{"id":"https://openalex.org/W4399724813","doi":"https://doi.org/10.1093/bioadv/vbae089","title":"Discovering genomic islands in unannotated bacterial genomes using sequence embedding","display_name":"Discovering genomic islands in unannotated bacterial genomes using sequence embedding","publication_year":2024,"publication_date":"2024-01-01","ids":{"openalex":"https://openalex.org/W4399724813","doi":"https://doi.org/10.1093/bioadv/vbae089","pmid":"https://pubmed.ncbi.nlm.nih.gov/38911822","pmcid":"https://www.ncbi.nlm.nih.gov/pmc/articles/11193100"},"language":"en","primary_location":{"id":"doi:10.1093/bioadv/vbae089","doi":"https://doi.org/10.1093/bioadv/vbae089","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioadv/vbae089","pdf_url":null,"source":{"id":"https://openalex.org/S4210234069","display_name":"Bioinformatics Advances","issn_l":"2635-0041","issn":["2635-0041"],"is_oa":true,"is_in_doaj":true,"is_core":true,"listed_in":["cwts-core","doaj","jufo-1","ki-jl-1","norway-1","oarl"],"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","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Bioinformatics Advances","raw_type":"journal-article"},"volume":null,"type":"article","is_traditional":true,"indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1093/bioadv/vbae089","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Priyanka Banerjee","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I173911158","display_name":"Iowa State University","ror":"https://ror.org/04rswrd78","country_code":"US","type":"education","lineage":["https://openalex.org/I173911158"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Priyanka Banerjee","raw_affiliation_strings":["Department of Computer Science, Iowa State University , Ames, IA 50011, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Iowa State University , Ames, IA 50011, United States","institution_ids":["https://openalex.org/I173911158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041404337","display_name":"Oliver Eulenstein","orcid":"https://orcid.org/0000-0002-5291-3798","observed_orcids":["https://orcid.org/0000-0002-5291-3798"]},"institutions":[{"id":"https://openalex.org/I173911158","display_name":"Iowa State University","ror":"https://ror.org/04rswrd78","country_code":"US","type":"education","lineage":["https://openalex.org/I173911158"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Oliver Eulenstein","raw_affiliation_strings":["Department of Computer Science, Iowa State University , Ames, IA 50011, United States"],"raw_orcid":"https://orcid.org/0000-0002-5291-3798","affiliations":[{"raw_affiliation_string":"Department of Computer Science, Iowa State University , Ames, IA 50011, United States","institution_ids":["https://openalex.org/I173911158"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5041597050","display_name":"Iddo Friedberg","orcid":"https://orcid.org/0000-0002-1789-8000","observed_orcids":["https://orcid.org/0000-0002-1789-8000"]},"institutions":[{"id":"https://openalex.org/I173911158","display_name":"Iowa State University","ror":"https://ror.org/04rswrd78","country_code":"US","type":"education","lineage":["https://openalex.org/I173911158"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Iddo Friedberg","raw_affiliation_strings":["Department of Veterinary Microbiology and Preventive Medicine, Iowa State University , Ames, IA 50011, United States"],"raw_orcid":"https://orcid.org/0000-0002-1789-8000","affiliations":[{"raw_affiliation_string":"Department of Veterinary Microbiology and Preventive Medicine, Iowa State University , Ames, IA 50011, United States","institution_ids":["https://openalex.org/I173911158"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5041597050"],"corresponding_institution_ids":["https://openalex.org/I173911158"],"apc_list":{"value":2917,"currency":"USD","value_usd":2917},"apc_paid":{"value":2917,"currency":"USD","value_usd":2917},"fwci":1.5377,"has_fulltext":true,"cited_by_count":13,"citation_normalized_percentile":{"value":0.82673304,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":98,"max":99},"biblio":{"volume":"4","issue":"1","first_page":"vbae089","last_page":"vbae089"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.9688000082969666,"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":0.9688000082969666,"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/T12946","display_name":"Fractal