{"id":"https://openalex.org/W4414717555","doi":"https://doi.org/10.1093/bioinformatics/btaf533","title":"Self-supervised representation learning on gene expression data","display_name":"Self-supervised representation learning on gene expression data","publication_year":2025,"publication_date":"2025-09-29","ids":{"openalex":"https://openalex.org/W4414717555","doi":"https://doi.org/10.1093/bioinformatics/btaf533","pmid":"https://pubmed.ncbi.nlm.nih.gov/41028963"},"language":"en","primary_location":{"id":"doi:10.1093/bioinformatics/btaf533","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btaf533","pdf_url":"https://academic.oup.com/bioinformatics/advance-article-pdf/doi/10.1093/bioinformatics/btaf533/64457398/btaf533.pdf","source":{"id":"https://openalex.org/S52395412","display_name":"Bioinformatics","issn_l":"1367-4803","issn":["1367-4803","1367-4811"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310311648","host_organization_name":"Oxford University Press","host_organization_lineage":["https://openalex.org/P4310311648","https://openalex.org/P4310311647"],"host_organization_lineage_names":["Oxford University Press","University of Oxford"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Bioinformatics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://academic.oup.com/bioinformatics/advance-article-pdf/doi/10.1093/bioinformatics/btaf533/64457398/btaf533.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5119801352","display_name":"Kevin Dradjat","orcid":null},"institutions":[{"id":"https://openalex.org/I4210107733","display_name":"Informatique, BioInformatique, Syst\u00e8mes Complexes","ror":"https://ror.org/01aqxgr98","country_code":"FR","type":"facility","lineage":["https://openalex.org/I277688954","https://openalex.org/I277688954","https://openalex.org/I4210107733","https://openalex.org/I88467170"]},{"id":"https://openalex.org/I4210142951","display_name":"Adlink (United Kingdom)","ror":"https://ror.org/04fxhkj84","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210142951"]}],"countries":["FR","GB"],"is_corresponding":true,"raw_author_name":"Kevin Dradjat","raw_affiliation_strings":["ADLIN , Evry-Courcouronnes 91000,","University Paris-Saclay (Univ. Evry) IBISC Laboratory, , Evry-Courcouronnes 91000,","ADLIN, Paris, France","IBISC Laboratory, University Paris-Saclay (Univ. Evry), France"],"raw_orcid":"https://orcid.org/0009-0009-9605-5295","affiliations":[{"raw_affiliation_string":"ADLIN , Evry-Courcouronnes 91000,","institution_ids":["https://openalex.org/I4210107733"]},{"raw_affiliation_string":"University Paris-Saclay (Univ. Evry) IBISC Laboratory, , Evry-Courcouronnes 91000,","institution_ids":["https://openalex.org/I4210107733"]},{"raw_affiliation_string":"ADLIN, Paris, France","institution_ids":["https://openalex.org/I4210142951"]},{"raw_affiliation_string":"IBISC Laboratory, University Paris-Saclay (Univ. Evry), France","institution_ids":["https://openalex.org/I4210107733"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048133789","display_name":"Massinissa Hamidi","orcid":"https://orcid.org/0000-0002-1211-3526"},"institutions":[{"id":"https://openalex.org/I4210107733","display_name":"Informatique, BioInformatique, Syst\u00e8mes Complexes","ror":"https://ror.org/01aqxgr98","country_code":"FR","type":"facility","lineage":["https://openalex.org/I277688954","https://openalex.org/I277688954","https://openalex.org/I4210107733","https://openalex.org/I88467170"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Massinissa Hamidi","raw_affiliation_strings":["University Paris-Saclay (Univ. Evry) IBISC Laboratory, , Evry-Courcouronnes 91000,","IBISC Laboratory, University Paris-Saclay (Univ. Evry), France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University Paris-Saclay (Univ. Evry) IBISC Laboratory, , Evry-Courcouronnes 91000,","institution_ids":["https://openalex.org/I4210107733"]},{"raw_affiliation_string":"IBISC Laboratory, University Paris-Saclay (Univ. Evry), France","institution_ids":["https://openalex.org/I4210107733"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5093953037","display_name":"Pierre Bartet","orcid":null},"institutions":[{"id":"https://openalex.org/I4210107733","display_name":"Informatique, BioInformatique, Syst\u00e8mes Complexes","ror":"https://ror.org/01aqxgr98","country_code":"FR","type":"facility","lineage":["https://openalex.org/I277688954","https://openalex.org/I277688954","https://openalex.org/I4210107733","https://openalex.org/I88467170"]},{"id":"https://openalex.org/I4210142951","display_name":"Adlink (United Kingdom)","ror":"https://ror.org/04fxhkj84","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210142951"]}],"countries":["FR","GB"],"is_corresponding":false,"raw_author_name":"Pierre Bartet","raw_affiliation_strings":["ADLIN , Evry-Courcouronnes 91000,","ADLIN, Paris, France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ADLIN , Evry-Courcouronnes 91000,","institution_ids":["https://openalex.org/I4210107733"]},{"raw_affiliation_string":"ADLIN, Paris, France","institution_ids":["https://openalex.org/I4210142951"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5008999121","display_name":"Blaise