{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,6]],"date-time":"2026-04-06T12:25:31Z","timestamp":1775478331969,"version":"3.50.1"},"update-to":[{"DOI":"10.1371\/journal.pcbi.1011570","type":"new_version","label":"New version","source":"publisher","updated":{"date-parts":[[2024,7,15]],"date-time":"2024-07-15T00:00:00Z","timestamp":1721001600000}}],"reference-count":54,"publisher":"Public Library of Science (PLoS)","issue":"7","license":[{"start":{"date-parts":[[2024,7,2]],"date-time":"2024-07-02T00:00:00Z","timestamp":1719878400000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Mertelsmann Foundation"}],"content-domain":{"domain":["www.ploscompbiol.org"],"crossmark-restriction":false},"short-container-title":["PLoS Comput Biol"],"abstract":"<jats:p>The classification of B cell lymphomas\u2014mainly based on light microscopy evaluation by a pathologist\u2014requires many years of training. Since the B cell receptor (BCR) of the lymphoma clonotype and the microenvironmental immune architecture are important features discriminating different lymphoma subsets, we asked whether BCR repertoire next-generation sequencing (NGS) of lymphoma-infiltrated tissues in conjunction with machine learning algorithms could have diagnostic utility in the subclassification of these cancers. We trained a random forest and a linear classifier via logistic regression based on patterns of clonal distribution, VDJ gene usage and physico-chemical properties of the top-n most frequently represented clonotypes in the BCR repertoires of 620 paradigmatic lymphoma samples\u2014nodular lymphocyte predominant B cell lymphoma (NLPBL), diffuse large B cell lymphoma (DLBCL) and chronic lymphocytic leukemia (CLL)\u2014alongside with 291 control samples. With regard to DLBCL and CLL, the models demonstrated optimal performance when utilizing only the most prevalent clonotype for classification, while in NLPBL\u2014that has a dominant background of non-malignant bystander cells\u2014a broader array of clonotypes enhanced model accuracy. Surprisingly, the straightforward logistic regression model performed best in this seemingly complex classification problem, suggesting linear separability in our chosen dimensions. It achieved a weighted F1-score of 0.84 on a test cohort including 125 samples from all three lymphoma entities and 58 samples from healthy individuals. Together, we provide proof-of-concept that at least the 3 studied lymphoma entities can be differentiated from each other using BCR repertoire NGS on lymphoma-infiltrated tissues by a trained machine learning model.<\/jats:p>","DOI":"10.1371\/journal.pcbi.1011570","type":"journal-article","created":{"date-parts":[[2024,7,2]],"date-time":"2024-07-02T15:28:28Z","timestamp":1719934108000},"page":"e1011570","update-policy":"https:\/\/doi.org\/10.1371\/journal.pcbi.corrections_policy","source":"Crossref","is-referenced-by-count":11,"title":["Detection of disease-specific signatures in B cell repertoires of lymphomas using machine learning"],"prefix":"10.1371","volume":"20","author":[{"ORCID":"https:\/\/orcid.org\/0009-0008-0871-7555","authenticated-orcid":true,"given":"Paul","family":"Schmidt-Barbo","sequence":"first","affiliation":[]},{"given":"Gabriel","family":"Kalweit","sequence":"additional","affiliation":[]},{"given":"Mehdi","family":"Naouar","sequence":"additional","affiliation":[]},{"given":"Lisa","family":"Paschold","sequence":"additional","affiliation":[]},{"given":"Edith","family":"Willscher","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9789-5776","authenticated-orcid":true,"given":"Christoph