The effect of low-dose IL-2 and Treg adoptive cell therapy in patients with type 1 diabetes

Abstract

BACKGROUNDA previous phase I study showed that the infusion of autologous Tregs expanded ex vivo into patients with recent-onset type 1 diabetes (T1D) had an excellent safety profile. However, the majority of the infused Tregs were undetectable in the peripheral blood 3 months postinfusion (Treg-T1D trial). Therefore, we conducted a phase I study (TILT trial) combining polyclonal Tregs and low-dose IL-2, shown to enhance Treg survival and expansion, and assessed the impact over time on Treg populations and other immune cells.METHODSPatients with T1D were treated with a single infusion of autologous polyclonal Tregs followed by one or two 5-day courses of recombinant human low-dose IL-2 (ld-IL-2). Flow cytometry, cytometry by time of flight, and 10x Genomics single-cell RNA-Seq were used to follow the distinct immune cell populations' phenotypes over time.RESULTSMultiparametric analysis revealed that the combination therapy led to an increase in the number of infused and endogenous Tregs but also resulted in a substantial increase from baseline in a subset of activated NK, mucosal associated invariant T, and clonal CD8+ T cell populations.CONCLUSIONThese data support the hypothesis that ld-IL-2 expands exogenously administered Tregs but also can expand cytotoxic cells. These results have important implications for the use of a combination of ld-IL-2 and Tregs for the treatment of autoimmune diseases with preexisting active immunity.TRIAL REGISTRATIONClinicalTrials.gov NCT01210664 (Treg-T1D trial), NCT02772679 (TILT trial).FUNDINGSean N. Parker Autoimmune Research Laboratory Fund, National Center for Research Resources.

Keywords: Autoimmunity; Clinical Trials; Diabetes; Immunotherapy; T cells.

Figure 1. Metabolic assessments.

(A) (Left column) C-peptide AUC is reported for fasting 4-hour mixed meal tolerance test (MMTT) without carbohydrate restriction for 3 days preceding testing. The target glucose level at the start of the test was between 70 and 200 mg/dL. Regular insulin or short-acting insulin analogs were allowed up to 6 and 2 hours before the test, respectively, to achieve the desired glucose level. The baseline blood samples (−10 minutes and 0 minutes) were drawn, and then patients drank Boost high protein nutritional energy drink (Nestle Nutrition) at 6 kcal/kg (1 kcal/mL) to a maximum of 360 mL. Blood was drawn at 15, 30, 60, 90, 120, 150, 180, 210, and 240 minutes following Boost dose. C-peptide AUC was calculated using the trapezoid rule. (Middle column) Hemoglobin A1c (HbA1c). (Right column) Insulin use. Insulin use for the 3 days immediately preceding the scheduled visit was self-reported. The average total insulin (long acting + short acting) use per day normalized to weight is reported. Table shows Treg and IL-2 dosage of each patient. MIU, million international units. (B) Percentage of relative C-peptide loss up to 104 and 78 weeks in patients from cohorts 1 and 2, respectively, of the TILT trial (2 left graphs) and from the placebo cohort of the AIDA and NT-14 trial (right graph). (C) Comparison of percentage of relative C-peptide loss at the indicated time point between the patients from TILT and placebo groups.

Figure 2. Longitudinal tracking of in vitro–expanded Tregs postinfusion.

(A) Graphs show the percentage of DNA enrichment with deuterium (²H) in PBMC sorted Treg cells from TILT trial patients. Enlarged view of the ²H labeling kinetics up to 63 days is represented in the upper right of each graph. Black dashed lines indicate the fifth day of each IL-2 infusion course. Table shows Treg and IL-2 dosage of each patient. (B) Graphs show the percentage of deuterated DNA enrichment normalized to the maximum value in total PBMCs over time in each patient from the TILT trial. Light blue lines and gray areas show superimposition to normalized percentage of deuterated DNA enrichment of the T1D trial. Table shows Treg dosage. (C) Percentage of ²H level in postinfusion sorted non-Tregs versus Tregs in TILT trial patients. Paired 2-tailed t tests were performed in order to assess statistical significance. *P < 0.05.

Figure 3. Low-dose IL-2 induces activation phenotype in the Treg subset at a protein level.

(A) Graphs represent the percentage of Tregs (left column) by flow cytometry at the indicated time points. TILT trial patient data are shown in upper graphs, and the Treg-T1D trial patients are represented in the lower graphs. Red asterisks indicate patients who received only 1 dose of IL-2. Tables indicate dosage of IL-2 and Tregs for each patient. Paired 2-tailed t tests were performed in order to assess statistical significance. (B and C) Percentage of FOXP3⁺ and median expression of FOXP3⁺ as well as median expression of CD27, CTLA-4, and HLA-DR was assessed by CyTOF. Data were normalized; cell populations were gated manually in CellEngine. Populations were then exported for analysis in R, and marker expression values were then arsinh-transformed with a cofactor of 5 and represented in dot plots. The results are plotted into 2 separated batches (batches 1 and 2) due to batch effect affecting the comparison of the samples within the same analysis pipeline (batches layout of the samples, Supplemental Table 3). Asterisks indicate significance relative to the control group determined by 1-way ANOVA. ***P < 0.001; ****P < 0.0001.

Figure 4. Low-dose IL-2 induces activation phenotype in the Treg subset at the mRNA level.

