{"id":"https://openalex.org/W7214955226","doi":"https://doi.org/10.64898/2026.09.27.754806","title":"PathoBERT: A Hybrid Attention-Based Genomic Language Model for Read-Level Bacterial Pathogenicity Prediction","display_name":"PathoBERT: A Hybrid Attention-Based Genomic Language Model for Read-Level Bacterial Pathogenicity Prediction","publication_year":2026,"publication_date":"2026-09-29","ids":{"openalex":"https://openalex.org/W7214955226","doi":"https://doi.org/10.64898/2026.09.27.754806"},"language":"en","primary_location":{"id":"doi:10.64898/2026.09.27.754806","doi":"https://doi.org/10.64898/2026.09.27.754806","is_oa":true,"landing_page_url":"https://doi.org/10.64898/2026.09.27.754806","pdf_url":"https://www.biorxiv.org/content/biorxiv/early/2026/09/29/2026.09.27.754806.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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"bioRxiv","raw_type":"posted-content"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://www.biorxiv.org/content/biorxiv/early/2026/09/29/2026.09.27.754806.full.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5033500589","display_name":"Salem A. El-aarag","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I338016083","display_name":"University of Sadat City","ror":"https://ror.org/05p2q6194","country_code":"EG","type":"education","lineage":["https://openalex.org/I338016083"]}],"countries":["EG"],"is_corresponding":false,"raw_author_name":"Salem A. El-aarag","raw_affiliation_strings":["Bioinformatics Department, Genetic Engineering and Biotechnology Research Institute (GEBRI), University of Sadat City, Egypt"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Bioinformatics Department, Genetic Engineering and Biotechnology Research Institute (GEBRI), University of Sadat City, Egypt","institution_ids":["https://openalex.org/I338016083"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5153637334","display_name":"Mario Flores","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I45438204","display_name":"The University of Texas at San Antonio","ror":"https://ror.org/01kd65564","country_code":"US","type":"education","lineage":["https://openalex.org/I45438204"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mario Flores","raw_affiliation_strings":["Department of Biomedical Engineering, University of Texas at San Antonios, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Biomedical Engineering, University of Texas at San Antonios, USA","institution_ids":["https://openalex.org/I45438204"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136555819","display_name":"Mohamed E. Hasan","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I338016083","display_name":"University of Sadat City","ror":"https://ror.org/05p2q6194","country_code":"EG","type":"education","lineage":["https://openalex.org/I338016083"]}],"countries":["EG"],"is_corresponding":false,"raw_author_name":"Mohamed E Hasan","raw_affiliation_strings":["Bioinformatics Department, Genetic Engineering and Biotechnology Research Institute (GEBRI), University of Sadat City, Egypt"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Bioinformatics Department, Genetic Engineering and Biotechnology Research Institute (GEBRI), University of Sadat City, Egypt","institution_ids":["https://openalex.org/I338016083"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5153606023","display_name":"Alaa E. Hemeida","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I338016083","display_name":"University of Sadat City","ror":"https://ror.org/05p2q6194","country_code":"EG","type":"education","lineage":["https://openalex.org/I338016083"]}],"countries":["EG"],"is_corresponding":false,"raw_author_name":"Alaa E. Hemeida","raw_affiliation_strings":["Bioinformatics Department, Genetic Engineering and Biotechnology Research Institute (GEBRI), University of Sadat City, Egypt"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Bioinformatics Department, Genetic Engineering and Biotechnology Research Institute (GEBRI), University of Sadat City, Egypt","institution_ids":["https://openalex.org/I338016083"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5059536477","display_name":"Mahmoud ElHefnawi","orcid":"https://orcid.org/0000-0003-3896-6911","observed_orcids":["https://orcid.org/0000-0003-3896-6911"]},"institutions":[{"id":"https://openalex.org/I4210131959","display_name":"National Research Centre","ror":"https://ror.org/02n85j827","country_code":"EG","type":"facility","lineage":["https://openalex.org/I4210131959"]}],"countries":["EG"],"is_corresponding":true,"raw_author_name":"Mahmoud ElHefnawi","raw_affiliation_strings":["Biomedical informatics and chemoinformatics group, Informatics and systems department, National Research Center, Egypt"],"raw_orcid":"https://orcid.org/0000-0003-3896-6911","affiliations":[{"raw_affiliation_string":"Biomedical informatics and