Detecting T cell receptors involved in immune responses from single repertoire snapshots

Abstract

Hypervariable T cell receptors (TCRs) play a key role in adaptive immunity, recognizing a vast diversity of pathogen-derived antigens. Our ability to extract clinically relevant information from large high-throughput sequencing of TCR repertoires (RepSeq) data is limited, because little is known about TCR-disease associations. We present Antigen-specific Lymphocyte Identification by Clustering of Expanded sequences (ALICE), a statistical approach that identifies TCR sequences actively involved in current immune responses from a single RepSeq sample and apply it to repertoires of patients with a variety of disorders - patients with autoimmune disease (ankylosing spondylitis [AS]), under cancer immunotherapy, or subject to an acute infection (live yellow fever [YF] vaccine). We validate the method with independent assays. ALICE requires no longitudinal data collection nor large cohorts, and it is directly applicable to most RepSeq datasets. Its results facilitate the identification of TCR variants associated with diseases and conditions, which can be used for diagnostics and rational vaccine design.

Fig 1. Identification of antigen-responding clonotypes using their recombination-based frequency.

(a) ALICE identifies locally enriched regions of the TCR sequence space, represented here as a graph. Vertices are TCR clonotypes observed in the repertoire, and edges connect sequences differing by at most 1 CDR3 amino acid. Antigen exposure induces the proliferation of multiple clonotypes with similar sequences recognizing a few immunodominant epitopes. ALICE identifies clonotypes with a higher numbers of neighbors than expected by a null model of recombination, separating clusters of antigen-responding clonotypes (in red) from clusters arising from recombination statistics (blue, green, and purple clusters). (b) The number of significant results (normalized by the total number of unique nucleotide sequences) found in naive- versus memory-published TCR beta repertoires from Thome and colleagues [16] demonstrates ALICE’s ability to selectively detect immune response signatures in the memory subset only. (c) Normalized number of significant hits found in published repertoires of MLR cultures compared to an unstimulated control [17]. The algorithm finds many more hits in the MLR repertoire. (d) Most clonotypes identified as antigen-responding in MLR culture expanded during the assay, as evidenced by their higher frequency in MLR culture than in the control (red dots). By contrast, clonotypes identified in the unstimulated repertoire (blue crosses) mostly remain unexpanded after the assay, as they probably are signatures of previous immune responses. The individual numerical values could be found in S1 Data. ALICE, Antigen-specific Lymphocyte Identification by Clustering of Expanded sequences; CDR3, Complementarity Determining Region 3; MLR, mixed lymphocyte reaction; PBMC, peripheral blood mononuclear cell; TCR, T cell receptor.

Fig 2. ALICE hits are found in various conditions.

(a) Identification of reactive clonotypes following immunization. Left panel shows the total number of ALICE immune response signatures before (day 0) and on the peak of the response to YF vaccine (day 15). Right panel shows the number of clonotypes identified by the algorithm that have high similarity to clonotypes significantly expanded after YF immunization from Pogorelyy and colleagues [10]. (b) Analysis of peripheral blood repertoires before and after checkpoint blockade cancer immunotherapy [20]. The larger number of ALICE signatures after (red) compared with before (blue) therapy represent clones triggered by the therapy. (c) ROC curves for distinguishing pre- and post-immunotherapy repertoires. The number of ALICE hits (red, AUROC = 0.77) is a better discriminant than the number of unique clonotypes (blue, AUROC = 0.65). The individual numerical values can be found in S1 Data. (d) Graph of expanded clonotypes in synovial fluid of 4 AS patients. Vertices represent significant clonotypes identified by the algorithm, and edges connect clonotypes with at most 1 amino acid mismatch. Zero-degree vertices are not shown. Vertices are colored according to the patients, and split vertices represent public sequences identified in several donors. The 2 sequences shared among all 3 HLA-B27⁺ patients were previously associated with AS and HLA-B27. (e) While the classical sequence logo of the central cluster in panel D is dominated by germline-encoded positions (top), selection factors highlight position-specific pressures acting on the expanded sequences (bottom). ALICE, Antigen-specific Lymphocyte Identification by Clustering of Expanded sequences; AS, ankylosing spondylitis; AUROC, area under the ROC; ROC, receiver operating characteristic; YF, yellow fever.