","family":"Schulthei\u00df","sequence":"additional","affiliation":[]},{"given":"Bruno","family":"M\u00e4rkl","sequence":"additional","affiliation":[]},{"given":"Stefan","family":"Dirnhofer","sequence":"additional","affiliation":[]},{"given":"Alexandar","family":"Tzankov","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0663-3004","authenticated-orcid":true,"given":"Mascha","family":"Binder","sequence":"additional","affiliation":[]},{"given":"Maria","family":"Kalweit","sequence":"additional","affiliation":[]}],"member":"340","published-online":{"date-parts":[[2024,7,2]]},"reference":[{"issue":"2","key":"pcbi.1011570.ref001","doi-asserted-by":"crossref","first-page":"S33","DOI":"10.1016\/j.jaci.2009.09.017","article-title":"Adaptive immunity","volume":"125","author":"FA Bonilla","year":"2010","journal-title":"J Allergy Clin Immunol"},{"issue":"3","key":"pcbi.1011570.ref002","doi-asserted-by":"crossref","first-page":"191","DOI":"10.1038\/nri3801","article-title":"The early history of B cells","volume":"15","author":"MD Cooper","year":"2015","journal-title":"Nat Rev Immunol"},{"key":"pcbi.1011570.ref003","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1007\/978-981-15-3532-1_1","article-title":"B Cell Development and Maturation","volume":"1254","author":"Y Wang","year":"2020","journal-title":"Adv Exp Med Biol"},{"issue":"4","key":"pcbi.1011570.ref004","doi-asserted-by":"crossref","first-page":"959","DOI":"10.1016\/j.jaci.2013.01.046","article-title":"B-cell biology and development","volume":"131","author":"K Pieper","year":"2013","journal-title":"J Allergy Clin Immunol"},{"key":"pcbi.1011570.ref005","doi-asserted-by":"crossref","first-page":"23","DOI":"10.1007\/978-981-15-3532-1_2","article-title":"B Cell Receptor Signaling","volume":"1254","author":"S Tanaka","year":"2020","journal-title":"Adv Exp Med Biol"},{"issue":"3","key":"pcbi.1011570.ref006","doi-asserted-by":"crossref","first-page":"524","DOI":"10.1016\/j.cell.2019.03.016","article-title":"B Cell Responses: Cell Interaction Dynamics and Decisions","volume":"177","author":"JG Cyster","year":"2019","journal-title":"Cell"},{"issue":"3","key":"pcbi.1011570.ref007","doi-asserted-by":"crossref","first-page":"137","DOI":"10.1038\/nri3804","article-title":"Dynamics of B cells in germinal centres","volume":"15","author":"NS De Silva","year":"2015","journal-title":"Nat Rev Immunol"},{"issue":"3","key":"pcbi.1011570.ref008","doi-asserted-by":"crossref","first-page":"233","DOI":"10.1111\/imm.13176","article-title":"V(D)J recombination, somatic hypermutation and class switch recombination of immunoglobulins: mechanism and regulation","volume":"160","author":"X Chi","year":"2020","journal-title":"Immunology"},{"issue":"10","key":"pcbi.1011570.ref009","doi-asserted-by":"crossref","first-page":"105002","DOI":"10.1016\/j.isci.2022.105002","article-title":"B-cell receptor repertoire sequencing: Deeper digging into the mechanisms and clinical aspects of immune-mediated diseases","volume":"25","author":"B Zheng","year":"2022","journal-title":"iScience"},{"key":"pcbi.1011570.ref010","doi-asserted-by":"crossref","first-page":"1753","DOI":"10.3389\/fimmu.2017.01753","article-title":"How B-Cell Receptor Repertoire Sequencing Can Be Enriched with Structural Antibody Data","volume":"8","author":"A Kovaltsuk","year":"2017","journal-title":"Front Immunol"},{"issue":"8","key":"pcbi.1011570.ref011","doi-asserted-by":"crossref","first-page":"1652","DOI":"10.1016\/j.immuni.2021.07.015","article-title":"The unique biology of germinal center B cells","volume":"54","author":"C