{"id":"https://openalex.org/W7223956409","doi":"https://doi.org/10.64898/2026.10.26.761949","title":"Evaluation design shapes estimates of cross-donor generalization in single-cell classification of cell-type","display_name":"Evaluation design shapes estimates of cross-donor generalization in single-cell classification of cell-type","publication_year":2026,"publication_date":"2026-10-27","ids":{"openalex":"https://openalex.org/W7223956409","doi":"https://doi.org/10.64898/2026.10.26.761949"},"language":"en","primary_location":{"id":"doi:10.64898/2026.10.26.761949","doi":"https://doi.org/10.64898/2026.10.26.761949","is_oa":true,"landing_page_url":"https://doi.org/10.64898/2026.10.26.761949","pdf_url":"https://www.biorxiv.org/content/biorxiv/early/2026/10/27/2026.10.26.761949.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":"acceptedVersion","is_accepted":true,"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/2026/10/27/2026.10.26.761949.full.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5007968053","display_name":"Xingyi Chen","orcid":"https://orcid.org/0009-0008-7226-2022","observed_orcids":["https://orcid.org/0009-0008-7226-2022"]},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xingyi Chen","raw_affiliation_strings":["Department of Applied Mathematics and Statistics, Johns Hopkins University, Baltimore, MD, USA"],"raw_orcid":"https://orcid.org/0009-0008-7226-2022","affiliations":[{"raw_affiliation_string":"Department of Applied Mathematics and Statistics, Johns Hopkins University, Baltimore, MD, USA","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5124377315","display_name":"Jiabei Li","orcid":"https://orcid.org/0009-0006-8707-8506","observed_orcids":["https://orcid.org/0009-0006-8707-8506"]},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jiabei Li","raw_affiliation_strings":["Department of Biomedical Engineering, Johns Hopkins University, Baltimore, MD, USA"],"raw_orcid":"https://orcid.org/0009-0006-8707-8506","affiliations":[{"raw_affiliation_string":"Department of Biomedical Engineering, Johns Hopkins University, Baltimore, MD, USA","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5063708781","display_name":"Alexis J. Battle","orcid":"https://orcid.org/0000-0002-5287-627X","observed_orcids":["https://orcid.org/0000-0002-5287-627X"]},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Alexis Battle","raw_affiliation_strings":["Data Science and AI Institute, Johns Hopkins University, Baltimore, MD, USA","Department of Biomedical Engineering, Johns Hopkins University, Baltimore, MD, USA","Department of Computer Science, Johns Hopkins University, Baltimore, MD, USA","Department of Genetic Medicine, Johns Hopkins University, Baltimore, MD, USA","Malone Center for Engineering in Healthcare, Johns Hopkins University, Baltimore, MD, USA"],"raw_orcid":"https://orcid.org/0000-0002-5287-627X","affiliations":[{"raw_affiliation_string":"Data Science and AI Institute, Johns Hopkins University, Baltimore, MD, USA","institution_ids":["https://openalex.org/I145311948"]},{"raw_affiliation_string":"Department of Biomedical Engineering, Johns Hopkins University, Baltimore, MD, USA","institution_ids":["https://openalex.org/I145311948"]},{"raw_affiliation_string":"Department of Computer Science, Johns Hopkins University, Baltimore, MD, USA","institution_ids":["https://openalex.org/I145311948"]},{"raw_affiliation_string":"Department of Genetic Medicine, Johns Hopkins University, Baltimore, MD, USA","institution_ids":["https://openalex.org/I145311948"]},{"raw_affiliation_string":"Malone Center for Engineering in Healthcare, Johns Hopkins University, Baltimore, MD, USA","institution_ids":["https://openalex.org/I145311948"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5063708781"],"corresponding_institution_ids":["https://openalex.org/I145311948"],"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/T11289","display_name":"Single-cell and spatial transcriptomics","score":0.9994999766349792,"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"}},"topics":[{"id":"https://openalex.org/T11289","display_name":"Single-cell and spatial