and DNA sequence analysis","score":0.009999999776482582,"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/T10120","display_name":"Bacterial Genetics and Biotechnology","score":0.004800000227987766,"subfield":{"id":"https://openalex.org/subfields/1311","display_name":"Genetics"},"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/genomic-islands","display_name":"genomic islands","score":1.0},{"id":"https://openalex.org/keywords/bacterial-genomes","display_name":"bacterial genomes","score":0.6850000023841858},{"id":"https://openalex.org/keywords/horizontal-gene-transfer","display_name":"horizontal gene transfer","score":0.8130000233650208},{"id":"https://openalex.org/keywords/sequence-embeddings","display_name":"sequence embeddings","score":0.8730000257492065},{"id":"https://openalex.org/keywords/antimicrobial-resistance-genes","display_name":"antimicrobial resistance genes","score":0.9089999794960022},{"id":"https://openalex.org/keywords/virulence-genes","display_name":"virulence genes","score":0.871999979019165}],"concepts":[{"id":"https://openalex.org/C141231307","wikidata":"https://www.wikidata.org/wiki/Q7020","display_name":"Genome","level":3,"score":0.653403639793396},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.6289728879928589},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.5882919430732727},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.5194137096405029},{"id":"https://openalex.org/C3742359","wikidata":"https://www.wikidata.org/wiki/Q4839988","display_name":"Bacterial genome size","level":4,"score":0.4759000241756439},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.4679742157459259},{"id":"https://openalex.org/C189206191","wikidata":"https://www.wikidata.org/wiki/Q222046","display_name":"Genomics","level":4,"score":0.4241214990615845},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.22199833393096924}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1093/bioadv/vbae089","doi":"https://doi.org/10.1093/bioadv/vbae089","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioadv/vbae089","pdf_url":null,"source":{"id":"https://openalex.org/S4210234069","display_name":"Bioinformatics Advances","issn_l":"2635-0041","issn":["2635-0041"],"is_oa":true,"is_in_doaj":true,"is_core":true,"listed_in":["cwts-core","doaj","jufo-1","ki-jl-1","norway-1","oarl"],"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","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Bioinformatics Advances","raw_type":"journal-article"},{"id":"doi:10.1101/2022.08.25.505341","doi":"https://doi.org/10.1101/2022.08.25.505341","is_oa":true,"landing_page_url":"https://doi.org/10.1101/2022.08.25.505341","pdf_url":"https://www.biorxiv.org/content/biorxiv/early/2022/08/26/2022.08.25.505341.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":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"bioRxiv","raw_type":"posted-content"},{"id":"pmh:oai:pubmedcentral.nih.gov:11193100","doi":null,"is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/11193100","pdf_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC11193100/pdf/vbae089.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,"listed_in":[],"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":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Bioinform Adv","raw_type":"Text"},{"id":"pmid:38911822","doi":null,"is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/38911822","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,"listed_in":[],"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 advances","raw_type":"Journal Article"}],"best_oa_location":{"id":"doi:10.1093/bioadv/vbae089","doi":"https://doi.org/10.1093/bioadv/vbae089","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioadv/vbae089","pdf_url":null,"source":{"id":"https://openalex.org/S4210234069","display_name":"Bioinformatics Advances","issn_l":"2635-0041","issn":["2635-0041"],"is_oa":true,"is_in_doaj":true,"is_core":true,"listed_in":["cwts-core","doaj","jufo-1","ki-jl-1","norway-1","oarl"],"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","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Bioinformatics Advances","raw_type":"journal-article"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320311090","display_name":"Iowa