{"id":"https://openalex.org/W7221506434","doi":"https://doi.org/10.64898/2026.10.07.757501","title":"PhageHost-GNN: novelty-aware and locally adaptable strain-level Klebsiella -phage prediction","display_name":"PhageHost-GNN: novelty-aware and locally adaptable strain-level Klebsiella -phage prediction","publication_year":2026,"publication_date":"2026-10-11","ids":{"openalex":"https://openalex.org/W7221506434","doi":"https://doi.org/10.64898/2026.10.07.757501"},"language":"en","primary_location":{"id":"doi:10.64898/2026.10.07.757501","doi":"https://doi.org/10.64898/2026.10.07.757501","is_oa":true,"landing_page_url":"https://doi.org/10.64898/2026.10.07.757501","pdf_url":"https://www.biorxiv.org/content/biorxiv/early/2026/10/11/2026.10.07.757501.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"},"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/2026/10/11/2026.10.07.757501.full.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5078283432","display_name":"Biffon Manyura Momanyi","orcid":"https://orcid.org/0000-0001-6893-9709","observed_orcids":["https://orcid.org/0000-0001-6893-9709"]},"institutions":[{"id":"https://openalex.org/I3045169105","display_name":"Southern University of Science and Technology","ror":"https://ror.org/049tv2d57","country_code":"CN","type":"education","lineage":["https://openalex.org/I3045169105"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Biffon Manyura Momanyi","raw_affiliation_strings":["The Department of Ocean Science and Engineering, Southern University of Science and Technology, Shenzhen, Guangdong 518055, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Department of Ocean Science and Engineering, Southern University of Science and Technology, Shenzhen, Guangdong 518055, China","institution_ids":["https://openalex.org/I3045169105"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013555471","display_name":"Kunhao Qin","orcid":"https://orcid.org/0000-0002-3740-4661","observed_orcids":["https://orcid.org/0000-0002-3740-4661"]},"institutions":[{"id":"https://openalex.org/I180726961","display_name":"Shenzhen University","ror":"https://ror.org/01vy4gh70","country_code":"CN","type":"education","lineage":["https://openalex.org/I180726961"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kunhao Qin","raw_affiliation_strings":["Department of Pathogen Biology, Shenzhen University Medical School, Shenzhen University, Shenzhen, Guangdong 518055, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Pathogen Biology, Shenzhen University Medical School, Shenzhen University, Shenzhen, Guangdong 518055, China","institution_ids":["https://openalex.org/I180726961"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035515939","display_name":"Kai Zhou","orcid":"https://orcid.org/0000-0002-7320-291X","observed_orcids":["https://orcid.org/0000-0002-7320-291X"]},"institutions":[{"id":"https://openalex.org/I180726961","display_name":"Shenzhen University","ror":"https://ror.org/01vy4gh70","country_code":"CN","type":"education","lineage":["https://openalex.org/I180726961"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kai Zhou","raw_affiliation_strings":["Department of Pathogen Biology, Shenzhen University Medical School, Shenzhen University, Shenzhen, Guangdong 518055, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Pathogen Biology, Shenzhen University Medical School, Shenzhen University, Shenzhen, Guangdong 518055, China","institution_ids":["https://openalex.org/I180726961"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5037516307","display_name":"Lu Fan","orcid":"https://orcid.org/0000-0002-4184-7211","observed_orcids":["https://orcid.org/0000-0002-4184-7211"]},"institutions":[{"id":"https://openalex.org/I3045169105","display_name":"Southern University of Science and Technology","ror":"https://ror.org/049tv2d57","country_code":"CN","type":"education","lineage":["https://openalex.org/I3045169105"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Lu Fan","raw_affiliation_strings":["The Department of Ocean Science and Engineering, Southern University of Science and Technology, Shenzhen, Guangdong 518055, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Department of Ocean Science and Engineering, Southern University of Science and Technology, Shenzhen, Guangdong 