{"id":"https://openalex.org/W4390790220","doi":"https://doi.org/10.3389/fmicb.2023.1331233","title":"ProkBERT family: genomic language models for microbiome applications","display_name":"ProkBERT family: genomic language models for microbiome applications","publication_year":2024,"publication_date":"2024-01-11","ids":{"openalex":"https://openalex.org/W4390790220","doi":"https://doi.org/10.3389/fmicb.2023.1331233","pmid":"https://pubmed.ncbi.nlm.nih.gov/38282738","pmcid":"https://www.ncbi.nlm.nih.gov/pmc/articles/10810988"},"language":"en","primary_location":{"id":"doi:10.3389/fmicb.2023.1331233","doi":"https://doi.org/10.3389/fmicb.2023.1331233","is_oa":true,"landing_page_url":"https://doi.org/10.3389/fmicb.2023.1331233","pdf_url":"https://www.frontiersin.org/articles/10.3389/fmicb.2023.1331233/pdf?isPublishedV2=False","source":{"id":"https://openalex.org/S2484704948","display_name":"Frontiers in Microbiology","issn_l":"1664-302X","issn":["1664-302X"],"is_oa":true,"is_in_doaj":true,"is_core":true,"listed_in":["cwts-core","doaj","jufo-1","ki-jl-1","norway-2","poland-100","russia-white-list-1","vabb-shw"],"host_organization":"https://openalex.org/P4310320527","host_organization_name":"Frontiers Media","host_organization_lineage":["https://openalex.org/P4310320527"],"host_organization_lineage_names":["Frontiers Media"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Microbiology","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://www.frontiersin.org/articles/10.3389/fmicb.2023.1331233/pdf?isPublishedV2=False","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5006056998","display_name":"Bal\u00e1zs Ligeti","orcid":"https://orcid.org/0000-0003-0301-0434","observed_orcids":["https://orcid.org/0000-0003-0301-0434"]},"institutions":[{"id":"https://openalex.org/I31882830","display_name":"P\u00e1zm\u00e1ny P\u00e9ter Catholic University","ror":"https://ror.org/05v9kya57","country_code":"HU","type":"education","lineage":["https://openalex.org/I31882830"]}],"countries":["HU"],"is_corresponding":true,"raw_author_name":"Bal\u00e1zs Ligeti","raw_affiliation_strings":["Faculty of Information Technology and Bionics, P\u00e1zm\u00e1ny P\u00e9ter Catholic University, Budapest, Hungary"],"raw_orcid":"https://orcid.org/0000-0003-0301-0434","affiliations":[{"raw_affiliation_string":"Faculty of Information Technology and Bionics, P\u00e1zm\u00e1ny P\u00e9ter Catholic University, Budapest, Hungary","institution_ids":["https://openalex.org/I31882830"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5093265715","display_name":"Istv\u00e1n Szepesi-Nagy","orcid":"https://orcid.org/0009-0005-8849-9006","observed_orcids":["https://orcid.org/0009-0005-8849-9006"]},"institutions":[{"id":"https://openalex.org/I31882830","display_name":"P\u00e1zm\u00e1ny P\u00e9ter Catholic University","ror":"https://ror.org/05v9kya57","country_code":"HU","type":"education","lineage":["https://openalex.org/I31882830"]}],"countries":["HU"],"is_corresponding":false,"raw_author_name":"Istv\u00e1n Szepesi-Nagy","raw_affiliation_strings":["Faculty of Information Technology and Bionics, P\u00e1zm\u00e1ny P\u00e9ter Catholic University, Budapest, Hungary"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Faculty of Information Technology and Bionics, P\u00e1zm\u00e1ny P\u00e9ter Catholic University, Budapest, Hungary","institution_ids":["https://openalex.org/I31882830"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108312247","display_name":"Babett Bodn\u00e1r","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I31882830","display_name":"P\u00e1zm\u00e1ny P\u00e9ter Catholic University","ror":"https://ror.org/05v9kya57","country_code":"HU","type":"education","lineage":["https://openalex.org/I31882830"]}],"countries":["HU"],"is_corresponding":false,"raw_author_name":"Babett Bodn\u00e1r","raw_affiliation_strings":["Faculty of Information Technology and Bionics, P\u00e1zm\u00e1ny P\u00e9ter Catholic University, Budapest, Hungary"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Faculty of Information Technology and Bionics, P\u00e1zm\u00e1ny P\u00e9ter Catholic University, Budapest, Hungary","institution_ids":["https://openalex.org/I31882830"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005415440","display_name":"No\u00e9mi