{"id":"https://openalex.org/W4414742928","doi":"https://doi.org/10.3389/fbinf.2025.1623488","title":"Optimizing clustering of CDR3 sequences using natural language processing, Word2Vec, and KMeans","display_name":"Optimizing clustering of CDR3 sequences using natural language processing, Word2Vec, and KMeans","publication_year":2025,"publication_date":"2025-10-02","ids":{"openalex":"https://openalex.org/W4414742928","doi":"https://doi.org/10.3389/fbinf.2025.1623488","pmid":"https://pubmed.ncbi.nlm.nih.gov/41113103"},"language":"en","primary_location":{"id":"doi:10.3389/fbinf.2025.1623488","is_oa":true,"landing_page_url":"https://doi.org/10.3389/fbinf.2025.1623488","pdf_url":"https://www.frontiersin.org/journals/bioinformatics/articles/10.3389/fbinf.2025.1623488/pdf","source":{"id":"https://openalex.org/S4210219554","display_name":"Frontiers in Bioinformatics","issn_l":"2673-7647","issn":["2673-7647"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320527","host_organization_name":"Frontiers Media","host_organization_lineage":["https://openalex.org/P4310320527"],"host_organization_lineage_names":["Frontiers Media"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Bioinformatics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.frontiersin.org/journals/bioinformatics/articles/10.3389/fbinf.2025.1623488/pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5119811267","display_name":"Sanskriti Baranwal","orcid":null},"institutions":[{"id":"https://openalex.org/I182980787","display_name":"University of Dallas","ror":"https://ror.org/00v3ak792","country_code":"US","type":"education","lineage":["https://openalex.org/I182980787"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sanskriti Baranwal","raw_affiliation_strings":["University of Dallas, Computer Science Department, Irving, TX, United States"],"affiliations":[{"raw_affiliation_string":"University of Dallas, Computer Science Department, Irving, TX, United States","institution_ids":["https://openalex.org/I182980787"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Ricardo Avila Sanchez","orcid":null},"institutions":[{"id":"https://openalex.org/I182980787","display_name":"University of Dallas","ror":"https://ror.org/00v3ak792","country_code":"US","type":"education","lineage":["https://openalex.org/I182980787"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ricardo Avila Sanchez","raw_affiliation_strings":["University of Dallas, Biology Department, Irving, TX, United States"],"affiliations":[{"raw_affiliation_string":"University of Dallas, Biology Department, Irving, TX, United States","institution_ids":["https://openalex.org/I182980787"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083827310","display_name":"Clement-Andi Edet","orcid":null},"institutions":[{"id":"https://openalex.org/I182980787","display_name":"University of Dallas","ror":"https://ror.org/00v3ak792","country_code":"US","type":"education","lineage":["https://openalex.org/I182980787"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Clement-Andi Edet","raw_affiliation_strings":["University of Dallas, Computer Science Department, Irving, TX, United States"],"affiliations":[{"raw_affiliation_string":"University of Dallas, Computer Science Department, Irving, TX, United States","institution_ids":["https://openalex.org/I182980787"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041443233","display_name":"Erick Chastain","orcid":"https://orcid.org/0000-0002-7927-3444"},"institutions":[{"id":"https://openalex.org/I182980787","display_name":"University of Dallas","ror":"https://ror.org/00v3ak792","country_code":"US","type":"education","lineage":["https://openalex.org/I182980787"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Erick Chastain","raw_affiliation_strings":["University of Dallas, Computer Science Department, Irving, TX, United States"],"affiliations":[{"raw_affiliation_string":"University of Dallas, Computer Science Department, Irving, TX, United States","institution_ids":["https://openalex.org/I182980787"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5030533815","display_name":"Inimary T. Toby","orcid":"https://orcid.org/0000-0003-0820-3999"},"institutions":[{"id":"https://openalex.org/I182980787","display_name":"University of Dallas","ror":"https://ror.org/00v3ak792","country_code":"US","type":"education","lineage":["https://openalex.org/I182980787"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Inimary Toby","raw_affiliation_strings":["University of Dallas, Biology Department, Irving, TX, United States"],"affiliations":[{"raw_affiliation_string":"University of Dallas, Biology Department, Irving, TX, United States","institution_ids":["https://openalex.org/I182980787"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5030533815"],"corresponding_institution_ids":["https://openalex.org/I182980787"],"apc_list":{"value":1900,"currency":"USD","value_usd":1900},"apc_paid":{"value":1900,"currency":"USD","value_usd":1900},"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.33045683,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"5","issue":null,"first_page":"1623488","last_page":"1623488"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10051","display_name":"Asthma and respiratory