Young","year":"2021","journal-title":"Immunity"},{"issue":"6","key":"pcbi.1011570.ref012","article-title":"Epidemiology and Etiology of Leukemia and Lymphoma","volume":"10","author":"JAB Bispo","year":"2020","journal-title":"Cold Spring Harb Perspect Med"},{"key":"pcbi.1011570.ref013","doi-asserted-by":"crossref","first-page":"161","DOI":"10.1007\/978-981-15-3532-1_12","article-title":"B Cell Lymphoma","volume":"1254","author":"X Meng","year":"2020","journal-title":"Adv Exp Med Biol"},{"key":"pcbi.1011570.ref014","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1007\/978-1-4939-9151-8_1","article-title":"Origin and Pathogenesis of B Cell Lymphomas","volume":"1956","author":"M Seifert","year":"2019","journal-title":"Methods Mol Biol"},{"issue":"4","key":"pcbi.1011570.ref015","doi-asserted-by":"crossref","first-page":"251","DOI":"10.1038\/nrc1589","article-title":"Mechanisms of B-cell lymphoma pathogenesis","volume":"5","author":"R. Kuppers","year":"2005","journal-title":"Nat Rev Cancer"},{"key":"pcbi.1011570.ref016","doi-asserted-by":"crossref","first-page":"139","DOI":"10.1007\/978-1-4939-9151-8_7","article-title":"Stereotyped B Cell Receptor Immunoglobulins in B Cell Lymphomas","volume":"1956","author":"A Agathangelidis","year":"2019","journal-title":"Methods Mol Biol"},{"issue":"10","key":"pcbi.1011570.ref017","doi-asserted-by":"crossref","first-page":"2252","DOI":"10.3109\/10428194.2013.879715","article-title":"Stereotyped B-cell receptors in chronic lymphocytic leukemia","volume":"55","author":"A Agathangelidis","year":"2014","journal-title":"Leuk Lymphoma"},{"key":"pcbi.1011570.ref018","doi-asserted-by":"crossref","first-page":"149","DOI":"10.1146\/annurev-pathol-050520-044652","article-title":"Molecular Monitoring of Lymphomas","volume":"18","author":"JG Schroers-Martin","year":"2023","journal-title":"Annu Rev Pathol"},{"issue":"6","key":"pcbi.1011570.ref019","doi-asserted-by":"crossref","first-page":"351","DOI":"10.1016\/j.trecan.2019.05.001","article-title":"Targeting the Tumor Microenvironment of Leukemia and Lymphoma","volume":"5","author":"UE Hopken","year":"2019","journal-title":"Trends Cancer"},{"issue":"5\u20136","key":"pcbi.1011570.ref020","doi-asserted-by":"crossref","first-page":"225","DOI":"10.1159\/000502912","article-title":"Lymphomas and Their Microenvironment: A Multifaceted Relationship","volume":"86","author":"T Menter","year":"2019","journal-title":"Pathobiology"},{"issue":"Supplement_1","key":"pcbi.1011570.ref021","doi-asserted-by":"crossref","first-page":"2891","DOI":"10.1182\/blood-2019-126927","article-title":"Cell of Origin Classification of DLBCL Using Targeted NGS Expression Profiling and Deep Learning","volume":"134","author":"M Albitar","year":"2019","journal-title":"Blood"},{"key":"pcbi.1011570.ref022","article-title":"Profiling the baseline performance and limits of machine learning models for adaptive immune receptor repertoire classification","author":"C Kanduri","year":"2021","journal-title":"bioRxiv"},{"key":"pcbi.1011570.ref023","article-title":"Modern Hopfield Networks and Attention for Immune Repertoire Classification","author":"M Widrich","year":"2020","journal-title":"bioRxiv"},{"issue":"5","key":"pcbi.1011570.ref024","doi-asserted-by":"crossref","first-page":"59","DOI":"10.1038\/s41408-020-0322-5","article-title":"Combining gene expression profiling and machine learning to diagnose B-cell non-Hodgkin lymphoma","volume":"10","author":"V Bob\u00e9e","year":"2020","journal-title":"Blood Cancer Journal"},{"issue":"14","key":"pcbi.1011570.ref025","doi-asserted-by":"crossref","first-page":"3391","DOI":"10.1182\/bloodadvances.2020001949","article-title":"A