518055, China","institution_ids":["https://openalex.org/I3045169105"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5037516307"],"corresponding_institution_ids":["https://openalex.org/I3045169105"],"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/T11048","display_name":"Bacteriophages and microbial interactions","score":0.9994999766349792,"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"}},"topics":[{"id":"https://openalex.org/T11048","display_name":"Bacteriophages and microbial interactions","score":0.9994999766349792,"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"}},{"id":"https://openalex.org/T12254","display_name":"Machine Learning in Bioinformatics","score":0.0,"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/T10878","display_name":"CRISPR and Genetic Engineering","score":0.0,"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/klebsiella","display_name":"Klebsiella","score":0.8980000019073486},{"id":"https://openalex.org/keywords/bacteriophages","display_name":"bacteriophages","score":0.843999981880188},{"id":"https://openalex.org/keywords/phage-therapy","display_name":"phage therapy","score":0.8960000276565552},{"id":"https://openalex.org/keywords/graph-neural-networks","display_name":"graph neural networks","score":0.8759999871253967},{"id":"https://openalex.org/keywords/fine-tuning","display_name":"fine-tuning","score":0.7160000205039978},{"id":"https://openalex.org/keywords/multidrug-resistance","display_name":"multidrug resistance","score":0.7519999742507935}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7021999955177307},{"id":"https://openalex.org/C66746571","wikidata":"https://www.wikidata.org/wiki/Q1134833","display_name":"ENCODE","level":3,"score":0.597000002861023},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.5343999862670898},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5271999835968018},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.4603999853134155},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.4422000050544739},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.4408999979496002},{"id":"https://openalex.org/C2775905019","wikidata":"https://www.wikidata.org/wiki/Q192572","display_name":"In silico","level":3,"score":0.4327000081539154},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.42800000309944153},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.40070000290870667},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.3982999920845032},{"id":"https://openalex.org/C2778738651","wikidata":"https://www.wikidata.org/wiki/Q16546687","display_name":"Novelty","level":2,"score":0.3982999920845032},{"id":"https://openalex.org/C177212765","wikidata":"https://www.wikidata.org/wiki/Q627335","display_name":"Workflow","level":2,"score":0.3831999897956848},{"id":"https://openalex.org/C66024118","wikidata":"https://www.wikidata.org/wiki/Q1122506","display_name":"Computational model","level":2,"score":0.3718000054359436},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3612000048160553},{"id":"https://openalex.org/C126831891","wikidata":"https://www.wikidata.org/wiki/Q221673","display_name":"Host (biology)","level":2,"score":0.3499999940395355},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.34869998693466187},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.3305000066757202},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.31929999589920044},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.31610000133514404},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.29420000314712524},{"id":"https://openalex.org/C87186988","wikidata":"https://www.wikidata.org/wiki/Q452197","display_name":"SBML","level":4,"score":0.2921999990940094},{"id":"https://openalex.org/C187691185","wikidata":"https://www.wikidata.org/wiki/Q2020720","display_name":"Grid","level":2,"score":0.2903999984264374},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.28780001401901245},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.2694999873638153},{"id":"https://openalex.org/C2779714256","wikidata":"https://www.wikidata.org/wiki/Q25305062","display_name":"Multiple Models","level":2,"score":0.2689000070095062},{"id":"https://openalex.org/C189474733","wikidata":"https://www.wikidata.org/wiki/Q917912","display_name":"Model building","level":2,"score":0.26840001344680786},{"id":"https://openalex.org/C45804977","wikidata":"https://www.wikidata.org/wiki/Q7239673","display_name":"Predictive modelling","level":2,"score":0.257099986076355},{"id":"https://openalex.org/C2984074130","wikidata":"https://www.wikidata.org/wiki/Q73539779","display_name":"R package","level":2,"score":0.2565999925136566}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.64898/2026.10.07.757501","doi":"https://doi.org/10.64898/2026.10.07.757501","is_oa":true,"landing_page_url":"https://doi.org/10.64898/2026.10.07.757501","pdf_url":"https://www.biorxiv.org/content/biorxiv/early/2026/10/11/2026.10.07.757501.