Ligeti-Nagy","orcid":"https://orcid.org/0000-0003-0851-7621","observed_orcids":["https://orcid.org/0000-0003-0851-7621"]},"institutions":[{"id":"https://openalex.org/I2802350943","display_name":"ELTE Research Centre for Linguistics","ror":"https://ror.org/005cqsz63","country_code":"HU","type":"facility","lineage":["https://openalex.org/I2802350943"]},{"id":"https://openalex.org/I4387152226","display_name":"Hungarian Research Network","ror":"https://ror.org/04w6pnc49","country_code":"HU","type":"other","lineage":["https://openalex.org/I4387152226"]}],"countries":["HU"],"is_corresponding":false,"raw_author_name":"No\u00e9mi Ligeti-Nagy","raw_affiliation_strings":["Language Technology Research Group, HUN-REN Hungarian Research Centre for Linguistics, Budapest, Hungary"],"raw_orcid":"https://orcid.org/0000-0003-0851-7621","affiliations":[{"raw_affiliation_string":"Language Technology Research Group, HUN-REN Hungarian Research Centre for Linguistics, Budapest, Hungary","institution_ids":["https://openalex.org/I2802350943","https://openalex.org/I4387152226"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5043311933","display_name":"J\u00e1nos Juh\u00e1sz","orcid":"https://orcid.org/0000-0002-1307-7387","observed_orcids":["https://orcid.org/0000-0002-1307-7387"]},"institutions":[{"id":"https://openalex.org/I101202996","display_name":"Semmelweis University","ror":"https://ror.org/01g9ty582","country_code":"HU","type":"education","lineage":["https://openalex.org/I101202996"]},{"id":"https://openalex.org/I31882830","display_name":"P\u00e1zm\u00e1ny P\u00e9ter Catholic University","ror":"https://ror.org/05v9kya57","country_code":"HU","type":"education","lineage":["https://openalex.org/I31882830"]}],"countries":["HU"],"is_corresponding":false,"raw_author_name":"J\u00e1nos Juh\u00e1sz","raw_affiliation_strings":["Faculty of Information Technology and Bionics, P\u00e1zm\u00e1ny P\u00e9ter Catholic University, Budapest, Hungary","Institute of Medical Microbiology, Semmelweis University, Budapest, Hungary"],"raw_orcid":"https://orcid.org/0000-0002-1307-7387","affiliations":[{"raw_affiliation_string":"Faculty of Information Technology and Bionics, P\u00e1zm\u00e1ny P\u00e9ter Catholic University, Budapest, Hungary","institution_ids":["https://openalex.org/I31882830"]},{"raw_affiliation_string":"Institute of Medical Microbiology, Semmelweis University, Budapest, Hungary","institution_ids":["https://openalex.org/I101202996"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5006056998"],"corresponding_institution_ids":["https://openalex.org/I31882830"],"apc_list":{"value":3295,"currency":"USD","value_usd":3295},"apc_paid":{"value":3295,"currency":"USD","value_usd":3295},"fwci":3.453,"has_fulltext":true,"cited_by_count":30,"citation_normalized_percentile":{"value":0.94691592,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":93,"max":100},"biblio":{"volume":"14","issue":null,"first_page":"1331233","last_page":"1331233"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.4625999927520752,"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":0.4625999927520752,"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/T12254","display_name":"Machine Learning in Bioinformatics","score":0.4490000009536743,"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/T11048","display_name":"Bacteriophages and microbial interactions","score":0.05180000141263008,"subfield":{"id":"https://openalex.org/subfields/2406","display_name":"Virology"},"field":{"id":"https://openalex.org/fields/24","display_name":"Immunology and Microbiology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/genomic-language-models","display_name":"genomic language models","score":0.7829999923706055},{"id":"https://openalex.org/keywords/phage-identification","display_name":"phage identification","score":0.8799999952316284},{"id":"https://openalex.org/keywords/self-supervised-learning","display_name":"self-supervised learning","score":0.671999990940094},{"id":"https://openalex.org/keywords/transfer-learning","display_name":"transfer learning","score":0.9760000109672546},{"id":"https://openalex.org/keywords/microbial-genomics","display_name":"microbial