transcriptomics","score":0.9994999766349792,"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/T10885","display_name":"Gene expression and cancer classification","score":0.00019999999494757503,"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/T12859","display_name":"Cell Image Analysis Techniques","score":9.999999747378752e-05,"subfield":{"id":"https://openalex.org/subfields/1304","display_name":"Biophysics"},"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/single-cell-classification","display_name":"single-cell classification","score":0.8640000224113464},{"id":"https://openalex.org/keywords/cell-type-classification","display_name":"cell type classification","score":0.8640000224113464},{"id":"https://openalex.org/keywords/evaluation-design","display_name":"evaluation design","score":0.7260000109672546},{"id":"https://openalex.org/keywords/assessment-bias","display_name":"evaluation bias","score":0.9089999794960022},{"id":"https://openalex.org/keywords/batch-effects","display_name":"batch effects","score":0.6489999890327454},{"id":"https://openalex.org/keywords/mixed-effects-models","display_name":"mixed models","score":0.8159999847412109},{"id":"https://openalex.org/keywords/peripheral-blood-mononuclear-cells","display_name":"peripheral blood mononuclear cells","score":0.5820000171661377},{"id":"https://openalex.org/keywords/lung","display_name":"lung","score":0.7720000147819519},{"id":"https://openalex.org/keywords/kidney","display_name":"kidney","score":0.871999979019165},{"id":"https://openalex.org/keywords/pancreas","display_name":"pancreas","score":0.8970000147819519},{"id":"https://openalex.org/keywords/blood","display_name":"blood","score":0.3869999945163727}],"concepts":[{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.7993000149726868},{"id":"https://openalex.org/C119043178","wikidata":"https://www.wikidata.org/wiki/Q320723","display_name":"Covariate","level":2,"score":0.7124999761581421},{"id":"https://openalex.org/C166955791","wikidata":"https://www.wikidata.org/wiki/Q629579","display_name":"Macro","level":2,"score":0.5091000199317932},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.49070000648498535},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.4846000075340271},{"id":"https://openalex.org/C90559484","wikidata":"https://www.wikidata.org/wiki/Q778379","display_name":"Expression (computer science)","level":2,"score":0.4325999915599823},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.40720000863075256},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.40130001306533813},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.37229999899864197},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.3646000027656555},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.36230000853538513},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3456999957561493},{"id":"https://openalex.org/C122123141","wikidata":"https://www.wikidata.org/wiki/Q176623","display_name":"Random variable","level":2,"score":0.33239999413490295},{"id":"https://openalex.org/C12426560","wikidata":"https://www.wikidata.org/wiki/Q189569","display_name":"Basis (linear algebra)","level":2,"score":0.3093999922275543},{"id":"https://openalex.org/C168743327","wikidata":"https://www.wikidata.org/wiki/Q1826427","display_name":"Random effects model","level":3,"score":0.29829999804496765},{"id":"https://openalex.org/C3018395757","wikidata":"https://www.wikidata.org/wiki/Q1379672","display_name":"Evaluation methods","level":2,"score":0.2874000072479248},{"id":"https://openalex.org/C5274069","wikidata":"https://www.wikidata.org/wiki/Q2285707","display_name":"Categorical variable","level":2,"score":0.2838999927043915},{"id":"https://openalex.org/C73782692","wikidata":"https://www.wikidata.org/wiki/Q196372","display_name":"Random error","level":2,"score":0.2802000045776367},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.27900001406669617},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.27379998564720154},{"id":"https://openalex.org/C96608239","wikidata":"https://www.wikidata.org/wiki/Q1199823","display_name":"Statistical power","level":2,"score":0.2599000036716461},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.2551000118255615},{"id":"https://openalex.org/C49781872","wikidata":"https://www.wikidata.org/wiki/Q1045555","display_name":"Maximum likelihood","level":2,"score":0.250900000333786}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.64898/2026.10.26.761949","doi":"https://doi.org/10.64898/2026.10.26.761949","is_oa":true,"landing_page_url":"https://doi.org/10.64898/2026.10.26.761949","pdf_url":"https://www.biorxiv.org/content/biorxiv/early/2026/10/27/2026.10.26.761949.