{"id":"https://openalex.org/W7221663469","doi":"https://doi.org/10.64898/2026.10.05.756786","title":"Efficient approximate Bayesian inference for large, heterogeneous biological datasets","display_name":"Efficient approximate Bayesian inference for large, heterogeneous biological datasets","publication_year":2026,"publication_date":"2026-10-12","ids":{"openalex":"https://openalex.org/W7221663469","doi":"https://doi.org/10.64898/2026.10.05.756786","pmid":"https://pubmed.ncbi.nlm.nih.gov/42999181","pmcid":"https://www.ncbi.nlm.nih.gov/pmc/articles/13742641"},"language":"en","primary_location":{"id":"doi:10.64898/2026.10.05.756786","doi":"https://doi.org/10.64898/2026.10.05.756786","is_oa":true,"landing_page_url":"https://doi.org/10.64898/2026.10.05.756786","pdf_url":"https://www.biorxiv.org/content/biorxiv/early/2026/10/12/2026.10.05.756786.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","pubmed"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://www.biorxiv.org/content/biorxiv/early/2026/10/12/2026.10.05.756786.full.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5013940835","display_name":"Jacy Zanussi","orcid":"https://orcid.org/0000-0003-2051-436X","observed_orcids":["https://orcid.org/0000-0003-2051-436X"]},"institutions":[{"id":"https://openalex.org/I204250578","display_name":"University of California, Irvine","ror":"https://ror.org/04gyf1771","country_code":"US","type":"education","lineage":["https://openalex.org/I204250578"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jacy T. Zanussi","raw_affiliation_strings":["Center for Complex Biological Systems, University of California, Irvine, CA, USA"],"raw_orcid":"https://orcid.org/0000-0003-2051-436X","affiliations":[{"raw_affiliation_string":"Center for Complex Biological Systems, University of California, Irvine, CA, USA","institution_ids":["https://openalex.org/I204250578"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5036077055","display_name":"Christopher E. Miles","orcid":"https://orcid.org/0000-0001-5494-403X","observed_orcids":["https://orcid.org/0000-0001-5494-403X"]},"institutions":[{"id":"https://openalex.org/I223532165","display_name":"University of Utah","ror":"https://ror.org/03r0ha626","country_code":"US","type":"education","lineage":["https://openalex.org/I223532165"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Christopher E. Miles","raw_affiliation_strings":["Department of Mathematics, University of Utah, Salt Lake City, UT, USA"],"raw_orcid":"https://orcid.org/0000-0001-5494-403X","affiliations":[{"raw_affiliation_string":"Department of Mathematics, University of Utah, Salt Lake City, UT, USA","institution_ids":["https://openalex.org/I223532165"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5036077055"],"corresponding_institution_ids":["https://openalex.org/I223532165"],"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/T12056","display_name":"Markov Chains and Monte Carlo Methods","score":0.9980000257492065,"subfield":{"id":"https://openalex.org/subfields/2613","display_name":"Statistics and Probability"},"field":{"id":"https://openalex.org/fields/26","display_name":"Mathematics"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T12056","display_name":"Markov Chains and Monte Carlo Methods","score":0.9980000257492065,"subfield":{"id":"https://openalex.org/subfields/2613","display_name":"Statistics and Probability"},"field":{"id":"https://openalex.org/fields/26","display_name":"Mathematics"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10621","display_name":"Gene Regulatory Network Analysis","score":0.0007999999797903001,"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/T10243","display_name":"Statistical Methods and Bayesian Inference","score":9.999999747378752e-05,"subfield":{"id":"https://openalex.org/subfields/2613","display_name":"Statistics and Probability"},"field":{"id":"https://openalex.org/fields/26","display_name":"Mathematics"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/approximate-bayesian-computation","display_name":"approximate Bayesian computation","score":0.9279999732971191},{"id":"https://openalex.org/keywords/sequential-monte-carlo","display_name":"sequential Monte Carlo","score":0.6439999938011169},{"id":"https://openalex.org/keywords/adaptive-batch-size","display_name":"adaptive batch size","score":0.9879999756813049},{"id":"https://openalex.org/keywords/simulation-based-inference","display_name":"simulation-based inference","score":0.8939999938011169},{"id":"https://openalex.org/keywords/mechanistic-model","display_name":"mechanistic model","score":0.7020000219345093},{"id":"https://openalex.org/keywords/single-cell-gene-expression","display_name":"single-cell gene expression","score":0.8379999995231628},{"id":"https://openalex.org/keywords/cell-shape","display_name":"cell shape","score":0.4580000042915344},{"id":"https://openalex.org/keywords/initial-conditions","display_name":"initial