],"ecosystems.":[175],"is":[179],"freely":[180],"available":[181],"at":[182],"https://bgc-atlas.cs.uni-tuebingen.de":[183],".":[184]},"counts_by_year":[],"updated_date":"2026-11-09T13:22:03.289127","created_date":"2026-09-20T00:00:00"}