{"id":"https://openalex.org/W7225114472","doi":"https://doi.org/10.21203/rs.3.rs-11542814/v1","title":"Knowledge or sparsity? Gene set masks in a single-cell VAE","display_name":"Knowledge or sparsity? Gene set masks in a single-cell VAE","publication_year":2026,"publication_date":"2026-11-02","ids":{"openalex":"https://openalex.org/W7225114472","doi":"https://doi.org/10.21203/rs.3.rs-11542814/v1"},"language":"en","primary_location":{"id":"doi:10.21203/rs.3.rs-11542814/v1","doi":"https://doi.org/10.21203/rs.3.rs-11542814/v1","is_oa":true,"landing_page_url":"https://doi.org/10.21203/rs.3.rs-11542814/v1","pdf_url":"https://www.researchsquare.com/article/rs-11542814/latest.pdf","source":{"id":"https://openalex.org/S4306525896","display_name":"Research Square","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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":"Research Square","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.researchsquare.com/article/rs-11542814/latest.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5159263535","display_name":"George Miliarakis","orcid":"https://orcid.org/0009-0009-3325-8386","observed_orcids":["https://orcid.org/0009-0009-3325-8386"]},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"George Miliarakis","raw_affiliation_strings":["Independent Researcher"],"raw_orcid":"https://orcid.org/0009-0009-3325-8386","affiliations":[{"raw_affiliation_string":"Independent Researcher","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":["https://openalex.org/A5159263535"],"corresponding_institution_ids":[],"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":0.9872999787330627,"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":0.9872999787330627,"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/T10887","display_name":"Bioinformatics and Genomic Networks","score":0.006099999882280827,"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/T10621","display_name":"Gene Regulatory Network Analysis","score":0.0026000000070780516,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/variational-autoencoder","display_name":"variational autoencoder","score":0.7689999938011169},{"id":"https://openalex.org/keywords/single-cell-transcriptomics","display_name":"single-cell transcriptomics","score":0.8579999804496765},{"id":"https://openalex.org/keywords/sparsity","display_name":"sparsity","score":0.5830000042915344},{"id":"https://openalex.org/keywords/hallmark-gene-sets","display_name":"Hallmark gene sets","score":0.9490000009536743},{"id":"https://openalex.org/keywords/lupus","display_name":"lupus","score":0.8859999775886536},{"id":"https://openalex.org/keywords/peripheral-blood-mononuclear-cells","display_name":"peripheral blood mononuclear cells","score":0.9940000176429749},{"id":"https://openalex.org/keywords/pathway-activity","display_name":"pathway activity","score":0.42399999499320984}],"concepts":[{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.6816999912261963},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5703999996185303},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5328999757766724},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5174999833106995},{"id":"https://openalex.org/C117220453","wikidata":"https://www.wikidata.org/wiki/Q5172842","display_name":"Correlation","level":2,"score":0.47279998660087585},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.4602000117301941},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.45750001072883606},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.3578000068664551},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.3562000095844269},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.34860000014305115},{"id":"https://openalex.org/C150194340","wikidata":"https://www.wikidata.org/wiki/Q26972","display_name":"Gene expression","level":3,"score":0.32190001010894775},{"id":"https://openalex.org/C152565575","wikidata":"https://www.wikidata.org/wiki/Q1124538","display_name":"Conditional random field","level":2,"score":0.31859999895095825},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.30559998750686646},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.29190000891685486},{"id":"https://openalex.org/C55078378","wikidata":"https://www.wikidata.org/wiki/Q1136628","display_name":"Pearson