{"id":"https://openalex.org/W7204039217","doi":"https://doi.org/10.64898/2026.08.21.746127","title":"Sequence-Derived Representations versus Pfam-Domain Content for Biosynthetic Gene Cluster Retrieval","display_name":"Sequence-Derived Representations versus Pfam-Domain Content for Biosynthetic Gene Cluster Retrieval","publication_year":2026,"publication_date":"2026-08-22","ids":{"openalex":"https://openalex.org/W7204039217","doi":"https://doi.org/10.64898/2026.08.21.746127"},"language":"en","primary_location":{"id":"doi:10.64898/2026.08.21.746127","doi":"https://doi.org/10.64898/2026.08.21.746127","is_oa":true,"landing_page_url":"https://doi.org/10.64898/2026.08.21.746127","pdf_url":"https://www.biorxiv.org/content/biorxiv/early/2026/08/22/2026.08.21.746127.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/2026/08/22/2026.08.21.746127.full.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5147889935","display_name":"Rustambek Urokov","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4387155254","display_name":"New Uzbekistan University","ror":"https://ror.org/035v3tr79","country_code":"UZ","type":"education","lineage":["https://openalex.org/I4387155254"]}],"countries":["UZ"],"is_corresponding":true,"raw_author_name":"Rustambek Urokov","raw_affiliation_strings":["New Uzbekistan University, Tashkent, Uzbekistan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"New Uzbekistan University, Tashkent, Uzbekistan","institution_ids":["https://openalex.org/I4387155254"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083112369","display_name":"Asifullah Khan","orcid":"https://orcid.org/0000-0003-2039-5305","observed_orcids":["https://orcid.org/0000-0003-2039-5305"]},"institutions":[{"id":"https://openalex.org/I4387155254","display_name":"New Uzbekistan University","ror":"https://ror.org/035v3tr79","country_code":"UZ","type":"education","lineage":["https://openalex.org/I4387155254"]}],"countries":["UZ"],"is_corresponding":false,"raw_author_name":"Asifullah Khan","raw_affiliation_strings":["New Uzbekistan University, Tashkent, Uzbekistan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"New Uzbekistan University, Tashkent, Uzbekistan","institution_ids":["https://openalex.org/I4387155254"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055333842","display_name":"Farkhod Eshboev","orcid":"https://orcid.org/0000-0003-3054-6111","observed_orcids":["https://orcid.org/0000-0003-3054-6111"]},"institutions":[{"id":"https://openalex.org/I4387155254","display_name":"New Uzbekistan University","ror":"https://ror.org/035v3tr79","country_code":"UZ","type":"education","lineage":["https://openalex.org/I4387155254"]}],"countries":["UZ"],"is_corresponding":false,"raw_author_name":"Farhod Eshboyev","raw_affiliation_strings":["New Uzbekistan University, Tashkent, Uzbekistan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"New Uzbekistan University, Tashkent, Uzbekistan","institution_ids":["https://openalex.org/I4387155254"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5147895507","display_name":"Dovud Asadov","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4387155254","display_name":"New Uzbekistan University","ror":"https://ror.org/035v3tr79","country_code":"UZ","type":"education","lineage":["https://openalex.org/I4387155254"]}],"countries":["UZ"],"is_corresponding":false,"raw_author_name":"Dovud Asadov","raw_affiliation_strings":["New Uzbekistan University, Tashkent, Uzbekistan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"New Uzbekistan University, Tashkent, Uzbekistan","institution_ids":["https://openalex.org/I4387155254"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078715775","display_name":"Sejuti Rahman","orcid":"https://orcid.org/0000-0001-6226-2434","observed_orcids":["https://orcid.org/0000-0001-6226-2434"]},"institutions":[{"id":"https://openalex.org/I4387155254","display_name":"New Uzbekistan University","ror":"https://ror.org/035v3tr79","country_code":"UZ","type":"education","lineage":["https://openalex.org/I4387155254"]}],"countries":["UZ"],"is_corresponding":false,"raw_author_name":"Sejuti