Convergent selection in antibody repertoires is revealed by deep learning

Abstract

Adaptive immunity is driven by the ability of lymphocytes to undergo V(D)J recombination and generate a highly diverse set of immune receptors (B cell receptors/secreted antibodies and T cell receptors) and their subsequent clonal selection and expansion upon molecular recognition of foreign antigens. These principles lead to remarkable, unique and dynamic immune receptor repertoires 1 . Deep sequencing provides increasing evidence for the presence of commonly shared (convergent) receptors across individual organisms within one species 2-4 . Convergent selection of specific receptors towards various antigens offers one explanation for these findings. For example, single cases of convergence have been reported in antibody repertoires of viral infection or allergy 5-8 . Recent studies demonstrate that convergent selection of sequence motifs within T cell receptor (TCR) repertoires can be identified on an even wider scale 9,10 . Here we report that there is extensive convergent selection in antibody repertoires of mice for a range of protein antigens and immunization conditions. We employed a deep learning approach utilizing variational autoencoders (VAEs) to model the underlying process of B cell receptor (BCR) recombination and assume that the data generation follows a Gaussian mixture model (GMM) in latent space. This provides both a latent embedding and cluster labels that group similar sequences, thus enabling the discovery of a multitude of convergent, antigen-associated sequence patterns. Using a linear, one-versus-all support vector machine (SVM), we confirm that the identified sequence patterns are predictive of antigenic exposure and outperform predictions based on the occurrence of public clones. Recombinant expression of both natural and in silico-generated antibodies possessing convergent patterns confirms their binding specificity to target antigens. Our work highlights to which extent convergence in antibody repertoires can occur and shows how deep learning can be applied for immunodiagnostics and antibody discovery and engineering.

Deep Mining of Human Antibody Repertoires: Concepts, Methodologies, and Applications

“…[ 124 ] Many computational tools [ 125–129 ] have also been developed to assemble paired V H and V L antibody sequences from the increasing single‐cell RNA‐Seq data. Moreover, novel technologies of single protein molecules in nanopores and convergent selection in antibody repertoires by deep learning [ 130 ] may profoundly accelerate Ig‐Seq development and antibody repertoire deep mining. Overall, it is expected that deep mining of the antibody repertoire will lead to more efficient and faster development of clinical diagnostics and immunological therapeutics.…”

Single-cell sequencing of plasma cells from COVID-19 patients reveals highly expanded clonal lineages produce specific and neutralizing antibodies to SARS-CoV-2

“…In the future, different strategies of selecting plasma cell clonal lineages could allow for improvement in successful identification of antigen-specific antibodies from single-cell sequencing data. In addition to clonal expansion, other factors could be incorporated into the selection criteria such as Ig isotype, somatic hypermutation and convergence in sequence space (59) .…”

immuneML: an ecosystem for machine learning analysis of adaptive immune receptor repertoires

“…Together this information shapes the foundation for AIRR-based diagnostics 6,[10][11][12][13] . Similarly, s equence -based prediction of antigen and epitope binding is of fundamental importance for AIR-based therapeutics discovery and engineering [14][15][16][17][18][19][20][21][22][23][24] . In this manuscript, the term AIRR signifies both AIRs and AIRRs (a collection of AIRs) if not specified otherwise.…”