{"id":"https://openalex.org/W7218641840","doi":"https://doi.org/10.64898/2026.09.28.755102","title":"Agent-optimized GPU polygenic scoring at cohort scale","display_name":"Agent-optimized GPU polygenic scoring at cohort scale","publication_year":2026,"publication_date":"2026-10-03","ids":{"openalex":"https://openalex.org/W7218641840","doi":"https://doi.org/10.64898/2026.09.28.755102"},"language":"en","primary_location":{"id":"doi:10.64898/2026.09.28.755102","doi":"https://doi.org/10.64898/2026.09.28.755102","is_oa":true,"landing_page_url":"https://doi.org/10.64898/2026.09.28.755102","pdf_url":"https://www.biorxiv.org/content/biorxiv/early/2026/10/03/2026.09.28.755102.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/2026/10/03/2026.09.28.755102.full.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5139743995","display_name":"Adam Afyouni","orcid":"https://orcid.org/0009-0003-4699-5226","observed_orcids":["https://orcid.org/0009-0003-4699-5226"]},"institutions":[{"id":"https://openalex.org/I1288882113","display_name":"Boston Children's Hospital","ror":"https://ror.org/00dvg7y05","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I1288882113"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Adam Afyouni","raw_affiliation_strings":["Boston Children\u2019s Hospital, Department of Pediatrics, Division of Genetics and Genomics, Boston, MA"],"raw_orcid":"https://orcid.org/0009-0003-4699-5226","affiliations":[{"raw_affiliation_string":"Boston Children\u2019s Hospital, Department of Pediatrics, Division of Genetics and Genomics, Boston, MA","institution_ids":["https://openalex.org/I1288882113"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5156811001","display_name":"Boyuan Yang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I150468666","display_name":"Emory University","ror":"https://ror.org/03czfpz43","country_code":"US","type":"education","lineage":["https://openalex.org/I150468666"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Boyuan Yang","raw_affiliation_strings":["Emory University, Atlanta, GA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Emory University, Atlanta, GA","institution_ids":["https://openalex.org/I150468666"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100331534","display_name":"Cong Liu","orcid":"https://orcid.org/0000-0001-6024-3037","observed_orcids":["https://orcid.org/0000-0001-6024-3037","https://orcid.org/0000-0002-3936-9580"]},"institutions":[{"id":"https://openalex.org/I1288882113","display_name":"Boston Children's Hospital","ror":"https://ror.org/00dvg7y05","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I1288882113"]},{"id":"https://openalex.org/I136199984","display_name":"Harvard University","ror":"https://ror.org/03vek6s52","country_code":"US","type":"education","lineage":["https://openalex.org/I136199984"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Cong Liu","raw_affiliation_strings":["Boston Children\u2019s Hospital, Children\u2019s Hospital Informatics Program, Boston, MA","Boston Children\u2019s Hospital, Department of Pediatrics, Division of Genetics and Genomics, Boston, MA","Harvard Medical School, Department of Pediatrics, Boston, MA"],"raw_orcid":"https://orcid.org/0000-0001-6024-3037","affiliations":[{"raw_affiliation_string":"Boston Children\u2019s Hospital, Children\u2019s Hospital Informatics Program, Boston, MA","institution_ids":["https://openalex.org/I1288882113"]},{"raw_affiliation_string":"Boston Children\u2019s Hospital, Department of Pediatrics, Division of Genetics and Genomics, Boston, MA","institution_ids":["https://openalex.org/I1288882113"]},{"raw_affiliation_string":"Harvard Medical School, Department of Pediatrics, Boston, MA","institution_ids":["https://openalex.org/I136199984"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5100331534"],"corresponding_institution_ids":["https://openalex.org/I1288882113","https://openalex.org/I136199984"],"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/T10261","display_name":"Genetic Associations and