{"id":"https://openalex.org/W4377861946","doi":"https://doi.org/10.1371/journal.pcbi.1011162","title":"Deep self-supervised learning for biosynthetic gene cluster detection and product classification","display_name":"Deep self-supervised learning for biosynthetic gene cluster detection and product classification","publication_year":2023,"publication_date":"2023-05-23","ids":{"openalex":"https://openalex.org/W4377861946","doi":"https://doi.org/10.1371/journal.pcbi.1011162","pmid":"https://pubmed.ncbi.nlm.nih.gov/37220151"},"language":"en","primary_location":{"id":"doi:10.1371/journal.pcbi.1011162","is_oa":true,"landing_page_url":"https://doi.org/10.1371/journal.pcbi.1011162","pdf_url":"https://journals.plos.org/ploscompbiol/article/file?id=10.1371/journal.pcbi.1011162&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.1011162&type=printable","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5042893509","display_name":"Carolina Rios-Martinez","orcid":"https://orcid.org/0000-0001-6927-2256"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]},{"id":"https://openalex.org/I4400600948","display_name":"Microsoft Research New England (United States)","ror":"https://ror.org/010wkqn50","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4400600948"]},{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Carolina Rios-Martinez","raw_affiliation_strings":["Department of Bioengineering, Stanford University, Stanford, California, United States of America","Microsoft Research New England, Cambridge, Massachusetts, United States of America"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Bioengineering, Stanford University, Stanford, California, United States of America","institution_ids":["https://openalex.org/I97018004"]},{"raw_affiliation_string":"Microsoft Research New England, Cambridge, Massachusetts, United States of America","institution_ids":["https://openalex.org/I1290206253","https://openalex.org/I4400600948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010673369","display_name":"Nicholas Bhattacharya","orcid":"https://orcid.org/0000-0003-1697-7177"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]},{"id":"https://openalex.org/I4400600948","display_name":"Microsoft Research New England (United States)","ror":"https://ror.org/010wkqn50","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4400600948"]},{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Nicholas Bhattacharya","raw_affiliation_strings":["Department of Mathematics, University of California, Berkeley, Berkeley, California, United States of America","Microsoft Research New England, Cambridge, Massachusetts, United States of America"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Mathematics, University of California, Berkeley, Berkeley, California, United States of America","institution_ids":["https://openalex.org/I95457486"]},{"raw_affiliation_string":"Microsoft Research New England, Cambridge, Massachusetts, United States of America","institution_ids":["https://openalex.org/I1290206253","https://openalex.org/I4400600948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071306257","display_name":"Ava P. Amini","orcid":"https://orcid.org/0000-0002-8601-6040"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]},{"id":"https://openalex.org/I4400600948","display_name":"Microsoft Research New England (United States)","ror":"https://ror.org/010wkqn50","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4400600948"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Ava P. Amini","raw_affiliation_strings":["Microsoft Research New England, Cambridge, Massachusetts, United States of America"],"raw_orcid":"https://orcid.org/0000-0002-8601-6040","affiliations":[{"raw_affiliation_string":"Microsoft Research New England, Cambridge, Massachusetts, United States of America","institution_ids":["https://openalex.org/I1290206253","https://openalex.org/I4400600948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033244104","display_name":"Lorin Crawford","orcid":"https://orcid.org/0000-0003-0178-8242"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]},{"id":"https://openalex.org/I4400600948","display_name":"Microsoft Research New England (United States)","ror":"https://ror.org/010wkqn50","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4400600948"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Lorin Crawford","raw_affiliation_strings":["Microsoft Research New England, Cambridge, Massachusetts, United States of America"],"raw_orcid":"https://orcid.org/0000-0003-0178-8242","affiliations":[{"raw_affiliation_string":"Microsoft Research New England, Cambridge, Massachusetts, United States of America","institution_ids":["https://openalex.org/I1290206253","https://openalex.org/I4400600948"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5060834723","display_name":"Kevin Yang","orcid":"https://orcid.org/0000-0001-9045-6826"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]},{"id":"https://openalex.org/I4400600948","display_name":"Microsoft Research New England (United States)","ror":"https://ror.org/010wkqn50","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4400600948"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Kevin K. Yang","raw_affiliation_strings":["Microsoft Research New England, Cambridge, Massachusetts, United States of America"],"raw_orcid":"https://orcid.org/0000-0001-9045-6826","affiliations":[{"raw_affiliation_string":"Microsoft Research New England, Cambridge, Massachusetts, United States of