{"id":"https://openalex.org/W7221099587","doi":"https://doi.org/10.64898/2026.10.02.756166","title":"Exploring noise in TCR specificity data through supervised learning","display_name":"Exploring noise in TCR specificity data through supervised learning","publication_year":2026,"publication_date":"2026-10-08","ids":{"openalex":"https://openalex.org/W7221099587","doi":"https://doi.org/10.64898/2026.10.02.756166"},"language":"en","primary_location":{"id":"doi:10.64898/2026.10.02.756166","doi":"https://doi.org/10.64898/2026.10.02.756166","is_oa":true,"landing_page_url":"https://doi.org/10.64898/2026.10.02.756166","pdf_url":"https://www.biorxiv.org/content/biorxiv/early/2026/10/08/2026.10.02.756166.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":"public-domain","license_id":"https://openalex.org/licenses/public-domain","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/2026/10/08/2026.10.02.756166.full.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5020934852","display_name":"Sebastian Nymann Deleuran","orcid":"https://orcid.org/0000-0001-5458-0889","observed_orcids":["https://orcid.org/0000-0001-5458-0889"]},"institutions":[{"id":"https://openalex.org/I96673099","display_name":"Technical University of Denmark","ror":"https://ror.org/04qtj9h94","country_code":"DK","type":"education","lineage":["https://openalex.org/I96673099"]}],"countries":["DK"],"is_corresponding":false,"raw_author_name":"Sebastian Nymann Deleuran","raw_affiliation_strings":["Department of Health Technology, Technical University of Denmark, DK-2800 Lyngby, Denmark"],"raw_orcid":"https://orcid.org/0000-0001-5458-0889","affiliations":[{"raw_affiliation_string":"Department of Health Technology, Technical University of Denmark, DK-2800 Lyngby, Denmark","institution_ids":["https://openalex.org/I96673099"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017344301","display_name":"Yogesh Basavaraju","orcid":"https://orcid.org/0000-0001-7742-9428","observed_orcids":["https://orcid.org/0000-0001-7742-9428"]},"institutions":[{"id":"https://openalex.org/I96673099","display_name":"Technical University of Denmark","ror":"https://ror.org/04qtj9h94","country_code":"DK","type":"education","lineage":["https://openalex.org/I96673099"]}],"countries":["DK"],"is_corresponding":false,"raw_author_name":"Yogesh Basavaraju","raw_affiliation_strings":["Department of Health Technology, Technical University of Denmark, DK-2800 Lyngby, Denmark"],"raw_orcid":"https://orcid.org/0000-0001-7742-9428","affiliations":[{"raw_affiliation_string":"Department of Health Technology, Technical University of Denmark, DK-2800 Lyngby, Denmark","institution_ids":["https://openalex.org/I96673099"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074865087","display_name":"Ruta Matuleviciute","orcid":"https://orcid.org/0000-0002-8856-792X","observed_orcids":["https://orcid.org/0000-0002-8856-792X"]},"institutions":[{"id":"https://openalex.org/I96673099","display_name":"Technical University of Denmark","ror":"https://ror.org/04qtj9h94","country_code":"DK","type":"education","lineage":["https://openalex.org/I96673099"]}],"countries":["DK"],"is_corresponding":false,"raw_author_name":"R\u016bta Matulevi\u010di\u016bt\u0117","raw_affiliation_strings":["Department of Health Technology, Technical University of Denmark, DK-2800 Lyngby, Denmark"],"raw_orcid":"https://orcid.org/0000-0002-8856-792X","affiliations":[{"raw_affiliation_string":"Department of Health Technology, Technical University of Denmark, DK-2800 Lyngby, Denmark","institution_ids":["https://openalex.org/I96673099"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071574286","display_name":"Kristoffer Haurum Johansen","orcid":"https://orcid.org/0000-0002-7711-9451","observed_orcids":["https://orcid.org/0000-0002-7711-9451"]},"institutions":[{"id":"https://openalex.org/I96673099","display_name":"Technical University of