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":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"bioRxiv","raw_type":"posted-content"}],"best_oa_location":{"id":"doi:10.64898/2026.10.26.761949","doi":"https://doi.org/10.64898/2026.10.26.761949","is_oa":true,"landing_page_url":"https://doi.org/10.64898/2026.10.26.761949","pdf_url":"https://www.biorxiv.org/content/biorxiv/early/2026/10/27/2026.10.26.761949.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":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"bioRxiv","raw_type":"posted-content"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/3","score":0.6240000128746033,"display_name":"Good health and well-being"}],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7223956409.pdf","grobid_xml":"https://content.openalex.org/works/W7223956409.grobid-xml"},"referenced_works_count":14,"referenced_works":["https://openalex.org/W2901677030","https://openalex.org/W2949237386","https://openalex.org/W2984472267","https://openalex.org/W3117771127","https://openalex.org/W3124814274","https://openalex.org/W3126641974","https://openalex.org/W3153732845","https://openalex.org/W4311662052","https://openalex.org/W4324045291","https://openalex.org/W4379879135","https://openalex.org/W4399816910","https://openalex.org/W4401314781","https://openalex.org/W4401441450","https://openalex.org/W7160428848"],"related_works":["https://openalex.org/W7155521292","https://openalex.org/W7170897467","https://openalex.org/W7213268588","https://openalex.org/W7169500584","https://openalex.org/W7160428848","https://openalex.org/W7158212776","https://openalex.org/W7037764826","https://openalex.org/W3007874153","https://openalex.org/W7167588833","https://openalex.org/W7196942373"],"abstract_inverted_index":{"Abstract":[0],"Motivation":[1],"Single-cell":[2],"cell-type":[3],"classifiers":[4],"are":[5,18,113,127],"often":[6],"evaluated":[7],"using":[8],"random":[9,37],"cell-level":[10,38],"splits,":[11],"although":[12],"cells":[13],"from":[14],"the":[15,90],"same":[16],"donor":[17],"not":[19],"independent.":[20],"We":[21],"asked":[22],"how":[23],"evaluation":[24,47,65,86,97],"design":[25],"affects":[26],"estimates":[27],"of":[28],"cross-donor":[29],"generalization.":[30],"Results":[31],"Across":[32],"PBMC":[33],"and":[34,59,73,76,94,108,111,119,130],"lung":[35],"datasets,":[36],"splitting":[39],"consistently":[40],"yielded":[41],"higher":[42],"macro":[43],"F1":[44],"than":[45],"donor-held-out":[46,96],"across":[48],"multiple":[49],"expression":[50],"representations.":[51],"This":[52],"gap":[53],"persisted":[54],"after":[55],"batch":[56],"covariate":[57],"adjustment":[58],"donor-level":[60],"mixed-effects":[61],"modeling.":[62],"In":[63],"contrast,":[64],"gaps":[66],"were":[67],"minimal":[68],"in":[69,77],"near-ceiling":[70],"kidney,":[71],"pancreas,":[72],"blood":[74],"benchmarks":[75],"a":[78],"randomized-label":[79],"floor":[80],"control.":[81],"These":[82],"results":[83],"show":[84],"that":[85,95],"bias":[87],"depends":[88],"on":[89,115],"underlying":[91],"classification":[92],"regime":[93],"is":[98],"necessary":[99],"when":[100],"claims":[101],"concern":[102],"generalization":[103],"to":[104],"unseen":[105],"individuals.":[106],"Availability":[107],"Implementation":[109],"Code":[110],"analyses":[112],"available":[114,129],"GitHub":[116],"at":[117,121,123],"https://github.com/danielchen05/scRNA-cross-donor-generalization/":[118],"archived":[120],"Zenodo":[122],"10.5281/zenodo.23669184.":[124],"All":[125],"data":[126],"publicly":[128],"cited.":[131],"Contact":[132],"ajbattle@jhu.edu":[133]},"counts_by_year":[],"updated_date":"2026-11-04T10:54:05.112534","created_date":"2026-10-28T00:00:00"}