Neoadjuvant PD-L1 plus CTLA-4 blockade in patients with cisplatin-ineligible operable high-risk urothelial carcinoma

Abstract

Immune checkpoint therapy is being tested in the neoadjuvant setting for patients with localized urothelial carcinoma^1,2, with one study reporting data in cisplatin-ineligible patients who received anti-PD-L1 monotherapy². The study reported that patients with bulky tumors, a known high-risk feature defined as greater than clinical T2 disease, had fewer responses, with pathological complete response rate of 17%². Here we report on the first pilot combination neoadjuvant trial ( NCT02812420 ) with anti-PD-L1 (durvalumab) plus anti-CTLA-4 (tremelimumab) in cisplatin-ineligible patients, with all tumors identified as having high-risk features (n = 28). High-risk features were defined by bulky tumors, variant histology, lymphovascular invasion, hydronephrosis and/or high-grade upper tract disease^3-5. The primary endpoint was safety and we observed 6 of 28 patients (21%) with grade ≥3 immune-related adverse events, consisting of asymptomatic laboratory abnormalities (n = 4), hepatitis and colitis (n = 2). We also observed pathological complete response of 37.5% and downstaging to pT1 or less in 58% of patients who completed surgery (n = 24). In summary, we provide initial safety, efficacy and biomarker data with neoadjuvant combination anti-PD-L1 plus anti-CTLA-4, which warrants further development for patients with localized urothelial carcinoma, especially cisplatin-ineligible patients with high-risk features who do not currently have an established standard-of-care neoadjuvant treatment.

Extended Data Fig 1:. Trial schema (NCT02812420)

Patients each had baseline TURBT for tumor resection, pathologic diagnosis, staging, and risk stratification. The first cohort of 28 patients each received durvalumab at 1500 mg plus tremelimumab 75 mg every 4 weeks for a total of 2 doses. The second cohort of 17 patients was planned to receive durvalumab at 1500 mg plus tremelimumab 300 mg × 1 dose and then only durvalumab at 1500 mg 4 weeks later (not reported in this manuscript). Surgery (radical cystectomy or applicable surgery to resect tumors) was performed 4–6 weeks after the last dose of treatment. A cystoscopy (or applicable imaging) with optional TURBT was performed at week 4 (post-treatment dose 1) to rule out patients with rapid disease progression. In the case of rapid disease progression, these patients were taken off the trial per clinical judgement from the treating physicians and the principal investigators. Pre- and post-treatment blood and tumor tissues were collected for correlative studies. TURBT-transurethral resection of bladder tumor. * A cystoscopy and optional TURBT prior to second dose.

Extended Data Fig. 2:. Response rate in association with adverse events or variant histology.

a. Pathologic response based on grade of immune-related adverse events. b. Pathologic response in pure urothelial carcinoma vs. urothelial carcinoma with variant histology.

Extended Data Fig. 3:. Distribution of PD-L1 expression in the immune and tumor cell compartments in pre-treatment tumor tissues of responders compared to non-responders.

a. Box plot showing density of immune cells expressing PD-L1 in pre-treatment tumor tissue samples from responders (R, n = 13, red) and non-responders (NR, n = 13, blue). b. Box plot showing density of tumor cells expressing PD-L1 in pre-treatment tumor tissue samples from responders (R, n = 13, red) and non-responders (NR, n = 13, blue). In the box plots of a and b, the horizontal bold line represents the median. The lower and upper hinges of the box correspond to the first and third quartiles (the 25th and 75th percentiles); the upper whisker extends from the hinge to the largest value no further than 1.5 × IQR from the hinge (where IQR is the distance between the first and third quartiles); and the lower whisker extends from the hinge to the smallest value at most 1.5 × IQR from the hinge. Statistical analysis was performed using two-sided Wilcoxon rank-sum test. P < 0.05 is considered statistically significant.

Extended Data Fig. 4:. Predicted neoantigen load in pre-treatment tumor tissue samples.

Box plot showing neoantigen load did not differ significantly between the R (n = 13, red) and NR (n = 10, blue) patients. The horizontal bold line represents the median. The lower and upper hinges of the box correspond to the first and third quartiles (the 25th and 75th percentiles); the upper whisker extends from the hinge to the largest value no further than 1.5 × IQR from the hinge (where IQR is the distance between the first and third quartiles); and the lower whisker extends from the hinge to the smallest value at most 1.5 × IQR from the hinge. The P value was calculated using two-sided Wilcoxon rank sum test. P < 0.05 is considered statistically significant.

