{"id":"https://openalex.org/W4319662820","doi":"https://doi.org/10.1371/journal.pcbi.1010462","title":"iPRESTO: Automated discovery of biosynthetic sub-clusters linked to specific natural product substructures","display_name":"iPRESTO: Automated discovery of biosynthetic sub-clusters linked to specific natural product substructures","publication_year":2023,"publication_date":"2023-02-09","ids":{"openalex":"https://openalex.org/W4319662820","doi":"https://doi.org/10.1371/journal.pcbi.1010462","pmid":"https://pubmed.ncbi.nlm.nih.gov/36758069"},"language":"en","primary_location":{"id":"doi:10.1371/journal.pcbi.1010462","is_oa":true,"landing_page_url":"https://doi.org/10.1371/journal.pcbi.1010462","pdf_url":"https://journals.plos.org/ploscompbiol/article/file?id=10.1371/journal.pcbi.1010462&type=printable","source":{"id":"https://openalex.org/S86033158","display_name":"PLoS Computational Biology","issn_l":"1553-734X","issn":["1553-734X","1553-7358"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310315706","host_organization_name":"Public Library of Science","host_organization_lineage":["https://openalex.org/P4310315706"],"host_organization_lineage_names":["Public Library of Science"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"PLOS Computational Biology","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://journals.plos.org/ploscompbiol/article/file?id=10.1371/journal.pcbi.1010462&type=printable","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5050633498","display_name":"Joris J. R. Louwen","orcid":"https://orcid.org/0000-0003-4887-9109"},"institutions":[{"id":"https://openalex.org/I913481162","display_name":"Wageningen University & Research","ror":"https://ror.org/04qw24q55","country_code":"NL","type":"education","lineage":["https://openalex.org/I913481162"]}],"countries":["NL"],"is_corresponding":true,"raw_author_name":"Joris J. R. Louwen","raw_affiliation_strings":["Bioinformatics Group, Wageningen University, Wageningen, the Netherlands"],"raw_orcid":"https://orcid.org/0000-0003-4887-9109","affiliations":[{"raw_affiliation_string":"Bioinformatics Group, Wageningen University, Wageningen, the Netherlands","institution_ids":["https://openalex.org/I913481162"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003484549","display_name":"Satria A. Kautsar","orcid":"https://orcid.org/0000-0002-9815-511X"},"institutions":[{"id":"https://openalex.org/I913481162","display_name":"Wageningen University & Research","ror":"https://ror.org/04qw24q55","country_code":"NL","type":"education","lineage":["https://openalex.org/I913481162"]}],"countries":["NL"],"is_corresponding":true,"raw_author_name":"Satria A. Kautsar","raw_affiliation_strings":["Bioinformatics Group, Wageningen University, Wageningen, the Netherlands"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Bioinformatics Group, Wageningen University, Wageningen, the Netherlands","institution_ids":["https://openalex.org/I913481162"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014623878","display_name":"Sven van der Burg","orcid":"https://orcid.org/0000-0003-1250-6968"},"institutions":[{"id":"https://openalex.org/I4210095242","display_name":"Netherlands eScience Center","ror":"https://ror.org/00rbjv475","country_code":"NL","type":"funder","lineage":["https://openalex.org/I2800991832","https://openalex.org/I4210090210","https://openalex.org/I4210095242"]}],"countries":["NL"],"is_corresponding":true,"raw_author_name":"Sven van der Burg","raw_affiliation_strings":["Netherlands eScience Center, Amsterdam, the Netherlands"],"raw_orcid":"https://orcid.org/0000-0003-1250-6968","affiliations":[{"raw_affiliation_string":"Netherlands eScience Center, Amsterdam, the Netherlands","institution_ids":["https://openalex.org/I4210095242"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034845813","display_name":"Marnix H. Medema","orcid":"https://orcid.org/0000-0002-2191-2821"},"institutions":[{"id":"https://openalex.org/I913481162","display_name":"Wageningen University & Research","ror":"https://ror.org/04qw24q55","country_code":"NL","type":"education","lineage":["https://openalex.org/I913481162"]}],"countries":["NL"],"is_corresponding":true,"raw_author_name":"Marnix H. Medema","raw_affiliation_strings":["Bioinformatics Group, Wageningen University, Wageningen, the Netherlands"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Bioinformatics