Learning the High-Dimensional Immunogenomic Features That Predict Public and Private Antibody Repertoires

Abstract

Recent studies have revealed that immune repertoires contain a substantial fraction of public clones, which may be defined as Ab or TCR clonal sequences shared across individuals. It has remained unclear whether public clones possess predictable sequence features that differentiate them from private clones, which are believed to be generated largely stochastically. This knowledge gap represents a lack of insight into the shaping of immune repertoire diversity. Leveraging a machine learning approach capable of capturing the high-dimensional compositional information of each clonal sequence (defined by CDR3), we detected predictive public clone and private clone-specific immunogenomic differences concentrated in CDR3's N1-D-N2 region, which allowed the prediction of public and private status with 80% accuracy in humans and mice. Our results unexpectedly demonstrate that public, as well as private, clones possess predictable high-dimensional immunogenomic features. Our support vector machine model could be trained effectively on large published datasets (3 million clonal sequences) and was sufficiently robust for public clone prediction across individuals and studies prepared with different library preparation and high-throughput sequencing protocols. In summary, we have uncovered the existence of high-dimensional immunogenomic rules that shape immune repertoire diversity in a predictable fashion. Our approach may pave the way for the construction of a comprehensive atlas of public mouse and human immune repertoires with potential applications in rational vaccine design and immunotherapeutics.

A compact vocabulary of paratope-epitope interactions enables predictability of antibody-antigen binding

“…Adaptive immune receptor repertoires represent a major target area for the application of machine learning in the hope that it may fast-track the in silico discovery and development of immunereceptor based immunotherapies and immunodiagnostics (Brown et al, 2019;Greiff et al, 2012;Mason et al, 2018Mason et al, , 2019Miho et al, 2018). The complexity of sequence dependencies that determine antigen binding (Dash et al, 2017;Glanville et al, 2017), immune receptor publicity (Greiff et al, 2017b) and immune status (immunodiagnostics) (Ostmeyer et al, 2019;Thomas et al, 2014) represent a perfect application ground for machine learning analysis (Arora et al, 2019;Cinelli et al, 2017;Greiff et al, 2017b;Liu et al, 2019;Mason et al, 2019;Sidhom et al, 2018;Sun et al, 2017). As discussed extensively in a recent literature review by us (Brown et al, 2019) the development of ML approaches for immune receptor datasets was and is still hampered by the lack of ground truth datasets.…”

“…Recent reports have, however, provided preliminary evidence for the potential predictability of antibody-antigen interaction: (i) The antibody repertoire field has now established that antibody sequence diversity underlies predictable rules (Elhanati et al, 2015;Greiff et al, 2017bGreiff et al, , 2017a. (ii) The presence of transferable "specificity units" between distinct antibody molecules was recently suggested by showing that tightly binding functional antibodies may be conceived by designing and improving seemingly unrelated paratopes (Nimrod et al, 2018).…”

T‐cell receptor and B‐cell receptor repertoire profiling in adaptive immunity

“…The latter is estimated to be at least 10 8 clonotypes for TCRβ, which is still larger than the diversity observed in the largest repertoire sequencing experiments , while a typical repertoire sequencing experiment samples less than one million cells. Inferring diversity from small samples is challenging, and many different metrics have been proposed for this task (Shannon entropy , RECON , DivE , Renyi entropy (https://arxiv.org/abs/1604.00487), and its transformation, Hill number‐based diversity estimators , Chao2 estimator ). V(D)J recombination and thymic selection result in a very diverse repertoire of naive T‐cells with more or less even distribution of clone sizes.…”

“…Although TCR/BCR nucleotide sequences can be used as unique clone identifiers, the occurrence of highly similar or identical receptor amino acid sequences between individuals is not impossible. Indeed, thousands of such ‘convergent’ immune receptor sequences can be found in bulk receptor repertoires from different individuals . Clonotypes present in more than a single donor are termed ‘public’, whereas clonotypes specific to an individual are considered ‘private’.…”

Evidence of Antibody Repertoire Functional Convergence through Public Baseline and Shared Response Structures

“…They found that just 0.022% of observed clonotypes were 'public' (seen in everyone). In a comple-D R A F T mentary approach, Greiff et al trained a Support Vector Machine on public and private clonal sequences to identify their high-dimensional features, proving that they have distinct immunogenomic properties (17). Clonotyping can also be used to detect antigen-specific immunoglobulins, through the identification of expanded clones after vaccination, or those present in unusually high proportions in individuals immune to certain diseases.…”