Denmark","ror":"https://ror.org/04qtj9h94","country_code":"DK","type":"education","lineage":["https://openalex.org/I96673099"]}],"countries":["DK"],"is_corresponding":false,"raw_author_name":"Kristoffer Haurum Johansen","raw_affiliation_strings":["Department of Health Technology, Technical University of Denmark, DK-2800 Lyngby, Denmark"],"raw_orcid":"https://orcid.org/0000-0002-7711-9451","affiliations":[{"raw_affiliation_string":"Department of Health Technology, Technical University of Denmark, DK-2800 Lyngby, Denmark","institution_ids":["https://openalex.org/I96673099"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033440492","display_name":"Sine Reker Hadrup","orcid":"https://orcid.org/0000-0002-5937-4344","observed_orcids":["https://orcid.org/0000-0002-5937-4344"]},"institutions":[{"id":"https://openalex.org/I96673099","display_name":"Technical University of Denmark","ror":"https://ror.org/04qtj9h94","country_code":"DK","type":"education","lineage":["https://openalex.org/I96673099"]}],"countries":["DK"],"is_corresponding":false,"raw_author_name":"Sine Reker Hadrup","raw_affiliation_strings":["Department of Health Technology, Technical University of Denmark, DK-2800 Lyngby, Denmark"],"raw_orcid":"https://orcid.org/0000-0002-5937-4344","affiliations":[{"raw_affiliation_string":"Department of Health Technology, Technical University of Denmark, DK-2800 Lyngby, Denmark","institution_ids":["https://openalex.org/I96673099"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5076702280","display_name":"Morten Nielsen","orcid":"https://orcid.org/0000-0001-7885-4311","observed_orcids":["https://orcid.org/0000-0001-7885-4311"]},"institutions":[{"id":"https://openalex.org/I96673099","display_name":"Technical University of Denmark","ror":"https://ror.org/04qtj9h94","country_code":"DK","type":"education","lineage":["https://openalex.org/I96673099"]}],"countries":["DK"],"is_corresponding":true,"raw_author_name":"Morten Nielsen","raw_affiliation_strings":["Department of Health Technology, Technical University of Denmark, DK-2800 Lyngby, Denmark"],"raw_orcid":"https://orcid.org/0000-0001-7885-4311","affiliations":[{"raw_affiliation_string":"Department of Health Technology, Technical University of Denmark, DK-2800 Lyngby, Denmark","institution_ids":["https://openalex.org/I96673099"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5076702280"],"corresponding_institution_ids":["https://openalex.org/I96673099"],"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/T12576","display_name":"vaccines and immunoinformatics approaches","score":0.8481000065803528,"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/T12576","display_name":"vaccines and immunoinformatics approaches","score":0.8481000065803528,"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/T10031","display_name":"T-cell and B-cell Immunology","score":0.07540000230073929,"subfield":{"id":"https://openalex.org/subfields/2403","display_name":"Immunology"},"field":{"id":"https://openalex.org/fields/24","display_name":"Immunology and Microbiology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T12254","display_name":"Machine Learning in Bioinformatics","score":0.013199999928474426,"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/t-cell-receptor-specificity","display_name":"T cell receptor specificity","score":0.8579999804496765},{"id":"https://openalex.org/keywords/noisy-labels","display_name":"label noise","score":0.847000002861023},{"id":"https://openalex.org/keywords/data-denoising","display_name":"data denoising","score":0.8090000152587891},{"id":"https://openalex.org/keywords/tcr-pmhc-interaction","display_name":"TCR-pMHC interaction","score":0.9559999704360962},{"id":"https://openalex.org/keywords/immunotherapy","display_name":"immunotherapy","score":0.5419999957084656},{"id":"https://openalex.org/keywords/training-data-quality","display_name":"training data