conditions","score":0.7400000095367432},{"id":"https://openalex.org/keywords/computational-cost-reduction","display_name":"computational complexity reduction","score":0.5709999799728394},{"id":"https://openalex.org/keywords/heterogeneous-biological-data","display_name":"heterogeneous biological data","score":0.5109999775886536}],"concepts":[{"id":"https://openalex.org/C2779377595","wikidata":"https://www.wikidata.org/wiki/Q21045424","display_name":"Approximate Bayesian computation","level":3,"score":0.776199996471405},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7038999795913696},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5848000049591064},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.572700023651123},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.5522000193595886},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5335000157356262},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.491100013256073},{"id":"https://openalex.org/C2781395549","wikidata":"https://www.wikidata.org/wiki/Q4680762","display_name":"Adaptive sampling","level":3,"score":0.4832000136375427},{"id":"https://openalex.org/C160234255","wikidata":"https://www.wikidata.org/wiki/Q812535","display_name":"Bayesian inference","level":3,"score":0.44850000739097595},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.44279998540878296},{"id":"https://openalex.org/C19499675","wikidata":"https://www.wikidata.org/wiki/Q232207","display_name":"Monte Carlo method","level":2,"score":0.43549999594688416},{"id":"https://openalex.org/C58489278","wikidata":"https://www.wikidata.org/wiki/Q1172284","display_name":"Data set","level":2,"score":0.4162999987602234},{"id":"https://openalex.org/C151201525","wikidata":"https://www.wikidata.org/wiki/Q177239","display_name":"Limit (mathematics)","level":2,"score":0.4074999988079071},{"id":"https://openalex.org/C160920958","wikidata":"https://www.wikidata.org/wiki/Q7662746","display_name":"Synthetic data","level":2,"score":0.4018999934196472},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.39489999413490295},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3944000005722046},{"id":"https://openalex.org/C149629883","wikidata":"https://www.wikidata.org/wiki/Q660926","display_name":"Fraction (chemistry)","level":2,"score":0.37610000371932983},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.3662000000476837},{"id":"https://openalex.org/C52740198","wikidata":"https://www.wikidata.org/wiki/Q1539564","display_name":"Importance sampling","level":3,"score":0.36410000920295715},{"id":"https://openalex.org/C134261354","wikidata":"https://www.wikidata.org/wiki/Q938438","display_name":"Statistical inference","level":2,"score":0.3614000082015991},{"id":"https://openalex.org/C201797286","wikidata":"https://www.wikidata.org/wiki/Q4914986","display_name":"Biological data","level":2,"score":0.36010000109672546},{"id":"https://openalex.org/C162376815","wikidata":"https://www.wikidata.org/wiki/Q2158281","display_name":"Frequentist inference","level":4,"score":0.3571000099182129},{"id":"https://openalex.org/C52421305","wikidata":"https://www.wikidata.org/wiki/Q1151499","display_name":"Particle filter","level":3,"score":0.35600000619888306},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.3528999984264374},{"id":"https://openalex.org/C111350023","wikidata":"https://www.wikidata.org/wiki/Q1191869","display_name":"Markov chain Monte Carlo","level":3,"score":0.32420000433921814},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2939999997615814},{"id":"https://openalex.org/C207201462","wikidata":"https://www.wikidata.org/wiki/Q182505","display_name":"Bayes' theorem","level":3,"score":0.2897000014781952},{"id":"https://openalex.org/C32230216","wikidata":"https://www.wikidata.org/wiki/Q7882499","display_name":"Uncertainty quantification","level":2,"score":0.28870001435279846},{"id":"https://openalex.org/C129848803","wikidata":"https://www.wikidata.org/wiki/Q2564360","display_name":"Sample size determination","level":2,"score":0.2809999883174896},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.27619999647140503},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.2703999876976013},{"id":"https://openalex.org/C917703","wikidata":"https://www.wikidata.org/wiki/Q7239668","display_name":"Predictive inference","level":5,"score":0.2565999925136566},{"id":"https://openalex.org/C2985139394","wikidata":"https://www.wikidata.org/wiki/Q49908","display_name":"Sampling scheme","level":3,"score":0.2558000087738037},{"id":"https://openalex.org/C57830394","wikidata":"https://www.wikidata.org/wiki/Q278079","display_name":"Posterior probability","level":3,"score":0.25529998540878296}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.64898/2026.10.05.756786","doi":"https://doi.org/10.64898/2026.10.05.756786","is_oa":true,"landing_page_url":"https://doi.org/10.64898/2026.10.05.756786","pdf_url":"https://www.biorxiv.org/content/biorxiv/early/2026/10/12/2026.10.05.756786.