{"id":"https://openalex.org/W4413994880","doi":"https://doi.org/10.3389/fbinf.2025.1528515","title":"Adaptive sampling methods facilitate the determination of reliable dataset sizes for evidence-based modeling","display_name":"Adaptive sampling methods facilitate the determination of reliable dataset sizes for evidence-based modeling","publication_year":2025,"publication_date":"2025-09-04","ids":{"openalex":"https://openalex.org/W4413994880","doi":"https://doi.org/10.3389/fbinf.2025.1528515","pmid":"https://pubmed.ncbi.nlm.nih.gov/40980693"},"language":"en","primary_location":{"id":"doi:10.3389/fbinf.2025.1528515","is_oa":true,"landing_page_url":"https://doi.org/10.3389/fbinf.2025.1528515","pdf_url":"https://www.frontiersin.org/journals/bioinformatics/articles/10.3389/fbinf.2025.1528515/pdf","source":{"id":"https://openalex.org/S4210219554","display_name":"Frontiers in Bioinformatics","issn_l":"2673-7647","issn":["2673-7647"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320527","host_organization_name":"Frontiers Media","host_organization_lineage":["https://openalex.org/P4310320527"],"host_organization_lineage_names":["Frontiers Media"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Bioinformatics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.frontiersin.org/journals/bioinformatics/articles/10.3389/fbinf.2025.1528515/pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5042261155","display_name":"Tim Breitenbach","orcid":"https://orcid.org/0000-0003-4615-1915"},"institutions":[{"id":"https://openalex.org/I25974101","display_name":"University of W\u00fcrzburg","ror":"https://ror.org/00fbnyb24","country_code":"DE","type":"education","lineage":["https://openalex.org/I25974101"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Tim Breitenbach","raw_affiliation_strings":["Lehrstuhl f\u00fcr Bioinformatik, Biozentrum, Julius-Maximilians-Universit\u00e4t W\u00fcrzburg, W\u00fcrzburg, Germany"],"affiliations":[{"raw_affiliation_string":"Lehrstuhl f\u00fcr Bioinformatik, Biozentrum, Julius-Maximilians-Universit\u00e4t W\u00fcrzburg, W\u00fcrzburg, Germany","institution_ids":["https://openalex.org/I25974101"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5086202312","display_name":"Thomas Dandekar","orcid":"https://orcid.org/0000-0003-1886-7625"},"institutions":[{"id":"https://openalex.org/I25974101","display_name":"University of W\u00fcrzburg","ror":"https://ror.org/00fbnyb24","country_code":"DE","type":"education","lineage":["https://openalex.org/I25974101"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Thomas Dandekar","raw_affiliation_strings":["Lehrstuhl f\u00fcr Bioinformatik, Biozentrum, Julius-Maximilians-Universit\u00e4t W\u00fcrzburg, W\u00fcrzburg, Germany"],"affiliations":[{"raw_affiliation_string":"Lehrstuhl f\u00fcr Bioinformatik, Biozentrum, Julius-Maximilians-Universit\u00e4t W\u00fcrzburg, W\u00fcrzburg, Germany","institution_ids":["https://openalex.org/I25974101"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5042261155"],"corresponding_institution_ids":["https://openalex.org/I25974101"],"apc_list":{"value":1900,"currency":"USD","value_usd":1900},"apc_paid":{"value":1900,"currency":"USD","value_usd":1900},"fwci":2.3691,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.90092722,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":"5","issue":null,"first_page":"1528515","last_page":"1528515"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10243","display_name":"Statistical Methods and Bayesian Inference","score":0.9779000282287598,"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/T10243","display_name":"Statistical Methods and Bayesian Inference","score":0.9779000282287598,"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/T12761","display_name":"Data Stream Mining Techniques","score":0.9708999991416931,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/T13702","display_name":"Machine Learning in Healthcare","score":0.9460999965667725,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/sampling","display_name":"Sampling (signal processing)","score":0.5960063338279724},{"id":"https://openalex.org/keywords/adaptive-sampling","display_name":"Adaptive sampling","score":0.5673170685768127},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.548414409160614},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3527768850326538},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.28495752811431885},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.15973806381225586},{"id":"https://openalex.org/keywords/monte-carlo-method","display_name":"Monte Carlo method","score":0.1033942699432373}],"concepts":[{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.5960063338279724},{"id":"https://openalex.org/C2781395549","wikidata":"https://www.wikidata.org/wiki/Q4680762","display_name":"Adaptive sampling","level":3,"score":0.5673170685768127},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.548414409160614},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3527768850326538},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.28495752811431885},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.15973806381225586},{"id":"https://openalex.org/C19499675","wikidata":"https://www.wikidata.org/wiki/Q232207","display_name":"Monte Carlo method","level":2,"score":0.1033942699432373},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.0},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.0}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.3389/fbinf.2025.1528515","is_oa":true,"landing_page_url":"https://doi.org/10.3389/fbinf.2025.1528515","pdf_url":"https://www.frontiersin.org/journals/bioinformatics/articles/10.3389/fbinf.2025.1528515/pdf","source":{"id":"https://openalex.org/S4210219554","display_name":"Frontiers in Bioinformatics","issn_l":"2673-7647","issn":["2673-7647"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320527","host_organization_name":"Frontiers