chemoinformatics group, Informatics and systems department, National Research Center, Egypt","institution_ids":["https://openalex.org/I4210131959"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5059536477"],"corresponding_institution_ids":["https://openalex.org/I4210131959"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.8335000276565552,"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":0.8335000276565552,"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":0.11349999904632568,"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/T13702","display_name":"Machine Learning in Healthcare","score":0.004000000189989805,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/genomic-language-models","display_name":"genomic language models","score":0.9120000004768372},{"id":"https://openalex.org/keywords/dnabert","display_name":"DNABERT","score":0.7670000195503235},{"id":"https://openalex.org/keywords/convolutional-attention","display_name":"convolutional attention","score":0.5730000138282776},{"id":"https://openalex.org/keywords/multi-scale-convolutional-attention","display_name":"multi-scale convolutional attention","score":0.8999999761581421},{"id":"https://openalex.org/keywords/majority-voting","display_name":"majority voting","score":0.5360000133514404},{"id":"https://openalex.org/keywords/short-read-sequencing","display_name":"short-read sequencing","score":0.6840000152587891},{"id":"https://openalex.org/keywords/attention-pooling","display_name":"attention pooling","score":0.40700000524520874}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6480000019073486},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.6248999834060669},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.6129999756813049},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5931000113487244},{"id":"https://openalex.org/C51679486","wikidata":"https://www.wikidata.org/wiki/Q380546","display_name":"DNA sequencing","level":3,"score":0.462799996137619},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.4551999866962433},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.453900009393692},{"id":"https://openalex.org/C141231307","wikidata":"https://www.wikidata.org/wiki/Q7020","display_name":"Genome","level":3,"score":0.4320000112056732},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.4052000045776367},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.39959999918937683},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.3937000036239624},{"id":"https://openalex.org/C64502627","wikidata":"https://www.wikidata.org/wiki/Q170065","display_name":"Pathogenicity","level":2,"score":0.3790999948978424},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.37720000743865967},{"id":"https://openalex.org/C189206191","wikidata":"https://www.wikidata.org/wiki/Q222046","display_name":"Genomics","level":4,"score":0.37630000710487366},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.3465000092983246},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.3361999988555908},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.3305000066757202},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.30630001425743103},{"id":"https://openalex.org/C24432333","wikidata":"https://www.wikidata.org/wiki/Q2068526","display_name":"Whole genome sequencing","level":4,"score":0.3012000024318695},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.2962000072002411},{"id":"https://openalex.org/C21200559","wikidata":"https://www.wikidata.org/wiki/Q7451068","display_name":"Sensitivity (control systems)","level":2,"score":0.29339998960494995},{"id":"https://openalex.org/C132917006","wikidata":"https://www.wikidata.org/wiki/Q5250436","display_name":"Deep sequencing","level":4,"score":0.2915000021457672},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.26899999380111694},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.2678999900817871}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.64898/2026.09.27.754806","doi":"https://doi.org/10.64898/2026.09.27.754806","is_oa":true,"landing_page_url":"https://doi.org/10.64898/2026.09.27.754806","pdf_url":"https://www.biorxiv.org/content/biorxiv/early/2026/09/29/2026.09.27.754806.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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"bioRxiv","raw_type":"posted-content"}],"best_oa_location":{"id":"doi:10.64898/2026.09.27.754806","doi":"https://doi.org/10.64898/2026.09.27.754806","is_oa":true,"landing_page_url":"https://doi.org/10.64898/2026.09.27.754806","pdf_url":"https://www.biorxiv.org/content/biorxiv/early/2026/09/29/2026.09.27.754806.