{"id":"https://openalex.org/W7224783448","doi":"https://doi.org/10.64898/2026.10.29.762857","title":"Degree bias predicts, outperforms and improves machine learning phage-host interaction predictions","display_name":"Degree bias predicts, outperforms and improves machine learning phage-host interaction predictions","publication_year":2026,"publication_date":"2026-10-30","ids":{"openalex":"https://openalex.org/W7224783448","doi":"https://doi.org/10.64898/2026.10.29.762857"},"language":"en","primary_location":{"id":"doi:10.64898/2026.10.29.762857","doi":"https://doi.org/10.64898/2026.10.29.762857","is_oa":true,"landing_page_url":"https://doi.org/10.64898/2026.10.29.762857","pdf_url":"https://www.biorxiv.org/content/biorxiv/early/2026/10/30/2026.10.29.762857.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"},"volume":null,"type":"preprint","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://www.biorxiv.org/content/biorxiv/early/2026/10/30/2026.10.29.762857.full.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5047792467","display_name":"Gustavo S. Jeuken","orcid":"https://orcid.org/0000-0002-4438-2325","observed_orcids":["https://orcid.org/0000-0002-4438-2325"]},"institutions":[{"id":"https://openalex.org/I865915315","display_name":"Vrije Universiteit Amsterdam","ror":"https://ror.org/008xxew50","country_code":"NL","type":"education","lineage":["https://openalex.org/I865915315"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Gustavo S Jeuken","raw_affiliation_strings":["Vrije Universiteit Amsterdam"],"raw_orcid":"https://orcid.org/0000-0002-4438-2325","affiliations":[{"raw_affiliation_string":"Vrije Universiteit Amsterdam","institution_ids":["https://openalex.org/I865915315"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5046993858","display_name":"Yuval Mulla","orcid":"https://orcid.org/0000-0002-6675-0977","observed_orcids":["https://orcid.org/0000-0002-6675-0977"]},"institutions":[{"id":"https://openalex.org/I865915315","display_name":"Vrije Universiteit Amsterdam","ror":"https://ror.org/008xxew50","country_code":"NL","type":"education","lineage":["https://openalex.org/I865915315"]}],"countries":["NL"],"is_corresponding":true,"raw_author_name":"Yuval Mulla","raw_affiliation_strings":["Vrije Universiteit Amsterdam"],"raw_orcid":"https://orcid.org/0000-0002-6675-0977","affiliations":[{"raw_affiliation_string":"Vrije Universiteit Amsterdam","institution_ids":["https://openalex.org/I865915315"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5046993858"],"corresponding_institution_ids":["https://openalex.org/I865915315"],"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":1.0,"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":1.0,"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/T11764","display_name":"Evolution and Genetic Dynamics","score":0.0,"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"}},{"id":"https://openalex.org/T11644","display_name":"Spam and Phishing Detection","score":0.0,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/phage-therapy","display_name":"phage therapy","score":0.8519999980926514},{"id":"https://openalex.org/keywords/network-degree","display_name":"network degree","score":0.527999997138977},{"id":"https://openalex.org/keywords/model-evaluation","display_name":"model evaluation","score":0.7929999828338623},{"id":"https://openalex.org/keywords/phage-selection","display_name":"phage selection","score":0.7239999771118164},{"id":"https://openalex.org/keywords/network-structure","display_name":"network structure","score":0.35100001096725464}],"concepts":[{"id":"https://openalex.org/C197640229","wikidata":"https://www.wikidata.org/wiki/Q2534066","display_name":"Predictability","level":2,"score":0.7634999752044678},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.7182000279426575},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.7171000242233276},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7128999829292297},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4853000044822693},{"id":"https://openalex.org/C58471807","wikidata":"https://www.wikidata.org/wiki/Q327120","display_name":"Receiver operating characteristic","level":2,"score":0.45559999346733093},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.3637000024318695},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.3499999940395355},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.3246999979019165},{"id":"https://openalex.org/C2780898871","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Performance metric","level":2,"score":0.3222000002861023},{"id":"https://openalex.org/C45804977","wikidata":"https://www.wikidata.org/wiki/Q7239673","display_name":"Predictive