{"id":"https://openalex.org/W2998796454","doi":"https://doi.org/10.1109/bibm47256.2019.8983041","title":"Supporting supervised learning in fungal Biosynthetic Gene Cluster discovery: new benchmark datasets","display_name":"Supporting supervised learning in fungal Biosynthetic Gene Cluster discovery: new benchmark datasets","publication_year":2019,"publication_date":"2019-11-01","ids":{"openalex":"https://openalex.org/W2998796454","doi":"https://doi.org/10.1109/bibm47256.2019.8983041","mag":"2998796454"},"language":"en","primary_location":{"id":"doi:10.1109/bibm47256.2019.8983041","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bibm47256.2019.8983041","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE International Conference on Bioinformatics and Biomedicine (BIBM)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2001.03260","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Hayda Almeida","orcid":null},"institutions":[{"id":"https://openalex.org/I60158472","display_name":"Concordia University","ror":"https://ror.org/0420zvk78","country_code":"CA","type":"education","lineage":["https://openalex.org/I60158472"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Hayda Almeida","raw_affiliation_strings":["Concordia University,Montreal,Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Concordia University,Montreal,Canada","institution_ids":["https://openalex.org/I60158472"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Adrian Tsang","orcid":null},"institutions":[{"id":"https://openalex.org/I60158472","display_name":"Concordia University","ror":"https://ror.org/0420zvk78","country_code":"CA","type":"education","lineage":["https://openalex.org/I60158472"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Adrian Tsang","raw_affiliation_strings":["Concordia University,Montreal,Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Concordia University,Montreal,Canada","institution_ids":["https://openalex.org/I60158472"]}]},{"author_position":"last","author":{"id":null,"display_name":"Abdoulaye Banir\u00e9 Diallo","orcid":null},"institutions":[{"id":"https://openalex.org/I159129438","display_name":"Universit\u00e9 du Qu\u00e9bec \u00e0 Montr\u00e9al","ror":"https://ror.org/002rjbv21","country_code":"CA","type":"education","lineage":["https://openalex.org/I159129438","https://openalex.org/I49663120"]},{"id":"https://openalex.org/I70931966","display_name":"Universit\u00e9 de Montr\u00e9al","ror":"https://ror.org/0161xgx34","country_code":"CA","type":"education","lineage":["https://openalex.org/I70931966"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Abdoulaye Banir\u00e9 Diallo","raw_affiliation_strings":["University of Quebec in Montreal,Montreal,Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Quebec in Montreal,Montreal,Canada","institution_ids":["https://openalex.org/I159129438","https://openalex.org/I70931966"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1280","last_page":"1287"},"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/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":0.9994999766349792,"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":0.9962000250816345,"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/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.9876000285148621,"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/supervised-learning","display_name":"Supervised learning","score":0.5934000015258789},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5914999842643738},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5814999938011169},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.5146999955177307},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.4514000117778778},{"id":"https://openalex.org/keywords/semi-supervised-learning","display_name":"Semi-supervised learning","score":0.42570000886917114},{"id":"https://openalex.org/keywords/binary-classification","display_name":"Binary classification","score":0.376800000667572}],"concepts":[{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.6238999962806702},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.609499990940094},{"id":"https://openalex.org/C136389625","wikidata":"https://www.wikidata.org/wiki/Q334384","display_name":"Supervised learning","level":3,"score":0.5934000015258789},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5914999842643738},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5848000049591064},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5814999938011169},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.5146999955177307},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.4514000117778778},{"id":"https://openalex.org/C58973888","wikidata":"https://www.wikidata.org/wiki/Q1041418","display_name":"Semi-supervised learning","level":2,"score":0.42570000886917114},{"id":"https://openalex.org/C66905080","wikidata":"https://www.wikidata.org/wiki/Q17005494","display_name":"Binary classification","level":3,"score":0.376800000667572},{"id":"https://openalex.org/C8038995","wikidata":"https://www.wikidata.org/wiki/Q1152135","display_name":"Unsupervised learning","level":2,"score":0.34130001068115234},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3269999921321869},{"id":"https://openalex.org/C2776145971","wikidata":"https://www.wikidata.org/wiki/Q30673951","display_name":"Labeled