quality","score":0.6740000247955322}],"concepts":[{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.6927000284194946},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.6672999858856201},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.619700014591217},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.6054999828338623},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6025000214576721},{"id":"https://openalex.org/C43214815","wikidata":"https://www.wikidata.org/wiki/Q7310987","display_name":"Reliability (semiconductor)","level":3,"score":0.5307000279426575},{"id":"https://openalex.org/C136389625","wikidata":"https://www.wikidata.org/wiki/Q334384","display_name":"Supervised learning","level":3,"score":0.5199000239372253},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5005000233650208},{"id":"https://openalex.org/C2776145971","wikidata":"https://www.wikidata.org/wiki/Q30673951","display_name":"Labeled data","level":2,"score":0.46700000762939453},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.4429999887943268},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3880999982357025},{"id":"https://openalex.org/C21200559","wikidata":"https://www.wikidata.org/wiki/Q7451068","display_name":"Sensitivity (control systems)","level":2,"score":0.37869998812675476},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.3495999872684479},{"id":"https://openalex.org/C58973888","wikidata":"https://www.wikidata.org/wiki/Q1041418","display_name":"Semi-supervised learning","level":2,"score":0.33239999413490295},{"id":"https://openalex.org/C2781170535","wikidata":"https://www.wikidata.org/wiki/Q30587856","display_name":"Noisy data","level":2,"score":0.32919999957084656},{"id":"https://openalex.org/C58489278","wikidata":"https://www.wikidata.org/wiki/Q1172284","display_name":"Data set","level":2,"score":0.3271999955177307},{"id":"https://openalex.org/C29265498","wikidata":"https://www.wikidata.org/wiki/Q7047719","display_name":"Noise measurement","level":3,"score":0.31349998712539673},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.30329999327659607},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.28450000286102295},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.2581000030040741},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.2524000108242035}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.64898/2026.10.02.756166","doi":"https://doi.org/10.64898/2026.10.02.756166","is_oa":true,"landing_page_url":"https://doi.org/10.64898/2026.10.02.756166","pdf_url":"https://www.biorxiv.org/content/biorxiv/early/2026/10/08/2026.10.02.756166.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":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"bioRxiv","raw_type":"posted-content"}],"best_oa_location":{"id":"doi:10.64898/2026.10.02.756166","doi":"https://doi.org/10.64898/2026.10.02.756166","is_oa":true,"landing_page_url":"https://doi.org/10.64898/2026.10.02.756166","pdf_url":"https://www.biorxiv.org/content/biorxiv/early/2026/10/08/2026.10.02.756166.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":"public-domain","license_id":"https://openalex.org/licenses/public-domain","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","display_name":"Good health and well-being","score":0.4000000059604645}],"study_designs":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320322436","display_name":"Novo