{"id":"https://openalex.org/W7213972987","doi":"https://doi.org/10.64898/2026.09.18.752634","title":"Phylogenies as graphs: structured neural networks improve host origin predictions from paramyxovirus sequences","display_name":"Phylogenies as graphs: structured neural networks improve host origin predictions from paramyxovirus sequences","publication_year":2026,"publication_date":"2026-09-21","ids":{"openalex":"https://openalex.org/W7213972987","doi":"https://doi.org/10.64898/2026.09.18.752634"},"language":"en","primary_location":{"id":"doi:10.64898/2026.09.18.752634","doi":"https://doi.org/10.64898/2026.09.18.752634","is_oa":true,"landing_page_url":"https://doi.org/10.64898/2026.09.18.752634","pdf_url":"https://www.biorxiv.org/content/biorxiv/early/2026/09/21/2026.09.18.752634.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/2026/09/21/2026.09.18.752634.full.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5111580619","display_name":"J. W. Herzig","orcid":"https://orcid.org/0000-0001-6434-4150","observed_orcids":["https://orcid.org/0000-0001-6434-4150"]},"institutions":[{"id":"https://openalex.org/I4210146449","display_name":"MRC University of Glasgow Centre for Virus Research","ror":"https://ror.org/03vaer060","country_code":"GB","type":"government","lineage":["https://openalex.org/I4210087105","https://openalex.org/I4210146449","https://openalex.org/I7882870","https://openalex.org/I90344618"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"James C Herzig","raw_affiliation_strings":["MRC-University of Glasgow Centre for Virus Research, Glasgow, UK"],"raw_orcid":"https://orcid.org/0000-0001-6434-4150","affiliations":[{"raw_affiliation_string":"MRC-University of Glasgow Centre for Virus Research, Glasgow, UK","institution_ids":["https://openalex.org/I4210146449"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003188710","display_name":"Haley Stone","orcid":"https://orcid.org/0000-0003-1997-0042","observed_orcids":["https://orcid.org/0000-0003-1997-0042"]},"institutions":[{"id":"https://openalex.org/I4210146449","display_name":"MRC University of Glasgow Centre for Virus Research","ror":"https://ror.org/03vaer060","country_code":"GB","type":"government","lineage":["https://openalex.org/I4210087105","https://openalex.org/I4210146449","https://openalex.org/I7882870","https://openalex.org/I90344618"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Haley Stone","raw_affiliation_strings":["MRC-University of Glasgow Centre for Virus Research, Glasgow, UK"],"raw_orcid":"https://orcid.org/0000-0003-1997-0042","affiliations":[{"raw_affiliation_string":"MRC-University of Glasgow Centre for Virus Research, Glasgow, UK","institution_ids":["https://openalex.org/I4210146449"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5038807761","display_name":"Liam Brierley","orcid":"https://orcid.org/0000-0002-3026-4723","observed_orcids":["https://orcid.org/0000-0002-3026-4723"]},"institutions":[{"id":"https://openalex.org/I4210146449","display_name":"MRC University of Glasgow Centre for Virus Research","ror":"https://ror.org/03vaer060","country_code":"GB","type":"government","lineage":["https://openalex.org/I4210087105","https://openalex.org/I4210146449","https://openalex.org/I7882870","https://openalex.org/I90344618"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Liam Brierley","raw_affiliation_strings":["MRC-University of Glasgow Centre for Virus Research, Glasgow, UK"],"raw_orcid":"https://orcid.org/0000-0002-3026-4723","affiliations":[{"raw_affiliation_string":"MRC-University of Glasgow Centre for Virus Research, Glasgow, UK","institution_ids":["https://openalex.org/I4210146449"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5111580619"],"corresponding_institution_ids":["https://openalex.org/I4210146449"],"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/T11135","display_name":"Virology and Viral Diseases","score":0.760699987411499,"subfield":{"id":"https://openalex.org/subfields/2713","display_name":"Epidemiology"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},"topics":[{"id":"https://openalex.org/T11135","display_name":"Virology and Viral