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"}],"best_oa_location":{"id":"doi:10.64898/2026.10.07.757501","doi":"https://doi.org/10.64898/2026.10.07.757501","is_oa":true,"landing_page_url":"https://doi.org/10.64898/2026.10.07.757501","pdf_url":"https://www.biorxiv.org/content/biorxiv/early/2026/10/11/2026.10.07.757501.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"},"sustainable_development_goals":[{"score":0.504800021648407,"id":"https://metadata.un.org/sdg/3","display_name":"Good health and well-being"}],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7221506434.pdf","grobid_xml":"https://content.openalex.org/works/W7221506434.grobid-xml"},"referenced_works_count":1,"referenced_works":["https://openalex.org/W2789412894"],"related_works":["https://openalex.org/W4398208413","https://openalex.org/W4416332079","https://openalex.org/W7220671738","https://openalex.org/W7125567298","https://openalex.org/W7214786235","https://openalex.org/W7154607299","https://openalex.org/W4406604086","https://openalex.org/W4416052827","https://openalex.org/W6980142503","https://openalex.org/W7203461017"],"abstract_inverted_index":{"Abstract":[0],"Interest":[1],"in":[2,111,116,184],"bacteriophages":[3],"as":[4],"alternative":[5,55],"treatments":[6],"for":[7,31,49,177,194],"bacterial":[8,32],"infections":[9],"has":[10],"grown":[11],"amid":[12],"the":[13,52,102,126,140,152,215],"ongoing":[14],"crisis":[15],"of":[16,54,66,198,217],"multidrug":[17],"resistance.":[18],"However,":[19],"their":[20],"narrow":[21],"host":[22],"range":[23],"makes":[24],"it":[25],"labor-intensive":[26],"to":[27,80,95,139,145,159,163],"identify":[28],"matching":[29],"phages":[30,136],"isolates":[33],"using":[34,77],"conventional":[35],"experimental":[36],"methods.":[37],"Although":[38],"existing":[39,161],"computational":[40],"models":[41,79,94,162],"based":[42,213],"on":[43,121,214],"biomolecular":[44],"features":[45],"have":[46],"shown":[47],"promise":[48],"phage-host":[50,195],"matching,":[51],"performance":[53],"model":[56,178],"settings,":[57],"including":[58],"data":[59],"embeddings,":[60],"across":[61],"datasets":[62,124,166],"with":[63],"different":[64],"degrees":[65],"novelty":[67,216],"remains":[68],"underexplored.":[69],"This":[70],"study":[71],"introduces":[72],"PhageHost-GNN,":[73],"a":[74,156,174],"novelty-aware":[75],"framework":[76,103,153,176],"routed":[78],"predict":[81],"strain-level":[82],"Klebsiella":[83],"-phage":[84],"interactions,":[85],"evaluated":[86],"under":[87],"three":[88,199],"clinical":[89,205],"scenarios.":[90],"Using":[91],"multiple":[92],"embedding":[93],"encode":[96],"sequence,":[97],"structural,":[98],"and":[99,109,114,135,148,181,191],"genomic-context":[100],"features,":[101],"achieved":[104],"AUPRCs":[105],"reaching":[106],"0.784,":[107],"0.731,":[108],"0.642":[110],"host-unseen,":[112],"phage-unseen,":[113],"both-unseen":[115],"silico":[117],"evaluations,":[118],"respectively.":[119],"Benchmarks":[120],"experimentally":[122],"validated":[123],"showed":[125],"clearest":[127],"advantage":[128],"over":[129],"fixed":[130],"embeddings":[131],"when":[132],"both":[133],"hosts":[134],"were":[137],"new":[138],"trained":[141],"model.":[142],"In":[143],"addition":[144],"direct":[146],"inference":[147,202],"de":[149,208],"novo":[150,209],"training,":[151],"further":[154],"implements":[155],"fine-tuning":[157,212],"pipeline":[158],"adapt":[160],"local":[164,182,218],"custom":[165],"while":[167],"reducing":[168],"model-training":[169],"time.":[170],"Overall,":[171],"PhageHost-GNN":[172],"provides":[173],"flexible":[175],"selection,":[179],"evaluation,":[180],"adaptation":[183,206],"practical":[185,201],"phage-therapy":[186],"screening.":[187],"New":[188],"aspects/highlights":[189],"Novelty-aware":[190],"multi-model":[192],"routing":[193],"prediction.":[196],"Implementation":[197],"clinically":[200],"settings.":[203],"Flexible":[204],"via":[207],"training":[210],"or":[211],"strain":[219],"datasets.":[220]},"counts_by_year":[],"updated_date":"2026-11-04T10:54:05.112534","created_date":"2026-10-13T00:00:00"}