refined cell-of-origin classifier with targeted NGS and artificial intelligence shows robust predictive value in DLBCL","volume":"4","author":"ZY Xu-Monette","year":"2020","journal-title":"Blood Advances"},{"issue":"1","key":"pcbi.1011570.ref026","doi-asserted-by":"crossref","first-page":"207","DOI":"10.1007\/s00428-022-03427-z","article-title":"Evolution in the definition and diagnosis of the Hodgkin lymphomas and related entities","volume":"482","author":"TA Tousseyn","year":"2023","journal-title":"Virchows Arch"},{"key":"pcbi.1011570.ref027","doi-asserted-by":"crossref","first-page":"23","DOI":"10.1007\/BF01025492","article-title":"Statistical analysis of the physical properties of the 20 naturally occurring amino acids","volume":"4","author":"A Kidera","year":"1985","journal-title":"Journal of Protein Chemistry"},{"issue":"2","key":"pcbi.1011570.ref028","doi-asserted-by":"crossref","first-page":"111","DOI":"10.1111\/j.2517-6161.1974.tb00994.x","article-title":"Cross-validatory choice and assessment of statistical predictions","volume":"36","author":"M. Stone","year":"1974","journal-title":"Journal of the royal statistical society: Series B (Methodological)"},{"issue":"10","key":"pcbi.1011570.ref029","doi-asserted-by":"crossref","first-page":"2654","DOI":"10.3324\/haematol.2021.278427","article-title":"Evolutionary clonal trajectories in nodular lymphocyte-predominant Hodgkin lymphoma with high risk of transformation","volume":"106","author":"L Paschold","year":"2021","journal-title":"haematologica"},{"issue":"1","key":"pcbi.1011570.ref030","doi-asserted-by":"crossref","first-page":"2465","DOI":"10.1038\/s41467-020-16375-6","article-title":"Lymphocyte predominant cells detect Moraxella catarrhalis-derived antigens in nodular lymphocyte-predominant Hodgkin lymphoma","volume":"11","author":"L Thurner","year":"2020","journal-title":"Nature communications"},{"issue":"1","key":"pcbi.1011570.ref031","doi-asserted-by":"crossref","first-page":"6004","DOI":"10.1038\/s41467-020-19817-3","article-title":"A deep learning diagnostic platform for diffuse large B-cell lymphoma with high accuracy across multiple hospitals","volume":"11","author":"D Li","year":"2020","journal-title":"Nature Communications"},{"issue":"2","key":"pcbi.1011570.ref032","first-page":"153","article-title":"Automated diagnosis of lymphoma with digital pathology images using deep learning. Annals of Clinical &","volume":"49","author":"H El Achi","year":"2019","journal-title":"Laboratory Science"},{"issue":"10","key":"pcbi.1011570.ref033","doi-asserted-by":"crossref","first-page":"1300","DOI":"10.1038\/s41374-020-0442-3","article-title":"Deep learning shows the capability of high-level computer-aided diagnosis in malignant lymphoma","volume":"100","author":"H Miyoshi","year":"2020","journal-title":"Laboratory Investigation"},{"issue":"10","key":"pcbi.1011570.ref034","doi-asserted-by":"crossref","first-page":"2419","DOI":"10.3390\/cancers13102419","article-title":"Deep learning for the classification of non-Hodgkin lymphoma on histopathological images","volume":"13","author":"G Steinbuss","year":"2021","journal-title":"Cancers"},{"issue":"1","key":"pcbi.1011570.ref035","doi-asserted-by":"crossref","first-page":"63","DOI":"10.1038\/s41746-020-0272-0","article-title":"Accurate diagnosis of lymphoma on whole-slide histopathology images using deep learning","volume":"3","author":"C Syrykh","year":"2020","journal-title":"NPJ digital medicine"},{"key":"pcbi.1011570.ref036","doi-asserted-by":"crossref","first-page":"335","DOI":"10.1007\/s00428-020-02894-6","article-title":"Number