modelling","level":2,"score":0.319599986076355},{"id":"https://openalex.org/C2775997480","wikidata":"https://www.wikidata.org/wiki/Q586277","display_name":"Degree (music)","level":2,"score":0.3188000023365021},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.3167000114917755},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.30709999799728394},{"id":"https://openalex.org/C104122410","wikidata":"https://www.wikidata.org/wiki/Q1416406","display_name":"Network model","level":2,"score":0.273499995470047},{"id":"https://openalex.org/C158600405","wikidata":"https://www.wikidata.org/wiki/Q5054566","display_name":"Causal inference","level":2,"score":0.26739999651908875}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.64898/2026.10.29.762857","doi":"https://doi.org/10.64898/2026.10.29.762857","is_oa":true,"landing_page_url":"https://doi.org/10.64898/2026.10.29.762857","pdf_url":"https://www.biorxiv.org/content/biorxiv/early/2026/10/30/2026.10.29.762857.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"}],"best_oa_location":{"id":"doi:10.64898/2026.10.29.762857","doi":"https://doi.org/10.64898/2026.10.29.762857","is_oa":true,"landing_page_url":"https://doi.org/10.64898/2026.10.29.762857","pdf_url":"https://www.biorxiv.org/content/biorxiv/early/2026/10/30/2026.10.29.762857.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"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7224783448.pdf","grobid_xml":"https://content.openalex.org/works/W7224783448.grobid-xml"},"referenced_works_count":4,"referenced_works":["https://openalex.org/W4399901153","https://openalex.org/W7139969573","https://openalex.org/W7161816662","https://openalex.org/W7203461017"],"related_works":["https://openalex.org/W2901212243","https://openalex.org/W4414306293","https://openalex.org/W4405613608","https://openalex.org/W4405833553","https://openalex.org/W7214786235","https://openalex.org/W4415736119","https://openalex.org/W2599963923","https://openalex.org/W7203872573","https://openalex.org/W4386980190","https://openalex.org/W4200394069"],"abstract_inverted_index":{"Phages":[0],"are":[1,10,36,72],"promising":[2],"therapeutics":[3],"for":[4,23,42,56,190],"difficult-to-treat":[5],"bacterial":[6,15,95],"infections.":[7],"However,":[8,68],"phages":[9,41],"highly":[11,73],"specific":[12],"in":[13],"which":[14],"strains":[16],"they":[17],"infect,":[18],"necessitating":[19],"extensive":[20],"experimental":[21,43],"screening":[22],"each":[24],"patient":[25],"isolate.":[26],"Machine":[27],"learning":[28],"(ML)":[29],"models":[30,121],"predicting":[31],"phage-host":[32],"interactions":[33],"from":[34,172],"genomes":[35],"increasingly":[37],"developed":[38],"to":[39,197],"prioritize":[40],"screening.":[44],"The":[45],"Area":[46],"Under":[47],"the":[48,83,113],"Receiver":[49],"Operating":[50],"Characteristic":[51],"(AUROC)":[52],"metric":[53],"is":[54,156],"standard":[55],"model":[57,103,154,191],"evaluation,":[58,143],"with":[59],"reported":[60],"high":[61],"scores":[62,76,116],"(0.7-0.95)":[63],"suggesting":[64],"strong":[65],"predictive":[66],"power.":[67],"because":[69],"phage-bacterium":[70],"networks":[71,140],"structured,":[74],"these":[75],"can":[77],"be":[78],"inflated":[79],"by":[80,90],"\"degree":[81],"bias\",":[82],"baseline":[84],"likelihood":[85],"of":[86,117],"infection":[87],"driven":[88],"purely":[89],"average":[91],"phage":[92,200],"infectivity":[93],"and":[94,111,141,149,178,181,193],"susceptibility.":[96],"Here,":[97],"we":[98,144,165],"show":[99],"that":[100,126,151,167],"an":[101],"interaction-naive":[102],"based":[104],"solely":[105],"on":[106],"network":[107,131],"degrees":[108],"accurately":[109],"predicts":[110],"outperforms":[112],"global":[114,127,161,180],"AUROC":[115,128,162],"five":[118],"published":[119],"ML":[120,153],"across":[122],"ten":[123],"datasets,":[124],"indicating":[125],"primarily":[129],"reflects":[130],"structure":[132],"rather":[133],"than":[134,160],"predicted":[135],"interactions.":[136],"Using":[137],"randomized":[138],"degree-conserved":[139],"degree-stratified":[142],"isolate":[145],"true":[146],"interaction":[147,176],"predictions":[148],"demonstrate":[150,166],"current":[152],"performance":[155],"far":[157],"more":[158],"modest":[159],"suggests.":[163],"Finally,":[164],"regressing":[168],"out":[169],"degree":[170],"bias":[171],"training":[173],"data":[174],"improves":[175],"predictability":[177],"boosts":[179],"stratified":[182],"performance.":[183],"Our":[184],"work":[185],"provides":[186],"a":[187,194],"critical":[188],"framework":[189],"evaluation":[192],"straightforward":[195],"route":[196],"improve":[198],"ML-guided":[199],"selection.":[201]},"counts_by_year":[],"updated_date":"2026-11-05T12:25:35.769452","created_date":"2026-10-31T00:00:00"}