Media","host_organization_lineage":["https://openalex.org/P4310320527"],"host_organization_lineage_names":["Frontiers Media"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Bioinformatics","raw_type":"journal-article"},{"id":"pmid:40980693","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/40980693","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,"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":"Frontiers in bioinformatics","raw_type":null},{"id":"pmh:oai:doaj.org/article:3c37d13ff5b143a0b40a47bb7fd49453","is_oa":true,"landing_page_url":"https://doaj.org/article/3c37d13ff5b143a0b40a47bb7fd49453","pdf_url":null,"source":{"id":"https://openalex.org/S112646816","display_name":"SHILAP Revista de lepidopterolog\u00eda","issn_l":"0300-5267","issn":["0300-5267","2340-4078"],"is_oa":true,"is_in_doaj":true,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Frontiers in Bioinformatics, Vol 5 (2025)","raw_type":"article"},{"id":"pmh:oai:europepmc.org:11253704","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/12444090","pdf_url":null,"source":{"id":"https://openalex.org/S4306400806","display_name":"Europe PMC (PubMed Central)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1303153112","host_organization_name":"European Bioinformatics Institute","host_organization_lineage":["https://openalex.org/I1303153112"],"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":null,"raw_type":"Text"},{"id":"pmh:oai:pubmedcentral.nih.gov:12444090","is_oa":true,"landing_page_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC12444090/","pdf_url":null,"source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Front Bioinform","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.3389/fbinf.2025.1528515","is_oa":true,"landing_page_url":"https://doi.org/10.3389/fbinf.2025.1528515","pdf_url":"https://www.frontiersin.org/journals/bioinformatics/articles/10.3389/fbinf.2025.1528515/pdf","source":{"id":"https://openalex.org/S4210219554","display_name":"Frontiers in Bioinformatics","issn_l":"2673-7647","issn":["2673-7647"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320527","host_organization_name":"Frontiers Media","host_organization_lineage":["https://openalex.org/P4310320527"],"host_organization_lineage_names":["Frontiers Media"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Bioinformatics","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4413994880.pdf","grobid_xml":"https://content.openalex.org/works/W4413994880.grobid-xml"},"referenced_works_count":24,"referenced_works":["https://openalex.org/W1886819223","https://openalex.org/W2092095117","https://openalex.org/W2102434872","https://openalex.org/W2107854016","https://openalex.org/W2132565565","https://openalex.org/W2132886902","https://openalex.org/W2134429390","https://openalex.org/W2175082661","https://openalex.org/W2179083909","https://openalex.org/W2895175378","https://openalex.org/W2951934944","https://openalex.org/W2958415029","https://openalex.org/W3044338806","https://openalex.org/W3125018083","https://openalex.org/W3192153590","https://openalex.org/W4211192810","https://openalex.org/W4220685469","https://openalex.org/W4225591000","https://openalex.org/W4285678695","https://openalex.org/W4381547856","https://openalex.org/W4394566602","https://openalex.org/W4394909957","https://openalex.org/W4399691497","https://openalex.org/W4410550689"],"related_works":["https://openalex.org/W2038693912","https://openalex.org/W1991602789","https://openalex.org/W1582396021","https://openalex.org/W1988359706","https://openalex.org/W312558119","https://openalex.org/W4210985407","https://openalex.org/W2335441444","https://openalex.org/W138014004","https://openalex.org/W2075598034","https://openalex.org/W2984441180"],"abstract_inverted_index":{"How":[0],"can":[1],"we":[2],"be":[3],"sure":[4],"that":[5,14,53,84,136],"there":[6],"is":[7,116],"sufficient":[8,163],"data":[9,21,56,67,72,76,112,153],"for":[10,99],"our":[11],"model,":[12],"such":[13],"the":[15,23,27,40,55,59,65,78,101,108,111,126,142,145,151,157,177,182],"predictions":[16],"remain":[17],"reliable":[18,147],"on":[19,141],"unseen":[20],"and":[22,46,58],"conclusions":[24,137,180],"drawn":[25,69],"from":[26,70],"fitted":[28],"model":[29,86],"would":[30],"not":[31,139],"vary":[32],"significantly":[33],"when":[34],"using":[35,118],"a":[36,50,71,85,96,123,162,172],"different":[37,131],"sample":[38,66],"of":[39,80,103,110,165,179,185],"same":[41],"size?":[42],"We":[43],"answer":[44],"these":[45],"related":[47],"questions":[48],"through":[49],"systematic":[51],"approach":[52,94],"examines":[54],"size":[57,109],"corresponding":[60],"gains":[61],"in":[62,125,150],"accuracy.":[63,92],"Assuming":[64],"are":[68],"pool":[73],"with":[74,105],"no":[75],"drift,":[77],"law":[79],"large":[81],"numbers":[82],"ensures":[83],"converges":[87],"to":[88,107,167],"its":[89],"ground":[90],"truth":[91],"Our":[93],"provides":[95],"heuristic":[97],"method":[98,159],"investigating":[100],"speed":[102,128],"convergence":[104,127,155],"respect":[106],"sample.":[113],"This":[114],"relationship":[115],"estimated":[117],"sampling":[119,169],"methods,":[120],"which":[121],"introduces":[122],"variation":[124],"results":[129],"across":[130],"runs.":[132],"To":[133],"stabilize":[134],"results-so":[135],"do":[138],"depend":[140],"run-and":[143],"extract":[144],"most":[146],"information":[148],"encoded":[149],"available":[152],"regarding":[154],"speed,":[156],"presented":[158],"automatically":[160],"determines":[161],"number":[164],"repetitions":[166],"reduce":[168],"deviations":[170],"below":[171],"predefined":[173],"threshold,":[174],"thereby":[175],"ensuring":[176],"reliability":[178],"about":[181],"required":[183],"amount":[184],"data.":[186]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-04-21T08:09:41.155169","created_date":"2025-10-10T00:00:00"}