of pathologists in Germany: comparison with European countries, USA, and Canada","volume":"478","author":"B M\u00e4rkl","year":"2021","journal-title":"Virchows Archiv"},{"issue":"1","key":"pcbi.1011570.ref037","doi-asserted-by":"crossref","first-page":"9516","DOI":"10.1038\/s41598-023-36144-x","article-title":"T cell repertoire breadth is associated with the number of acute respiratory infections in the LoewenKIDS birth cohort","volume":"13","author":"L Paschold","year":"2023","journal-title":"Scientific Reports"},{"key":"pcbi.1011570.ref038","doi-asserted-by":"crossref","DOI":"10.3389\/fimmu.2022.876306","article-title":"Rapid Hypermutation B Cell Trajectory Recruits Previously Primed B Cells Upon Third SARS-Cov-2 mRNA Vaccination","volume":"13","author":"L Paschold","year":"2022","journal-title":"Frontiers in Immunology"},{"issue":"3","key":"pcbi.1011570.ref039","doi-asserted-by":"crossref","first-page":"49","DOI":"10.1038\/s41408-022-00650-4","article-title":"Subclonal heterogeneity sheds light on the transformation trajectory in IGLV3-21R110 chronic lymphocytic leukemia","volume":"12","author":"L Paschold","year":"2022","journal-title":"Blood Cancer Journal"},{"issue":"1","key":"pcbi.1011570.ref040","doi-asserted-by":"crossref","DOI":"10.1172\/JCI142966","article-title":"SARS-CoV-2\u2013specific antibody rearrangements in prepandemic immune repertoires of risk cohorts and patients with COVID-19","volume":"131","author":"L Paschold","year":"2021","journal-title":"The Journal of Clinical Investigation"},{"issue":"2","key":"pcbi.1011570.ref041","doi-asserted-by":"crossref","first-page":"442","DOI":"10.1016\/j.immuni.2020.06.024","article-title":"Next-generation sequencing of T and B cell receptor repertoires from COVID-19 patients showed signatures associated with severity of disease","volume":"53","author":"C Schulthei\u00df","year":"2020","journal-title":"Immunity"},{"issue":"11","key":"pcbi.1011570.ref042","doi-asserted-by":"crossref","DOI":"10.1016\/j.isci.2021.103325","article-title":"Maturation trajectories and transcriptional landscape of plasmablasts and autoreactive B cells in COVID-19","volume":"24","author":"C Schulthei\u00df","year":"2021","journal-title":"Iscience"},{"issue":"4","key":"pcbi.1011570.ref043","doi-asserted-by":"crossref","first-page":"1073","DOI":"10.1038\/s41375-020-01025-z","article-title":"SLAMF receptors negatively regulate B cell receptor signaling in chronic lymphocytic leukemia via recruitment of prohibitin-2","volume":"35","author":"L von Wenserski","year":"2021","journal-title":"Leukemia"},{"issue":"4","key":"pcbi.1011570.ref044","doi-asserted-by":"crossref","first-page":"1436","DOI":"10.1002\/hep.31473","article-title":"Next-generation Immunosequencing reveals pathological T-cell architecture in autoimmune hepatitis","volume":"73","author":"C Schulthei\u00df","year":"2021","journal-title":"Hepatology"},{"key":"pcbi.1011570.ref045","doi-asserted-by":"crossref","first-page":"1897","DOI":"10.3389\/fimmu.2019.01897","article-title":"High-throughput immunogenetics reveals a lack of physiological T cell clusters in patients with autoimmune cytopenias","volume":"10","author":"D Simnica","year":"2019","journal-title":"Frontiers in Immunology"},{"issue":"1","key":"pcbi.1011570.ref046","doi-asserted-by":"crossref","first-page":"820","DOI":"10.1038\/s41467-019-08677-1","article-title":"Differential organization of tonic and chronic B cell antigen receptors in the plasma membrane","volume":"10","author":"MA Gomes de Castro","year":"2019","journal-title":"Nature