Diseases","score":0.760699987411499,"subfield":{"id":"https://openalex.org/subfields/2713","display_name":"Epidemiology"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},{"id":"https://openalex.org/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.1354999989271164,"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/T12492","display_name":"Zoonotic diseases and public health","score":0.03269999846816063,"subfield":{"id":"https://openalex.org/subfields/2739","display_name":"Public Health, Environmental and Occupational Health"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/paramyxovirus","display_name":"paramyxovirus","score":0.9549999833106995},{"id":"https://openalex.org/keywords/graph-neural-networks","display_name":"graph neural networks","score":0.9409999847412109},{"id":"https://openalex.org/keywords/viral-phylogeny","display_name":"viral phylogeny","score":0.9890000224113464},{"id":"https://openalex.org/keywords/viral-genome-sequence","display_name":"viral genome sequence","score":0.5559999942779541},{"id":"https://openalex.org/keywords/zoonotic-disease-surveillance","display_name":"zoonotic disease surveillance","score":0.8429999947547913},{"id":"https://openalex.org/keywords/genome-composition","display_name":"genome composition","score":0.7149999737739563},{"id":"https://openalex.org/keywords/sparse-training-data","display_name":"sparse training data","score":0.6110000014305115},{"id":"https://openalex.org/keywords/emerging-viruses","display_name":"emerging viruses","score":0.5370000004768372}],"concepts":[{"id":"https://openalex.org/C141231307","wikidata":"https://www.wikidata.org/wiki/Q7020","display_name":"Genome","level":3,"score":0.682200014591217},{"id":"https://openalex.org/C90132467","wikidata":"https://www.wikidata.org/wiki/Q171184","display_name":"Phylogenetics","level":3,"score":0.5867000222206116},{"id":"https://openalex.org/C193252679","wikidata":"https://www.wikidata.org/wiki/Q242125","display_name":"Phylogenetic tree","level":3,"score":0.5525000095367432},{"id":"https://openalex.org/C126831891","wikidata":"https://www.wikidata.org/wiki/Q221673","display_name":"Host (biology)","level":2,"score":0.5511000156402588},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.522599995136261},{"id":"https://openalex.org/C86251818","wikidata":"https://www.wikidata.org/wiki/Q816754","display_name":"Benchmarking","level":2,"score":0.5188999772071838},{"id":"https://openalex.org/C15151743","wikidata":"https://www.wikidata.org/wiki/Q903778","display_name":"Metagenomics","level":3,"score":0.4984999895095825},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.48429998755455017},{"id":"https://openalex.org/C189206191","wikidata":"https://www.wikidata.org/wiki/Q222046","display_name":"Genomics","level":4,"score":0.4602000117301941},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.45419999957084656},{"id":"https://openalex.org/C2778136018","wikidata":"https://www.wikidata.org/wiki/Q10350689","display_name":"Predictive power","level":2,"score":0.42340001463890076},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4205000102519989},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.4129999876022339},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4025999903678894},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3928000032901764},{"id":"https://openalex.org/C51679486","wikidata":"https://www.wikidata.org/wiki/Q380546","display_name":"DNA sequencing","level":3,"score":0.3614000082015991},{"id":"https://openalex.org/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","level":1,"score":0.35420000553131104},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.3089999854564667},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.29910001158714294},{"id":"https://openalex.org/C45804977","wikidata":"https://www.wikidata.org/wiki/Q7239673","display_name":"Predictive modelling","level":2,"score":0.295199990272522},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.28519999980926514},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.27869999408721924},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.2784999907016754},{"id":"https://openalex.org/C24432333","wikidata":"https://www.wikidata.org/wiki/Q2068526","display_name":"Whole