diseases","score":0.9966999888420105,"subfield":{"id":"https://openalex.org/subfields/2737","display_name":"Physiology"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},"topics":[{"id":"https://openalex.org/T10051","display_name":"Asthma and respiratory diseases","score":0.9966999888420105,"subfield":{"id":"https://openalex.org/subfields/2737","display_name":"Physiology"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},{"id":"https://openalex.org/T10322","display_name":"Respiratory Support and Mechanisms","score":0.9721999764442444,"subfield":{"id":"https://openalex.org/subfields/2740","display_name":"Pulmonary and Respiratory Medicine"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},{"id":"https://openalex.org/T10549","display_name":"Neonatal Respiratory Health Research","score":0.9517999887466431,"subfield":{"id":"https://openalex.org/subfields/2740","display_name":"Pulmonary and Respiratory Medicine"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/word2vec","display_name":"Word2vec","score":0.6743999719619751},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.6047000288963318},{"id":"https://openalex.org/keywords/repertoire","display_name":"Repertoire","score":0.4674000144004822},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.4415000081062317},{"id":"https://openalex.org/keywords/mixture-model","display_name":"Mixture model","score":0.4171000123023987},{"id":"https://openalex.org/keywords/k-means-clustering","display_name":"k-means clustering","score":0.40220001339912415},{"id":"https://openalex.org/keywords/unsupervised-learning","display_name":"Unsupervised learning","score":0.34380000829696655},{"id":"https://openalex.org/keywords/immune-system","display_name":"Immune system","score":0.3012999892234802}],"concepts":[{"id":"https://openalex.org/C2776461190","wikidata":"https://www.wikidata.org/wiki/Q22673982","display_name":"Word2vec","level":3,"score":0.6743999719619751},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6255999803543091},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.6047000288963318},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.51419997215271},{"id":"https://openalex.org/C2778473898","wikidata":"https://www.wikidata.org/wiki/Q2145110","display_name":"Repertoire","level":2,"score":0.4674000144004822},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.46560001373291016},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.4415000081062317},{"id":"https://openalex.org/C61224824","wikidata":"https://www.wikidata.org/wiki/Q2260434","display_name":"Mixture model","level":2,"score":0.4171000123023987},{"id":"https://openalex.org/C207968372","wikidata":"https://www.wikidata.org/wiki/Q310401","display_name":"k-means clustering","level":3,"score":0.40220001339912415},{"id":"https://openalex.org/C8038995","wikidata":"https://www.wikidata.org/wiki/Q1152135","display_name":"Unsupervised learning","level":2,"score":0.34380000829696655},{"id":"https://openalex.org/C8891405","wikidata":"https://www.wikidata.org/wiki/Q1059","display_name":"Immune system","level":2,"score":0.3012999892234802},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.3003999888896942},{"id":"https://openalex.org/C2908999202","wikidata":"https://www.wikidata.org/wiki/Q15332550","display_name":"Toll-Like Receptor 9","level":5,"score":0.28349998593330383},{"id":"https://openalex.org/C92835128","wikidata":"https://www.wikidata.org/wiki/Q1277447","display_name":"Hierarchical clustering","level":3,"score":0.2799000144004822},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.27639999985694885},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.2718000113964081},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.27059999108314514},{"id":"https://openalex.org/C193419808","wikidata":"https://www.wikidata.org/wiki/Q1645075","display_name":"Acquired immune system","level":3,"score":0.26829999685287476},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.2667999863624573},{"id":"https://openalex.org/C15151743","wikidata":"https://www.wikidata.org/wiki/Q903778","display_name":"Metagenomics","level":3,"score":0.2615000009536743},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2572999894618988},{"id":"https://openalex.org/C164866538","wikidata":"https://www.wikidata.org/wiki/Q367351","display_name":"Cluster (spacecraft)","level":2,"score":0.257099986076355},{"id":"https://openalex.org/C207936829","wikidata":"https://www.wikidata.org/wiki/Q423163","display_name":"Major histocompatibility complex","level":3,"score":0.2531999945640564},{"id":"https://openalex.org/C9756297","wikidata":"https://www.wikidata.org/wiki/Q126223","display_name":"Immunological synapse","level":5,"score":0.25290000438690186},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2522999942302704}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.3389/fbinf.2025.1623488","is_oa":true,"landing_page_url":"https://doi.org/10.3389/fbinf.2025.1623488","pdf_url":"https://www.frontiersin.org/journals/bioinformatics/articles/10.3389/fbinf.2025.1623488/pdf","source":{"id":"https://openalex.org/S4210219554","display_name":"Frontiers in Bioinformatics","issn_l":"2673-7647","issn":["2673-7647"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320527","host_organization_name":"Frontiers Media","host_organization_lineage":["https://openalex.org/P4310320527"],"host_organization_lineage_names":["Frontiers