genomics","score":0.5600000023841858},{"id":"https://openalex.org/keywords/microbiome-analysis","display_name":"microbiome analysis","score":0.6259999871253967},{"id":"https://openalex.org/keywords/protein-function-prediction","display_name":"protein function prediction","score":0.3070000112056732}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6662567853927612},{"id":"https://openalex.org/C177606310","wikidata":"https://www.wikidata.org/wiki/Q5674297","display_name":"Adaptability","level":2,"score":0.5458905100822449},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.5451956391334534},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5422111749649048},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5351712703704834},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5175853967666626},{"id":"https://openalex.org/C143121216","wikidata":"https://www.wikidata.org/wiki/Q1330402","display_name":"Microbiome","level":2,"score":0.5043610334396362},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.4810369312763214},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.41313350200653076},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.2741820812225342},{"id":"https://openalex.org/C60644358","wikidata":"https://www.wikidata.org/wiki/Q128570","display_name":"Bioinformatics","level":1,"score":0.22124025225639343},{"id":"https://openalex.org/C18903297","wikidata":"https://www.wikidata.org/wiki/Q7150","display_name":"Ecology","level":1,"score":0.1442371904850006},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.3389/fmicb.2023.1331233","doi":"https://doi.org/10.3389/fmicb.2023.1331233","is_oa":true,"landing_page_url":"https://doi.org/10.3389/fmicb.2023.1331233","pdf_url":"https://www.frontiersin.org/articles/10.3389/fmicb.2023.1331233/pdf?isPublishedV2=False","source":{"id":"https://openalex.org/S2484704948","display_name":"Frontiers in Microbiology","issn_l":"1664-302X","issn":["1664-302X"],"is_oa":true,"is_in_doaj":true,"is_core":true,"listed_in":["cwts-core","doaj","jufo-1","ki-jl-1","norway-2","poland-100","russia-white-list-1","vabb-shw"],"host_organization":"https://openalex.org/P4310320527","host_organization_name":"Frontiers Media","host_organization_lineage":["https://openalex.org/P4310320527"],"host_organization_lineage_names":["Frontiers Media"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Microbiology","raw_type":"journal-article"},{"id":"doi:10.1101/2023.11.09.566411","doi":"https://doi.org/10.1101/2023.11.09.566411","is_oa":true,"landing_page_url":"http://dx.doi.org/10.1101/2023.11.09.566411","pdf_url":"https://www.biorxiv.org/content/biorxiv/early/2023/11/15/2023.11.09.566411.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-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"bioRxiv","raw_type":"posted-content"},{"id":"pmh:oai:pubmedcentral.nih.gov:10810988","doi":null,"is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/10810988","pdf_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC10810988/pdf/fmicb-14-1331233.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":"Front Microbiol","raw_type":"Text"},{"id":"pmid:38282738","doi":null,"is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/38282738","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":"Frontiers in microbiology","raw_type":"Journal Article"},{"id":"pmh:oai:doaj.org/article:70aca71fe6ac4140ae6e25e38af27a2b","doi":null,"is_oa":true,"landing_page_url":"https://doaj.org/article/70aca71fe6ac4140ae6e25e38af27a2b","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Frontiers in Microbiology, Vol 14 (2024)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.3389/fmicb.2023.1331233","doi":"https://doi.org/10.3389/fmicb.2023.1331233","is_oa":true,"landing_page_url":"https://doi.org/10.3389/fmicb.2023.1331233","pdf_url":"https://www.frontiersin.org/articles/10.3389/fmicb.2023.1331233/pdf?isPublishedV2=False","source":{"id":"https://openalex.org/S2484704948","display_name":"Frontiers in Microbiology","issn_l":"1664-302X","issn":["1664-302X"],"is_oa":true,"is_in_doaj":true,"is_core":true,"listed_in":["cwts-core","doaj","jufo-1","ki-jl-1","norway-2","poland-100","russia-white-list-1","vabb-shw"],"host_organization":"https://openalex.org/P4310320527","host_organization_name":"Frontiers