Epidemiology","score":0.5073000192642212,"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"}},"topics":[{"id":"https://openalex.org/T10261","display_name":"Genetic Associations and Epidemiology","score":0.5073000192642212,"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/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.3743000030517578,"subfield":{"id":"https://openalex.org/subfields/1708","display_name":"Hardware and Architecture"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10594","display_name":"Genetic and phenotypic traits in livestock","score":0.015200000256299973,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/polygenic-risk-score","display_name":"polygenic risk score","score":0.6570000052452087},{"id":"https://openalex.org/keywords/gpu-computing","display_name":"GPU computing","score":0.7369999885559082},{"id":"https://openalex.org/keywords/sparse-matrix-multiplication","display_name":"sparse matrix multiplication","score":0.9070000052452087},{"id":"https://openalex.org/keywords/1000-genomes-project","display_name":"1000 Genomes Project","score":0.8080000281333923},{"id":"https://openalex.org/keywords/genetic-risk-models","display_name":"genetic risk models","score":0.5619999766349792},{"id":"https://openalex.org/keywords/cold-start","display_name":"cold start","score":0.3919999897480011},{"id":"https://openalex.org/keywords/reproducibility","display_name":"reproducibility","score":0.5099999904632568},{"id":"https://openalex.org/keywords/synthetic-data-training","display_name":"synthetic data training","score":0.39500001072883606}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6669999957084656},{"id":"https://openalex.org/C122048520","wikidata":"https://www.wikidata.org/wiki/Q2913954","display_name":"Percentile","level":2,"score":0.6182000041007996},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.49570000171661377},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.4228000044822693},{"id":"https://openalex.org/C179518139","wikidata":"https://www.wikidata.org/wiki/Q5140297","display_name":"Coding (social sciences)","level":2,"score":0.396699994802475},{"id":"https://openalex.org/C97425143","wikidata":"https://www.wikidata.org/wiki/Q164786","display_name":"1000 Genomes Project","level":5,"score":0.38499999046325684},{"id":"https://openalex.org/C160920958","wikidata":"https://www.wikidata.org/wiki/Q7662746","display_name":"Synthetic data","level":2,"score":0.3736000061035156},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3637999892234802},{"id":"https://openalex.org/C196083921","wikidata":"https://www.wikidata.org/wiki/Q7915758","display_name":"Variance (accounting)","level":2,"score":0.36239999532699585},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.34380000829696655},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3393999934196472},{"id":"https://openalex.org/C22679943","wikidata":"https://www.wikidata.org/wiki/Q159375","display_name":"Standard deviation","level":2,"score":0.3253999948501587},{"id":"https://openalex.org/C141231307","wikidata":"https://www.wikidata.org/wiki/Q7020","display_name":"Genome","level":3,"score":0.31790000200271606},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3118000030517578},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.3077000081539154},{"id":"https://openalex.org/C192953774","wikidata":"https://www.wikidata.org/wiki/Q7307127","display_name":"Reference genome","level":4,"score":0.3010999858379364},{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.28870001435279846},{"id":"https://openalex.org/C3020493868","wikidata":"https://www.wikidata.org/wiki/Q55631277","display_name":"Real world data","level":2,"score":0.2847999930381775},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.2745000123977661},{"id":"https://openalex.org/C148524875","wikidata":"https://www.wikidata.org/wiki/Q6975395","display_name":"F1 score","level":2,"score":0.2702000141143799},{"id":"https://openalex.org/C24432333","wikidata":"https://www.wikidata.org/wiki/Q2068526","display_name":"Whole