product-moment correlation coefficient","level":2,"score":0.28450000286102295},{"id":"https://openalex.org/C2776291640","wikidata":"https://www.wikidata.org/wiki/Q2912517","display_name":"Value (mathematics)","level":2,"score":0.28119999170303345},{"id":"https://openalex.org/C58489278","wikidata":"https://www.wikidata.org/wiki/Q1172284","display_name":"Data set","level":2,"score":0.2678000032901764},{"id":"https://openalex.org/C2776912625","wikidata":"https://www.wikidata.org/wiki/Q1485","display_name":"Systemic lupus erythematosus","level":3,"score":0.2662999927997589},{"id":"https://openalex.org/C169903167","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Test set","level":2,"score":0.26409998536109924},{"id":"https://openalex.org/C163175372","wikidata":"https://www.wikidata.org/wiki/Q3339222","display_name":"Linear model","level":2,"score":0.25619998574256897}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21203/rs.3.rs-11542814/v1","doi":"https://doi.org/10.21203/rs.3.rs-11542814/v1","is_oa":true,"landing_page_url":"https://doi.org/10.21203/rs.3.rs-11542814/v1","pdf_url":"https://www.researchsquare.com/article/rs-11542814/latest.pdf","source":{"id":"https://openalex.org/S4306525896","display_name":"Research Square","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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":"Research Square","raw_type":"posted-content"}],"best_oa_location":{"id":"doi:10.21203/rs.3.rs-11542814/v1","doi":"https://doi.org/10.21203/rs.3.rs-11542814/v1","is_oa":true,"landing_page_url":"https://doi.org/10.21203/rs.3.rs-11542814/v1","pdf_url":"https://www.researchsquare.com/article/rs-11542814/latest.pdf","source":{"id":"https://openalex.org/S4306525896","display_name":"Research Square","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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":"Research Square","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/W7225114472.pdf","grobid_xml":"https://content.openalex.org/works/W7225114472.grobid-xml"},"referenced_works_count":55,"referenced_works":["https://openalex.org/W1959608418","https://openalex.org/W1965555277","https://openalex.org/W2000177767","https://openalex.org/W2003367638","https://openalex.org/W2011301426","https://openalex.org/W2061554433","https://openalex.org/W2078483536","https://openalex.org/W2130410032","https://openalex.org/W2133402546","https://openalex.org/W2148347826","https://openalex.org/W2149023664","https://openalex.org/W2157825442","https://openalex.org/W2214074259","https://openalex.org/W2295124130","https://openalex.org/W2342249984","https://openalex.org/W2399306074","https://openalex.org/W2767792097","https://openalex.org/W2774307122","https://openalex.org/W2800392236","https://openalex.org/W2883007291","https://openalex.org/W2901677030","https://openalex.org/W2912272542","https://openalex.org/W2949237386","https://openalex.org/W2954825129","https://openalex.org/W2964121744","https://openalex.org/W2970971581","https://openalex.org/W3000145506","https://openalex.org/W3003257820","https://openalex.org/W3012280517","https://openalex.org/W3035965352","https://openalex.org/W3047163763","https://openalex.org/W3127177949","https://openalex.org/W3204708585","https://openalex.org/W4214708334","https://openalex.org/W4252684946","https://openalex.org/W4306353191","https://openalex.org/W4318981406","https://openalex.org/W4362521490","https://openalex.org/W4363673883","https://openalex.org/W4386923889","https://openalex.org/W4387362936","https://openalex.org/W4388539829","https://openalex.org/W4389134031","https://openalex.org/W4402902773","https://openalex.org/W4408446720","https://openalex.org/W4411130818","https://openalex.org/W4412929241","https://openalex.org/W4415887674","https://openalex.org/W4417414129","https://openalex.org/W7141164538","https://openalex.org/W7154499116","https://openalex.org/W7155392601","https://openalex.org/W7159833008","https://openalex.org/W7197027666","https://openalex.org/W7202270001"],"related_works":["https://openalex.org/W3111593274","https://openalex.org/W3024013192","https://openalex.org/W4308826408","https://openalex.org/W7165193441","https://openalex.org/W3204708585","https://openalex.org/W4412392864","https://openalex.org/W3127177949","https://openalex.org/W4416912160","https://openalex.org/W2903466834","https://openalex.org/W7127617180"],"abstract_inverted_index":{"Abstract":[0],"Background.":[1],"Some":[2],"knowledge-guided":[3],"single-cell":[4,61],"models":[5,62],"assign":[6,369],"gene":[7,51,111,115,212,293,328,345],"sets":[8,112,237,294,305,354,368],"to":[9,158,167,200],"latent":[10,371],"variables;":[11],"each":[12,370],"value":[13],"then":[14],"reports":[15],"the":[16,33,43,47,50,105,108,119,130,146,149,170,175,197,201,216,223,235,239,258,261,266,277,288,292,303,307,317,321,327,338,341,344,349,358,363,366],"activity":[17],"of":[18,28,36,185,257,282,316,333,343,357],"a":[19,64,73,78,182,272,373],"known":[20],"pathway.":[21],"Earlier":[22],"work":[23],"shows":[24],"that":[25],"randomized":[26],"versions":[27],"supervised":[29],"pathway-informed":[30],"networks,":[31],"with":[32,77,91,129,155,177,181,226,231,326],"same":[34,131,318],"share":[35],"zero":[37],"weights,":[38],"can":[39],"match":[40],"or":[41,53,93,103,113],"outperform":[42],"curated":[44,353,367],"ones.":[45],"Whether":[46],"knowledge":[48],"in":[49,118,151,204,218,280,295,337],"sets,":[52],"only":[54],"their":[55],"sparsity,":[56],"explains":[57],"how":[58,144],"well":[59,145],"unsupervised":[60],"capture":[63,159],"cell\u2019s":[65],"response":[66,322],"is":[67],"not":[68],"known.":[69],"Methods.":[70],"We":[71,173],"trained":[72],"variational":[74],"autoencoder":[75],"(VAE)":[76],"linear":[79],"decoder":[80,98,147],"on":[81,139,143,153,238,306,324],"peripheral":[82],"blood":[83],"mononuclear":[84],"cells":[85,187],"from":[86,190],"eight":[87,283],"lupus":[88,240,308],"patients,":[89],"stimulated":[90],"interferon-\u03b2":[92],"left":[94],"as":[95,134],"controls.":[96],"The":[97,352],"was":[99],"either":[100],"unrestricted":[101],"(vanilla)":[102],"masked;":[104],"masks":[106,128,214,225,279,315],"were":[107,137],"50":[109],"Hallmark":[110,236,304],"co-expressed":[114,334],"groups":[116,286,332],"found":[117,336],"data.":[120,309],"Fully":[121],"random,":[122],"within-set":[123],"random":[124,127,224,263,278,314,350],"and":[125,142,164,180,229,250,265,299],"expression-matched":[126],"sparsity":[132,319],"served":[133],"references.":[135],"Variants":[136],"scored":[138],"held-out":[140],"reconstruction":[141],"reproduces":[148],"shift":[150,217,289],"expression":[152,219],"stimulation,":[154],"Spearman\u2019s":[156],"rho":[157],"all":[160,205,209,296],"genes":[161,335],"without":[162],"discrimination":[163],"Pearson\u2019s":[165],"r":[166],"account":[168],"for":[169],"strongest":[171],"responders.":[172],"repeated":[174],"comparison":[176],"Reactome":[178],"pathways":[179],"second":[183],"dataset":[184],"interferon-\u03b2-stimulated":[186],"(four":[188],"benchmarks":[189,298],"two":[191],"datasets).":[192],"Results.":[193],"Every":[194],"mask":[195,264,347],"worsened":[196],"fit":[198,359],"relative":[199],"vanilla":[202,267],"model":[203],"tested":[206],"seeds.":[207],"In":[208,311],"four":[210,297],"benchmarks,":[211],"set":[213,329,346],"reproduced":[215,287],"slightly":[220],"better":[221,230,290,301],"than":[222,276,291,302],"Spearman":[227],"correlation":[228],"Pearson":[232],"correlation.":[233],"With":[234],"data,":[241,313],"they":[242],"recovered":[243],"10%":[244],"(Spearman,":[245],"95%":[246,253],"CI":[247,254],"[8,":[248],"11])":[249],"56%":[251],"(Pearson,":[252],"[49,":[255],"62])":[256],"gap":[259],"between":[260],"fully":[262],"model.":[268],"They":[269],"also":[270],"reached":[271],"lower":[273],"test":[274],"loss":[275],"seven":[281],"comparisons.":[284],"Co-expressed":[285],"fitted":[300],"Conclusion.":[310],"these":[312],"decode":[320],"almost":[323],"par":[325],"mask.":[330],"Uncurated":[331],"data":[339],"exceed":[340],"gain":[342],"over":[348],"masks.":[351],"offset":[355],"part":[356],"lost":[360],"by":[361],"restricting":[362],"decoder.":[364],"Only":[365],"variable":[372],"biological":[374],"name":[375],"chosen":[376],"before":[377],"training.":[378]},"counts_by_year":[],"updated_date":"2026-11-04T10:54:05.112534","created_date":"2026-11-03T00:00:00"}