State University","ror":"https://ror.org/04rswrd78"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4399724813.pdf","grobid_xml":"https://content.openalex.org/works/W4399724813.grobid-xml"},"referenced_works_count":34,"referenced_works":["https://openalex.org/W1501531009","https://openalex.org/W1553112231","https://openalex.org/W1614298861","https://openalex.org/W1895949598","https://openalex.org/W1917989004","https://openalex.org/W1968146772","https://openalex.org/W2029702456","https://openalex.org/W2042626827","https://openalex.org/W2057197272","https://openalex.org/W2081741335","https://openalex.org/W2108228587","https://openalex.org/W2110630265","https://openalex.org/W2115590956","https://openalex.org/W2119952049","https://openalex.org/W2121166240","https://openalex.org/W2121621283","https://openalex.org/W2121695290","https://openalex.org/W2129978006","https://openalex.org/W2131744502","https://openalex.org/W2141879010","https://openalex.org/W2151183612","https://openalex.org/W2158847524","https://openalex.org/W2159487602","https://openalex.org/W2170747616","https://openalex.org/W2583689529","https://openalex.org/W2610656577","https://openalex.org/W2790921906","https://openalex.org/W2807480080","https://openalex.org/W2951765074","https://openalex.org/W2987707723","https://openalex.org/W3023097186","https://openalex.org/W3046275257","https://openalex.org/W3120018424","https://openalex.org/W3161876650"],"related_works":["https://openalex.org/W3186277893","https://openalex.org/W2276690235","https://openalex.org/W1964752634","https://openalex.org/W3163993014","https://openalex.org/W2786780977","https://openalex.org/W7062405568","https://openalex.org/W2906549729","https://openalex.org/W4394893984","https://openalex.org/W4212839729","https://openalex.org/W2172093365"],"abstract_inverted_index":{"Motivation:":[0],"Genomic":[1],"islands":[2],"(GEIs)":[3],"are":[4,12],"clusters":[5],"of":[6,27,43,80,97,115,132,140,164],"genes":[7],"in":[8,24,63,87,166],"bacterial":[9,168],"genomes":[10],"that":[11,152],"typically":[13],"acquired":[14],"by":[15,29],"horizontal":[16],"gene":[17],"transfer.":[18],"GEIs":[19,49,57,165],"play":[20],"a":[21,94,111,123,144],"crucial":[22],"role":[23],"the":[25,88,138],"evolution":[26],"bacteria":[28],"rapidly":[30],"introducing":[31],"genetic":[32],"diversity":[33],"and":[34,52,65,135,161,171],"thus":[35],"helping":[36],"them":[37],"adapt":[38],"to":[39,45,118],"changing":[40],"environments.":[41],"Specifically":[42],"interest":[44],"human":[46],"health,":[47],"many":[48,71],"contain":[50],"pathogenicity":[51],"antimicrobial":[53],"resistance":[54],"genes.":[55],"Detecting":[56],"is,":[58],"therefore,":[59],"an":[60,129,177],"important":[61],"problem":[62],"biomedical":[64],"environmental":[66],"research.":[67],"There":[68],"have":[69],"been":[70],"previous":[72],"studies":[73,82],"for":[74],"computationally":[75],"identifying":[76],"GEIs.":[77,120],"Still,":[78],"most":[79],"these":[81],"rely":[83],"on":[84,93,100],"detecting":[85],"anomalies":[86],"unannotated":[89,167],"nucleotide":[90,102],"sequences":[91,117],"or":[92],"fixed":[95],"set":[96],"known":[98],"features":[99],"annotated":[101],"sequences.":[103],"Results:":[104],"Here,":[105],"we":[106,136],"present":[107],"TreasureIsland,":[108],"which":[109],"uses":[110],"new":[112,145],"unsupervised":[113],"representation":[114],"DNA":[116],"predict":[119],"We":[121,150],"developed":[122],"high-precision":[124],"boundary":[125],"detection":[126],"method":[127],"featuring":[128],"incremental":[130],"fine-tuning":[131],"GEI":[133,157],"borders,":[134],"evaluated":[137],"accuracy":[139,154],"this":[141],"framework":[142],"using":[143],"comprehensive":[146],"reference":[147],"dataset,":[148],"Benbow.":[149],"show":[151],"TreasureIsland's":[153],"rivals":[155],"other":[156],"predictors,":[158],"enabling":[159],"efficient":[160],"faster":[162],"identification":[163],"genomes.":[169],"Availability":[170],"implementation:":[172],"TreasureIsland":[173],"is":[174],"available":[175],"under":[176],"MIT":[178],"license":[179],"at:":[180],"https://github.com/FriedbergLab/GenomicIslandPrediction.":[181]},"counts_by_year":[{"year":2026,"cited_by_count":6},{"year":2025,"cited_by_count":7}],"updated_date":"2026-11-06T12:05:46.655746","created_date":"2024-06-18T00:00:00"}
