{"id":"https://openalex.org/W4283659942","doi":"https://doi.org/10.1093/bioinformatics/btac420","title":"Improving candidate Biosynthetic Gene Clusters in fungi through reinforcement learning","display_name":"Improving candidate Biosynthetic Gene Clusters in fungi through reinforcement learning","publication_year":2022,"publication_date":"2022-06-28","ids":{"openalex":"https://openalex.org/W4283659942","doi":"https://doi.org/10.1093/bioinformatics/btac420","pmid":"https://pubmed.ncbi.nlm.nih.gov/35762945"},"language":"en","primary_location":{"id":"doi:10.1093/bioinformatics/btac420","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btac420","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/38/16/3984/49889902/btac420.pdf","source":{"id":"https://openalex.org/S52395412","display_name":"Bioinformatics","issn_l":"1367-4803","issn":["1367-4803","1367-4811"],"is_oa":false,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310311648","host_organization_name":"Oxford University Press","host_organization_lineage":["https://openalex.org/P4310311648","https://openalex.org/P4310311647"],"host_organization_lineage_names":["Oxford University Press","University of Oxford"],"type":"journal"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Bioinformatics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://academic.oup.com/bioinformatics/article-pdf/38/16/3984/49889902/btac420.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5025498717","display_name":"Hayda Almeida","orcid":"https://orcid.org/0000-0002-3149-4547"},"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/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":["Centre for Structural and Functional Genomics, Concordia University , Montr\u00e9al, QC H4B 1R6, Canada","Departement d\u2019Informatique, UQAM , Montr\u00e9al, QC H2X 3Y7, Canada","Laboratoire d\u2019Alg\u00e8bre, de Combinatoire, et d\u2019Informatique Math\u00e9matique (LACIM), UQAM , Montr\u00e9al, QC H2X 3Y, Canada"],"raw_orcid":"https://orcid.org/0000-0002-3149-4547","affiliations":[{"raw_affiliation_string":"Centre for Structural and Functional Genomics, Concordia University , Montr\u00e9al, QC H4B 1R6, Canada","institution_ids":["https://openalex.org/I60158472"]},{"raw_affiliation_string":"Departement d\u2019Informatique, UQAM , Montr\u00e9al, QC H2X 3Y7, Canada","institution_ids":["https://openalex.org/I159129438"]},{"raw_affiliation_string":"Laboratoire d\u2019Alg\u00e8bre, de Combinatoire, et d\u2019Informatique Math\u00e9matique (LACIM), UQAM , Montr\u00e9al, QC H2X 3Y, Canada","institution_ids":["https://openalex.org/I159129438"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060119095","display_name":"Adrian Tsang","orcid":"https://orcid.org/0000-0002-5892-4797"},"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/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":["Centre for Structural and Functional Genomics, Concordia University , Montr\u00e9al, QC H4B 1R6, Canada","Departement d\u2019Informatique, UQAM , Montr\u00e9al, QC H2X 3Y7, Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Centre for Structural and Functional Genomics, Concordia University , Montr\u00e9al, QC H4B 1R6, Canada","institution_ids":["https://openalex.org/I60158472"]},{"raw_affiliation_string":"Departement d\u2019Informatique, UQAM , Montr\u00e9al, QC H2X 3Y7, Canada","institution_ids":["https://openalex.org/I159129438"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5061553529","display_name":"Abdoulaye Banir\u00e9 Diallo","orcid":"https://orcid.org/0000-0002-1168-9371"},"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"]}],"countries":["CA"],"is_corresponding":true,"raw_author_name":"Abdoulaye Banir\u00e9 Diallo","raw_affiliation_strings":["Centre of Excellence in Research on Orphan Diseases\u2014Courtois Foundation (CERMO-FC) , UQAM, Montr\u00e9al, QC H2X 3Y7, Canada","Departement d\u2019Informatique, UQAM , Montr\u00e9al, QC H2X 3Y7, Canada","Laboratoire d\u2019Alg\u00e8bre, de Combinatoire, et d\u2019Informatique Math\u00e9matique (LACIM), UQAM , Montr\u00e9al, QC H2X 3Y, Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Centre of Excellence in Research on Orphan Diseases\u2014Courtois Foundation (CERMO-FC) , UQAM, Montr\u00e9al, QC H2X 3Y7, Canada","institution_ids":["https://openalex.org/I159129438"]},{"raw_affiliation_string":"Departement d\u2019Informatique, UQAM , Montr\u00e9al, QC H2X 3Y7, Canada","institution_ids":["https://openalex.org/I159129438"]},{"raw_affiliation_string":"Laboratoire d\u2019Alg\u00e8bre, de Combinatoire, et d\u2019Informatique Math\u00e9matique (LACIM), UQAM , Montr\u00e9al, QC H2X 3Y, Canada","institution_ids":["https://openalex.org/I159129438"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5061553529"],"corresponding_institution_ids":["https://openalex.org/I159129438"],"apc_list":{"value":3618,"currency":"USD","value_usd":3618},"apc_paid":{"value":3618,"currency":"USD","value_usd":3618},"fwci":0.8394,"has_fulltext":true,"cited_by_count":11,"citation_normalized_percentile":{"value":0.70006473,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":98},"biblio":{"volume":"38","issue":"16","first_page":"3984","last_page":"3991"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10887","display_name":"Bioinformatics