Group, Wageningen University, Wageningen, the Netherlands","institution_ids":["https://openalex.org/I913481162"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5075156076","display_name":"Justin J. J. van der Hooft","orcid":"https://orcid.org/0000-0002-9340-5511"},"institutions":[{"id":"https://openalex.org/I24027795","display_name":"University of Johannesburg","ror":"https://ror.org/04z6c2n17","country_code":"ZA","type":"education","lineage":["https://openalex.org/I24027795"]},{"id":"https://openalex.org/I913481162","display_name":"Wageningen University & Research","ror":"https://ror.org/04qw24q55","country_code":"NL","type":"education","lineage":["https://openalex.org/I913481162"]}],"countries":["NL","ZA"],"is_corresponding":true,"raw_author_name":"Justin J. J. van der Hooft","raw_affiliation_strings":["Bioinformatics Group, Wageningen University, Wageningen, the Netherlands","Department of Biochemistry, University of Johannesburg, Johannesburg, South Africa"],"raw_orcid":"https://orcid.org/0000-0002-9340-5511","affiliations":[{"raw_affiliation_string":"Bioinformatics Group, Wageningen University, Wageningen, the Netherlands","institution_ids":["https://openalex.org/I913481162"]},{"raw_affiliation_string":"Department of Biochemistry, University of Johannesburg, Johannesburg, South Africa","institution_ids":["https://openalex.org/I24027795"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5003484549","https://openalex.org/A5014623878","https://openalex.org/A5034845813","https://openalex.org/A5050633498","https://openalex.org/A5075156076"],"corresponding_institution_ids":["https://openalex.org/I24027795","https://openalex.org/I4210095242","https://openalex.org/I913481162"],"apc_list":{"value":2655,"currency":"USD","value_usd":2655},"apc_paid":{"value":2655,"currency":"USD","value_usd":2655},"fwci":3.0677,"has_fulltext":true,"cited_by_count":14,"citation_normalized_percentile":{"value":0.90541282,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":"19","issue":"2","first_page":"e1010462","last_page":"e1010462"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10252","display_name":"Microbial Natural Products and Biosynthesis","score":0.9998000264167786,"subfield":{"id":"https://openalex.org/subfields/2736","display_name":"Pharmacology"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},"topics":[{"id":"https://openalex.org/T10252","display_name":"Microbial Natural Products and Biosynthesis","score":0.9998000264167786,"subfield":{"id":"https://openalex.org/subfields/2736","display_name":"Pharmacology"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},{"id":"https://openalex.org/T11882","display_name":"Plant biochemistry and biosynthesis","score":0.9951000213623047,"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":0.9947999715805054,"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/computational-biology","display_name":"Computational biology","score":0.6539002060890198},{"id":"https://openalex.org/keywords/natural-product","display_name":"Natural product","score":0.5472131371498108},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.5017948150634766},{"id":"https://openalex.org/keywords/encode","display_name":"ENCODE","score":0.4999663829803467},{"id":"https://openalex.org/keywords/gene","display_name":"Gene","score":0.4861852526664734},{"id":"https://openalex.org/keywords/cluster","display_name":"Cluster (spacecraft)","score":0.4835052788257599},{"id":"https://openalex.org/keywords/genome","display_name":"Genome","score":0.4532736837863922},{"id":"https://openalex.org/keywords/gene-cluster","display_name":"Gene cluster","score":0.45218226313591003},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.4022192358970642},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.3919660747051239},{"id":"https://openalex.org/keywords/genetics","display_name":"Genetics","score":0.27043116092681885},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.09155058860778809},{"id":"https://openalex.org/keywords/biochemistry","display_name":"Biochemistry","score":0.07941046357154846}],"concepts":[{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.6539002060890198},{"id":"https://openalex.org/C2779396153","wikidata":"https://www.wikidata.org/wiki/Q901227","display_name":"Natural