Media","host_organization_lineage":["https://openalex.org/P4310320527"],"host_organization_lineage_names":["Frontiers Media"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Microbiology","raw_type":"journal-article"},"sustainable_development_goals":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G3146357332","display_name":null,"funder_award_id":"HIR 10-001","funder_id":"https://openalex.org/F4320306127","funder_display_name":"U.S. Department of Veterans Affairs"}],"funders":[{"id":"https://openalex.org/F1100377486","display_name":"European High Performance Computing Joint Undertaking","ror":"https://ror.org/04dvh0v63"},{"id":"https://openalex.org/F4320306127","display_name":"U.S. Department of Veterans Affairs","ror":"https://ror.org/05rsv9s98"},{"id":"https://openalex.org/F4320321994","display_name":"Hungarian Scientific Research Fund","ror":"https://ror.org/00v349e63"},{"id":"https://openalex.org/F4320326762","display_name":"Nemzeti Kutat\u00e1si Fejleszt\u00e9si \u00e9s Innov\u00e1ci\u00f3s Hivatal","ror":null}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4390790220.pdf","grobid_xml":"https://content.openalex.org/works/W4390790220.grobid-xml"},"referenced_works_count":86,"referenced_works":["https://openalex.org/W1019830208","https://openalex.org/W1975540898","https://openalex.org/W1987971958","https://openalex.org/W2004548026","https://openalex.org/W2006492816","https://openalex.org/W2022366078","https://openalex.org/W2023816042","https://openalex.org/W2034200083","https://openalex.org/W2047288044","https://openalex.org/W2083122216","https://openalex.org/W2095724929","https://openalex.org/W2096093282","https://openalex.org/W2101350700","https://openalex.org/W2119123521","https://openalex.org/W2126569085","https://openalex.org/W2133253129","https://openalex.org/W2156125289","https://openalex.org/W2157331557","https://openalex.org/W2158023121","https://openalex.org/W2160053034","https://openalex.org/W2165698076","https://openalex.org/W2170747616","https://openalex.org/W2173732482","https://openalex.org/W2311607323","https://openalex.org/W2314649741","https://openalex.org/W2443415468","https://openalex.org/W2470052926","https://openalex.org/W2526784604","https://openalex.org/W2601450892","https://openalex.org/W2626778328","https://openalex.org/W2735006823","https://openalex.org/W2754289562","https://openalex.org/W2760000637","https://openalex.org/W2799200068","https://openalex.org/W2800015127","https://openalex.org/W2889230731","https://openalex.org/W2889772740","https://openalex.org/W2896457183","https://openalex.org/W2900007277","https://openalex.org/W2903162518","https://openalex.org/W2903705053","https://openalex.org/W2909409778","https://openalex.org/W2919115771","https://openalex.org/W2952239877","https://openalex.org/W2963341956","https://openalex.org/W2963739921","https://openalex.org/W2973727699","https://openalex.org/W2981852735","https://openalex.org/W3003110834","https://openalex.org/W3010746544","https://openalex.org/W3025306404","https://openalex.org/W3030163527","https://openalex.org/W3033129278","https://openalex.org/W3035524453","https://openalex.org/W3039032764","https://openalex.org/W3081166989","https://openalex.org/W3109735703","https://openalex.org/W3119507732","https://openalex.org/W3127238141","https://openalex.org/W3127656915","https://openalex.org/W3127836515","https://openalex.org/W3132229552","https://openalex.org/W3138273830","https://openalex.org/W3171649327","https://openalex.org/W3177828909","https://openalex.org/W3187418919","https://openalex.org/W3203343200","https://openalex.org/W3214710775","https://openalex.org/W4210265219","https://openalex.org/W4220685469","https://openalex.org/W4245668478","https://openalex.org/W4280524269","https://openalex.org/W4282936970","https://openalex.org/W4289593660","https://openalex.org/W4289712796","https://openalex.org/W4292800918","https://openalex.org/W4308736754","https://openalex.org/W4309305993","https://openalex.org/W4315641887","https://openalex.org/W4318685265","https://openalex.org/W4318756379","https://openalex.org/W4382490702","https://openalex.org/W4386253786","https://openalex.org/W4394808305","https://openalex.org/W4404821554","https://openalex.org/W6853888595"],"related_works":["https://openalex.org/W4416134680","https://openalex.org/W4221138532","https://openalex.org/W7125629749","https://openalex.org/W4416235444","https://openalex.org/W7141556418","https://openalex.org/W4411107668","https://openalex.org/W4407907970","https://openalex.org/W4388706791","https://openalex.org/W4417411274","https://openalex.org/W4401435602"],"abstract_inverted_index":{"Background:":[0],"In":[1,191],"the":[2,10,32,43,69,101,105,136,146,161,212,236,281],"evolving":[3],"landscape":[4],"of":[5,12,34,48,62,75,111,145,164,207,238,254],"microbiology":[6,38,239],"and":[7,22,24,45,58,114,119,129,186,202,216,221,240,248,273],"microbiome":[8],"analysis,":[9],"integration":[11],"machine":[13,261],"learning":[14,128,262],"is":[15,229],"crucial":[16],"for":[17,80,89,244,280],"understanding":[18,110],"complex":[19,44,139],"microbial":[20,49,112,140],"interactions,":[21],"predicting":[23],"recognizing":[25],"novel":[26,147],"functionalities":[27],"within":[28],"extensive":[29],"datasets.":[30,65],"However,":[31],"effectiveness":[33],"these":[35],"methods":[36],"in":[37,104,188,218,235,260,264],"faces":[39],"challenges":[40],"due":[41],"to":[42,134,159],"heterogeneous":[46],"nature":[47],"data,":[50],"further":[51],"complicated":[52],"by":[53],"low":[54],"signal-to-noise":[55],"ratios,":[56],"context-dependency,":[57],"a":[59,73,85,154,230,252,257],"significant":[60,155,258],"shortage":[61],"appropriately":[63],"labeled":[64],"This":[66,97,168],"study":[67],"introduces":[68],"ProkBERT":[70,122,158,194,226],"model":[71,227],"family,":[72],"collection":[74],"large":[76],"language":[77],"models,":[78],"designed":[79],"genomic":[81],"tasks.":[82,184,223],"It":[83],"provides":[84],"generalizable":[86],"sequence":[87],"representation":[88],"nucleotide":[90],"sequences,":[91],"learned":[92],"from":[93],"unlabeled":[94],"genome":[95],"data.":[96],"approach":[98],"helps":[99],"overcome":[100,160],"above-mentioned":[102],"limitations":[103,163],"field,":[106],"thereby":[107],"improving":[108],"our":[109],"ecosystems":[113],"their":[115],"impact":[116],"on":[117,126,270],"health":[118],"disease.":[120],"Methods:":[121],"models":[123,195,267],"are":[124,268],"based":[125],"transfer":[127],"self-supervised":[130],"methodologies,":[131],"enabling":[132],"them":[133],"use":[135],"abundant":[137],"yet":[138,232],"data":[141],"effectively.":[142],"The":[143,225,266],"introduction":[144],"Local":[148],"Context-Aware":[149],"(LCA)":[150],"tokenization":[151],"technique":[152],"marks":[153,256],"advancement,":[156],"allowing":[157],"contextual":[162],"traditional":[165],"transformer":[166],"models.":[167],"methodology":[169],"not":[170],"only":[171],"retains":[172],"rich":[173],"local":[174],"context":[175],"but":[176],"also":[177],"demonstrates":[178],"remarkable":[179],"adaptability":[180,250],"across":[181,251],"various":[182],"bioinformatics":[183],"Results:":[185],"0.62":[187],"mixed-species":[189],"contexts.":[190],"phage":[192],"identification,":[193],"consistently":[196],"outperformed":[197],"established":[198],"tools":[199],"like":[200],"VirSorter2":[201],"DeepVirFinder,":[203],"achieving":[204],"an":[205,277],"MCC":[206],"0.85.":[208],"These":[209],"results":[210],"underscore":[211],"models'":[213],"exceptional":[214],"accuracy":[215],"generalizability":[217],"both":[219],"supervised":[220],"unsupervised":[222],"Conclusions:":[224],"family":[228],"compact":[231],"powerful":[233],"tool":[234,279],"field":[237],"bioinformatics.":[241],"Its":[242],"capacity":[243],"rapid,":[245],"accurate":[246],"analyses":[247],"its":[249],"spectrum":[253],"tasks":[255],"advancement":[259],"applications":[263],"microbiology.":[265],"available":[269],"GitHub":[271],"(https://github.com/nbrg-ppcu/prokbert)":[272],"HuggingFace":[274],"(https://huggingface.co/nerualbioinfo)":[275],"providing":[276],"accessible":[278],"community.":[282]},"counts_by_year":[{"year":2026,"cited_by_count":14},{"year":2025,"cited_by_count":14},{"year":2024,"cited_by_count":2}],"updated_date":"2026-11-04T10:54:05.112534","created_date":"2024-01-13T00:00:00"}