{"id":"https://openalex.org/W3185430726","doi":"https://doi.org/10.1109/tcbb.2021.3098394","title":"scRAE: Deterministic Regularized Autoencoders With Flexible Priors for Clustering Single-Cell Gene Expression Data","display_name":"scRAE: Deterministic Regularized Autoencoders With Flexible Priors for Clustering Single-Cell Gene Expression Data","publication_year":2021,"publication_date":"2021-07-21","ids":{"openalex":"https://openalex.org/W3185430726","doi":"https://doi.org/10.1109/tcbb.2021.3098394","mag":"3185430726","pmid":"https://pubmed.ncbi.nlm.nih.gov/34288873"},"language":"en","primary_location":{"id":"doi:10.1109/tcbb.2021.3098394","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcbb.2021.3098394","pdf_url":null,"source":{"id":"https://openalex.org/S36029991","display_name":"IEEE/ACM Transactions on Computational Biology and Bioinformatics","issn_l":"1545-5963","issn":["1545-5963","1557-9964","2374-0043"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Computational Biology and Bioinformatics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5045635774","display_name":"Arnab Kumar Mondal","orcid":"https://orcid.org/0000-0001-7297-374X"},"institutions":[{"id":"https://openalex.org/I68891433","display_name":"Indian Institute of Technology Delhi","ror":"https://ror.org/049tgcd06","country_code":"IN","type":"education","lineage":["https://openalex.org/I68891433"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Arnab Kumar Mondal","raw_affiliation_strings":["oIIT Delhi, New Delhi, India"],"raw_orcid":"https://orcid.org/0000-0001-7297-374X","affiliations":[{"raw_affiliation_string":"oIIT Delhi, New Delhi, India","institution_ids":["https://openalex.org/I68891433"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019098931","display_name":"Himanshu Asnani","orcid":null},"institutions":[{"id":"https://openalex.org/I11947397","display_name":"Tata Institute of Fundamental Research","ror":"https://ror.org/03ht1xw27","country_code":"IN","type":"education","lineage":["https://openalex.org/I11947397","https://openalex.org/I2799351866","https://openalex.org/I3149292468"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Himanshu Asnani","raw_affiliation_strings":["TIFR, Mumbai, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"TIFR, Mumbai, India","institution_ids":["https://openalex.org/I11947397"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103677687","display_name":"Parag Singla","orcid":"https://orcid.org/0009-0000-9190-9794"},"institutions":[{"id":"https://openalex.org/I68891433","display_name":"Indian Institute of Technology Delhi","ror":"https://ror.org/049tgcd06","country_code":"IN","type":"education","lineage":["https://openalex.org/I68891433"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Parag Singla","raw_affiliation_strings":["oIIT Delhi, New Delhi, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"oIIT Delhi, New Delhi, India","institution_ids":["https://openalex.org/I68891433"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5074080229","display_name":"Prathosh AP","orcid":"https://orcid.org/0000-0002-8699-5760"},"institutions":[{"id":"https://openalex.org/I68891433","display_name":"Indian Institute of Technology Delhi","ror":"https://ror.org/049tgcd06","country_code":"IN","type":"education","lineage":["https://openalex.org/I68891433"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Prathosh AP","raw_affiliation_strings":["oIIT Delhi, New Delhi, India"],"raw_orcid":"https://orcid.org/0000-0002-8699-5760","affiliations":[{"raw_affiliation_string":"oIIT Delhi, New Delhi, India","institution_ids":["https://openalex.org/I68891433"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.3172,"has_fulltext":false,"cited_by_count":10,"citation_normalized_percentile":{"value":0.55071335,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":97,"max":98},"biblio":{"volume":"19","issue":"5","first_page":"2996","last_page":"3007"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11289","display_name":"Single-cell and spatial transcriptomics","score":0.9998000264167786,"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":0.9998000264167786,"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/T10515","display_name":"Cancer-related molecular mechanisms research","score":0.9940000176429749,"subfield":{"id":"https://openalex.org/subfields/1306","display_name":"Cancer Research"},"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/T10062","display_name":"MicroRNA in disease regulation","score":0.987500011920929,"subfield":{"id":"https://openalex.org/subfields/1306","display_name":"Cancer Research"},"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/cluster-analysis","display_name":"Cluster analysis","score":0.7409117221832275},{"id":"https://openalex.org/keywords/regularization","display_name":"Regularization (linguistics)","score":0.6959823369979858},{"id":"https://openalex.org/keywords/curse-of-dimensionality","display_name":"Curse of dimensionality","score":0.6270285844802856},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6225352883338928},{"id":"https://openalex.org/keywords/prior-probability","display_name":"Prior