genome sequencing","level":4,"score":0.2757999897003174},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.2736000120639801},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.2727999985218048},{"id":"https://openalex.org/C8769409","wikidata":"https://www.wikidata.org/wiki/Q2066554","display_name":"Viral evolution","level":4,"score":0.26330000162124634},{"id":"https://openalex.org/C105565629","wikidata":"https://www.wikidata.org/wiki/Q1248292","display_name":"Gene prediction","level":4,"score":0.258899986743927}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.64898/2026.09.18.752634","doi":"https://doi.org/10.64898/2026.09.18.752634","is_oa":true,"landing_page_url":"https://doi.org/10.64898/2026.09.18.752634","pdf_url":"https://www.biorxiv.org/content/biorxiv/early/2026/09/21/2026.09.18.752634.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:10.64898/2026.09.18.752634","doi":"https://doi.org/10.64898/2026.09.18.752634","is_oa":true,"landing_page_url":"https://doi.org/10.64898/2026.09.18.752634","pdf_url":"https://www.biorxiv.org/content/biorxiv/early/2026/09/21/2026.09.18.752634.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":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G5216326461","display_name":"Predicting emergence risk of future zoonotic viruses through computational learning","funder_award_id":"MR/X019616/1","funder_id":"https://openalex.org/F4320334626","funder_display_name":"Medical Research Council"}],"funders":[{"id":"https://openalex.org/F4320334626","display_name":"Medical Research Council","ror":"https://ror.org/03x94j517"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7213972987.pdf","grobid_xml":"https://content.openalex.org/works/W7213972987.grobid-xml"},"referenced_works_count":58,"referenced_works":["https://openalex.org/W1972969203","https://openalex.org/W1999716303","https://openalex.org/W2058069729","https://openalex.org/W2073033917","https://openalex.org/W2120145798","https://openalex.org/W2127435093","https://openalex.org/W2132881916","https://openalex.org/W2137569894","https://openalex.org/W2157395790","https://openalex.org/W2160378127","https://openalex.org/W2321500703","https://openalex.org/W2519887557","https://openalex.org/W2560136348","https://openalex.org/W2577688552","https://openalex.org/W2614081736","https://openalex.org/W2616882914","https://openalex.org/W2759289851","https://openalex.org/W2794187484","https://openalex.org/W2801128564","https://openalex.org/W2885799720","https://openalex.org/W2918016039","https://openalex.org/W2940459311","https://openalex.org/W2950954328","https://openalex.org/W2978726586","https://openalex.org/W2979689710","https://openalex.org/W3008394341","https://openalex.org/W3020238093","https://openalex.org/W3035074698","https://openalex.org/W3048846953","https://openalex.org/W3155024268","https://openalex.org/W3204961752","https://openalex.org/W3215755691","https://openalex.org/W4213362500","https://openalex.org/W4224436523","https://openalex.org/W4281565932","https://openalex.org/W4291221220","https://openalex.org/W4319762935","https://openalex.org/W4367059220","https://openalex.org/W4385691081","https://openalex.org/W4386887311","https://openalex.org/W4393995158","https://openalex.org/W4402221296","https://openalex.org/W4402595532","https://openalex.org/W4403889702","https://openalex.org/W4404521618","https://openalex.org/W4412093882","https://openalex.org/W4413988468","https://openalex.org/W4416793665","https://openalex.org/W4416823253","https://openalex.org/W4416976792","https://openalex.org/W4417037293","https://openalex.org/W6911585731","https://openalex.org/W7125633298","https://openalex.org/W7125899633","https://openalex.org/W7128091637","https://openalex.org/W7130740824","https://openalex.org/W7160408120","https://openalex.org/W7213469911"],"related_works":["https://openalex.org/W1982763078","https://openalex.org/W3048846953","https://openalex.org/W4389239374","https://openalex.org/W7165455556","https://openalex.org/W7143450706","https://openalex.org/W3215755691","https://openalex.org/W4402595532","https://openalex.org/W4320033719","https://openalex.org/W7131839