Nordisk","ror":"https://ror.org/0435rc536"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7221099587.pdf","grobid_xml":"https://content.openalex.org/works/W7221099587.grobid-xml"},"referenced_works_count":35,"referenced_works":["https://openalex.org/W1822028895","https://openalex.org/W1855237549","https://openalex.org/W1857461391","https://openalex.org/W1990806106","https://openalex.org/W2137995988","https://openalex.org/W2560321925","https://openalex.org/W2613978126","https://openalex.org/W2671261300","https://openalex.org/W2752126733","https://openalex.org/W2901423492","https://openalex.org/W2999528130","https://openalex.org/W3160101264","https://openalex.org/W3160420762","https://openalex.org/W3196626346","https://openalex.org/W3217516687","https://openalex.org/W4220974185","https://openalex.org/W4311619464","https://openalex.org/W4317532687","https://openalex.org/W4319455163","https://openalex.org/W4367295958","https://openalex.org/W4367834512","https://openalex.org/W4368357399","https://openalex.org/W4387037681","https://openalex.org/W4390031324","https://openalex.org/W4394786758","https://openalex.org/W4396721167","https://openalex.org/W4399375446","https://openalex.org/W4404511368","https://openalex.org/W4406143499","https://openalex.org/W4410039374","https://openalex.org/W4412856064","https://openalex.org/W4416764216","https://openalex.org/W7116919600","https://openalex.org/W7147196492","https://openalex.org/W7163741019"],"related_works":["https://openalex.org/W7204571693","https://openalex.org/W7211968273","https://openalex.org/W7214428179","https://openalex.org/W4387037681","https://openalex.org/W4319234834","https://openalex.org/W7207622423","https://openalex.org/W4410039374","https://openalex.org/W4403881295","https://openalex.org/W7222871701","https://openalex.org/W7061097464"],"abstract_inverted_index":{"Abstract":[0],"Accurate":[1],"prediction":[2],"of":[3,13,37,92,147,151,161,195],"T":[4],"cell":[5],"receptor":[6],"(TCR)":[7],"specificity":[8,59],"can":[9],"potentially":[10],"accelerate":[11],"development":[12],"novel":[14],"immunotherapies,":[15],"yet":[16],"public":[17],"databases":[18],"used":[19],"to":[20,53,109,167],"train":[21],"these":[22],"models":[23],"contain":[24],"substantial":[25],"label":[26],"noise.":[27],"This":[28],"uncertainty":[29],"complicates":[30],"model":[31],"evaluation":[32],"and":[33,70,184],"limits":[34],"the":[35,63,66,110,128,157,193],"reliability":[36],"predicted":[38,163],"TCR-pMHC":[39,132],"interactions.":[40],"In":[41],"this":[42],"work,":[43],"we":[44,115],"present":[45],"a":[46,186],"simple":[47],"supervised":[48],"machine":[49],"learning":[50],"denoising":[51,82,107],"scheme":[52],"identify":[54],"low-quality":[55],"labels":[56],"in":[57,127,192],"TCR":[58],"data.":[60],"We":[61],"evaluated":[62],"framework":[64],"using":[65],"TCRvdb":[67],"validation":[68,150],"dataset":[69,182],"further":[71,155],"corroborated":[72],"it":[73],"via":[74],"structural":[75],"modeling":[76],"with":[77,120,159],"AlphaFold":[78,140],"3.":[79],"Here,":[80],"our":[81,106],"approach":[83,108],"successfully":[84],"identified":[85,134],"non-validated":[86,96],"TCRs,":[87],"achieving":[88],"an":[89],"average":[90],"MCC":[91],"0.47":[93],"for":[94,102,188],"filtering":[95],"examples":[97],"while":[98],"retaining":[99],"high":[100],"sensitivity":[101],"validated":[103],"examples.":[104],"Applying":[105],"complete":[111],"NetTCR":[112],"training":[113,190],"dataset,":[114],"observed":[116],"that":[117,174],"data":[118,191],"associated":[119],"known":[121],"noisy":[122],"attributes":[123],"were":[124],"significantly":[125],"enriched":[126],"filtered":[129],"subset.":[130],"Furthermore,":[131],"complexes":[133],"as":[135,164],"noise":[136,165],"consistently":[137],"produced":[138],"lower":[139],"3":[141],"confidence":[142],"scores,":[143],"providing":[144],"independent":[145],"evidence":[146],"misannotation.":[148],"Experimental":[149],"30":[152],"selected":[153],"TCRs":[154,162],"supported":[156],"approach,":[158],"80%":[160],"failing":[166],"demonstrate":[168,173],"functional":[169],"reactivity.":[170],"Our":[171],"findings":[172],"current":[175],"performance":[176],"metrics":[177],"may":[178],"be":[179],"obscured":[180],"by":[181],"inaccuracies":[183],"provide":[185],"method":[187],"refining":[189],"absence":[194],"gold-standard":[196],"benchmarks.":[197]},"counts_by_year":[],"updated_date":"2026-11-08T12:12:28.789561","created_date":"2026-10-10T00:00:00"}