Hanczar","orcid":"https://orcid.org/0000-0002-5606-8296"},"institutions":[{"id":"https://openalex.org/I4210107733","display_name":"Informatique, BioInformatique, Syst\u00e8mes Complexes","ror":"https://ror.org/01aqxgr98","country_code":"FR","type":"facility","lineage":["https://openalex.org/I277688954","https://openalex.org/I277688954","https://openalex.org/I4210107733","https://openalex.org/I88467170"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Blaise Hanczar","raw_affiliation_strings":["University Paris-Saclay (Univ. Evry) IBISC Laboratory, , Evry-Courcouronnes 91000,","IBISC Laboratory, University Paris-Saclay (Univ. Evry), France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University Paris-Saclay (Univ. Evry) IBISC Laboratory, , Evry-Courcouronnes 91000,","institution_ids":["https://openalex.org/I4210107733"]},{"raw_affiliation_string":"IBISC Laboratory, University Paris-Saclay (Univ. Evry), France","institution_ids":["https://openalex.org/I4210107733"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5119801352"],"corresponding_institution_ids":["https://openalex.org/I4210107733","https://openalex.org/I4210142951"],"apc_list":{"value":3989,"currency":"USD","value_usd":3989},"apc_paid":{"value":3989,"currency":"USD","value_usd":3989},"fwci":0.3866,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.61921487,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":"41","issue":"11","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10885","display_name":"Gene expression and cancer classification","score":0.7724000215530396,"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/T10885","display_name":"Gene expression and cancer classification","score":0.7724000215530396,"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/T12254","display_name":"Machine Learning in Bioinformatics","score":0.09080000221729279,"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/T11289","display_name":"Single-cell and spatial transcriptomics","score":0.02710000053048134,"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/representation","display_name":"Representation (politics)","score":0.569100022315979},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.5045999884605408},{"id":"https://openalex.org/keywords/expression","display_name":"Expression (computer science)","score":0.4442000091075897},{"id":"https://openalex.org/keywords/external-data-representation","display_name":"External Data Representation","score":0.4106999933719635},{"id":"https://openalex.org/keywords/gene-expression","display_name":"Gene expression","score":0.390500009059906},{"id":"https://openalex.org/keywords/source-code","display_name":"Source code","score":0.38670000433921814}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7450000047683716},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6409000158309937},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.569100022315979},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.5045999884605408},{"id":"https://openalex.org/C90559484","wikidata":"https://www.wikidata.org/wiki/Q778379","display_name":"Expression (computer science)","level":2,"score":0.4442000091075897},{"id":"https://openalex.org/C116409475","wikidata":"https://www.wikidata.org/wiki/Q1385056","display_name":"External Data Representation","level":2,"score":0.4106999933719635},{"id":"https://openalex.org/C150194340","wikidata":"https://www.wikidata.org/wiki/Q26972","display_name":"Gene expression","level":3,"score":0.390500009059906},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.38670000433921814},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.38100001215934753},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3589000105857849},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.3310000002384186},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.326200008392334},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3107999861240387},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.25940001010894775}],"mesh":[{"descriptor_ui":"D000069550","descriptor_name":"Machine Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000069550","descriptor_name":"Machine Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000069553","descriptor_name":"Supervised Machine Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000069553","descriptor_name":"Supervised Machine Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D010641","descriptor_name":"Phenotype","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D010641","descriptor_name":"Phenotype","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":true},{"descriptor_ui":"D015870","descriptor_name":"Gene Expression","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","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":"D030541","descriptor_name":"Databases, Genetic","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D030541","descriptor_name":"Databases, Genetic","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false}],"locations_count":4,"locations":[{"id":"doi:10.1093/bioinformatics/btaf533","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btaf533","pdf_url":"https://academic.oup.com/bioinformatics/advance-article-pdf/doi/10.1093/bioinformatics/btaf533/64457398/btaf533.pdf","source":{"id":"https://openalex.org/S52395412","display_name":"Bioinformatics","issn_l":"1367-4803","issn":["1367-4803","1367-4811"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310311648","host_organization_name":"Oxford