America","institution_ids":["https://openalex.org/I1290206253","https://openalex.org/I4400600948"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5010673369","https://openalex.org/A5033244104","https://openalex.org/A5042893509","https://openalex.org/A5060834723","https://openalex.org/A5071306257"],"corresponding_institution_ids":["https://openalex.org/I1290206253","https://openalex.org/I4400600948","https://openalex.org/I95457486","https://openalex.org/I97018004"],"apc_list":{"value":2655,"currency":"USD","value_usd":2655},"apc_paid":{"value":2655,"currency":"USD","value_usd":2655},"fwci":5.6694,"has_fulltext":true,"cited_by_count":40,"citation_normalized_percentile":{"value":0.96602916,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":"19","issue":"5","first_page":"e1011162","last_page":"e1011162"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.9993000030517578,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},"topics":[{"id":"https://openalex.org/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.9993000030517578,"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/T10252","display_name":"Microbial Natural Products and Biosynthesis","score":0.9993000030517578,"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/T12254","display_name":"Machine Learning in Bioinformatics","score":0.9957000017166138,"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/computational-biology","display_name":"Computational biology","score":0.6132646203041077},{"id":"https://openalex.org/keywords/genome","display_name":"Genome","score":0.5952655673027039},{"id":"https://openalex.org/keywords/natural-product","display_name":"Natural product","score":0.5410541296005249},{"id":"https://openalex.org/keywords/gene","display_name":"Gene","score":0.5214966535568237},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.4532521665096283},{"id":"https://openalex.org/keywords/supervised-learning","display_name":"Supervised learning","score":0.43271058797836304},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.38107830286026},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.36299747228622437},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.3013010323047638},{"id":"https://openalex.org/keywords/genetics","display_name":"Genetics","score":0.21466714143753052}],"concepts":[{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.6132646203041077},{"id":"https://openalex.org/C141231307","wikidata":"https://www.wikidata.org/wiki/Q7020","display_name":"Genome","level":3,"score":0.5952655673027039},{"id":"https://openalex.org/C2779396153","wikidata":"https://www.wikidata.org/wiki/Q901227","display_name":"Natural product","level":2,"score":0.5410541296005249},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.5214966535568237},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.4532521665096283},{"id":"https://openalex.org/C136389625","wikidata":"https://www.wikidata.org/wiki/Q334384","display_name":"Supervised learning","level":3,"score":0.43271058797836304},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.38107830286026},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.36299747228622437},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.3013010323047638},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.21466714143753052},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0}],"mesh":[{"descriptor_ui":"D000069553","descriptor_name":"Supervised Machine Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000069553","descriptor_name":"Supervised Machine Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000069553","descriptor_name":"Supervised Machine Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000069553","descriptor_name":"Supervised Machine Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D001688","descriptor_name":"Biological Products","qualifier_ui":"Q000378","qualifier_name":"metabolism","is_major_topic":true},{"descriptor_ui":"D001688","descriptor_name":"Biological Products","qualifier_ui":"Q000378","qualifier_name":"metabolism","is_major_topic":true},{"descriptor_ui":"D001688","descriptor_name":"Biological Products","qualifier_ui":"Q000378","qualifier_name":"metabolism","is_major_topic":true},{"descriptor_ui":"D001688","descriptor_name":"Biological Products","qualifier_ui":"Q000378","qualifier_name":"metabolism","is_major_topic":true},{"descriptor_ui":"D005810","descriptor_name":"Multigene Family","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D005810","descriptor_name":"Multigene Family","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D005810","descriptor_name":"Multigene Family","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D005810","descriptor_name":"Multigene Family","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D016680","descriptor_name":"Genome, Bacterial","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D016680","descriptor_name":"Genome, Bacterial","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D016680","descriptor_name":"Genome, Bacterial","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D016680","descriptor_name":"Genome, Bacterial","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D054892","descriptor_name":"Metagenome","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D054892","descriptor_name":"Metagenome","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D054892","descriptor_name":"Metagenome","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D054892","descriptor_name":"Metagenome","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false}],"locations_count":4,"locations":[{"id":"doi:10.1371/journal.pcbi.1011162","is_oa":true,"landing_page_url":"https://doi.org/10.1371/journal.pcbi.1011162","pdf_url":"https://journals.plos.org/ploscompbiol/article/file?id=10.1371/journal.pcbi.1011162&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:37220151","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/37220151","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:pubmedcentral.nih.gov:10241353","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/10241353","pdf_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC10241353/pdf/pcbi.1011162.