{"id":"https://openalex.org/W7126087959","doi":"https://doi.org/10.1109/bibm66473.2025.11356651","title":"Proscope: Modeling Biosynthetic Diversity Via Probabilistic Structure-Aware Co-Embedding","display_name":"Proscope: Modeling Biosynthetic Diversity Via Probabilistic Structure-Aware Co-Embedding","publication_year":2025,"publication_date":"2025-12-15","ids":{"openalex":"https://openalex.org/W7126087959","doi":"https://doi.org/10.1109/bibm66473.2025.11356651"},"language":null,"primary_location":{"id":"doi:10.1109/bibm66473.2025.11356651","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bibm66473.2025.11356651","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Bioinformatics and Biomedicine (BIBM)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100670475","display_name":"Yiting Li","orcid":"https://orcid.org/0000-0003-2164-7068"},"institutions":[{"id":"https://openalex.org/I115228651","display_name":"Agency for Science, Technology and Research","ror":"https://ror.org/036wvzt09","country_code":"SG","type":"government","lineage":["https://openalex.org/I115228651"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Yiting Li","raw_affiliation_strings":["Agency for Science, Technology and Research,Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Agency for Science, Technology and Research,Singapore","institution_ids":["https://openalex.org/I115228651"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5124160834","display_name":"Eriko Takano","orcid":null},"institutions":[{"id":"https://openalex.org/I115228651","display_name":"Agency for Science, Technology and Research","ror":"https://ror.org/036wvzt09","country_code":"SG","type":"government","lineage":["https://openalex.org/I115228651"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Eriko Takano","raw_affiliation_strings":["Agency for Science, Technology and Research,Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Agency for Science, Technology and Research,Singapore","institution_ids":["https://openalex.org/I115228651"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5124237721","display_name":"Jing Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Jing Zhang","raw_affiliation_strings":["The Chinese University of Hong Kong,Hong Kong,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong,Hong Kong,China","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5124281100","display_name":"Ben Draper","orcid":null},"institutions":[{"id":"https://openalex.org/I115228651","display_name":"Agency for Science, Technology and Research","ror":"https://ror.org/036wvzt09","country_code":"SG","type":"government","lineage":["https://openalex.org/I115228651"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Ben Draper","raw_affiliation_strings":["Agency for Science, Technology and Research,Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Agency for Science, Technology and Research,Singapore","institution_ids":["https://openalex.org/I115228651"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5124225310","display_name":"Wayne Wei Zhong Yeo","orcid":null},"institutions":[{"id":"https://openalex.org/I115228651","display_name":"Agency for Science, Technology and Research","ror":"https://ror.org/036wvzt09","country_code":"SG","type":"government","lineage":["https://openalex.org/I115228651"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Wayne Wei Zhong Yeo","raw_affiliation_strings":["Agency for Science, Technology and Research,Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Agency for Science, Technology and Research,Singapore","institution_ids":["https://openalex.org/I115228651"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5110299768","display_name":"Breitling Rainer","orcid":null},"institutions":[{"id":"https://openalex.org/I115228651","display_name":"Agency for Science, Technology and Research","ror":"https://ror.org/036wvzt09","country_code":"SG","type":"government","lineage":["https://openalex.org/I115228651"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Rainer Breitling","raw_affiliation_strings":["Agency for Science, Technology and Research,Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Agency for Science, Technology and Research,Singapore","institution_ids":["https://openalex.org/I115228651"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.66616136,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"4905","last_page":"4913"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10211","display_name":"Computational Drug Discovery Methods","score":0.3122999966144562,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/T10211","display_name":"Computational Drug Discovery Methods","score":0.3122999966144562,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/T10887","display_name":"Bioinformatics and Genomic Networks","score":0.17020000517368317,"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/T11948","display_name":"Machine Learning in Materials Science","score":0.15700000524520874,"subfield":{"id":"https://openalex.org/subfields/2505","display_name":"Materials Chemistry"},"field":{"id":"https://openalex.org/fields/25","display_name":"Materials Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.6626999974250793},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.6258000135421753},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.5235999822616577},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.40540000796318054},{"id":"https://openalex.org/keywords/product","display_name":"Product (mathematics)","score":0.4002000093460083},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.391400009393692},{"id":"https://openalex.org/keywords/chemical-space","display_name":"Chemical space","score":0.37049999833106995},{"id":"https://openalex.org/keywords/matrix-decomposition","display_name":"Matrix decomposition","score":0.3370000123977661}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6628999710083008},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.6626999974250793},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.6258000135421753},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.5235999822616577},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4205000102519989},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.40540000796318054},{"id":"https://openalex.org/C90673727","wikidata":"https://www.wikidata.org/wiki/Q901718","display_name":"Product (mathematics)","level":2,"score":0.4002000093460083},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.39410001039505005},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.391400009393692},{"id":"https://openalex.org/C99726746","wikidata":"https://www.wikidata.org/wiki/Q906396","display_name":"Chemical space","level":3,"score":0.37049999833106995},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.34940001368522644},{"id":"https://openalex.org/C42355184","wikidata":"https://www.wikidata.org/wiki/Q1361088","display_name":"Matrix decomposition","level":3,"score":0.3370000123977661},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.31679999828338623},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.310699999332428},{"id":"https://openalex.org/C2779396153","wikidata":"https://www.wikidata.org/wiki/Q901227","display_name":"Natural product","level":2,"score":0.30799999833106995},{"id":"https://openalex.org/C114289077","wikidata":"https://www.wikidata.org/wiki/Q3284399","display_name":"Statistical model","level":2,"score":0.2976999878883362},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.2930999994277954},{"id":"https://openalex.org/C164866538","wikidata":"https://www.wikidata.org/wiki/Q367351","display_name":"Cluster (spacecraft)","level":2,"score":0.29089999198913574},{"id":"https://openalex.org/C74187038","wikidata":"https://www.wikidata.org/wiki/Q1418791","display_name":"Drug discovery","level":2,"score":0.2881999909877777},{"id":"https://openalex.org/C2776517306","wikidata":"https://www.wikidata.org/wiki/Q29017317","display_name":"Similarity measure","level":2,"score":0.2847999930381775},{"id":"https://openalex.org/C2780009758","wikidata":"https://www.wikidata.org/wiki/Q6804172","display_name":"Measure (data warehouse)","level":2,"score":0.2827000021934509},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.27090001106262207},{"id":"https://openalex.org/C2639959","wikidata":"https://www.wikidata.org/wiki/Q1344778","display_name":"Distance measures","level":2,"score":0.2662000060081482},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.2531999945640564},{"id":"https://openalex.org/C61224824","wikidata":"https://www.wikidata.org/wiki/Q2260434","display_name":"Mixture model","level":2,"score":0.25270000100135803},{"id":"https://openalex.org/C2776608160","wikidata":"https://www.wikidata.org/wiki/Q4785462","display_name":"Natural (archaeology)","level":2,"score":0.25099998712539673}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/bibm66473.2025.11356651","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bibm66473.2025.11356651","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Bioinformatics and Biomedicine (BIBM)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W2009257824","https://openalex.org/W2956018683","https://openalex.org/W2962839482","https://openalex.org/W2962964995","https://openalex.org/W2967688728","https://openalex.org/W2988823324","https://openalex.org/W2990471452","https://openalex.org/W2991118492","https://openalex.org/W3035524453","https://openalex.org/W3091334475","https://openalex.org/W3146944767","https://openalex.org/W3161596995","https://openalex.org/W3168433561","https://openalex.org/W3177350810","https://openalex.org/W4281697264","https://openalex.org/W4377861946","https://openalex.org/W4382239609","https://openalex.org/W4405220977"],"related_works":[],"abstract_inverted_index":{"A":[0],"key":[1],"challenge":[2],"of":[3,14,137,151,217],"natural":[4,12,229],"product":[5,13],"discovery":[6,130],"is":[7,124],"to":[8,52,60,62,155,159,228],"retrieve":[9],"the":[10,54,110,115,134,149,160,179,187,210,215],"corresponding":[11],"a":[15,22,46,73,95,143,194,203],"given":[16],"biosynthetic":[17,64],"gene":[18,35,226],"cluster":[19],"(BGC).":[20],"As":[21],"single":[23],"BGC":[24],"may":[25],"produce":[26],"multiple":[27],"structural":[28],"analogs,":[29],"modeling":[30,218],"such":[31],"one-to-many":[32],"relationships":[33],"between":[34,102],"clusters":[36,227],"and":[37,58,82,89,173,202,221],"compounds":[38,83],"remains":[39],"challenging.":[40],"Existing":[41],"retrieval":[42,116,135],"approaches":[43],"often":[44,125],"learn":[45],"deterministic":[47],"embedding":[48,97],"space,":[49],"which":[50],"struggle":[51],"capture":[53],"inherent":[55],"biological":[56],"complexity":[57],"fail":[59],"generalize":[61],"novel":[63],"classes.":[65],"To":[66,99,132],"address":[67],"this":[68],"issue,":[69],"we":[70,108,141],"introduce":[71,142],"ProSCOPE,":[72],"Probabilistic":[74],"Structureaware":[75],"Co-Embedding":[76],"framework":[77,166],"that":[78,147,183],"models":[79],"both":[80],"BGCs":[81],"as":[84,114],"diagonal":[85],"Gaussian":[86],"distributions":[87,103],"bridges":[88],"bridge":[90],"these":[91],"two":[92,168],"modalities":[93],"in":[94,104,127,199,209,224],"shared":[96],"space.":[98],"measure":[100],"similarity":[101,158],"an":[105],"efficient":[106],"way,":[107],"employ":[109],"closed-form":[111],"2-Wasserstein":[112],"distance":[113,117],"metric.":[118],"Furthermore,":[119],"retrieving":[120],"structurally":[121],"similar":[122],"analogs":[123],"valuable":[126],"real-word":[128],"drug":[129],"applications.":[131],"improve":[133],"performance":[136],"chemically":[138],"relevant":[139],"compounds,":[140],"structure-aware":[144],"training":[145],"strategy":[146],"modulates":[148],"contribution":[150],"negative":[152],"samples":[153],"according":[154],"their":[156],"chemical":[157],"ground":[161],"truth.":[162],"We":[163],"evaluate":[164],"our":[165],"across":[167],"realistic":[169],"scenarios:":[170],"standard":[171],"cross-validation":[172],"class":[174],"holdout":[175],"settings.":[176],"Experiments":[177],"on":[178],"MIBiG":[180],"dataset":[181],"demonstrate":[182],"ProSCOPE":[184,192],"substantially":[185],"outperforms":[186],"previous":[188],"pointbased":[189],"co-embedding":[190],"model.":[191],"achieves":[193],"7.5":[195],"%":[196],"relative":[197],"improvement":[198,208],"in-distribution":[200],"Recall@10":[201],"significant$\\mathbf{1":[204],"6.":[205],"3":[206],"\\%}$relative":[207],"challenging":[211],"out-of-distribution":[212],"Recall@10,":[213],"highlighting":[214],"benefit":[216],"distributional":[219],"uncertainty":[220],"domain":[222],"structure":[223],"linking":[225],"products.":[230]},"counts_by_year":[],"updated_date":"2026-08-12T21:12:35.861297","created_date":"2026-01-30T00:00:00"}