probability","score":0.50809645652771},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.49811649322509766},{"id":"https://openalex.org/keywords/clustering-high-dimensional-data","display_name":"Clustering high-dimensional data","score":0.49651390314102173},{"id":"https://openalex.org/keywords/autoencoder","display_name":"Autoencoder","score":0.49436473846435547},{"id":"https://openalex.org/keywords/latent-variable","display_name":"Latent variable","score":0.43693453073501587},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4211500287055969},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3877996802330017},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.3616916537284851},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.35866275429725647},{"id":"https://openalex.org/keywords/bayesian-probability","display_name":"Bayesian probability","score":0.12581342458724976}],"concepts":[{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.7409117221832275},{"id":"https://openalex.org/C2776135515","wikidata":"https://www.wikidata.org/wiki/Q17143721","display_name":"Regularization (linguistics)","level":2,"score":0.6959823369979858},{"id":"https://openalex.org/C111030470","wikidata":"https://www.wikidata.org/wiki/Q1430460","display_name":"Curse of dimensionality","level":2,"score":0.6270285844802856},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6225352883338928},{"id":"https://openalex.org/C177769412","wikidata":"https://www.wikidata.org/wiki/Q278090","display_name":"Prior probability","level":3,"score":0.50809645652771},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.49811649322509766},{"id":"https://openalex.org/C184509293","wikidata":"https://www.wikidata.org/wiki/Q5136711","display_name":"Clustering high-dimensional data","level":3,"score":0.49651390314102173},{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.49436473846435547},{"id":"https://openalex.org/C51167844","wikidata":"https://www.wikidata.org/wiki/Q4422623","display_name":"Latent variable","level":2,"score":0.43693453073501587},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4211500287055969},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3877996802330017},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.3616916537284851},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.35866275429725647},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.12581342458724976}],"mesh":[{"descriptor_ui":"D015870","descriptor_name":"Gene Expression","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D015870","descriptor_name":"Gene Expression","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D015870","descriptor_name":"Gene Expression","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016000","descriptor_name":"Cluster Analysis","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016000","descriptor_name":"Cluster Analysis","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016000","descriptor_name":"Cluster Analysis","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D017423","descriptor_name":"Sequence Analysis, RNA","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D017423","descriptor_name":"Sequence Analysis, RNA","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D017423","descriptor_name":"Sequence Analysis, RNA","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D020869","descriptor_name":"Gene Expression Profiling","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D020869","descriptor_name":"Gene Expression Profiling","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D020869","descriptor_name":"Gene Expression Profiling","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D059010","descriptor_name":"Single-Cell Analysis","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D059010","descriptor_name":"Single-Cell Analysis","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D059010","descriptor_name":"Single-Cell Analysis","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true}],"locations_count":2,"locations":[{"id":"doi:10.1109/tcbb.2021.3098394","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcbb.2021.3098394","pdf_url":null,"source":{"id":"https://openalex.org/S36029991","display_name":"IEEE/ACM Transactions on Computational Biology and Bioinformatics","issn_l":"1545-5963","issn":["1545-5963","1557-9964","2374-0043"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Computational Biology and Bioinformatics","raw_type":"journal-article"},{"id":"pmid:34288873","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/34288873","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":"IEEE/ACM transactions on computational biology and bioinformatics","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.44999998807907104,"id":"https://metadata.un.org/sdg/17","display_name":"Partnerships for the goals"}],"awards":[{"id":"https://openalex.org/G6491371590","display_name":null,"funder_award_id":"N66001-17-2-4032","funder_id":"https://openalex.org/F4320332180","funder_display_name":"Defense Advanced Research Projects Agency"}],"funders":[{"id":"https://openalex.org/F4320332180","display_name":"Defense Advanced Research Projects