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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"bioRxiv","raw_type":"posted-content"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/3","score":0.504800021648407,"display_name":"Good health and well-being"}],"study_designs":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320310077","display_name":"National Research Centre","ror":"https://ror.org/02n85j827"},{"id":"https://openalex.org/F4320310677","display_name":"University of Texas at San Antonio","ror":"https://ror.org/01kd65564"},{"id":"https://openalex.org/F4320321116","display_name":"Academy of Scientific Research and Technology","ror":"https://ror.org/02k284p70"},{"id":"https://openalex.org/F4320321655","display_name":"Science and Technology Development Fund","ror":"https://ror.org/044vr6g03"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7214955226.pdf","grobid_xml":"https://content.openalex.org/works/W7214955226.grobid-xml"},"referenced_works_count":2,"referenced_works":["https://openalex.org/W2042571564","https://openalex.org/W2167277498"],"related_works":["https://openalex.org/W2961729414","https://openalex.org/W2519678269","https://openalex.org/W6887570747","https://openalex.org/W2570535773","https://openalex.org/W4399929485","https://openalex.org/W2911730062","https://openalex.org/W4220815300","https://openalex.org/W7119539324","https://openalex.org/W3200251465","https://openalex.org/W4416183055"],"abstract_inverted_index":{"Abstract":[0],"Motivation":[1],"Although":[2],"recent":[3],"deep":[4,41],"learning":[5,42],"models":[6,214],"have":[7],"achieved":[8,148],"promising":[9],"results":[10],"on":[11,96,109,164],"read-level":[12,116],"classification":[13,162],"tasks,":[14],"their":[15],"robustness":[16],"to":[17,22,27],"realistic":[18],"sequencing":[19,83,91,98,229],"conditions,":[20],"sensitivity":[21],"read":[23,124],"length,":[24],"and":[25,61,77,100,131,153,174,195,236,241,263],"ability":[26],"support":[28],"reliable":[29],"genome-level":[30,102],"inference":[31,103],"remain":[32],"incompletely":[33],"characterized.":[34],"Here,":[35],"we":[36],"present":[37],"PathoBERT,":[38],"a":[39,46,54,105,119,182,221],"hybrid":[40],"framework":[43,223],"that":[44,181,209],"integrates":[45],"LoRA-adapted":[47],"DNABERT":[48],"encoder":[49],"with":[50,169,215],"convolutional":[51],"feature":[52,218],"extraction,":[53],"modified":[55],"Convolutional":[56,63],"Block":[57],"Attention":[58,64],"Module":[59],"(MCBAM),":[60],"Multi-Scale":[62],"(MSCA)":[65],"for":[66,88,224],"bacterial":[67],"pathogenicity":[68,225],"prediction.":[69],"Results":[70],"The":[71,93,232,254],"model":[72,94],"demonstrated":[73,180],"near-complete":[74],"strand":[75],"invariance":[76],"maintained":[78],"robust":[79,222],"performance":[80,139,163],"under":[81],"simulated":[82],"errors,":[84],"highlighting":[85],"its":[86],"suitability":[87],"real-world":[89],"next-generation":[90],"applications.":[92],"operates":[95],"individual":[97],"reads":[99],"supports":[101],"through":[104],"read-aggregation":[106],"strategy":[107],"based":[108],"the":[110,123,144,165,189,201,249],"Pathogenic":[111],"Fraction":[112],"(PathFrac),":[113],"which":[114],"combines":[115],"predictions":[117],"using":[118,156],"majority-vote":[120],"framework.":[121],"At":[122,143],"level,":[125,146],"PathoBERT":[126,147],"outperformed":[127],"DeePaC":[128,173],"at":[129,140,261],"short":[130],"moderate":[132],"fragment":[133],"lengths":[134],"(100\u2013150":[135],"bp),":[136],"achieving":[137],"peak":[138],"150":[141],"bp.":[142],"genome":[145],"perfect":[149,161],"separation":[150],"between":[151],"pathogenic":[152],"non-pathogenic":[154],"genomes":[155],"PathFrac-based":[157],"aggregation,":[158],"resulting":[159],"in":[160,192],"evaluated":[166],"benchmark":[167],"compared":[168],"competing":[170],"approaches,":[171],"namely":[172],"PathogenFinder":[175],"2.":[176],"Representation-level":[177],"analyses":[178],"further":[179],"progressive":[183],"refinement":[184],"of":[185],"pathogen-associated":[186],"features":[187],"throughout":[188],"architecture,":[190],"culminating":[191],"highly":[193],"separable":[194],"biologically":[196],"meaningful":[197],"latent":[198],"representations":[199],"within":[200],"final":[202],"attention-pooled":[203],"embedding":[204],"space.":[205],"These":[206],"findings":[207],"demonstrate":[208],"integrating":[210],"contextual":[211],"genomic":[212],"language":[213],"attention-guided":[216],"multi-scale":[217],"extraction":[219],"provides":[220],"prediction":[226],"from":[227,248],"short-read":[228],"data.":[230],"Availability":[231],"supplementary":[233],"data,":[234],"datasets,":[235],"archived":[237],"source":[238,255],"code":[239,256],"generated":[240],"analyzed":[242],"during":[243],"this":[244],"study":[245],"are":[246],"available":[247,258],"Zenodo":[250],"repository":[251],"(DOI:":[252],"10.5281/zenodo.11179933).":[253],"is":[257],"via":[259],"GitHub":[260],"https://github.com/MahmoudElHefnawi/PathoBERT":[262],"https://github.com/salimalaarag/PathoBERT":[264],".":[265]},"counts_by_year":[],"updated_date":"2026-11-09T13:22:03.289127","created_date":"2026-10-01T00:00:00"}