412","https://openalex.org/W4393996836"],"abstract_inverted_index":{"Abstract":[0],"Accurately":[1],"identifying":[2],"the":[3,90,146,165,168,197,208,229,232,237,252,289,310,313,338,344],"host":[4,38,47,150,230,238,366],"of":[5,87,145,149,167,212,219,254,312,317],"a":[6,13,69,142,204,239,296,315],"virus":[7,234,240],"from":[8,41,257],"its":[9,244],"genome":[10,43,63,154,193,215,245],"sequence":[11,246],"is":[12,58,121,133,247,362],"task":[14],"with":[15,61,153,299],"important":[16,249,364],"applications":[17,137,285],"in":[18,36,81,135,192,196,203,207,343,377],"zoonotic":[19],"disease":[20],"surveillance":[21,253],"and":[22,65,100,138,175,181,210,260,323,328,368],"filling":[23],"data":[24,120,227,263],"gaps":[25,264],"for":[26,161,251],"metagenomic":[27],"sampling.":[28],"Machine":[29],"learning":[30,274],"approaches":[31],"have":[32,201,224,275,303],"seen":[33],"broad":[34],"application":[35],"making":[37,116],"predictions":[39,101,117,163,380],"directly":[40],"viral":[42,55,79,187,214,341],"sequences.":[44,216],"However,":[45,217,282],"most":[46,283],"prediction":[48,132,151,367],"models":[49,271],"do":[50,222,286],"not":[51,223,287],"incorporate":[52],"information":[53],"on":[54,243],"phylogeny,":[56],"which":[57,76,231,265,294],"strongly":[59],"correlated":[60],"both":[62,250],"composition":[64],"host.":[66,300],"We":[67,92,350],"apply":[68],"novel":[70,172,371],"graph":[71,305,372],"neural":[72,98,306,373],"network":[73,374],"(GNN)":[74],"approach":[75,174,332,375],"explicitly":[77,336],"represents":[78],"phylogeny":[80,104,140,361],"model":[82,176,345],"architecture":[83],"to":[84,185,261,279,308,326,335,357,365,382],"predict":[85,309],"hosts":[86,311],"origin":[88],"within":[89],"paramyxoviruses.":[91],"conduct":[93],"rigorous":[94],"benchmarking":[95],"against":[96],"non-structured":[97],"networks":[99,307],"made":[102],"using":[103,272],"alone,":[105],"showing":[106],"that":[107,129,139,319,360,369],"GNNs":[108],"carry":[109],"distinct":[110],"advantages":[111],"over":[112],"other":[113,186,383],"methods":[114],"when":[115],"where":[118],"training":[119,169],"sparse.":[122],"Validation":[123],"across":[124],"different":[125],"phylogenetic":[126,131,290],"scales":[127],"shows":[128],"simple":[130],"effective":[134],"many":[136,218],"contributes":[141],"large":[143],"proportion":[144],"predictive":[147],"power":[148,159],"models,":[152],"compositional":[155],"features":[156],"providing":[157],"additional":[158],"only":[160],"specific":[162],"outside":[164],"range":[166],"data.":[170],"This":[171],"modelling":[173],"validation":[177],"framework":[178],"are":[179],"flexible":[180],"can":[182],"be":[183],"applied":[184,278,304],"families.":[188],"Author":[189],"summary":[190],"Advances":[191],"sequencing":[194],"technology":[195],"last":[198],"two":[199],"decades":[200],"resulted":[202],"huge":[205],"increase":[206],"number":[209],"diversity":[211],"available":[213],"these":[220],"genomes":[221],"reliable":[225],"associated":[226],"regarding":[228],"source":[233],"infects.":[235],"Predicting":[236],"infects":[241],"based":[242],"therefore":[248],"emerging":[255,324],"diseases":[256],"animal":[258,329],"reservoirs":[259],"fill":[262],"will":[266],"enable":[267],"future":[268],"research.":[269],"Computational":[270],"machine":[273],"been":[276],"widely":[277],"this":[280],"problem.":[281],"previous":[284],"consider":[288],"relationships":[291],"between":[292,340],"viruses,":[293],"has":[295],"strong":[297],"correlation":[298],"Here,":[301],"we":[302],"paramyxoviruses,":[314],"family":[316],"viruses":[318],"contains":[320],"numerous":[321],"endemic":[322],"threats":[325],"human":[327],"health.":[330],"Our":[331],"allows":[333],"us":[334],"represent":[337],"relationship":[339],"sequences":[342],"architecture,":[346],"helping":[347],"improve":[348],"predictions.":[349],"thoroughly":[351],"assess":[352],"our":[353,370],"model\u2019s":[354],"performance":[355],"relative":[356],"alternatives,":[358],"finding":[359],"very":[363],"results":[376],"more":[378],"accurate":[379],"compared":[381],"methods.":[384]},"counts_by_year":[],"updated_date":"2026-11-09T13:22:03.289127","created_date":"2026-09-22T00:00:00"}