product","level":2,"score":0.5472131371498108},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.5017948150634766},{"id":"https://openalex.org/C66746571","wikidata":"https://www.wikidata.org/wiki/Q1134833","display_name":"ENCODE","level":3,"score":0.4999663829803467},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.4861852526664734},{"id":"https://openalex.org/C164866538","wikidata":"https://www.wikidata.org/wiki/Q367351","display_name":"Cluster (spacecraft)","level":2,"score":0.4835052788257599},{"id":"https://openalex.org/C141231307","wikidata":"https://www.wikidata.org/wiki/Q7020","display_name":"Genome","level":3,"score":0.4532736837863922},{"id":"https://openalex.org/C36857842","wikidata":"https://www.wikidata.org/wiki/Q1501261","display_name":"Gene cluster","level":3,"score":0.45218226313591003},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4022192358970642},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.3919660747051239},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.27043116092681885},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.09155058860778809},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.07941046357154846},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[{"descriptor_ui":"D001419","descriptor_name":"Bacteria","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D001419","descriptor_name":"Bacteria","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D001419","descriptor_name":"Bacteria","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D001688","descriptor_name":"Biological Products","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D001688","descriptor_name":"Biological Products","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D001688","descriptor_name":"Biological Products","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D005810","descriptor_name":"Multigene Family","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D005810","descriptor_name":"Multigene Family","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D005810","descriptor_name":"Multigene Family","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D053719","descriptor_name":"Tandem Mass Spectrometry","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D053719","descriptor_name":"Tandem Mass Spectrometry","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D053719","descriptor_name":"Tandem Mass Spectrometry","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D055432","descriptor_name":"Metabolomics","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D055432","descriptor_name":"Metabolomics","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D055432","descriptor_name":"Metabolomics","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false}],"locations_count":6,"locations":[{"id":"doi:10.1371/journal.pcbi.1010462","is_oa":true,"landing_page_url":"https://doi.org/10.1371/journal.pcbi.1010462","pdf_url":"https://journals.plos.org/ploscompbiol/article/file?id=10.1371/journal.pcbi.1010462&type=printable","source":{"id":"https://openalex.org/S86033158","display_name":"PLoS Computational Biology","issn_l":"1553-734X","issn":["1553-734X","1553-7358"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310315706","host_organization_name":"Public Library of Science","host_organization_lineage":["https://openalex.org/P4310315706"],"host_organization_lineage_names":["Public Library of Science"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"PLOS Computational Biology","raw_type":"journal-article"},{"id":"pmid:36758069","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/36758069","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"PLoS computational biology","raw_type":null},{"id":"pmh:oai:library.wur.nl:wurpubs/611664","is_oa":true,"landing_page_url":"https://research.wur.nl/en/publications/ipresto-automated-discovery-of-biosynthetic-sub-clusters-linked-t","pdf_url":"https://edepot.wur.nl/588764","source":{"id":"https://openalex.org/S4210201231","display_name":"Socio-Environmental Systems Modeling","issn_l":"2663-3027","issn":["2663-3027"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"ISSN: 1553-734X","raw_type":"Article/Letter to editor"},{"id":"pmh:oai:pubmedcentral.nih.gov:9946207","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/9946207","pdf_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC9946207/pdf/pcbi.1010462.pdf","source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"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":"PLoS