Immunogenicity of CAR T cells in cancer therapy

Abstract

Patient-derived T cells genetically reprogrammed to express CD19-specific chimeric antigen receptors (CARs) have shown remarkable clinical responses and are commercially available for the treatment of patients with certain advanced-stage B cell malignancies. Nonetheless, several trials have revealed pre-existing and/or treatment-induced immune responses to the mouse-derived single-chain variable fragments included in these constructs. These responses might have contributed to both treatment failure and the limited success of redosing strategies observed in some patients. Data from early phase clinical trials suggest that CAR T cells are also associated with immunogenicity-related events in patients with solid tumours. Generally, the clinical implications of anti-CAR immune responses are poorly understood and highly variable between different CAR constructs and malignancies. These observations highlight an urgent need to uncover the mechanisms of immunogenicity in patients receiving CAR T cells and develop validated assays to enable clinical detection. In this Review, we describe the current clinical evidence of anti-CAR immune responses and discuss how new CAR T cell technologies might impact the risk of immunogenicity. We then suggest ways to reduce the risks of anti-CAR immune responses to CAR T cell products that are advancing towards the clinic. Finally, we summarize measures that investigators could consider in order to systematically monitor and better comprehend the possible effects of immunogenicity during trials involving CAR T cells as well as in routine clinical practice.

Fig. 1 ∣. Mechanisms of action of anti-CAR immune responses.

Acquired anti-chimeric antigen receptor (CAR) immune responses can be humoral or cellular. Cellular immunity probably arises from the processing and cross-presentation of foreign (mouse, viral or non-self human) sequences to the CAR molecule in the context of a major histocompatibility complex (MHC). CAR peptides from apoptotic or necrotic CAR T cells can be displayed by antigen-presenting cells and used to prime T cell responses in secondary lymphoid organs (panel a). CAR-specific CD8⁺ T cells or cytotoxic CD4⁺ T cells can eliminate CAR T cells that present fragments of the CAR molecule via MHC-mediated recognition. Humoral immunity can be primed through CAR proteins in apoptotic bodies presented by follicular dendritic cells to B cells. Supported by anti-CAR T cells, CAR-specific B cells can expand and then undergo class switching and plasma cell differentiation, producing different classes of immunoglobulins with distinct functions. Anti-CAR antibodies can potentially induce the death of CAR T cells via several mechanisms, including antibody-dependent cellular cytotoxicity, whereby interactions between CAR-bound antibodies and the Fc receptor (FcR) domains of innate immune cells, such as natural killer (NK) cells or macrophages, leads to cytotoxicity via the release of perforin and/or granzymes, or phagocytosis (panel b) and complement-dependent cytotoxicity owing to CAR-bound antibodies that activate the complement cascade, leading to the formation of membrane attack complexes and cell lysis (panel c). Following CAR engagement, anti-CAR IgE could also bind to the FcR of mast cells, thus promoting degranulation and CAR T cell death (panel d). Excessive release of multiple vasoactive mediators in mast cell granula could lead to systemic anaphylaxis, which was lethal in one patient. KIR, killer immunoglobulin-like receptor.

Fig. 2 ∣. Differences in anti-CAR immune responses following the targeting of B cell versus solid-tumour antigens.

a ∣ Chimeric antigen receptor (CAR) T cells targeting B cell malignancies induce aplasia of non-malignant B cells, thus reducing the potential for anti-CAR humoral immunity. b ∣ CAR T cells directed to solid-tumour antigens (targets not expressed on B cells) might have an increased risk of inducing both cellular and humoral anti-CAR immunity. MHC, major histocompatibility complex; TAA, tumour-associated antigen.

Fig. 3 ∣. Engineering CAR T cells to reduce their inherent immunogenicity.

