{"id":"https://openalex.org/W7171539932","doi":"https://doi.org/10.1145/3807503.3819436","title":"Exploring the Evolutionary Landscape of AI-Generated Viral Sequences: a Case Study on HIV-1","display_name":"Exploring the Evolutionary Landscape of AI-Generated Viral Sequences: a Case Study on HIV-1","publication_year":2026,"publication_date":"2026-06-30","ids":{"openalex":"https://openalex.org/W7171539932","doi":"https://doi.org/10.1145/3807503.3819436"},"language":null,"primary_location":{"id":"doi:10.1145/3807503.3819436","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3807503.3819436","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 17th ACM International Conference on Bioinformatics, Computational Biology and Health Informatics","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3807503.3819436","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5120794639","display_name":"Pablo Arozarena Donelli","orcid":"https://orcid.org/0009-0002-3188-2504"},"institutions":[{"id":"https://openalex.org/I123338534","display_name":"Universit\u00e0 degli Studi del Piemonte Orientale \u201cAmedeo Avogadro\u201d","ror":"https://ror.org/04387x656","country_code":"IT","type":"education","lineage":["https://openalex.org/I123338534"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Pablo Arozarena Donelli","raw_affiliation_strings":["Computer Science Institute, DISIT, University of Piemonte Orientale, Alessandria, Italy"],"raw_orcid":"https://orcid.org/0009-0002-3188-2504","affiliations":[{"raw_affiliation_string":"Computer Science Institute, DISIT, University of Piemonte Orientale, Alessandria, Italy","institution_ids":["https://openalex.org/I123338534"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5093116844","display_name":"Simone Rancati","orcid":"https://orcid.org/0009-0002-4405-1697"},"institutions":[{"id":"https://openalex.org/I25217355","display_name":"University of Pavia","ror":"https://ror.org/00s6t1f81","country_code":"IT","type":"education","lineage":["https://openalex.org/I25217355"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Simone Rancati","raw_affiliation_strings":["BMI lab \u201cMario Stefanelli\u201d, Department of Electric, Computer and Biomedical Engineering, University of Pavia, Pavia, Italy"],"raw_orcid":"https://orcid.org/0009-0002-4405-1697","affiliations":[{"raw_affiliation_string":"BMI lab \u201cMario Stefanelli\u201d, Department of Electric, Computer and Biomedical Engineering, University of Pavia, Pavia, Italy","institution_ids":["https://openalex.org/I25217355"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044714123","display_name":"Giovanna Nicora","orcid":"https://orcid.org/0000-0001-7007-0862"},"institutions":[{"id":"https://openalex.org/I25217355","display_name":"University of Pavia","ror":"https://ror.org/00s6t1f81","country_code":"IT","type":"education","lineage":["https://openalex.org/I25217355"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Giovanna Nicora","raw_affiliation_strings":["BMI lab \u201cMario Stefanelli\u201d, Department of Electric, Computer and Biomedical Engineering, University of Pavia, Pavia, Italy"],"raw_orcid":"https://orcid.org/0000-0001-7007-0862","affiliations":[{"raw_affiliation_string":"BMI lab \u201cMario Stefanelli\u201d, Department of Electric, Computer and Biomedical Engineering, University of Pavia, Pavia, Italy","institution_ids":["https://openalex.org/I25217355"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050932220","display_name":"Riccardo Bellazzi","orcid":"https://orcid.org/0000-0002-6974-9808"},"institutions":[{"id":"https://openalex.org/I25217355","display_name":"University of Pavia","ror":"https://ror.org/00s6t1f81","country_code":"IT","type":"education","lineage":["https://openalex.org/I25217355"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Riccardo Bellazzi","raw_affiliation_strings":["BMI lab \u201cMario Stefanelli\u201d, Department of Electric, Computer and Biomedical Engineering, University of Pavia, Pavia, Italy"],"raw_orcid":"https://orcid.org/0000-0002-6974-9808","affiliations":[{"raw_affiliation_string":"BMI lab \u201cMario Stefanelli\u201d, Department of Electric, Computer and Biomedical Engineering, University of Pavia, Pavia, Italy","institution_ids":["https://openalex.org/I25217355"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090028219","display_name":"Enea Parimbelli","orcid":"https://orcid.org/0000-0003-0679-828X"},"institutions":[{"id":"https://openalex.org/I25217355","display_name":"University of Pavia","ror":"https://ror.org/00s6t1f81","country_code":"IT","type":"education","lineage":["https://openalex.org/I25217355"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Enea Parimbelli","raw_affiliation_strings":["BMI lab \u201cMario Stefanelli\u201d, Department of Electric, Computer and Biomedical Engineering, University of Pavia, Pavia, Italy"],"raw_orcid":"https://orcid.org/0000-0003-0679-828X","affiliations":[{"raw_affiliation_string":"BMI lab \u201cMario Stefanelli\u201d, Department of Electric, Computer and Biomedical Engineering, University of Pavia, Pavia, Italy","institution_ids":["https://openalex.org/I25217355"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5032023872","display_name":"Luigi Portinale","orcid":"https://orcid.org/0000-0002-6053-4667"},"institutions":[{"id":"https://openalex.org/I123338534","display_name":"Universit\u00e0 degli Studi del Piemonte Orientale \u201cAmedeo Avogadro\u201d","ror":"https://ror.org/04387x656","country_code":"IT","type":"education","lineage":["https://openalex.org/I123338534"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Luigi Portinale","raw_affiliation_strings":["Computer Science Institute, DISIT, University of Piemonte Orientale, Alessandria, Italy"],"raw_orcid":"https://orcid.org/0000-0002-6053-4667","affiliations":[{"raw_affiliation_string":"Computer Science Institute, DISIT, University of Piemonte Orientale, Alessandria, Italy","institution_ids":["https://openalex.org/I123338534"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":null,"topics":[],"keywords":[{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.3089999854564667},{"id":"https://openalex.org/keywords/ectotherm","display_name":"Ectotherm","score":0.2703000009059906},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.267300009727478},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.2605000138282776}],"concepts":[{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.3206999897956848},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.3089999854564667},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.3050999939441681},{"id":"https://openalex.org/C18903297","wikidata":"https://www.wikidata.org/wiki/Q7150","display_name":"Ecology","level":1,"score":0.27459999918937683},{"id":"https://openalex.org/C13376991","wikidata":"https://www.wikidata.org/wiki/Q587698","display_name":"Ectotherm","level":2,"score":0.2703000009059906},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.26809999346733093},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.267300009727478},{"id":"https://openalex.org/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","level":1,"score":0.26249998807907104},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.2605000138282776},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.2587999999523163}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3807503.3819436","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3807503.3819436","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 17th ACM International Conference on Bioinformatics, Computational Biology and Health Informatics","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3807503.3819436","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3807503.3819436","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 17th ACM International Conference on Bioinformatics, Computational Biology and Health