Agency","ror":"https://ror.org/02caytj08"},{"id":"https://openalex.org/F7525545622","display_name":"Adobe Research","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":58,"referenced_works":["https://openalex.org/W1959608418","https://openalex.org/W1967327758","https://openalex.org/W1979283544","https://openalex.org/W1984984201","https://openalex.org/W2032518018","https://openalex.org/W2060245619","https://openalex.org/W2069089843","https://openalex.org/W2076774151","https://openalex.org/W2100495367","https://openalex.org/W2102212449","https://openalex.org/W2135937351","https://openalex.org/W2162833336","https://openalex.org/W2368109179","https://openalex.org/W2523369352","https://openalex.org/W2523620612","https://openalex.org/W2598326928","https://openalex.org/W2735067671","https://openalex.org/W2741943936","https://openalex.org/W2747545374","https://openalex.org/W2788348358","https://openalex.org/W2794083495","https://openalex.org/W2800392236","https://openalex.org/W2889326414","https://openalex.org/W2901677030","https://openalex.org/W2906625258","https://openalex.org/W2937917790","https://openalex.org/W2949329924","https://openalex.org/W2951381561","https://openalex.org/W2951506174","https://openalex.org/W2952303649","https://openalex.org/W2952650776","https://openalex.org/W2953251392","https://openalex.org/W2977253392","https://openalex.org/W2978541146","https://openalex.org/W2982357115","https://openalex.org/W2989807288","https://openalex.org/W2997470228","https://openalex.org/W3007103623","https://openalex.org/W3011464861","https://openalex.org/W3024013192","https://openalex.org/W3029148360","https://openalex.org/W3091988478","https://openalex.org/W3127011314","https://openalex.org/W3137285774","https://openalex.org/W3138479716","https://openalex.org/W3163972593","https://openalex.org/W4251194840","https://openalex.org/W4298082496","https://openalex.org/W6638484148","https://openalex.org/W6640963894","https://openalex.org/W6684050148","https://openalex.org/W6685380521","https://openalex.org/W6735913928","https://openalex.org/W6741832134","https://openalex.org/W6745535286","https://openalex.org/W6777596526","https://openalex.org/W6780248173","https://openalex.org/W6798444936"],"related_works":["https://openalex.org/W2159052453","https://openalex.org/W3013693939","https://openalex.org/W2566616303","https://openalex.org/W3131327266","https://openalex.org/W2752972570","https://openalex.org/W4297051394","https://openalex.org/W2988134182","https://openalex.org/W3168675052","https://openalex.org/W4378768646","https://openalex.org/W1988922486"],"abstract_inverted_index":{"Clustering":[0],"single-cell":[1,136,188],"RNA":[2,137],"sequence":[3],"(scRNA-seq)":[4],"data":[5,54,104],"poses":[6],"statistical":[7],"and":[8,15,61,113,168],"computational":[9],"challenges":[10],"due":[11],"to":[12,46,56,111,162],"their":[13,92],"high-dimensionality":[14],"data-sparsity,":[16],"also":[17],"known":[18],"as":[19],"'dropout'":[20],"events.":[21],"Recently,":[22],"Regularized":[23],"Auto-Encoder":[24],"(RAE)":[25],"based":[26],"deep":[27],"neural":[28],"network":[29],"models":[30],"have":[31],"achieved":[32],"remarkable":[33],"success":[34],"in":[35,43,74,91,103,170],"learning":[36],"robust":[37],"low-dimensional":[38,58],"representations.":[39],"The":[40,192],"basic":[41],"idea":[42],"RAEs":[44,82],"is":[45,153,197],"learn":[47],"a":[48,57,65,75,96,106,124,146],"non-linear":[49],"mapping":[50],"from":[51,84],"the":[52,69,85,119,129,135,157,166,171,176,179],"high-dimensional":[53],"space":[55,60],"latent":[59,70,100,172],"vice-versa,":[62],"simultaneously":[63],"imposing":[64],"distributional":[66],"prior":[67,109,149],"on":[68,185],"space,":[71],"which":[72,152],"brings":[73],"regularization":[76,101],"effect.":[77],"This":[78,159],"paper":[79],"argues":[80],"that":[81],"suffer":[83],"infamous":[86],"problem":[87],"of":[88,134,142,178],"bias-variance":[89],"trade-off":[90,163],"naive":[93],"formulation.":[94],"While":[95],"simple":[97],"AE":[98,144],"wita":[99],"results":[102],"over-fitting,":[105],"very":[107],"strong":[108],"leads":[110],"under-representation":[112],"thus":[114],"bad":[115],"clustering.":[116],"To":[117],"address":[118],"above":[120],"issues,":[121],"we":[122],"propose":[123],"modified":[125],"RAE":[126],"framework":[127],"(called":[128],"scRAE)":[130],"for":[131,194],"effective":[132],"clustering":[133],"sequencing":[138],"data.":[139],"scRAE":[140,161],"consists":[141],"deterministic":[143],"with":[145,156],"flexibly":[147],"learnable":[148],"generator":[150],"network,":[151],"jointly":[154],"trained":[155],"AE.":[158],"facilitates":[160],"better":[164],"between":[165],"bias":[167],"variance":[169],"space.":[173],"We":[174],"demonstrate":[175],"efficacy":[177],"proposed":[180],"method":[181],"through":[182],"extensive":[183],"experimentation":[184],"several":[186],"real-world":[187],"Gene":[189],"expression":[190],"datasets.":[191],"code":[193],"our":[195],"work":[196],"available":[198],"at":[199],"https://github.com/arnabkmondal/scRAE.":[200]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":4},{"year":2022,"cited_by_count":4}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}