Phase II Clinical and Translational Study of Everolimus ± Paclitaxel as First-Line Therapy in Cisplatin-Ineligible Advanced Urothelial Carcinoma

Abstract

Background: Treatment options have been historically limited for cisplatin-ineligible patients with advanced urothelial carcinoma (UC). Given the need for alternatives to platinum-based chemotherapy, including non-chemotherapy regimens for patients with both impaired renal function and borderline functional status, in 2010 (prior to the immune checkpoint blockade era in metastatic UC), we initiated a phase II trial to test the activity of everolimus or everolimus plus paclitaxel in the cisplatin-ineligible setting.

Methods: This was an open-label phase II trial conducted within the US-based Hoosier Cancer Research Network (ClinicalTrials.gov number: NCT01215136). Patients who were cisplatin-ineligible with previously untreated advanced UC were enrolled. Patients with both impaired renal function and poor performance status were enrolled into cohort 1; patients with either were enrolled into cohort 2. Patients received everolimus 10 mg daily alone (cohort 1) or with paclitaxel 80 mg/m2 on days 1, 8, and 15 of each 28-day cycle (cohort 2). The primary outcome was clinical benefit at 4 months. Secondary outcomes were adverse events, progression-free survival (PFS), and 1-year overall survival (OS). Exploratory endpoints included genomic correlates of outcomes. The trial was not designed for comparison between cohorts.

Results: A total of 36 patients were enrolled from 2010 to 2018 (cohort 1, N = 7; cohort 2, N = 29); the trial was terminated due to slow accrual. Clinical benefit at 4 months was attained by 0 (0%, 95% confidence interval [CI] 0-41.0%) patients in cohort 1 and 11 patients (37.9%, 95% CI 20.7-57.7%) in cohort 2. Median PFS was 2.33 (95% CI 1.81-Inf) months in cohort 1 and 5.85 (95% CI 2.99-8.61) months in cohort 2. Treatment was discontinued due to adverse events for 2 patients (29%) in cohort 1 and 11 patients (38%) in cohort 2. Molecular alterations in microtubule associated genes may be associated with treatment benefit but this requires further testing.

Conclusion: Everolimus plus paclitaxel demonstrates clinical activity in cisplatin-ineligible patients with metastatic UC, although the specific contribution of everolimus cannot be delineated. Patients with both impaired renal function and borderline functional status may be difficult to enroll to prospective trials. (ClinicalTrials.gov Identifier NCT01215136).

Keywords: cisplatin-ineligible; everolimus; genomic; paclitaxel; urothelial cancer.

Figure 1.

Kaplan-Meier curves for (A) progression-free survival and (B) overall survival, stratified by cohort. The median progression-free survival was 2.33 (95% CI 1.81-Inf) months in cohort 1 and 5.85 (95% CI 2.99-8.61) months in cohort 2. Median overall survival was 4.5 (95% CI 2.33-Inf) months in cohort 1 and 10.9 (95% CI 6.97-16.4) months in cohort 2.

Figure 2.

Mutational landscape of whole-exome sequencing cohort (N = 17). Genes mutated in at least three samples in the cohort are listed. Each column represents one sample. The vertical bar plot depicts tumor mutation burden in each sample. The horizontal bar plot summarizes the number and type of mutations (by color) for each gene. The tracks along the bottom provide additional clinical context, color coding each sample according to the patient’s gender and clinical outcome. The most commonly mutated gene in the cohort was TP53 (N = 9); 8 of 9 patients with TP53 mutations were responders (Fisher’s exact P = .29). Other notable recurrent mutations included the microtubule-related genes MACF1 (N = 4) and FRY (N = 4). All 6 patients with mutations in either MACF1 or FRY were responders, although the association was not statistically significant (Fisher’s exact P =.24 two sided; P =.14 one sided).

Figure 3.

A heatmap of the genome-wide copy number variation (CNV) profiles based on median log2ratio, stratified by response. Individual patient samples are shown along the y-axis with amplification events in red and loss events in blue. The number of CNV events at each genomic locus for responders and nonresponders are summarized as bar plots at the top for both responders and non-responders. Copy number segmentation profiles were qualitatively similar between responders and non-responders.

Figure 4.

Significantly enriched amplification (red) and deletion (blue) events in the overall cohort of 17 samples, using GISTIC 2.0. Annotated cytobands indicate significant calls (FDR < 0.1) with the peaks corresponding to the significance value on the x-axis. The most significant regions included 2q11.2, 2q11.1 for gains and 1p36.13, 7q22.1, 12q12, 2q11.1 for losses. The significantly amplified regions included several genes involved in fibroblast growth factor signaling, upstream of the PI3K/AKT/mTOR pathway: FGF3, FGF4, FGF9, FGF19, and FRS2.

Figure 5.

Mutational signature analysis revealed that samples fell into two clusters with distinct patterns of single-nucleotide alterations throughout the genome. Cluster 1 (N = 8) was dominated by COSMIC v2 signatures 2 and 13, which are associated with APOBEC cytidine deaminases. Cluster 2 (N = 6) was characterized by dominance of signature 5, which has been associated with ERCC2 mutations. Mutational signature clusters were not associated with response (Fisher’s exact P = 1 two-sided).

Figure 6.

Clustering of samples by transcriptomic profile using principal components analysis failed to identify separate clusters based on paclitaxel treatment responsiveness. R: responders; P: nonresponders.