Role of CAR T Cell Metabolism for Therapeutic Efficacy

Abstract

Chimeric antigen receptor (CAR) T cells hold enormous potential. However, a substantial proportion of patients receiving CAR T cells will not reach long-term full remission. One of the causes lies in their premature exhaustion, which also includes a metabolic anergy of adoptively transferred CAR T cells. T cell phenotypes that have been shown to be particularly well suited for CAR T cell therapy display certain metabolic characteristics; whereas T-stem cell memory (T_SCM) cells, characterized by self-renewal and persistence, preferentially meet their energetic demands through oxidative phosphorylation (OXPHOS), effector T cells (T_EFF) rely on glycolysis to support their cytotoxic function. Various parameters of CAR T cell design and manufacture co-determine the metabolic profile of the final cell product. A co-stimulatory 4-1BB domain promotes OXPHOS and formation of central memory T cells (T_CM), while T cells expressing CARs with CD28 domains predominantly utilize aerobic glycolysis and differentiate into effector memory T cells (T_EM). Therefore, modification of CAR co-stimulation represents one of the many strategies currently being investigated for improving CAR T cells' metabolic fitness and survivability within a hostile tumor microenvironment (TME). In this review, we will focus on the role of CAR T cell metabolism in therapeutic efficacy together with potential targets of intervention.

Keywords: CAR T cells; bioenergetics; immune escape; immunometabolism; metabolism; tumor microenvironment.

Figure 1

Current barriers in CAR T cell therapy. Clinical efficacy of CAR T cell therapy can be limited by various factors. The heterogeneity of tumors can give rise to variants that do not carry the target antigen on their surface. Immune checkpoint molecules (e.g., PD-L1 on tumor and/or stroma cells that binds to PD-1 on CAR T cells) can slow down anti-tumor activity. Overall, CAR T cells enter an immunosuppressive TME with tolerance-promoting cells such as myeloid-derived suppressor cells (MDSCs), tumor associated macrophages (TAM) or T_Regs and inhospitable metabolic conditions (i.e., hypoxia, acidosis, oxidative stress, depletion of critical nutrients, etc.). In fact, the TME and the tumor cells within can represent an impermeable obstacle for CAR T cells due to their poor trafficking resulting in an insufficient infiltration of tumor tissue. In addition, CAR T cells’ (over)activation can lead to severe and potentially life-threatening toxicities with cytokine release (CRS); immune effector cell-associated neurotoxicity syndrome (ICANS) and long-lasting hematotoxicity as the most common.

Figure 2

T cell differentiation is interconnected to metabolism. As naïve T cells (T_N) leave the thymus and undergo antigen presentation, they experience a metabolic switch from oxidative phosphorylation (OXPHOS) to glycolysis as they become effector T cells (T_EFF). After antigen clearance, a small subset of T cells become stem central (T_SCM) and central memory (T_CM) T cells, which mostly rely on OXPHOS. In case of TCR re-engagement, effector memory T cells (T_EM) rapidly shift to a high glycolytic activity that supports their strong effector function. Lastly, terminally differentiated T cells (T_EMRA) appeared rather senescent. T cell subsets that rely more on OXPHOS (T_N, T_SCM, T_CM) are characterized by stemness, self-renewal and proliferation capacity. On the contrary, glycolysis-fueled cells (T_EM, T_EFF) display high cytotoxic function that ultimately leads them to senescence (T_EMRA).

Figure 3

Metabolic barriers for T cells in the TME. The metabolic fitness of T cells can be compromised in a variety of ways within the TME. Critical nutrients such as glucose (GLUC) are depleted. Bioenergetically active tumors secrete bioactive molecules such as lactic acid (LACT), which impedes glycolysis. Dying cancer cells release vast amounts of potassium (K) that limits glucose and amino acid uptake. The two ectonucleotidases CD39/CD73 degrade ATP into adenosine (ADE), which also impairs metabolic T cell fitness. Increased levels of lipids together with an increased fatty acid uptake of TME-infiltrating T cells promotes exhaustion and lipotoxicity.

Figure 4

Impact of CAR design on CAR T cell metabolism. (A) Co-stimulatory signaling domains (CD28, 4-1BB, CD28+4-1BB) of CARs can impact several metabolic parameters such expression of glucose transporter (GLUT), extracellular acidification rate (ECAR), oxygen consumption rate (OCR) or spared respirator capacity (SRC). (B) Ubiquitination (Ub) and tonicity of CARs with impact on bioenergetics (and exhaustion).

Figure 5

Strategies to modulate CAR T cell metabolism. (A) Strategies to block glycolysis. Cell culturing conditions can be improved by optimizing the use serum-containing and/or serum-free media. Treatment with cytokines such as IL-7, IL-15 or IL-21 led to the generation of the preferred T cell phenotype. Metabolic skewing (towards FAO and OXPHOS) can also be achieved by interfering with glycolysis by interfering with glycolytic enzymes such as hexokinase 2 (HK2) or glycolytic signaling such as the PI3K/Akt/mTOR axis. (B) Strategies to enhances oxidative phosphorylation (OXPHOS). Genetic engineering can be utilized for driving mitochondrial biogenesis and fitness (by, e.g., PGC1α) or metabolizing/redirect substrates such as 2-HG (by, e.g., D2HGDH), kynurenine (by, e.g., kynureninase) or O₂ (by, e.g., LbNOX). Supplementation of nutrients such as inosine, L-arginine or short chain fatty acids (SCFAs) could also have a beneficial effect for CAR T cell metabolism and stemness. Abbreviations: Phosphoinositide 3-kinase (PI3K), protein kinase B (Akt), mammalian target of rapamycin (mTOR), interleukin (IL), interleukin receptor (IL-R), fatty acid oxidation (FAO), oxidative phosphorylation (OXPHOS), Peroxisome proliferator-activated receptor-gamma coactivator alpha (PGC1α), short chain fatty acids (SCFA), 2-Deoxy-D-glucose (2-DG), hexokinase 2 (HK2), glucose-6-phosphate (glucose-6P), tricarboxylic acid (TCA), alpha-ketoglutarate (α-KG), 2-hydroxyglutarate (2-HG), D-2-hydroxyglutarate dehydrogenase (D2HGDH), Kynureninase (KYNU), 3-hydroxyanthranilic acid (3hAn), alanine (Ala), Lactobacillus brevis NADH oxidase (LbNOX).