data","level":2,"score":0.3246000111103058},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.31200000643730164},{"id":"https://openalex.org/C189119545","wikidata":"https://www.wikidata.org/wiki/Q5128022","display_name":"Probabilistic classification","level":4,"score":0.305400013923645},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.3012000024318695},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.2946999967098236},{"id":"https://openalex.org/C2776482837","wikidata":"https://www.wikidata.org/wiki/Q3553958","display_name":"Multi-label classification","level":2,"score":0.2870999872684479},{"id":"https://openalex.org/C74187038","wikidata":"https://www.wikidata.org/wiki/Q1418791","display_name":"Drug discovery","level":2,"score":0.27160000801086426}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/bibm47256.2019.8983041","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bibm47256.2019.8983041","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE International Conference on Bioinformatics and Biomedicine (BIBM)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2001.03260","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2001.03260","pdf_url":"https://arxiv.org/pdf/2001.03260","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"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":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2001.03260","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2001.03260","pdf_url":"https://arxiv.org/pdf/2001.03260","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"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":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W1202680985","https://openalex.org/W1968216644","https://openalex.org/W1985653548","https://openalex.org/W2009257824","https://openalex.org/W2024368780","https://openalex.org/W2086953382","https://openalex.org/W2105224575","https://openalex.org/W2137490801","https://openalex.org/W2161426703","https://openalex.org/W2187341651","https://openalex.org/W2229450847","https://openalex.org/W2291640041","https://openalex.org/W2308546048","https://openalex.org/W2502949459","https://openalex.org/W2558253576","https://openalex.org/W2588882259","https://openalex.org/W2604636508","https://openalex.org/W2609551972","https://openalex.org/W2613440185","https://openalex.org/W2783301523","https://openalex.org/W2897661414","https://openalex.org/W2898402099","https://openalex.org/W2899600207","https://openalex.org/W2967688728","https://openalex.org/W6728365157"],"related_works":[],"abstract_inverted_index":{"Fungal":[0],"Biosynthetic":[1],"Gene":[2],"Clusters":[3],"(BGCs)":[4],"of":[5,10,13,26,30,44,145,160,218],"secondary":[6],"metabolites":[7],"are":[8,129,198],"clusters":[9],"genes":[11],"capable":[12],"producing":[14],"natural":[15,46],"products,":[16],"compounds":[17],"that":[18],"play":[19],"an":[20],"important":[21],"role":[22],"in":[23,65,83,111,123,209],"the":[24,42,120,158,189,216],"production":[25],"a":[27,141,219],"wide":[28],"variety":[29],"bioactive":[31],"compounds,":[32],"including":[33],"antibiotics":[34],"and":[35,68,76,95,113,167,204],"pharmaceuticals.":[36],"Identifying":[37],"BGCs":[38,92,110,166],"can":[39],"lead":[40],"to":[41,48,61,89,105,118,131,173,187,200,226],"discovery":[43,64,191],"novel":[45],"products":[47],"benefit":[49],"human":[50],"health.":[51],"Previous":[52],"work":[53,178],"has":[54],"been":[55,81,103],"focused":[56],"on":[57],"developing":[58],"automatic":[59],"tools":[60],"support":[62,188],"BGC":[63,137,153,185,190,207],"plants,":[66],"fungi,":[67],"bacteria.":[69],"Data-driven":[70],"methods,":[71],"as":[72,74],"well":[73,107,116,220],"probabilistic":[75],"supervised":[77,133,161,194,222],"learning":[78,100,162,223],"methods":[79,87,101,163],"have":[80,102],"explored":[82],"identifying":[84,109],"BGCs.":[85,149,228],"Most":[86],"applied":[88],"identify":[90],"fungal":[91,148,152,165,184,210],"were":[93],"data-driven":[94,174],"presented":[96],"limited":[97],"scope.":[98],"Supervised":[99],"shown":[104],"perform":[106,119,132,201],"at":[108],"bacteria,":[112],"could":[114,156],"be":[115],"suited":[117],"same":[121],"task":[122,192],"fungi.":[124],"But":[125],"labeled":[126],"data":[127],"instances":[128],"needed":[130],"learning.":[134,195],"Openly":[135],"accessible":[136],"databases":[138],"contain":[139],"only":[140],"very":[142],"small":[143],"portion":[144],"previously":[146],"curated":[147],"Making":[150],"new":[151,181],"datasets":[154,186,197],"available":[155,183],"motivate":[157],"development":[159],"for":[164],"potentially":[168],"improve":[169],"prediction":[170],"performance":[171,217],"compared":[172],"methods.":[175],"In":[176,212],"this":[177],"we":[179,214],"propose":[180],"publicly":[182],"using":[193],"These":[196],"prepared":[199],"binary":[202],"classification":[203],"predict":[205,227],"candidate":[206],"regions":[208],"genomes.":[211],"addition":[213],"analyse":[215],"supported":[221],"tool":[224],"developed":[225]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2022,"cited_by_count":2}],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2020-01-23T00:00:00"}