Detection of disease-specific signatures in B cell repertoires of lymphomas using machine learning. Detection of disease-specific signatures in B cell repertoires of lymphomas

The classification of B cell lymphomas - mainly based on light microscopy evaluation by a pathologist - requires many years of training. Since the B cell receptor (BCR) of the lymphoma clone and the microenvironmental immune architecture are important features discriminating different lymphoma subsets, we asked if 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 clones in the BCR repertoires of 620 paradigmatic lymphomas - nodular lymphocyte predominant B cell lymphoma (NLPHL), diffuse large B cell lymphoma (DLBCL) and chronic lymphocytic leukemia (CLL) - as well as 291 control tissues. With regard to DLBCL and CLL, the models demonstrated optimal performance when utilizing only the most prevalent clone for classification, while in NLPHL - that has a dominant background of non-malignant bystander cells - a broader array of clones enhanced model accuracy. Surprisingly, the straightforward logistic regression model outperformed 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 cases from all three lymphoma entities and 58 healthy individuals. Together, we provide proof-of-concept that different lymphoma entities can be differentiated from each other using BCR repertoire NGS on lymphoma-infiltrated tissues by a trained machine learning model.