genome sequencing","level":4,"score":0.26910001039505005},{"id":"https://openalex.org/C94353045","wikidata":"https://www.wikidata.org/wiki/Q13200112","display_name":"Percentile rank","level":3,"score":0.2685000002384186},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.2590000033378601},{"id":"https://openalex.org/C90673727","wikidata":"https://www.wikidata.org/wiki/Q901718","display_name":"Product (mathematics)","level":2,"score":0.25130000710487366}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.64898/2026.09.28.755102","doi":"https://doi.org/10.64898/2026.09.28.755102","is_oa":true,"landing_page_url":"https://doi.org/10.64898/2026.09.28.755102","pdf_url":"https://www.biorxiv.org/content/biorxiv/early/2026/10/03/2026.09.28.755102.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:10.64898/2026.09.28.755102","doi":"https://doi.org/10.64898/2026.09.28.755102","is_oa":true,"landing_page_url":"https://doi.org/10.64898/2026.09.28.755102","pdf_url":"https://www.biorxiv.org/content/biorxiv/early/2026/10/03/2026.09.28.755102.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":[],"funders":[{"id":"https://openalex.org/F4320332161","display_name":"National Institutes of Health","ror":"https://ror.org/01cwqze88"},{"id":"https://openalex.org/F4320337348","display_name":"National Human Genome Research Institute","ror":"https://ror.org/00baak391"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7218641840.pdf","grobid_xml":"https://content.openalex.org/works/W7218641840.grobid-xml"},"referenced_works_count":32,"referenced_works":["https://openalex.org/W2015831381","https://openalex.org/W2099085143","https://openalex.org/W2605897695","https://openalex.org/W2797527950","https://openalex.org/W2883257939","https://openalex.org/W2952683761","https://openalex.org/W2958615822","https://openalex.org/W2983859156","https://openalex.org/W3035965352","https://openalex.org/W3045441625","https://openalex.org/W3134184401","https://openalex.org/W4285730313","https://openalex.org/W4294012180","https://openalex.org/W4378907379","https://openalex.org/W4387561453","https://openalex.org/W4389727268","https://openalex.org/W4391925496","https://openalex.org/W4402385990","https://openalex.org/W4402874940","https://openalex.org/W4402952666","https://openalex.org/W4405427357","https://openalex.org/W4407683692","https://openalex.org/W4414973451","https://openalex.org/W4417080527","https://openalex.org/W6929343257","https://openalex.org/W6948264221","https://openalex.org/W7106695004","https://openalex.org/W7125135101","https://openalex.org/W7125486061","https://openalex.org/W7128532971","https://openalex.org/W7161939707","https://openalex.org/W7162959084"],"related_works":["https://openalex.org/W7161939707","https://openalex.org/W7155754225","https://openalex.org/W6893145011","https://openalex.org/W6906770462","https://openalex.org/W7165455756","https://openalex.org/W4399210639","https://openalex.org/W4412053001","https://openalex.org/W3165984471","https://openalex.org/W7125578769","https://openalex.org/W4402585660"],"abstract_inverted_index":{"Abstract":[0],"A":[1,188,230],"polygenic":[2],"score":[3,421],"(PGS)":[4],"is":[5,237,253],"a":[6,16,19,31,55,61,98,104,207,215,235,241,316,419],"unitless":[7],"weighted":[8],"sum":[9],"of":[10,145,151,169,264,342],"allele":[11],"dosages,":[12],"interpretable":[13],"only":[14,255],"as":[15,54,214,240,319],"percentile":[17],"within":[18,206],"reference":[20,33,221,415],"distribution.":[21],"Evaluating":[22],"risk":[23,233,299,405],"across":[24],"models":[25,42,202,406],"requires":[26],"scoring":[27,217,291],"each":[28],"individual":[29],"against":[30,80,173,199,295,401],"whole":[32,225],"panel,":[34],"but":[35,244,356],"current":[36],"CPU":[37],"pipelines":[38],"process":[39],"targets":[40],"or":[41],"sequentially,":[43],"making":[44],"full":[45],"cross-product":[46],"calculations":[47],"prohibitively":[48],"expensive.":[49],"We":[50,309,324,411],"reformulated":[51],"PGS":[52,226],"calculation":[53,312],"cohort-wide":[56