Rahman","raw_affiliation_strings":["New Uzbekistan University, Tashkent, Uzbekistan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"New Uzbekistan University, Tashkent, Uzbekistan","institution_ids":["https://openalex.org/I4387155254"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5147909578","display_name":"Dilafruz Kushokova","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4387155254","display_name":"New Uzbekistan University","ror":"https://ror.org/035v3tr79","country_code":"UZ","type":"education","lineage":["https://openalex.org/I4387155254"]}],"countries":["UZ"],"is_corresponding":false,"raw_author_name":"Dilafruz Kushokova","raw_affiliation_strings":["New Uzbekistan University, Tashkent, Uzbekistan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"New Uzbekistan University, Tashkent, Uzbekistan","institution_ids":["https://openalex.org/I4387155254"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5147889935"],"corresponding_institution_ids":["https://openalex.org/I4387155254"],"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":0.9735999703407288,"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":0.9735999703407288,"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":0.007600000128149986,"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/T10211","display_name":"Computational Drug Discovery Methods","score":0.0017999999690800905,"subfield":{"id":"https://openalex.org/subfields/3002","display_name":"Drug Discovery"},"field":{"id":"https://openalex.org/fields/30","display_name":"Pharmacology, Toxicology and Pharmaceutics"},"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":0.9490000009536743},{"id":"https://openalex.org/keywords/streptomyces-griseus","display_name":"Streptomyces griseus","score":0.9229999780654907},{"id":"https://openalex.org/keywords/representation-learning","display_name":"representation learning","score":0.6539999842643738},{"id":"https://openalex.org/keywords/jaccard-similarity","display_name":"Jaccard similarity","score":0.4959999918937683}],"concepts":[{"id":"https://openalex.org/C203519979","wikidata":"https://www.wikidata.org/wiki/Q865360","display_name":"Jaccard index","level":3,"score":0.9516000151634216},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.5582000017166138},{"id":"https://openalex.org/C2780873923","wikidata":"https://www.wikidata.org/wiki/Q7623385","display_name":"Streptomyces griseus","level":4,"score":0.5410000085830688},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4390999972820282},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.38659998774528503},{"id":"https://openalex.org/C24432333","wikidata":"https://www.wikidata.org/wiki/Q2068526","display_name":"Whole genome sequencing","level":4,"score":0.37400001287460327},{"id":"https://openalex.org/C141231307","wikidata":"https://www.wikidata.org/wiki/Q7020","display_name":"Genome","level":3,"score":0.35370001196861267},{"id":"https://openalex.org/C2908923196","wikidata":"https://www.wikidata.org/wiki/Q5205742","display_name":"Gene Annotation","level":4,"score":0.335999995470047},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.33559998869895935},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.33410000801086426},{"id":"https://openalex.org/C164866538","wikidata":"https://www.wikidata.org/wiki/Q367351","display_name":"Cluster (spacecraft)","level":2,"score":0.33230000734329224},{"id":"https://openalex.org/C2984074130","wikidata":"https://www.wikidata.org/wiki/Q73539779","display_name":"R package","level":2,"score":0.32440000772476196},{"id":"https://openalex.org/C2777267654","wikidata":"https://www.wikidata.org/wiki/Q3519023","display_name":"Test (biology)","level":2,"score":0.3199000060558319},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.31869998574256897},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.3000999987125397},{"id":"https://openalex.org/C91682802","wikidata":"https://www.wikidata.org/wiki/Q620538","display_name":"Multidimensional