Comput Biol","raw_type":"Text"},{"id":"pmh:oai:RePEc:plo:pcbi00:1010462","is_oa":false,"landing_page_url":"https://journals.plos.org/ploscompbiol/article?id=10.1371/journal.pcbi.1010462","pdf_url":null,"source":{"id":"https://openalex.org/S4306401271","display_name":"RePEc: Research Papers in Economics","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I77793887","host_organization_name":"Federal Reserve Bank of St. Louis","host_organization_lineage":["https://openalex.org/I77793887"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article"},{"id":"pmh:oai:doaj.org/article:419ecef4d2274796a4183bc7e93ac229","is_oa":true,"landing_page_url":"https://doaj.org/article/419ecef4d2274796a4183bc7e93ac229","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"PLoS Computational Biology, Vol 19, Iss 2, p e1010462 (2023)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1371/journal.pcbi.1010462","is_oa":true,"landing_page_url":"https://doi.org/10.1371/journal.pcbi.1010462","pdf_url":"https://journals.plos.org/ploscompbiol/article/file?id=10.1371/journal.pcbi.1010462&type=printable","source":{"id":"https://openalex.org/S86033158","display_name":"PLoS Computational Biology","issn_l":"1553-734X","issn":["1553-734X","1553-7358"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310315706","host_organization_name":"Public Library of Science","host_organization_lineage":["https://openalex.org/P4310315706"],"host_organization_lineage_names":["Public Library of Science"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"PLOS Computational Biology","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.4399999976158142,"display_name":"Responsible consumption and production","id":"https://metadata.un.org/sdg/12"}],"awards":[{"id":"https://openalex.org/G1078236034","display_name":null,"funder_award_id":"NLESC.OEC.2021.002","funder_id":"https://openalex.org/F4320314239","funder_display_name":"Netherlands eScience Center"},{"id":"https://openalex.org/G4368164343","display_name":null,"funder_award_id":"ASDI.2017.030","funder_id":"https://openalex.org/F4320314239","funder_display_name":"Netherlands eScience Center"},{"id":"https://openalex.org/G6800288988","display_name":null,"funder_award_id":"2017.030","funder_id":"https://openalex.org/F4320314239","funder_display_name":"Netherlands eScience Center"}],"funders":[{"id":"https://openalex.org/F4320314239","display_name":"Netherlands eScience Center","ror":"https://ror.org/00rbjv475"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4319662820.pdf","grobid_xml":"https://content.openalex.org/works/W4319662820.grobid-xml"},"referenced_works_count":56,"referenced_works":["https://openalex.org/W168564468","https://openalex.org/W1596515083","https://openalex.org/W1989920626","https://openalex.org/W1989963383","https://openalex.org/W2006604775","https://openalex.org/W2009257824","https://openalex.org/W2013805051","https://openalex.org/W2013908820","https://openalex.org/W2014874550","https://openalex.org/W2033618948","https://openalex.org/W2037417378","https://openalex.org/W2038043464","https://openalex.org/W2041537722","https://openalex.org/W2049735624","https://openalex.org/W2050028164","https://openalex.org/W2064073012","https://openalex.org/W2101234009","https://openalex.org/W2102652793","https://openalex.org/W2116007667","https://openalex.org/W2126714764","https://openalex.org/W2129911187","https://openalex.org/W2145974700","https://openalex.org/W2158301078","https://openalex.org/W2165599843","https://openalex.org/W2170328021","https://openalex.org/W2551876238","https://openalex.org/W2556797268","https://openalex.org/W2587991145","https://openalex.org/W2611021352","https://openalex.org/W2626886916","https://openalex.org/W2749132107","https://openalex.org/W2893448478","https://openalex.org/W2898402099","https://openalex.org/W2905116739","https://openalex.org/W2912880347","https://openalex.org/W2944443413","https://openalex.org/W2956419562","https://openalex.org/W2980832688","https://openalex.org/W2984933828","https://openalex.org/W2990471452","https://openalex.org/W3024192869","https://openalex.org/W3095583226","https://openalex.org/W3096851604","https://openalex.org/W3107629351","https://openalex.org/W3121081543","https://openalex