10x Genomics single-cell RNA-Seq data were analyzed by Scanpy package. (A) UMAPs show expression of FOXP3 in cluster 11 from UMAP in Supplemental Figure 2 in the TILT patient samples and Treg-T1D patient samples. (B) Volcano plots represent differential gene expression analysis of the Treg cell compartment (Supplemental Figure 2, cluster 11) from TILT and Treg-T1D patients at day 0 (left volcano plot) and day 7 (right volcano plot). Downregulated (red dots) and upregulated genes (green dots) are indicated in log₂(fold change) (log2FC) with a P < 0.005. Gene expressions with P values greater than 0.005 were filtered out. Vertical dashed lines represent thresholds of log2FC of –0.6 and 0.6 corresponding to a fold change of 1.5 times. Table indicates the log2FC values of the indicated genes. Blue cells indicate nonsignificant genes filtered out due to a P > 0.005. (C) Dot plot shows longitudinal changes over time of percentage of FOXP3⁺ cells in cluster 11 for the 2 trials. Asterisks indicate significance relative to the control group determined by 1-way ANOVA. *P < 0.05; **P < 0.01; ***P < 0.001; ****P < 0.0001. (D) Graphs represent mean mRNA expression of the indicated genes normalized to day 0 for the patients of each clinical trial group (TILT in upper graphs and Treg-T1D in lower graphs). Red asterisks indicate patients that received only 1 dose of IL-2. (E) UMAP and leiden clustering of the Treg cluster 11. Heatmap shows Treg markers’ and activation markers’ mean expression in the indicated clusters. Stacked bar chart shows the percentage of cells in each cluster in Treg-T1D versus TILT patients.

Figure 5. Low-dose IL-2 induces cytotoxic phenotype in the NK cell subset and mucosal invariant associated T cell subset.

10x Genomics single-cell RNA-Seq data were analyzed by Scanpy package. (A) Volcano plots represent differential gene expression analysis of the NK cell compartment (Supplemental Figure 2, cluster 4) from TILT and Treg-T1D patients at day 0 (left volcano plot) and day 7 (right volcano plot). Downregulated (red dots) and upregulated genes (green dots) are indicated in log2FC with a P < 0.005. Gene expressions with P values greater than 0.005 were filtered out. Vertical dashed lines represent thresholds of log2FC of –0.6 and 0.6 corresponding to a fold change of 1.5 times. Table indicates the log2FC values of the indicated genes. Blue cells indicate nonsignificant genes filtered out due to a P > 0.005. (B) Percentage of GZMB⁺ cells in the NK cluster (Supplemental Figure 2, cluster 4) were calculated and shown on upper graphs for TILT trial patients and lower graphs for Treg-T1D trial patients. Tables indicate dosage of IL-2 and Tregs for each patient. (C) Dot plot represents percentage over time of GZMB⁺ cells in NK clusters in TILT and Treg-T1D trial patients. Asterisks indicate significance relative to the control group determined by 1-way ANOVA. *P < 0.05. (D) Graphs show correlation of day 0 to day 28 changes in the percentage of GZMB⁺ NK and day 0 to day 7 changes in the percentage of FOXP3⁺ Treg cells in TILT patients (upper graph) and Treg-T1D patients (lower graph). (E) Volcano plots represent differential gene expression analysis of the MAIT cell compartment (Supplemental Figure 2, cluster 6) from TILT and Treg-T1D patients at day 0 (left volcano plot) and day 7 (right volcano plot). Table indicates the log2FC values of the indicated genes. Blue cells indicate nonsignificant genes filtered out due to a P > 0.005.

Figure 6. Low-dose IL-2 treatment promotes a cytotoxic phenotype in the CD8⁺ T cell subset.

(A) Flow cytometry analysis shows the percentage of total CD3⁺CD8⁺ T cells (left column) and CD8⁺CD25⁺ T cells (right column) at the collected time points. Upper graphs represent patients from the TILT trials, and lower graphs represent patients from the Treg-T1D trial. The table indicates the dosage of IL-2 and Tregs for each patient. (B) Single-cell RNA-Seq data were analyzed by Scanpy package. Volcano plots represent differential gene expression analysis of the PRF1⁺GZMB⁺CD8 T cell compartment (Supplemental Figure 2, cluster 5) from TILT and Treg-T1D patients at day 0 (left volcano plot) and day 7 (right volcano plot). Downregulated (red dots) and upregulated genes (green dots) are indicated in log2FC with a P < 0.005. Gene expressions with a P values greater than 0.005 were filtered out. Vertical dashed lines represent thresholds of log2FC of –0.6 and 0.6 corresponding to a fold change of 1.5 times. Table indicates the log2FC values of the indicated genes. Blue cells indicate non-significant genes filtered out due to a P > 0.005. (C) Table indicates the log2FC values of the indicated genes. Blue cells indicate nonsignificant genes filtered out due to a P > 0.005. (D) Dot plot shows PRF1 mRNA mean expression over time in PRF1⁺GZMB⁺CD8⁺ T cell cluster in TILT and Treg-T1D trial patients. Asterisks indicate significance relative to the control group determined by 1-way ANOVA. *P < 0.05.

Figure 7. Low-dose IL-2 increases clonal expansion of the PRF1⁺GZMB⁺CD8⁺ T cell compartment.

(A) Clonal diversity from the Treg, PRF1⁺GZMB⁺CD8 T cell, and total CD3⁺ populations was evaluated by the calculation of the Gini index. Dot plots show values of Gini index for each patient from the TILT and the Treg-T1D trial. Unpaired 2-tailed t tests were performed in order to assess statistical significance. (B) Left UMAP plot represents clusters of immune cells identified in Supplemental Figure 2. Density plots on the right represent mapping of TCR clones expanded more than 30 times in each clinical trial group. (C) Heatmaps represent cytotoxicity and activation markers gene expression (log normalized) of all the cells expressing expanded TCRs. Left y axis links the patient to the depicted expanded TCRs.