scaling","level":2,"score":0.2766999900341034},{"id":"https://openalex.org/C2780201653","wikidata":"https://www.wikidata.org/wiki/Q7623378","display_name":"Streptomyces albus","level":4,"score":0.25769999623298645},{"id":"https://openalex.org/C60644358","wikidata":"https://www.wikidata.org/wiki/Q128570","display_name":"Bioinformatics","level":1,"score":0.25429999828338623}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.64898/2026.08.21.746127","doi":"https://doi.org/10.64898/2026.08.21.746127","is_oa":true,"landing_page_url":"https://doi.org/10.64898/2026.08.21.746127","pdf_url":"https://www.biorxiv.org/content/biorxiv/early/2026/08/22/2026.08.21.746127.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:10.64898/2026.08.21.746127","doi":"https://doi.org/10.64898/2026.08.21.746127","is_oa":true,"landing_page_url":"https://doi.org/10.64898/2026.08.21.746127","pdf_url":"https://www.biorxiv.org/content/biorxiv/early/2026/08/22/2026.08.21.746127.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":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7204039217.pdf","grobid_xml":"https://content.openalex.org/works/W7204039217.grobid-xml"},"referenced_works_count":6,"referenced_works":["https://openalex.org/W2990471452","https://openalex.org/W3121081543","https://openalex.org/W3161596995","https://openalex.org/W4309305948","https://openalex.org/W4327550249","https://openalex.org/W4417478313"],"related_works":["https://openalex.org/W4229073727","https://openalex.org/W3091334475","https://openalex.org/W4400519476","https://openalex.org/W7171979250","https://openalex.org/W6950347627","https://openalex.org/W7165181415","https://openalex.org/W4416759958","https://openalex.org/W2941821699","https://openalex.org/W4283659942","https://openalex.org/W4377861946"],"abstract_inverted_index":{"Abstract":[0],"Retrieving":[1],"BGCs":[2,24,56,66],"related":[3],"to":[4,127],"those":[5],"of":[6,23,94,103,119],"a":[7,14,115,123,172],"known":[8],"producer":[9],"can":[10,25,141],"be":[11],"regarded":[12],"as":[13],"representation-learning":[15],"objective.":[16,158],"We":[17],"hypothesize":[18],"that":[19,138,168],"ESM-2":[20],"sequence-derived":[21,139],"representations":[22,140],"improve":[26],"retrieval":[27,88],"beyond":[28],"the":[29,36,80,136,153,162],"Pfam-domain":[30],"content":[31],"metric.":[32],"Our":[33,131,159],"toolkit":[34],"is":[35],"following:":[37],"group-disjoint":[38],"train,":[39],"validation,":[40,73],"and":[41,49,74,105,164],"test":[42,76,81],"assignments,":[43],"validation-frozen":[44],"model":[45],"selection,":[46],"five":[47],"seeds,":[48],"family-level":[50],"paired":[51],"inference.":[52],"Of":[53,79],"6,953":[54],"atlas":[55],"from":[57],"182":[58],"deduplicated":[59],"Streptomyces":[60],"griseus":[61],"genome":[62],"accessions,":[63],"5,325":[64],"silver-labeled":[65],"are":[67,85,169],"split":[68],"into":[69],"98":[70],"training,":[71],"21":[72,75],"reference":[77,82],"groups.":[78],"groups,":[83],"16":[84],"eligible":[86],"for":[87,156,171],"diagnostics.":[89],"Pfam":[90,112,129,151],"Jaccard":[91,113],"scored":[92,99,108],"Recall@50":[93],"0.8788,":[95],"while":[96],"Pfam-augmented":[97,106],"BGC-SetNet":[98,107],"0.8472.":[100],"The":[101],"combination":[102],"ESM":[104],"0.8769.":[109],"A":[110],"weighted":[111],"obtained":[114],"slightly":[116],"higher":[117],"score":[118],"0.8789,":[120],"which":[121],"has":[122],"negligible":[124],"difference":[125],"compared":[126],"unweighted":[128],"Jaccard.":[130],"results":[132,160],"do":[133],"not":[134],"support":[135],"claim":[137],"recover":[142],"alternative":[143],"biosynthetic":[144],"pathways":[145],"on":[146],"this":[147,157],"benchmark.":[148],"Instead,":[149],"explicit":[150],"remains":[152],"major":[154],"signal":[155],"define":[161],"curation":[163],"pathway-level":[165],"validation":[166],"processes":[167],"necessary":[170],"more":[173],"robust":[174],"biological":[175],"test.":[176]},"counts_by_year":[],"updated_date":"2026-11-09T13:22:03.289127","created_date":"2026-08-24T00:00:00"}