University Press","host_organization_lineage":["https://openalex.org/P4310311648","https://openalex.org/P4310311647"],"host_organization_lineage_names":["Oxford University Press","University of Oxford"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Bioinformatics","raw_type":"journal-article"},{"id":"pmid:41028963","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/41028963","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":"Bioinformatics (Oxford, England)","raw_type":"Journal Article"},{"id":"pmh:oai:europepmc.org:11416079","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/12611300","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:HAL:hal-05297165v1","is_oa":false,"landing_page_url":"https://univ-evry.hal.science/hal-05297165","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Bioinformatics, 2025, 41 (11), pp.btaf533. ⟨10.1093/bioinformatics/btaf533⟩","raw_type":"info:eu-repo/semantics/article"}],"best_oa_location":{"id":"doi:10.1093/bioinformatics/btaf533","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btaf533","pdf_url":"https://academic.oup.com/bioinformatics/advance-article-pdf/doi/10.1093/bioinformatics/btaf533/64457398/btaf533.pdf","source":{"id":"https://openalex.org/S52395412","display_name":"Bioinformatics","issn_l":"1367-4803","issn":["1367-4803","1367-4811"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310311648","host_organization_name":"Oxford University Press","host_organization_lineage":["https://openalex.org/P4310311648","https://openalex.org/P4310311647"],"host_organization_lineage_names":["Oxford University Press","University of Oxford"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Bioinformatics","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4414717555.pdf","grobid_xml":"https://content.openalex.org/works/W4414717555.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"MOTIVATION:":[0],"Predicting":[1],"phenotypes":[2],"from":[3,72],"gene":[4,52,93,138,229],"expression":[5,53,94,139,230],"data":[6,40,95,119,231,244],"is":[7,235],"a":[8,61,183],"crucial":[9],"task":[10],"in":[11,48,225],"biomedical":[12],"research,":[13],"enabling":[14],"insights":[15],"into":[16],"disease":[17],"mechanisms,":[18],"drug":[19],"responses,":[20],"and":[21,27,44,120,152,196,245,253],"personalized":[22],"medicine.":[23],"Traditional":[24],"machine":[25],"learning":[26,29,56,89,163,224],"deep":[28],"rely":[30],"on":[31,105,178,207],"supervised":[32,168],"learning,":[33],"which":[34,125],"requires":[35],"large":[36],"quantities":[37],"of":[38,51,75,86,117,186,189,222,228],"labeled":[39],"that":[41,161,239],"are":[42,255],"costly":[43],"time-consuming":[45],"to":[46,64,91,108,112,121,218],"obtain":[47],"the":[49,73,84,114,118,144,176,187,208,220,226,236],"case":[50,209],"data.":[54,77,180],"Self-supervised":[55],"has":[57],"recently":[58],"emerged":[59],"as":[60],"promising":[62],"approach":[63],"overcome":[65],"these":[66,204],"limitations":[67],"by":[68,174,192],"extracting":[69],"information":[70,151],"directly":[71],"structure":[74,116],"unlabeled":[76],"RESULTS:":[78],"In":[79],"this":[80],"study,":[81],"we":[82,141,213],"investigate":[83],"application":[85,221],"state-of-the-art":[87],"self-supervised":[88,102,162,223,246],"methods":[90,146,164,205],"bulk":[92,242],"for":[96,129,202],"phenotype":[97,154],"prediction.":[98],"We":[99,181,198],"selected":[100,145],"three":[101],"methods,":[103],"based":[104],"different":[106],"approaches,":[107],"assess":[109],"their":[110,194],"ability":[111],"exploit":[113],"inherent":[115],"generate":[122],"qualitative":[123],"representations":[124],"can":[126,147,165],"be":[127],"used":[128],"downstream":[130],"predictive":[131],"tasks.":[132],"By":[133],"using":[134,203],"several":[135],"publicly":[136],"available":[137,256],"datasets,":[140],"demonstrate":[142],"how":[143],"effectively":[148],"capture":[149],"complex":[150],"improve":[153],"prediction":[155],"accuracy.":[156],"The":[157,251],"results":[158,254],"obtained":[159],"show":[160],"outperform":[166],"traditional":[167],"models":[169],"besides":[170],"offering":[171],"significant":[172],"advantage":[173],"reducing":[175],"dependency":[177],"annotated":[179],"provide":[182,200],"comprehensive":[184],"analysis":[185],"performance":[188],"each":[190],"method":[191],"highlighting":[193],"strengths":[195],"limitations.":[197],"also":[199],"recommendations":[201],"depending":[206],"under":[210],"study.":[211],"Finally,":[212],"outline":[214],"future":[215],"research":[216],"directions":[217],"enhance":[219],"field":[227],"analysis.":[232],"This":[233],"study":[234],"first":[237],"work":[238],"deals":[240],"with":[241],"RNA-Seq":[243],"learning.":[247],"AVAILABILITY":[248],"AND":[249],"IMPLEMENTATION:":[250],"code":[252],"at":[257],"https://github.com/kdradjat/ssrl-rnaseq.":[258]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-08-21T09:56:20.448147","created_date":"2025-10-10T00:00:00"}