Media"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Bioinformatics","raw_type":"journal-article"},{"id":"pmid:41113103","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/41113103","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":"Frontiers in bioinformatics","raw_type":null},{"id":"pmh:oai:doaj.org/article:40ef32110e4746e8b6455fb22d58e63a","is_oa":true,"landing_page_url":"https://doaj.org/article/40ef32110e4746e8b6455fb22d58e63a","pdf_url":null,"source":{"id":"https://openalex.org/S112646816","display_name":"SHILAP Revista de lepidopterolog\u00eda","issn_l":"0300-5267","issn":["0300-5267","2340-4078"],"is_oa":true,"is_in_doaj":true,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Frontiers in Bioinformatics, Vol 5 (2025)","raw_type":"article"},{"id":"pmh:oai:europepmc.org:11333564","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/12528129","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"}],"best_oa_location":{"id":"doi:10.3389/fbinf.2025.1623488","is_oa":true,"landing_page_url":"https://doi.org/10.3389/fbinf.2025.1623488","pdf_url":"https://www.frontiersin.org/journals/bioinformatics/articles/10.3389/fbinf.2025.1623488/pdf","source":{"id":"https://openalex.org/S4210219554","display_name":"Frontiers in Bioinformatics","issn_l":"2673-7647","issn":["2673-7647"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320527","host_organization_name":"Frontiers Media","host_organization_lineage":["https://openalex.org/P4310320527"],"host_organization_lineage_names":["Frontiers Media"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Bioinformatics","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4414742928.pdf"},"referenced_works_count":32,"referenced_works":["https://openalex.org/W1614298861","https://openalex.org/W1985921653","https://openalex.org/W2043071551","https://openalex.org/W2051241958","https://openalex.org/W2089041106","https://openalex.org/W2286228001","https://openalex.org/W2605177850","https://openalex.org/W2616207459","https://openalex.org/W2670890989","https://openalex.org/W2671261300","https://openalex.org/W2728919089","https://openalex.org/W2793513555","https://openalex.org/W2885500852","https://openalex.org/W2980789587","https://openalex.org/W3049325061","https://openalex.org/W3111056735","https://openalex.org/W3134285993","https://openalex.org/W3135351475","https://openalex.org/W3184997006","https://openalex.org/W3210968255","https://openalex.org/W4211250103","https://openalex.org/W4287751334","https://openalex.org/W4317565748","https://openalex.org/W4366091687","https://openalex.org/W4376278433","https://openalex.org/W4380143048","https://openalex.org/W4385216881","https://openalex.org/W4389399619","https://openalex.org/W4392584927","https://openalex.org/W4401256607","https://openalex.org/W4403828429","https://openalex.org/W4408177310"],"related_works":[],"abstract_inverted_index":{"T-cell":[0],"receptor":[1],"(TCR)":[2],"sequencing":[3],"has":[4],"emerged":[5],"as":[6],"a":[7,32,64,144],"powerful":[8],"tool":[9],"for":[10,167],"understanding":[11],"adaptive":[12],"immune":[13,123,169],"responses,":[14],"yet":[15],"challenges":[16],"persist":[17],"in":[18,91,128,159,171],"deciphering":[19],"the":[20,129,133,155,165],"immense":[21],"diversity":[22],"of":[23,110,132,157],"Complementarity-Determining":[24],"Region":[25],"3":[26],"(CDR3)":[27],"sequences.":[28],"This":[29,150],"study":[30,151],"presents":[31],"novel":[33],"natural":[34],"language":[35],"processing":[36],"(NLP)-based":[37],"pipeline":[38],"to":[39,147],"cluster":[40],"CDR3":[41,134],"sequences":[42],"from":[43],"TCR":[44],"\u03b2-chain":[45],"repertoires":[46],"using":[47],"Word2Vec":[48,71],"embeddings,":[49],"principal":[50],"component":[51],"analysis":[52,161],"(PCA),":[53],"and":[54,76,83,105,113,174],"KMeans":[55],"clustering.":[56],"Focusing":[57],"on":[58,73],"Acute":[59],"Respiratory":[60],"Distress":[61],"Syndrome":[62],"(ARDS),":[63],"life-threatening":[65],"inflammatory":[66],"lung":[67],"condition,":[68],"we":[69],"trained":[70],"models":[72],"healthy":[74],"controls":[75],"applied":[77],"unsupervised":[78],"clustering":[79],"across":[80],"ARDS,":[81],"non-ARDS,":[82],"control":[84,94],"datasets.":[85],"Dimensionality-reduced":[86],"embeddings":[87],"revealed":[88],"clear":[89],"distinctions":[90],"repertoire":[92,111],"structure:":[93],"samples":[95,115],"exhibited":[96],"tight,":[97],"low-diversity":[98],"clusters;":[99],"ARDS":[100],"patients":[101],"showed":[102],"high":[103],"dispersion":[104],"numerous":[106],"diffuse":[107],"clusters":[108],"indicative":[109],"disruption;":[112],"non-ARDS":[114],"displayed":[116],"intermediate":[117],"organization.":[118],"These":[119],"differences":[120],"suggest":[121],"that":[122],"activation":[124],"states":[125],"are":[126],"embedded":[127],"structural":[130],"topology":[131],"space.":[135],"Our":[136],"framework":[137],"successfully":[138],"captured":[139],"these":[140],"latent":[141],"patterns,":[142],"offering":[143],"scalable":[145],"approach":[146],"biomarker":[148],"discovery.":[149],"not":[152],"only":[153],"reinforces":[154],"utility":[156],"NLP":[158],"immunological":[160],"but":[162],"also":[163],"paves":[164],"way":[166],"data-driven":[168],"monitoring":[170],"critical":[172],"care":[173],"personalized":[175],"diagnostics.":[176]},"counts_by_year":[],"updated_date":"2026-04-21T08:09:41.155169","created_date":"2025-10-10T00:00:00"}