Extended Data Fig. 5:. Mutational analysis of specific genes in pre-treatment tumor tissue samples in correlation with response.

a. CoOncoplot showing mutations in DNA-damage response (DDR) genes in responders (R, n = 13, right) and non-responders (NR, n = 10, left). b. CoOncoplot showing mutations in KRAS, PIK3CA, PBRM1, EGFR, NRAS, APC2 and FGFR genes in responders (R, n = 13, right) and non-responders (NR, n = 10, left). Each row represents a gene and the gene name is listed in the middle of the two heatmaps and their respective frequencies are listed on the left of the first heatmap (NR) and on the right of the second heatmap (R). Each column represents a patient. Each row represents a gene and the gene name is listed in the middle of the two heatmaps and their respective frequencies are listed on the left of the first heatmap (NR) and on the right of the second heatmap (R). The p-values comparing the distribution of mutations between R and NR are shown within parentheses next to each gene name. N/A denotes not applicable. The colors of rectangles in the body of the heatmap indicates different types of somatic mutations and the key identifying each mutation type is shown at the bottom. P values calculated using two-sided Fisher’s exact test.

Extended Data Fig. 6:. Biological responses in peripheral blood and tumor tissue samples after treatment with durvalumab plus tremelimumab.

a–e. Immune profiling by CyTOF analysis was performed on peripheral blood samples collected pre- and post-treatment. a-c, Categorical scatter plots showing frequency of subsets of CD4 T cells expressing PD-1, LAG3, and TIM3 pre- and post-treatment. Pre- indicates pre-treatment (blue circles; n = 22); Post1 indicates post-treatment, dose 1 (brown squares; n = 22); Post2 indicates post-treatment, dose 2 (pink triangles; n = 21). d, Categorical scatter plot showing frequency of ICOS + CD4 T cells pre- and post-treatment. Sample numbers and color schema same as in a-c. For a-d, error bars are shown as mean±standard deviation. e, Paired dot plots showing frequency of ICOS+ CD4 T cells in matched pre- and post-treatment (Post2) blood samples. NR indicates non-responders (n = 7); R indicates responders (n = 10). P values were calculated using the two-sided Wilcoxon rank-sum test in a-d and Wilcoxon signed-rank test in e. f, Representative multiplex immunofluorescence images (magnification; 20X) from one non-responder, NR (top) and one responder, R (bottom) patient at pre-treatment, Pre (left) and post-treatment, Post2 (right) time points. The samples were stained for the following markers: ICOS (red) and CD4 (green). Nuclei were stained with DAPI (blue). White arrows point to CD4 T cells expressing ICOS. Matched pre- and post-treatment samples from 10 patients (R = 5 and NR = 5) had similar analyses completed with corresponding images that were used to generate the data in g. g, Paired dot plots showing percentage of ICOS+CD4 T cells in matched pre- (blue circles) and post- (pink triangles) treatment tumor tissue samples from non-responders, NR (n = 5) and responders, R (n = 5). P values were calculated using the two-sided Wilcoxon rank-sum test. P < 0.05 is considered statistically significant.

Extended Data Fig. 7:. Distribution of B cells, CD4 T cells, and CD8 T cells in pre-treatment tumor tissues of responders compared to non-responders.

a. Box plot showing density of B cells (CD20+) in pre-treatment tumor tissue samples from responders (R, n = 10) and non-responders (NR, n = 9). b. Box plot showing density of CD4 T cells in pre-treatment tumor tissue samples from responders (R, n = 10) and non-responders (NR, n = 9). c. Box plot showing density of CD8 T cells in pre-treatment tumor tissue samples from responders (R, n = 10) and non-responders (NR, n = 9). In the box plots, the horizontal bold line represents the median. The lower and upper hinges of the box correspond to the first and third quartiles (the 25th and 75th percentiles); the upper whisker extends from the hinge to the largest value no further than 1.5 × IQR from the hinge (where IQR is the distance between the first and third quartiles); and the lower whisker extends from the hinge to the smallest value at most 1.5 × IQR from the hinge. Statistical analysis was performed using two-sided Wilcoxon rank-sum test. P < 0.05 is considered statistically significant.

Extended Data Fig. 8:. Association of POU2AF1 gene and TLS signature with response.

Pre-treatment tumor tissue samples from patients with TLS were analyzed by Nanostring. a, Box plot showing a comparison of POU2AF1 gene expression level between R (n = 9, red) and NR (n = 7, blue) patients. b, Box plot showing a comparison of 4-gene TLS signature derived from gene expression profiling of pre-treatment tumor tissue samples from R (n = 9, red) and NR (n = 7, blue) patients. In the box plots, the horizontal bold line represents the median. The lower and upper hinges of the box correspond to the first and third quartiles (the 25th and 75th percentiles); the upper whisker extends from the hinge to the largest value no further than 1.5 × IQR from the hinge (where IQR is the distance between the first and third quartiles); and the lower whisker extends from the hinge to the smallest value at most 1.5 × IQR from the hinge. P values were calculated using the two-sided unpaired student’s t–test, P < 0.05 is considered statistically significant.