Informatics","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W1969028669","https://openalex.org/W2087757756","https://openalex.org/W2114850508","https://openalex.org/W2119859604","https://openalex.org/W2142678478","https://openalex.org/W2166637863","https://openalex.org/W3127238141","https://openalex.org/W3177828909","https://openalex.org/W3195375135","https://openalex.org/W4281790889","https://openalex.org/W4304607335","https://openalex.org/W4404821554","https://openalex.org/W4407820212","https://openalex.org/W4412884821","https://openalex.org/W4414283152"],"related_works":[],"abstract_inverted_index":{"Generative":[0],"genomic":[1],"Language":[2],"Models":[3],"(gLMs)":[4],"have":[5],"shown":[6],"immense":[7],"promise":[8],"in":[9,126],"capturing":[10],"the":[11,36,76,90,101,108,166,170,176,190,223],"statistical":[12],"regularities":[13],"of":[14,40,55,100,105,117,140,187,197],"DNA,":[15],"yet":[16],"a":[17,45,52,61,122,137,146,185,194,220,238,264],"persistent":[18],"challenge":[19],"remains:":[20],"distinguishing":[21],"statistically":[22],"plausible":[23],"\"biological":[24],"hallucinations\"":[25],"from":[26],"truly":[27],"functional":[28,129,269],"synthetic":[29],"sequences.":[30],"In":[31],"this":[32],"work,":[33],"we":[34,66,218],"evaluate":[35],"potential":[37],"biological":[38,258],"viability":[39],"HIV-1":[41,77],"sequences":[42,70,102],"generated":[43,193,205],"by":[44],"compact":[46,249],"17M-parameter,":[47],"decoder-only":[48],"transformer":[49],"trained":[50],"on":[51,60],"pan-viral":[53],"corpus":[54],"400,000":[56],"complete":[57],"genomes.":[58],"Focusing":[59],"stable":[62],"low":[63],"temperature":[64],"setting,":[65],"analyzed":[67],"142":[68],"AI-generated":[69],"(approximately":[71],"2.5":[72],"kb":[73],"long)":[74],"spanning":[75],"gag/pol":[78],"region.":[79],"Our":[80],"validation":[81],"pipeline":[82],"employed":[83],"BLASTn":[84],"homology":[85],"searches,":[86],"mutational":[87],"profiling":[88],"against":[89,222],"HXB2":[91],"reference,":[92],"and":[93,174,231,260,274],"subtyping/recombination":[94],"tools.":[95],"Results":[96],"show":[97],"that":[98,204,248],"63.9%":[99],"(69":[103],"out":[104],"108)":[106],"covering":[107],"full":[109],"gag":[110,155],"Coding":[111],"DNA":[112],"Sequence":[113],"(CDS)":[114],"were":[115],"free":[116],"premature":[118],"stop":[119],"codons,":[120],"indicating":[121],"high":[123],"success":[124],"rate":[125],"generating":[127],"potentially":[128],"Open":[130],"Reading":[131],"Frames":[132],"(ORFs).":[133],"Mutational":[134],"analysis":[135],"revealed":[136],"diverse":[138],"landscape":[139],"28\u201348":[141],"mutations":[142],"per":[143],"sequence":[144],"with":[145,165,237],"balanced":[147],"synonymous/non-synonymous":[148],"ratio.":[149],"Notably,":[150],"calculated":[151],"Shannon":[152],"entropy":[153],"across":[154],"subregions":[156],"(p17,":[157],"p24,":[158],"p7,":[159],"p6)":[160],"mirrored":[161],"natural":[162,215],"conservation":[163,261],"patterns,":[164],"capsid":[167],"(p24)":[168],"exhibiting":[169],"lowest":[171],"variability":[172],"(0.13)":[173],"p6":[175],"highest":[177],"(0.33).":[178],"While":[179],"training":[180],"data":[181],"imbalance":[182],"led":[183],"to":[184,214,241,252],"predominance":[186],"Subtype":[188,198],"B,":[189],"model":[191],"successfully":[192],"recombination":[195],"variant":[196],"A.":[199],"AlphaFold2":[200],"structural":[201],"predictions":[202],"confirmed":[203],"proteins":[206],"maintain":[207],"biophysical":[208],"stability,":[209],"yielding":[210],"pLDDT":[211],"scores":[212],"comparable":[213],"references.":[216],"Finally,":[217],"integrated":[219],"benchmark":[221],"non-adapted":[224],"base":[225],"Mistral":[226],"model,":[227,235],"state-of-art":[228],"gLM":[229],"Evo2,":[230],"stochastic":[232],"Markov":[233],"6-mer":[234],"together":[236],"memorization":[239],"audit":[240],"prove":[242],"output":[243],"innovation.":[244],"These":[245],"findings":[246],"demonstrate":[247],"gLMs":[250],"adapted":[251],"viral":[253,270],"genomics":[254],"can":[255],"internalize":[256],"intricate":[257],"constraints":[259],"signatures,":[262],"providing":[263],"resource-efficient":[265],"pathway":[266],"for":[267,272],"designing":[268],"components":[271],"vaccine":[273],"gene":[275],"therapy":[276],"research.":[277]},"counts_by_year":[],"updated_date":"2026-07-30T17:31:21.811387","created_date":"2026-07-29T00:00:00"}