communications"},{"issue":"15","key":"pcbi.1011570.ref047","first-page":"1755","article-title":"The phosphotyrosine phosphatase SHP2 promotes anergy in chronic lymphocytic leukemia","volume":"131","author":"S Schliffke","year":"2018","journal-title":"Blood, The Journal of the American Society of Hematology"},{"issue":"4","key":"pcbi.1011570.ref048","doi-asserted-by":"crossref","first-page":"e1417720","DOI":"10.1080\/2162402X.2017.1417720","article-title":"Dynamic changes of the normal B lymphocyte repertoire in CLL in response to ibrutinib or FCR chemo-immunotherapy","volume":"7","author":"S Schliffke","year":"2018","journal-title":"Oncoimmunology"},{"issue":"11","key":"pcbi.1011570.ref049","doi-asserted-by":"crossref","first-page":"2232","DOI":"10.1038\/leu.2016.157","article-title":"Clinical response to ibrutinib is accompanied by normalization of the T-cell environment in CLL-related autoimmune cytopenia","volume":"30","author":"S Schliffke","year":"2016","journal-title":"Leukemia"},{"issue":"5","key":"pcbi.1011570.ref050","doi-asserted-by":"crossref","first-page":"380","DOI":"10.1038\/nmeth.3364","article-title":"MiXCR: software for comprehensive adaptive immunity profiling","volume":"12","author":"DA Bolotin","year":"2015","journal-title":"Nature methods"},{"issue":"11","key":"pcbi.1011570.ref051","doi-asserted-by":"crossref","first-page":"738","DOI":"10.1016\/j.it.2015.09.006","article-title":"Bioinformatic and statistical analysis of adaptive immune repertoires","volume":"36","author":"V Greiff","year":"2015","journal-title":"Trends in immunology"},{"key":"pcbi.1011570.ref052","doi-asserted-by":"crossref","first-page":"131","DOI":"10.1016\/0022-5193(66)90013-0","article-title":"The measurement of diversity in different types of biological collections","volume":"13","author":"EC Pielou","year":"1966","journal-title":"Journal of theoretical biology"},{"issue":"3","key":"pcbi.1011570.ref053","doi-asserted-by":"crossref","first-page":"379","DOI":"10.1002\/j.1538-7305.1948.tb01338.x","article-title":"A mathematical theory of communication","volume":"27","author":"CE Shannon","year":"1948","journal-title":"The Bell system technical journal"},{"issue":"1","key":"pcbi.1011570.ref054","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1186\/s40425-015-0070-4","article-title":"Peripheral T cell receptor diversity is associated with clinical outcomes following ipilimumab treatment in metastatic melanoma","volume":"3","author":"MA Postow","year":"2015","journal-title":"Journal for immunotherapy of cancer"}],"updated-by":[{"DOI":"10.1371\/journal.pcbi.1011570","type":"new_version","label":"New version","source":"publisher","updated":{"date-parts":[[2024,7,15]],"date-time":"2024-07-15T00:00:00Z","timestamp":1721001600000}}],"container-title":["PLOS Computational Biology"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pcbi.1011570","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,7,15]],"date-time":"2024-07-15T13:47:30Z","timestamp":1721051250000},"score":1,"resource":{"primary":{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pcbi.1011570"}},"subtitle":[],"editor":[{"given":"Stacey D.","family":"Finley","sequence":"first","affiliation":[]}],"short-title":[],"issued":{"date-parts":[[2024,7,2]]},"references-count":54,"journal-issue":{"issue":"7","published-online":{"date-parts":[[2024,7,2]]}},"URL":"https:\/\/doi.org\/10.1371\/journal.pcbi.1011570","relation":{"has-preprint":[{"id-type":"doi","id":"10.1101\/2023.10.05.561150","asserted-by":"object"}]},"ISSN":["1553-7358"],"issn-type":[{"value":"1553-7358","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,7,2]]}}}