],"sparse":[57],"matrix":[58,322],"product":[59,289],"on":[60,123,249,315,336,348,361,365],"GPU":[62],"and":[63,76,92,116,137,181,332,345,358],"optimized":[64],"it":[65,260,334],"via":[66],"an":[67,156,292,327,376],"autonomous":[68],"coding":[69,329,378],"agent":[70,88,161,330,379],"under":[71,408],"read-only":[72],"inputs,":[73],"cold":[74],"starts,":[75],"strict":[77],"numerical":[78],"validation":[79],"pgsc_calc.":[81,121],"The":[82,389],"scorer":[83,102,129],"was":[84,130],"\u201ctrained\u201d":[85],"by":[86],"the":[87,101,108,127,134,152,178,194,224,311,352,372,397,413,430],"accessing":[89],"synthetic":[90,99,153],"data":[91,179,350],"real":[93,125,362,366],"1000":[94,196,398],"Genomes":[95,399],"data.":[96],"On":[97],"benchmark,":[100],"achieved":[103],"10.6-fold":[105],"speedup":[106],"during":[107],"training":[109],"course":[110],"(184.9":[111],"s":[112],"to":[113,167,175,183,279,313],"17.4":[114],"s)":[115],"ran":[117],"71-fold":[118],"faster":[119],"than":[120,133,283],"However,":[122],"held-out":[124],"genomes,":[126],"synthetic-trained":[128],"15.3-fold":[131],"slower":[132],"real-data-trained":[135],"version":[136],"diverged":[138],"significantly":[139],"from":[140,155],"pgsc_calc":[141],"(maximum":[142],"absolute":[143],"difference":[144],"3.7\u00d710\u207b\u00b9":[146],"vs.":[147],"3.1\u00d710\u207b\u2074).":[148],"Three":[149],"replications":[150],"loop":[154],"identical":[157],"prompt":[158],"showed":[159],"that":[160,245,288,301,369,418],"optimization":[162],"trajectory":[163],"variance":[164],"explains":[165],"91":[166],"96%":[168],"total":[170],"wall-clock":[171],"variance,":[172],"0":[174],"2.6%":[176],"for":[177,185,223,234],"sampled":[180],"0.2":[182],"3.3%":[184],"repeated":[186,340],"execution.":[187],"memory-bounded":[189],"rebuild":[190],"then":[191,325],"scored":[192,392],"all":[193,200,393,402],"3,202":[195,394],"Genome":[197],"genotypes":[198],"5,385":[201,403],"in":[203,396,407],"6.5":[204],"h":[205],"72":[208],"GB":[209],"memory":[210],"cap,":[211],"released":[212],"here":[213],"frozen":[216],"manifest":[218],"with":[219],"ancestry-stratified":[220],"distributions":[222,416],"Catalog":[227],"Author":[228],"summary":[229],"person\u2019s":[231],"genetic":[232,298],"disease":[236,285],"usually":[238,277],"summarized":[239],"single":[242],"number,":[243],"number":[246],"means":[247,290],"nothing":[248],"its":[250,337],"own.":[251],"It":[252],"useful":[254],"once":[256],"we":[257],"know":[258,280],"where":[259],"falls":[261],"among":[262],"thousands":[263],"other":[265],"people":[266,395],"(i.e.":[267],"percentile).":[268],"Meanwhile,":[269],"someone":[270],"who":[271],"has":[272],"had":[273],"their":[274],"genome":[275],"sequenced":[276],"wants":[278],"about":[281],"more":[282],"one":[284,320],"risk.":[286],"Producing":[287],"entire":[293],"population":[294],"every":[296],"published":[297,404],"model":[300],"exists,":[302],"which":[303],"today\u2019s":[304],"tools":[305],"cannot":[306],"do":[307],"efficiently.":[308],"rebuilt":[310],"run":[314],"graphics":[317],"card":[318],"large":[321],"multiplication.":[323],"let":[326],"AI":[328,377],"rewrite":[331],"speed":[333],"up":[335],"own,":[338],"through":[339],"cycles":[341],"measuring,":[343],"planning":[344],"testing.":[346],"Practicing":[347],"artificial":[349],"made":[351],"code":[353],"fast":[354],"there":[355],"slow,":[357],"sometimes":[359],"inaccurate,":[360],"genomes.":[363],"Practising":[364],"genomes":[367],"avoided":[368],"trap.":[370],"Running":[371],"same":[373],"instructions":[374],"using":[375],"three":[380,384],"separate":[381],"times":[382],"produced":[383],"very":[385],"different":[386],"program":[387,391],"sets.":[388],"final":[390],"Project":[400],"seven":[409],"hours.":[410],"release":[412],"resulting":[414],"so":[417],"new":[420],"can":[422],"be":[423],"interpreted":[424],"at":[425],"once,":[426],"without":[427],"anyone":[428],"re-running":[429],"cohort.":[431]},"counts_by_year":[],"updated_date":"2026-11-09T13:22:03.289127","created_date":"2026-10-04T00:00:00"}