and Genomic Networks","score":0.7039999961853027,"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/T10887","display_name":"Bioinformatics and Genomic Networks","score":0.7039999961853027,"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/T10497","display_name":"Fungal and yeast genetics research","score":0.07800000160932541,"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":0.07090000063180923,"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/candidate-gene","display_name":"Candidate gene","score":0.7435725927352905},{"id":"https://openalex.org/keywords/aspergillus-nidulans","display_name":"Aspergillus nidulans","score":0.6417580842971802},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.625319242477417},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4451446235179901},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.4105831980705261},{"id":"https://openalex.org/keywords/genome","display_name":"Genome","score":0.4100252389907837},{"id":"https://openalex.org/keywords/computational-biology","display_name":"Computational biology","score":0.39722371101379395},{"id":"https://openalex.org/keywords/gene","display_name":"Gene","score":0.32996052503585815},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3287617564201355},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.2658652067184448},{"id":"https://openalex.org/keywords/genetics","display_name":"Genetics","score":0.15631303191184998},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.0856989324092865}],"concepts":[{"id":"https://openalex.org/C69991583","wikidata":"https://www.wikidata.org/wiki/Q1423575","display_name":"Candidate gene","level":3,"score":0.7435725927352905},{"id":"https://openalex.org/C2776923806","wikidata":"https://www.wikidata.org/wiki/Q683881","display_name":"Aspergillus nidulans","level":4,"score":0.6417580842971802},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.625319242477417},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4451446235179901},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.4105831980705261},{"id":"https://openalex.org/C141231307","wikidata":"https://www.wikidata.org/wiki/Q7020","display_name":"Genome","level":3,"score":0.4100252389907837},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.39722371101379395},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.32996052503585815},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3287617564201355},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.2658652067184448},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.15631303191184998},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0856989324092865},{"id":"https://openalex.org/C143065580","wikidata":"https://www.wikidata.org/wiki/Q3285695","display_name":"Mutant","level":3,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0}],"mesh":[{"descriptor_ui":"D005658","descriptor_name":"Fungi","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":true},{"descriptor_ui":"D005658","descriptor_name":"Fungi","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":true},{"descriptor_ui":"D005658","descriptor_name":"Fungi","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":true},{"descriptor_ui":"D005810","descriptor_name":"Multigene Family","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":true},{"descriptor_ui":"D005810","descriptor_name":"Multigene Family","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D016681","descriptor_name":"Genome, Fungal","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016681","descriptor_name":"Genome, Fungal","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016681","descriptor_name":"Genome, Fungal","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D053898","descriptor_name":"Biosynthetic Pathways","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D053898","descriptor_name":"Biosynthetic Pathways","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D053898","descriptor_name":"Biosynthetic Pathways","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false}],"locations_count":3,"locations":[{"id":"doi:10.1093/bioinformatics/btac420","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btac420","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/38/16/3984/49889902/btac420.pdf","source":{"id":"https://openalex.org/S52395412","display_name":"Bioinformatics","issn_l":"1367-4803","issn":["1367-4803","1367-4811"],"is_oa":false,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310311648","host_organization_name":"Oxford University Press","host_organization_lineage":["https://openalex.org/P4310311648","https://openalex.org/P4310311647"],"host_organization_lineage_names":["Oxford University Press","University of Oxford"],"type":"journal"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Bioinformatics","raw_type":"journal-article"},{"id":"pmid:35762945","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/35762945","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":"Bioinformatics (Oxford, England)","raw_type":null},{"id":"pmh:oai:pubmedcentral.nih.gov:9364373","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/9364373","pdf_url":null,"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":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Bioinformatics","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.1093/bioinformatics/btac420","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btac420","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/38/16/3984/49889902/btac420.pdf","source":{"id":"https://openalex.org/S52395412","display_name":"Bioinformatics","issn_l":"1367-4803","issn":["1367-4803","1367-4811"],"is_oa":false,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310311648","host_organization_name":"Oxford University Press","host_organization_lineage":["https://openalex.org/P4310311648","https://openalex.org/P4310311647"],"host_organization_lineage_names":["Oxford University Press","University of Oxford"],"type":"journal"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Bioinformatics","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320311271","display_name":"Universit\u00e9 du Qu\u00e9bec \u00e0 Montr\u00e9al","ror":"https://ror.org/002rjbv21"},{"id":"https://openalex.org/F4320334593","display_name":"Natural Sciences and Engineering Research Council of Canada","ror":"https://ror.org/01h531d29"},{"id":"https://openalex.org/F4320334841","display_name":"Fonds de recherche du Qu\u00e9bec \u2013 Nature et technologies","ror":"https://ror.org/00b9f9778"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4283659942.pdf","grobid_xml":"https://content.openalex.org/works/W4283659942.grobid-xml"},"referenced_works_count":28,"referenced_works":["https://openalex.org/W32403112","https://openalex.org/W41554520","https://openalex.org/W1702652459","https://openalex.org/W1985653548","https://openalex.org/W2009257824","https://openalex.org/W2086953382","https://openalex.org/W2161426703","https://openalex.org/W2203188126","https://openalex.org/W2291640041","https://openalex.org/W2588882259","https://openalex.org/W2604636508","https://openalex.org/W2768956845","https://openalex.org/W2802441085","https://openalex.org/W2895546948","https://openalex.org/W2898402099","https://openalex.org/W2899600207","https://openalex.org/W2905340019","https://openalex.org/W2919912236","https://openalex.org/W2937768374","https://openalex.org/W2950658269","https://openalex.org/W2967688728","https://openalex.org/W2980832688","https://openalex.org/W3010606899","https://openalex.org/W3015501589","https://openalex.org/W3110037558","https://openalex.org/W3161596995","https://openalex.org/W3162746231","https://openalex.org/W6769413408"],"related_works":["https://openalex.org/W1997737537","https://openalex.org/W2366259742","https://openalex.org/W2076838980","https://openalex.org/W36632611","https://openalex.org/W3195693837","https://openalex.org/W1979551057","https://openalex.org/W2969978537","https://openalex.org/W3004983351","https://openalex.org/W4388226147","https://openalex.org/W157310628"],"abstract_inverted_index":{"MOTIVATION:":[0],"Precise":[1],"identification":[2],"of":[3,13,41,96,134,138],"Biosynthetic":[4],"Gene":[5],"Clusters":[6],"(BGCs)":[7],"is":[8,17],"a":[9],"challenging":[10],"task.":[11],"Performance":[12],"BGC":[14],"discovery":[15],"tools":[16,120],"limited":[18],"by":[19,100,111,149],"their":[20],"capacity":[21],"to":[22,27,67,121],"accurately":[23],"predict":[24],"components":[25],"belonging":[26],"candidate":[28,42,69,79,139],"BGCs,":[29,43],"often":[30],"overestimating":[31],"cluster":[32,109,127],"boundaries.":[33],"To":[34],"support":[35],"optimizing":[36,135],"the":[37,97,132,145],"composition":[38],"and":[39,53,88,106,108,116],"boundaries":[40],"we":[44],"propose":[45],"reinforcement":[46,63],"learning":[47,64],"approach":[48],"relying":[49],"on":[50,78],"protein":[51],"domains":[52],"functional":[54],"annotations":[55],"from":[56],"expert":[57],"curated":[58],"BGCs.":[59],"RESULTS:":[60],"The":[61,91],"proposed":[62],"method":[65],"aims":[66],"improve":[68],"BGCs":[70,80,140],"obtained":[71,81],"with":[72],"state-of-the-art":[73],"tools.":[74],"It":[75],"was":[76],"evaluated":[77],"for":[82,103,114],"two":[83],"fungal":[84],"genomes,":[85],"Aspergillus":[86,89],"niger":[87],"nidulans.":[90],"results":[92],"highlight":[93],"an":[94],"improvement":[95],"gene":[98],"precision":[99,110,125],"above":[101,112],"15%":[102],"TOUCAN,":[104],"fungiSMASH":[105,115],"DeepBGC;":[107],"25%":[113],"DeepBCG,":[117],"allowing":[118],"these":[119],"obtain":[122],"almost":[123],"perfect":[124],"in":[126,141],"prediction.":[128],"This":[129],"can":[130],"pave":[131],"way":[133],"current":[136],"prediction":[137],"fungi,":[142],"while":[143],"minimizing":[144],"curation":[146],"effort":[147],"required":[148],"domain":[150],"experts.":[151],"AVAILABILITY":[152],"AND":[153],"IMPLEMENTATION:":[154],"https://github.com/bioinfoUQAM/RL-bgc-components.":[155],"SUPPLEMENTARY":[156],"INFORMATION:":[157],"Supplementary":[158],"data":[159],"are":[160],"available":[161],"at":[162],"Bioinformatics":[163],"online.":[164]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":2}],"updated_date":"2026-06-19T15:47:20.252518","created_date":"2025-10-10T00:00:00"}