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"},{"id":"pmid:42999181","doi":null,"is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/42999181","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"bioRxiv : the preprint server for biology","raw_type":"Journal Article"}],"best_oa_location":{"id":"doi:10.64898/2026.10.05.756786","doi":"https://doi.org/10.64898/2026.10.05.756786","is_oa":true,"landing_page_url":"https://doi.org/10.64898/2026.10.05.756786","pdf_url":"https://www.biorxiv.org/content/biorxiv/early/2026/10/12/2026.10.05.756786.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":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7221663469.pdf","grobid_xml":"https://content.openalex.org/works/W7221663469.grobid-xml"},"referenced_works_count":29,"referenced_works":["https://openalex.org/W1639036308","https://openalex.org/W1995780830","https://openalex.org/W2053332694","https://openalex.org/W2061570747","https://openalex.org/W2067392831","https://openalex.org/W2075251971","https://openalex.org/W2081970839","https://openalex.org/W2084924279","https://openalex.org/W2152246075","https://openalex.org/W2155418451","https://openalex.org/W2218765604","https://openalex.org/W2436219157","https://openalex.org/W2568869761","https://openalex.org/W2973917400","https://openalex.org/W2984417636","https://openalex.org/W3000211799","https://openalex.org/W3033895182","https://openalex.org/W3043504524","https://openalex.org/W4256266823","https://openalex.org/W4283260535","https://openalex.org/W4317499882","https://openalex.org/W4320858579","https://openalex.org/W4388870165","https://openalex.org/W4409251195","https://openalex.org/W4413300888","https://openalex.org/W4414533431","https://openalex.org/W4416548309","https://openalex.org/W7164851849","https://openalex.org/W7212143764"],"related_works":["https://openalex.org/W2135267747","https://openalex.org/W3009943122","https://openalex.org/W7100689584","https://openalex.org/W1604857520","https://openalex.org/W2051823273","https://openalex.org/W2082850612","https://openalex.org/W2068936262","https://openalex.org/W162812001","https://openalex.org/W2016474290","https://openalex.org/W2225543371"],"abstract_inverted_index":{"Simulation-based":[0],"inference":[1,232],"(SBI)":[2],"offers":[3],"a":[4,34,46,63,91,208],"route":[5],"to":[6,20,49,52,201,230],"connect":[7],"biological":[8,170,236],"data":[9,177],"with":[10,147],"mechanistic":[11,35,231],"models.":[12],"At":[13],"the":[14,101,125,129,140,148,151,154,166,195,211,217,228],"frontier":[15],"of":[16,55,66,95,103,150,184,203,210],"biology,":[17],"datasets":[18],"continue":[19],"grow":[21,146],"in":[22,180,223],"scale":[23,181],"and":[24,26,123,143,172,182,189,221,226],"richness,":[25],"increasingly":[27],"record":[28],"heterogeneity":[29,60],"between":[30,219],"individual":[31],"observations":[32,96],"that":[33,106,116,178],"model":[36],"can":[37],"take":[38],"into":[39],"account.":[40],"Approximate":[41],"Bayesian":[42],"Computation":[43],"(ABC)":[44],"remains":[45],"popular":[47],"approach":[48,115],"SBI":[50],"due":[51],"its":[53],"ease":[54],"use,":[56],"but":[57],"incorporating":[58],"this":[59,87],"often":[61],"requires":[62],"separate":[64],"simulation":[65],"each":[67,98,193],"observation,":[68],"which":[69],"is":[70,131,137],"prohibitively":[71],"expensive":[72],"at":[73,100,207],"scale.":[74],"A":[75],"previously":[76],"proposed":[77],"technique,":[78],"minibatch":[79,114],"Sequential":[80],"Monte":[81],"Carlo":[82],"ABC":[83,159,206,225],"(SMC":[84],"ABC),":[85],"reduces":[86],"cost":[88],"by":[89,139],"simulating":[90],"fixed-size":[92],"random":[93],"subset":[94],"for":[97,161],"proposal,":[99],"price":[102],"sampling":[104],"noise":[105],"limits":[107],"precision.":[108],"Here,":[109],"we":[110],"present":[111],"an":[112],"adaptive":[113,134,196,214],"uses":[117],"small":[118],"batches":[119],"during":[120],"early":[121],"exploration":[122],"increases":[124],"batch":[126,135],"size":[127,136,149],"as":[128],"posterior":[130],"refined.":[132],"The":[133],"set":[138],"target":[141],"precision":[142,222],"does":[144],"not":[145],"dataset,":[152],"so":[153],"savings":[155],"over":[156],"full-data":[157,204],"SMC":[158,205,224],"increase":[160],"larger":[162],"datasets.":[163,237],"We":[164],"demonstrate":[165],"method":[167],"on":[168,173,233],"synthetic":[169],"models":[171],"real":[174],"single-cell":[175],"gene-expression":[176],"vary":[179],"type":[183],"heterogeneity,":[185],"including":[186],"cell":[187],"geometry":[188],"initial":[190],"condition.":[191],"In":[192],"case,":[194],"scheme":[197],"obtains":[198],"posteriors":[199],"close":[200],"those":[202],"fraction":[209],"cost.":[212],"Altogether,":[213],"minibatching":[215],"improves":[216],"tradeoff":[218],"speed":[220],"opens":[227],"door":[229],"large,":[234],"heterogeneous":[235]},"counts_by_year":[],"updated_date":"2026-11-09T13:22:03.289127","created_date":"2026-10-14T00:00:00"}