Figure 1.. Safety and efficacy outcomes of patients with high-risk, cisplatin-ineligible urothelial carcinoma to neoadjuvant therapy with durvalumab plus tremelimumab.

a, pertinent treatment related adverse events, b, Pie chart of post-durvalumab + tremelimumab treatment pathologic stages in all 24 patients who completed cystectomy. c, Pie chart of post-durvalumab plus tremelimumab treatment pathologic stages in the 12 patients with 3-D mass/cT4a disease who completed cystectomy. d, CT scans showing a large bladder tumor at pre-treatment and e, Near complete resolution of the bladder tumor after durvalumab plus tremelimumab treatment. f, Overall survival (OS). All patients (N=28) were included in the OS analysis using Kaplan–Meier (KM) methods. One-year OS was 88.8% (SE=6.1%). g, Relapse-free survival (RFS). Patients who underwent cystectomy were included in the analysis (N=24). One-year RFS was 82.8% (SE=7.9%). pCR: Pathologic complete response; pT: Pathologic T stage; LN+: Lymph node positive disease.

Figure 2.. Exploratory biomarker analysis: gene expression, DNA alterations and tertiary lymphoid structures (TLS) in pre-treatment tumor tissue samples.

Pre-treatment tumor tissue samples from patients enrolled in the study were analyzed by nanostring, whole exome sequencing, immunohistochemistry, and multiplex immunofluorescence. a-e, The tumor and immune microenvironment molecular profiles and TLS density were compared between responders (R, red) and non-responders (NR, blue) a, Box plot showing a comparison of tGE8 transcriptional signature derived from gene expression profiling of pre-treatment tumor tissue samples from R (n=9) and NR (n=12) patients. The number of patients (n) in each cohort are indicated below the x-axis. P values were calculated using the two-sided unpaired student’s t–test. b, Box plot showing tumor mutation burden (TMB, number of somatic mutations per megabase) did not differ significantly between the R (n=13) and NR (n=10) groups. The number (n) of patient samples analyzed in each group are also listed below the x-axis. P values were calculated using two-sided Wilcoxon rank-sum test. c, Oncoplot showing the somatic mutation landscape of the most frequently mutated genes. Each row represents a gene, which are ordered based on decreasing mutation frequencies from top to bottom. The gens are listed on the left and their respective frequencies are listed on the right of the heatmap. Each column represents a patient and the color bar at the bottom shows clinical response for each patient, which is color coded for R (red) and NR (blue). The number of patients in each response category: NR, n=10 and R, n=13 are also listed below the color bar. The colors of rectangles in the body of the heatmap indicates different types of somatic mutations and the key identifying each mutation type is shown at the bottom below the color bar for response. The bar plot on the top shows the counts of mutations for each patient sample and the colors in the bar plots correspond to the colors showing mutation types in the body of the heatmap. The bar plot on the right side shows the counts of mutations for each gene and the colors in the bar plots correspond to the colors showing mutation types in the body of the heatmap. d, Box plot showing association of tertiary lymphoid structures (TLS) in pre-treatment tumor tissue samples with response, higher TLS density in responders (R, n=13) compared to non-responders (NR, n=13). The number (n) of patient samples analyzed in each group are also listed below the x-axis. P values were calculated using two-sided Wilcoxon rank-sum test. For the box plots in a, b, and d: The horizontal bold line represents the median. The lower and upper hinges of the box correspond to the first and third quartiles (the 25th and 75th percentiles); the upper whisker extends from the hinge to the largest value no further than 1.5 × IQR from the hinge (where IQR is the distance between the first and third quartiles); and the lower whisker extends from the hinge to the smallest value at most 1.5 × IQR from the hinge. e, Stacked bar plot showing distribution of responder and non-responder patients stratified by pre-treatment TLS density (low versus high). A significant difference was observed between the two groups with the TLS^high group showing higher proportion of responders. Actual number of patients in each group are indicated within the bar plots. P values shown on the graph were calculated using two-sided Fisher’s exact test. f, Representative single stain IHC images showing a TLS from baseline tumor tissue of a responder patient; however, 26 patients (R=13 and NR=13) had similar analyses completed with corresponding images that were used to generate the data in d and e. Images of a TLS at 10X magnification are shown for haematoxylin and eosin (H&E) staining and single stain IHC of CD20, CD4, CD8, FoxP3, and CD21. g, Representative images from multiplex immunofluorescence staining of pre-treatment tumor tissue of a responder patient showing a tertiary lymphoid structure (TLS) using the following markers: CD20, CD4, CD21, CD8, FOXP3 and DAPI. Original magnification, 20X. Images were reproduced in samples from 4 other patients in order to confirm that the TLS structures were comprised of CD4 T cells, CD8 T cells and CD20 B cells. h, Kaplan-Meier estimates of overall survival (OS, n=26 patients) by pre-treatment TLS density shown by high (TLS^high, turquoise) and low (TLS^low, salmon) groups. The median pre-treatment TLS density (0.155 TLS/mm²) was used as the cutoff to segregate the groups. Patients with a TLS density above the median were grouped to the TLS^high group and the remaining patients were grouped to the TLS^low group. Patient numbers are included in the table below the graph and P values were calculated by two-sided log-rank test. Overall survival was defined as the time interval between first dose of treatment and death or last contact. i, Kaplan-Meier estimates of relapse free survival (RFS, n=23 patients) by pre-treatment TLS density as described in h, above. Patient numbers are included in the table below the graph and P values were calculated by log-rank test. Relapse free survival was defined as the time between cystectomy and death, relapse, or last follow up.