{"id":"https://openalex.org/W7207793520","doi":"https://doi.org/10.64898/2026.08.28.747622","title":"Dataset structure outweighs method choice in single-cell cell-type annotation","display_name":"Dataset structure outweighs method choice in single-cell cell-type annotation","publication_year":2026,"publication_date":"2026-09-03","ids":{"openalex":"https://openalex.org/W7207793520","doi":"https://doi.org/10.64898/2026.08.28.747622"},"language":"en","primary_location":{"id":"doi:10.64898/2026.08.28.747622","doi":"https://doi.org/10.64898/2026.08.28.747622","is_oa":true,"landing_page_url":"https://doi.org/10.64898/2026.08.28.747622","pdf_url":null,"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://doi.org/10.64898/2026.08.28.747622","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5116629494","display_name":"Oliver Wardhana","orcid":"https://orcid.org/0009-0001-6022-1978","observed_orcids":["https://orcid.org/0009-0001-6022-1978"]},"institutions":[{"id":"https://openalex.org/I107639228","display_name":"University of Notre Dame","ror":"https://ror.org/00mkhxb43","country_code":"US","type":"education","lineage":["https://openalex.org/I107639228"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Oliver Wardhana","raw_affiliation_strings":["Department of Biological Sciences, University of Notre Dame, Notre Dame, IN, USA"],"raw_orcid":"https://orcid.org/0009-0001-6022-1978","affiliations":[{"raw_affiliation_string":"Department of Biological Sciences, University of Notre Dame, Notre Dame, IN, USA","institution_ids":["https://openalex.org/I107639228"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5116629494"],"corresponding_institution_ids":["https://openalex.org/I107639228"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":1,"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":1.0,"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":1.0,"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":0.0,"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":0.0,"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-rna-sequencing","display_name":"single-cell RNA sequencing","score":0.7179999947547913},{"id":"https://openalex.org/keywords/dataset-structure","display_name":"dataset structure","score":0.6930000185966492},{"id":"https://openalex.org/keywords/class-imbalance","display_name":"class imbalance","score":0.7080000042915344},{"id":"https://openalex.org/keywords/foundation-models","display_name":"foundation models","score":0.5389999747276306},{"id":"https://openalex.org/keywords/large-language-models","display_name":"large language models","score":0.8519999980926514},{"id":"https://openalex.org/keywords/cross-platform-transfer","display_name":"cross-platform transfer","score":0.5429999828338623},{"id":"https://openalex.org/keywords/marker-database","display_name":"marker database","score":0.7229999899864197},{"id":"https://openalex.org/keywords/label-transfer","display_name":"label transfer","score":0.49799999594688416},{"id":"https://openalex.org/keywords/method-selection","display_name":"method selection","score":0.3269999921321869}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6535999774932861},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.5672000050544739},{"id":"https://openalex.org/C177212765","wikidata":"https://www.wikidata.org/wiki/Q627335","display_name":"Workflow","level":2,"score":0.5185999870300293},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.5060999989509583},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.45809999108314514},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4291999936103821},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4120999872684479},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.39890000224113464},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.39629998803138733},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3783000111579895},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.37720000743865967},{"id":"https://openalex.org/C55166926","wikidata":"https://www.wikidata.org/wiki/Q2892946","display_name":"Oracle","level":2,"score":0.36579999327659607},{"id":"https://openalex.org/C81669768","wikidata":"https://www.wikidata.org/wiki/Q2359161","display_name":"Precision and recall","level":2,"score":0.35530000925064087},{"id":"https://openalex.org/C206588197","wikidata":"https://www.wikidata.org/wiki/Q846574","display_name":"Reuse","level":2,"score":0.33160001039505005},{"id":"https://openalex.org/C196083921","wikidata":"https://www.wikidata.org/wiki/Q7915758","display_name":"Variance (accounting)","level":2,"score":0.30959999561309814},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.30090001225471497},{"id":"https://openalex.org/C119043178","wikidata":"https://www.wikidata.org/wiki/Q320723","display_name":"Covariate","level":2,"score":0.2978000044822693},{"id":"https://openalex.org/C185429906","wikidata":"https://www.wikidata.org/wiki/Q1130160","display_name":"Estimator","level":2,"score":0.2806999981403351},{"id":"https://openalex.org/C127705205","wikidata":"https://www.wikidata.org/wiki/Q5748245","display_name":"Heuristics","level":2,"score":0.27079999446868896},{"id":"https://openalex.org/C2780598303","wikidata":"https://www.wikidata.org/wiki/Q65921492","display_name":"Flexibility (engineering)","level":2,"score":0.2621999979019165},{"id":"https://openalex.org/C115901376","wikidata":"https://www.wikidata.org/wiki/Q184199","display_name":"Automation","level":2,"score":0.2581000030040741},{"id":"https://openalex.org/C132459708","wikidata":"https://www.wikidata.org/wiki/Q744069","display_name":"Extrapolation","level":2,"score":0.25600001215934753},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.25589999556541443},{"id":"https://openalex.org/C70437156","wikidata":"https://www.wikidata.org/wiki/Q7228652","display_name":"Pooling","level":2,"score":0.25540000200271606},{"id":"https://openalex.org/C183115368","wikidata":"https://www.wikidata.org/wiki/Q856577","display_name":"Weighting","level":2,"score":0.2531999945640564}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.64898/2026.08.28.747622","doi":"https://doi.org/10.64898/2026.08.28.747622","is_oa":true,"landing_page_url":"https://doi.org/10.64898/2026.08.28.747622","pdf_url":null,"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:10.64898/2026.08.28.747622","doi":"https://doi.org/10.64898/2026.08.28.747622","is_oa":true,"landing_page_url":"https://doi.org/10.64898/2026.08.28.747622","pdf_url":null,"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":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":83,"referenced_works":["https://openalex.org/W1552434751","https://openalex.org/W1981509058","https://openalex.org/W2053154970","https://openalex.org/W2059185913","https://openalex.org/W2130850760","https://openalex.org/W2415341492","https://openalex.org/W2462007197","https://openalex.org/W2472063172","https://openalex.org/W2523369352","https://openalex.org/W2523620612","https://openalex.org/W2612519453","https://openalex.org/W2772624269","https://openalex.org/W2796170779","https://openalex.org/W2800392236","https://openalex.org/W2894687190","https://openalex.org/W2896518632","https://openalex.org/W2897346235","https://openalex.org/W2907514116","https://openalex.org/W2907783748","https://openalex.org/W2931036699","https://openalex.org/W2947877009","https://openalex.org/W2949067670","https://openalex.org/W2949177718","https://openalex.org/W2951506174","https://openalex.org/W2951914955","https://openalex.org/W2959295202","https://openalex.org/W2964643116","https://openalex.org/W2966569571","https://openalex.org/W2971653850","https://openalex.org/W2984629040","https://openalex.org/W2995410603","https://openalex.org/W2998065416","https://openalex.org/W3000145506","https://openalex.org/W3004512212","https://openalex.org/W3005233576","https://openalex.org/W3006566541","https://openalex.org/W3014185549","https://openalex.org/W3015184839","https://openalex.org/W3016020856","https://openalex.org/W3019068524","https://openalex.org/W3024842005","https://openalex.org/W3028505928","https://openalex.org/W3036137852","https://openalex.org/W3041129226","https://openalex.org/W3080570713","https://openalex.org/W3092982430","https://openalex.org/W3093900604","https://openalex.org/W3096486351","https://openalex.org/W3099810371","https://openalex.org/W3121168830","https://openalex.org/W3124814274","https://openalex.org/W3130453114","https://openalex.org/W3164692211","https://openalex.org/W3196650609","https://openalex.org/W3198123874","https://openalex.org/W3209238322","https://openalex.org/W3211479370","https://openalex.org/W4221065117","https://openalex.org/W4225743911","https://openalex.org/W4295083893","https://openalex.org/W4297243391","https://openalex.org/W4301391557","https://openalex.org/W4307432965","https://openalex.org/W4316096017","https://openalex.org/W4324045291","https://openalex.org/W4361301386