Improving chimeric antigen receptor (CAR) design in order to limit inherent immunogenicity involves selecting tumour-binding moieties with the least immunogenic potential. Here, we show methods of replacing elements of single-chain variable fragments (scFvs) derived from mouse antibodies with human sequences or replacing the entire mouse-derived scFv with human-derived heavy-chain variable fragments or fully human scFvs. CARs with heavy-chain-only variable fragment tumour-recognition domains have the additional advantage of not requiring linkers, which are another possible source of immunogenicity. As an alternative to scFvs, the ligand of a tumour-associated receptor (or vice versa) can be attached to the constant regions of the CAR. Such constructs exploiting interactions between endogenous receptors and their ligands might enable tumour targeting with minimal risk of immunogenicity.

Fig. 4 ∣. Strategies to avoid immune elimination of allogeneic CAR T cells.

a ∣ The presence of incompatible major histocompatibility complexes (MHCs) can boost anti-chimeric antigen receptor (CAR) responses to allogeneic CAR T cells. Resting T cells express MHC class I (MHC I), while T cells can also upregulate MHC class II (MHC II) after activation. b ∣ MHC acts as a potent inhibitory receptor via the killer immunoglobulin-like receptor (KIR) on natural killer (NK) cells. Eliminating MHC I from the surface of resting CAR T cells can prevent alloimmune reactions while also increasing the risk of NK cell-mediated cytotoxicity. c ∣ Multiplex gene editing can be used to eliminate CAR T cell-surface MHC expression while also sparing the less-diverse human leukocyte antigen (HLA)-C subtype, which might minimize the risk of rejection by NK cells. Careful MHC matching of donor-derived products should also be performed. d ∣ Disrupting the functional expression of CIITA, which encodes the master transcriptional regulator of MHC II, or of the common constant chain CD74 could be used to remove MHC II from the cell surface without provoking alloimmune responses to activated CAR T cells. e ∣ Alloimmune defence receptors (ADRs) targeting the activation marker 4-1BB on allospecific T cells might improve the persistence of allogeneic CAR T cells. ADRs introduced into B2M-negative and MHC I-deficient CAR T cells are likely to actively eliminate the risk of NK cell lysis. f ∣ Site-specific insertion of universal MHC I constructs (such as those based on a decoy peptide-loaded monomorphic HLA-E) into the B2M gene prevent NK cell targeting of allogeneic-induced pluripotent stem-derived cells. g ∣ Alternatively, the overexpression of CD47 prevents effective alloreactive T cell/NK cell activation and antibody-dependent cellular cytotoxicity (ADCC) by acting as a ‘do not eat me’ signal.

Fig. 5 ∣. Monitoring, mitigation and management of anti-CAR immunity in the clinic.

Mitigation of anti-CAR immunity through lymphodepletion regimens can reduce the numbers of circulating lymphoid cells as well as of antigen-presenting cells prior to CAR T cell infusion. Furthermore, cytoreductive treatments might reduce the numbers of certain immunosuppressive cells in the tumour microenvironment, leading to tumour cell death and creating a pro-inflammatory milieu that promotes the antitumour efficacy of CAR T cells. The monitoring of patients receiving CAR T cells should begin as soon as a patient is considered for therapy. Conventional cancer treatment regimens, including monoclonal antibodies of mouse origin, can induce human anti-mouse antibodies (HAMAs) in patients^,. Therefore, careful evaluation of pre-existing immunity is important for the avoidance of anaphylaxis after CAR T cell infusion. Subsequently, monitoring in clinical trials should include surveillance for possible HAMAs and specific anti-CAR immune responses, including antibody and T cell analysis. The management of low-level anti-CAR immunity can be achieved using repeat lymphodepletion to reduce anti-CAR immunity prior to redosing with the same CAR T cell product. Humanized CAR T cell constructs could be considered in patients who progressed or relapsed after a previous infusion of CAR T cells containing mouse single-chain variable fragments (scFvs) or who required subsequent infusions to prevent disease progression. However, this approach could be associated with additional costs and/or treatment delays.