Technical development and validation of a clinically applicable microenvironment classifier as a biomarker of tumour hypoxia for soft tissue sarcoma

Abstract

Background: Soft tissue sarcomas (STS) are rare, heterogeneous tumours and biomarkers are needed to inform management. We previously derived a prognostic tumour microenvironment classifier (24-gene hypoxia signature). Here, we developed/validated an assay for clinical application.

Methods: Technical performance of targeted assays (Taqman low-density array, nanoString) was compared in 28 prospectively collected formalin-fixed, paraffin-embedded (FFPE) biopsies. The nanoString assay was biologically validated by comparing to HIF-1α/CAIX immunohistochemistry (IHC) in clinical samples. The Manchester (n = 165) and VORTEX Phase III trial (n = 203) cohorts were used for clinical validation. The primary outcome was overall survival (OS).

Results: Both assays demonstrated excellent reproducibility. The nanoString assay detected upregulation of the 24-gene signature under hypoxia in vitro, and 16/24 hypoxia genes were upregulated in tumours with high CAIX expression in vivo. Patients with hypoxia-high tumours had worse OS in the Manchester (HR 3.05, 95% CI 1.54-5.19, P = 0.0005) and VORTEX (HR 2.13, 95% CI 1.19-3.77, P = 0.009) cohorts. In the combined cohort, it was independently prognostic for OS (HR 2.24, 95% CI 1.42-3.53, P = 0.00096) and associated with worse local recurrence-free survival (HR 2.17, 95% CI 1.01-4.68, P = 0.04).

Conclusions: This study comprehensively validates a microenvironment classifier befitting FFPE STS biopsies. Future uses include: (1) selecting high-risk patients for perioperative chemotherapy; and (2) biomarker-driven trials of hypoxia-targeted therapies.

Fig. 1. Biological validation of a nanoString assay for the 24-gene hypoxia signature demonstrates that the targeted assay measures hypoxia in vitro and in vivo.

Heatmaps of the 24 hypoxia genes (red—low expression, blue – high expression) in (a). STS cell lines (HT1080 and SKUT1) cultured under decreasing oxygen concentration (21%, 1%, 0.2%, 24 h of exposure); b FFPE tumour samples (CAIX protein expression negative versus positive) from the VORTEX-Biobank (n = 152); c protein expression of HIF-1α in tumours (n = 136) classified as hypoxia-low (red) versus hypoxia high (blue) by the 24-gene signature. d Protein expression of CAIX in tumours (n = 152) classified as hypoxia-low (red) versus hypoxia high (blue) by the 24-gene signature. Box and whisker plots show the median, interquartile range and range for the percentage of tumour cells stained (immunohistochemistry).

Fig. 2. Technical performance of the nanoString assay for the 24-gene hypoxia signature.

a The raw (pre-normalisation data) gene expression profiles are shown for a single reference RNA sample in the first run versus each subsequent repeat (n = 12 repeats). Each data point is the expression value for an individual hypoxia gene. Spearman’s ρ > 0.99 for all repeats. The mean versus variance of the raw expression values for each gene (black data points are hypoxia genes, and green data points are endogenous control genes) are plotted for (b). the Manchester cohort; and c the VORTEX-Biobank cohort demonstrating low variance of the endogenous controls compared to hypoxia signature genes. RNA quality control measures are shown for hypoxia-low versus hypoxia-high samples from the combined cohort (n = 280). No statistically significant differences (Mann–Whitney U test) were found in (d). RNA yield; e RNA integrity number (RIN); f DV200 (percentage of RNA fragments over 200 bases) or g sample age.

Fig. 3. Clinical validation of a 24-gene hypoxia-associated signature in two cohorts when measured in routine pre-treatment FFPE biopsies using a targeted nanoString assay.

The graphs show Kaplan–Meier survival estimates in patients with hypoxia-low versus hypoxia-high tumours by the 24-gene nanoString hypoxia assay in the Manchester (n = 126), VORTEX-Biobank (n = 154) and combined (n = 280) cohorts. a Overall survival in the Manchester cohort; b overall survival in the VORTEX-Biobank cohort; c local recurrence-free survival in the combined cohort; d overall survival in patients stratified by hypoxia and Sarculator 10-year pOS in the combined cohort. A targeted nanoString assay was used to generate gene expression data from formalin-fixed paraffin-embedded (FFPE) tumour samples. Un-shrunken hypoxia-low and hypoxia-high centroids from the 24-gene STS hypoxia signature in the original training cohort were used to generate hypoxia class predictions. Each new tumour sample was assigned to the nearest class centroid using the Spearman distance. Individual 10-year predicted overall survival was calculated using Sarculator. Patients were classified as clinically high risk (10-year pOS <60%) or clinically low-risk (10-year pOS ≥60%).