","https://openalex.org/W4377029825","https://openalex.org/W4377157608","https://openalex.org/W4378838672","https://openalex.org/W4385421874","https://openalex.org/W4388292371","https://openalex.org/W4391432211","https://openalex.org/W4392167979","https://openalex.org/W4392168151","https://openalex.org/W4393153069","https://openalex.org/W4399387478","https://openalex.org/W4401441450","https://openalex.org/W4404793799","https://openalex.org/W4405328867","https://openalex.org/W4409566559","https://openalex.org/W4409727640","https://openalex.org/W4411746733","https://openalex.org/W4417088107"],"related_works":["https://openalex.org/W4205288985","https://openalex.org/W3117771127","https://openalex.org/W4401441450","https://openalex.org/W4212963356","https://openalex.org/W3024842005","https://openalex.org/W7154910252","https://openalex.org/W4417416947","https://openalex.org/W7061362767","https://openalex.org/W4307803506","https://openalex.org/W4411046667"],"abstract_inverted_index":{"Abstract":[0],"Automated":[1],"cell-type":[2,60],"annotation":[3,18,215],"is":[4],"a":[5,84,158],"prerequisite":[6],"for":[7,177,186,194,227],"nearly":[8],"all":[9],"single-cell":[10],"RNA-sequencing":[11],"(scRNA-seq)":[12],"analysis,":[13],"and":[14,32,62,95,112,119,132,144,199,204,241],"the":[15,97,121],"proliferation":[16],"of":[17,129,179],"tools":[19,79],"\u2014":[20,36],"spanning":[21],"marker-based,":[22],"similarity-based,":[23],"classical":[24],"machine-learning,":[25],"deep-learning,":[26],"semi-supervised,":[27],"large":[28],"language":[29],"model":[30],"(LLM),":[31],"transformer":[33],"foundation-model":[34],"families":[35,82,124],"has":[37],"exceeded":[38],"any":[39,73],"existing":[40],"guidance":[41],"on":[42],"how":[43,152],"to":[44,72,225],"select":[45],"among":[46,201,206],"them.":[47],"Existing":[48],"benchmarks":[49],"utilize":[50],"convenient,":[51],"well-known":[52],"datasets":[53],"in":[54,157],"which":[55],"cell":[56,154,210],"number,":[57,61],"class":[58],"imbalance,":[59],"differential-expression":[63],"strength":[64],"vary":[65],"concurrently,":[66],"so":[67],"performance":[68],"cannot":[69],"be":[70],"attributed":[71],"dataset":[74,174],"property.":[75],"We":[76,171],"benchmarked":[77],"63":[78],"from":[80],"seven":[81],"using":[83],"Taguchi":[85],"L9(3\u2074)":[86],"orthogonal":[87],"array":[88],"that":[89,173],"varied":[90],"these":[91],"four":[92],"properties":[93],"independently":[94],"extended":[96],"comparison":[98],"under":[99],"more":[100],"realistic":[101],"conditions:":[102],"real":[103],"data,":[104],"cross-platform":[105],"transfer,":[106],"public":[107],"marker":[108],"databases,":[109],"LLM":[110,207],"annotation,":[111],"fine-tuned":[113,133],"foundation":[114,134],"models.":[115],"With":[116],"standardized":[117],"preprocessing":[118],"inputs,":[120],"leading":[122],"cell-level":[123],"performed":[125],"within":[126],"0.06":[127],"\u03ba":[128,180],"one":[130],"another,":[131],"models":[135],"averaged":[136],"only":[137],"slightly":[138],"higher.":[139],"Across":[140],"families,":[141,193],"sequencing":[142],"platforms,":[143],"data":[145],"types,":[146],"accuracy":[147],"was":[148],"predicted":[149],"near-linearly":[150],"by":[151],"separable":[153],"types":[155,211],"were":[156,190],"shared":[159],"expression":[160],"embedding":[161],"space,":[162],"measured":[163],"as":[164,238],"k-nearest-neighbor":[165],"(kNN)":[166],"purity":[167],"(R\u00b2":[168],"=":[169],"0.85\u20130.99).":[170],"found":[172],"identity":[175,184],"accounted":[176,185],"\u224884%":[178],"variance":[181],"while":[182],"tool":[183],"\u22484%.":[187],"Strong":[188],"performers":[189],"distributed":[191],"across":[192],"example,":[195],"Seurat":[196],"label":[197],"transfer":[198],"singleCellNet":[200],"reference-based":[202],"classifiers":[203],"mLLMCelltype":[205],"annotators.":[208],"When":[209],"cleanly":[212],"separate,":[213],"many":[214],"methods":[216],"suffice;":[217],"when":[218],"they":[219],"do":[220],"not,":[221],"algorithmic":[222],"complexity":[223],"struggles":[224],"compensate":[226],"noisy":[228],"signal.":[229],"Method":[230],"selection":[231],"should":[232],"therefore":[233],"prioritize":[234],"available":[235],"resources,":[236],"such":[237],"curated":[239],"references":[240],"compute":[242],"availability,":[243],"over":[244],"sophisticated":[245],"modeling.":[246]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-11-09T13:22:03.289127","created_date":"2026-09-04T00:00:00"}