.org/W3158208374","https://openalex.org/W3161596995","https://openalex.org/W3194396730","https://openalex.org/W4213445088","https://openalex.org/W4231510805","https://openalex.org/W4286785973","https://openalex.org/W4317811065","https://openalex.org/W6639619044","https://openalex.org/W6675354045","https://openalex.org/W6680848828","https://openalex.org/W6684489972"],"related_works":["https://openalex.org/W2468279273","https://openalex.org/W2354198838","https://openalex.org/W1989130879","https://openalex.org/W2103419012","https://openalex.org/W2988126442","https://openalex.org/W1974414866","https://openalex.org/W2057568687","https://openalex.org/W2063982682","https://openalex.org/W2338543196","https://openalex.org/W1544691147"],"abstract_inverted_index":{"Microbial":[0],"specialised":[1],"metabolism":[2],"is":[3],"full":[4],"of":[5,37,40,51,69,131,156,159,179,191,203,252,284,290],"valuable":[6],"natural":[7,58,71,82,301],"products":[8],"that":[9,18,45],"are":[10,22,46,113],"applied":[11],"clinically,":[12],"agriculturally,":[13],"and":[14,73,94,122,153,224,281],"industrially.":[15],"The":[16],"genes":[17,42],"encode":[19],"their":[20,294],"biosynthesis":[21,50,226],"often":[23],"physically":[24],"clustered":[25],"on":[26,120,150,213],"the":[27,49,67,180,192,204,220,276],"genome":[28],"in":[29,56,208,233,259],"biosynthetic":[30],"gene":[31,296],"clusters":[32],"(BGCs).":[33],"Many":[34],"BGCs":[35,172,221,261,286],"consist":[36],"multiple":[38],"groups":[39],"co-evolving":[41],"called":[43,147],"sub-clusters":[44,133,168,207,267],"responsible":[47],"for":[48,80,90,108,143,189,222,243,249,278],"a":[52,57,70,140,177,187,240,250],"specific":[53],"chemical":[54,92],"moiety":[55],"product.":[59],"Sub-clusters":[60],"therefore":[61],"provide":[62],"an":[63,127],"important":[64],"link":[65],"between":[66],"structures":[68,84,93],"product":[72,83,302],"its":[74],"BGC,":[75],"which":[76],"can":[77,257],"be":[78],"leveraged":[79],"predicting":[81],"from":[85,173],"sequence,":[86],"as":[87,89,236,238],"well":[88,237],"linking":[91,260,289],"metabolomics-derived":[95],"mass":[96],"features":[97],"to":[98,134,166,200,262,268,293],"BGCs.":[99,194,211],"While":[100],"some":[101],"initial":[102],"computational":[103],"methodologies":[104],"have":[105,116],"been":[106,118,231],"devised":[107],"sub-cluster":[109,145,182],"detection,":[110,146],"current":[111],"approaches":[112],"not":[114,229],"scalable,":[115],"only":[117],"run":[119],"small":[121],"outdated":[123],"datasets,":[124],"or":[125],"produce":[126],"impractically":[128],"large":[129],"number":[130],"possible":[132],"mine":[135,167],"through.":[136],"Here,":[137],"we":[138,184,216,247],"constructed":[139],"scalable":[141],"method":[142,197],"unsupervised":[144],"iPRESTO,":[148],"based":[149],"topic":[151],"modelling":[152],"statistical":[154],"analysis":[155],"co-occurrence":[157],"patterns":[158],"enzyme-coding":[160],"protein":[161],"families.":[162],"iPRESTO":[163],"was":[164,198],"used":[165],"across":[169],"150,000":[170],"prokaryotic":[171],"antiSMASH-DB.":[174],"After":[175],"annotating":[176],"fraction":[178],"resulting":[181],"families,":[183],"could":[185,217],"predict":[186],"substructure":[188,271],"16%":[190],"antiSMASH-DB":[193],"Additionally,":[195,246],"our":[196],"able":[199],"confirm":[201],"83%":[202],"experimentally":[205],"characterised":[206],"MIBiG":[209],"reference":[210],"Based":[212],"iPRESTO-detected":[214,266],"sub-clusters,":[215],"correctly":[218],"identify":[219],"xenorhabdin":[223],"salbostatin":[225],"(which":[227],"had":[228],"yet":[230],"annotated":[232],"BGC":[234,242],"databases),":[235],"propose":[239],"candidate":[241],"akashin":[244],"biosynthesis.":[245],"show":[248],"collection":[251],"145":[253],"actinobacteria":[254],"how":[255],"substructures":[256],"aid":[258],"molecules":[263,292],"by":[264,287],"correlating":[265],"MS/MS-derived":[269],"Mass2Motifs":[270],"patterns.":[272],"This":[273],"work":[274],"paves":[275],"way":[277],"deeper":[279],"functional":[280],"structural":[282],"annotation":[283],"microbial":[285],"improved":[288],"orphan":[291],"cognate":[295],"clusters,":[297],"thus":[298],"facilitating":[299],"accelerated":[300],"discovery.":[303]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":1}],"updated_date":"2026-05-06T08:25:59.206177","created_date":"2025-10-10T00:00:00"}