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:doaj.org/article:d54c16375c8f498aace42016b43edaf3","is_oa":true,"landing_page_url":"https://doaj.org/article/d54c16375c8f498aace42016b43edaf3","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 5, p e1011162 (2023)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1371/journal.pcbi.1011162","is_oa":true,"landing_page_url":"https://doi.org/10.1371/journal.pcbi.1011162","pdf_url":"https://journals.plos.org/ploscompbiol/article/file?id=10.1371/journal.pcbi.1011162&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":0.5699999928474426,"display_name":"Industry, innovation and infrastructure","id":"https://metadata.un.org/sdg/9"}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4377861946.pdf","grobid_xml":"https://content.openalex.org/works/W4377861946.grobid-xml"},"referenced_works_count":47,"referenced_works":["https://openalex.org/W2009257824","https://openalex.org/W2143485490","https://openalex.org/W2145974700","https://openalex.org/W2147526198","https://openalex.org/W2151831732","https://openalex.org/W2156226201","https://openalex.org/W2187810943","https://openalex.org/W2256742438","https://openalex.org/W2332821092","https://openalex.org/W2410975458","https://openalex.org/W2611021352","https://openalex.org/W2896134881","https://openalex.org/W2899779000","https://openalex.org/W2915392951","https://openalex.org/W2951433247","https://openalex.org/W2967688728","https://openalex.org/W2970971581","https://openalex.org/W2971227267","https://openalex.org/W2980832688","https://openalex.org/W2999211744","https://openalex.org/W3010387158","https://openalex.org/W3040739508","https://openalex.org/W3111174583","https://openalex.org/W3127238141","https://openalex.org/W3146944767","https://openalex.org/W3161596995","https://openalex.org/W3165163830","https://openalex.org/W3171689166","https://openalex.org/W3174477824","https://openalex.org/W3177500196","https://openalex.org/W3179485843","https://openalex.org/W3186612807","https://openalex.org/W3202686461","https://openalex.org/W3211728297","https://openalex.org/W3213545574","https://openalex.org/W4205773061","https://openalex.org/W4210702584","https://openalex.org/W4213095938","https://openalex.org/W4220691725","https://openalex.org/W4220931862","https://openalex.org/W4280491725","https://openalex.org/W4281287617","https://openalex.org/W4288066876","https://openalex.org/W4290546063","https://openalex.org/W4388024559","https://openalex.org/W4392302569","https://openalex.org/W6682627296"],"related_works":["https://openalex.org/W2086525401","https://openalex.org/W2006735166","https://openalex.org/W2079327011","https://openalex.org/W2053325634","https://openalex.org/W2968368302","https://openalex.org/W3178279768","https://openalex.org/W193851735","https://openalex.org/W2414309485","https://openalex.org/W2773861473","https://openalex.org/W1971903861"],"abstract_inverted_index":{"Natural":[0],"products":[1,20],"are":[2,21,57],"chemical":[3],"compounds":[4],"that":[5,116],"form":[6],"the":[7,14,98],"basis":[8],"of":[9,25,43,55,83,100,123],"many":[10],"therapeutics":[11],"used":[12],"in":[13,35,110,131],"pharmaceutical":[15],"industry.":[16],"In":[17],"microbes,":[18],"natural":[19],"synthesized":[22],"by":[23],"groups":[24],"colocalized":[26],"genes":[27],"called":[28],"biosynthetic":[29],"gene":[30],"clusters":[31],"(BGCs).":[32],"With":[33],"advances":[34],"high-throughput":[36],"sequencing,":[37],"there":[38],"has":[39],"been":[40],"an":[41],"increase":[42],"complete":[44],"microbial":[45,132],"isolate":[46],"genomes":[47],"and":[48,69,87,106,125,134,153],"metagenomes,":[49],"from":[50,72],"which":[51],"a":[52,62,89,146],"vast":[53],"number":[54],"BGCs":[56,71,80,105,124,130],"undiscovered.":[58],"Here,":[59],"we":[60,78],"introduce":[61],"self-supervised":[63,142],"learning":[64],"approach":[65,102],"designed":[66],"to":[67,103],"identify":[68],"characterize":[70,107],"such":[73],"data.":[74],"To":[75],"do":[76],"this,":[77],"represent":[79],"as":[81,145],"chains":[82],"functional":[84],"protein":[85],"domains":[86],"train":[88],"masked":[90],"language":[91],"model":[92,118],"on":[93],"these":[94],"domains.":[95],"We":[96,113],"assess":[97],"ability":[99],"our":[101,117],"detect":[104,129],"BGC":[108,136,151],"properties":[109],"bacterial":[111],"genomes.":[112],"also":[114],"demonstrate":[115],"can":[119],"learn":[120],"meaningful":[121],"representations":[122],"their":[126],"constituent":[127],"domains,":[128],"genomes,":[133],"predict":[135],"product":[137],"classes.":[138],"These":[139],"results":[140],"highlight":[141],"neural":[143],"networks":[144],"promising":[147],"framework":[148],"for":[149],"improving":[150],"prediction":[152],"classification.":[154]},"counts_by_year":[{"year":2026,"cited_by_count":6},{"year":2025,"cited_by_count":25},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":1}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}