Development and Validation of a Gene Signature Classifier for Consensus Molecular Subtyping of Colorectal Carcinoma in a CLIA-Certified Setting

Abstract

Purpose: Consensus molecular subtyping (CMS) of colorectal cancer has potential to reshape the colorectal cancer landscape. We developed and validated an assay that is applicable on formalin-fixed, paraffin-embedded (FFPE) samples of colorectal cancer and implemented the assay in a Clinical Laboratory Improvement Amendments (CLIA)-certified laboratory.

Experimental design: We performed an in silico experiment to build an optimal CMS classifier using a training set of 1,329 samples from 12 studies and validation set of 1,329 samples from 14 studies. We constructed an assay on the basis of NanoString CodeSets for the top 472 genes, and performed analyses on paired flash-frozen (FF)/FFPE samples from 175 colorectal cancers to adapt the classifier to FFPE samples using a subset of genes found to be concordant between FF and FFPE, tested the classifier's reproducibility and repeatability, and validated in a CLIA-certified laboratory. We assessed prognostic significance of CMS in 345 patients pooled across three clinical trials.

Results: The best classifier was weighted support vector machine with high accuracy across platforms and gene lists (>0.95), and the 472-gene model outperforming existing classifiers. We constructed subsets of 99 and 200 genes with high FF/FFPE concordance, and adapted FFPE-based classifier that had strong classification accuracy (>80%) relative to "gold standard" CMS. The classifier was reproducible to sample type and RNA quality, and demonstrated poor prognosis for CMS1-3 and good prognosis for CMS2 in metastatic colorectal cancer (P < 0.001).

Conclusions: We developed and validated a colorectal cancer CMS assay that is ready for use in clinical trials, to assess prognosis in standard-of-care settings and explore as predictor of therapy response.

Trial registration: ClinicalTrials.gov NCT03436563.

Figure-1:

Flowchart showing approach development and validation of CMS classifier on colorectal cancer subtyping consortium (CRCSC) (1A) and development of NanoString classifier on colorectal cancer samples.

Figure-1:

Flowchart showing approach development and validation of CMS classifier on colorectal cancer subtyping consortium (CRCSC) (1A) and development of NanoString classifier on colorectal cancer samples.

Figure 2:

Sample-wise and Gene-wise correlation of paired FF/FFPE Samples: Figure- 2A: Histogram of sample-wise Spearman correlation of paired FF/FFPE values across all 472 CMS genes on Nanostring assay, with threshold of 0.75 marked with red vertical line. Figure-2B and 2C: Association of sample-wise FF/FFPE with RNA Quality: Scatterplot of gene-specific Spearman correlation of FF/FFPE vs. RNA quality of FF samples (2B, based on RIN) and FFPE samples (2C, based on % with 200nt). Figure-2D: Histogram of gene-wise Spearman correlation of paired FF/FFPE values based on samples with sample-wise correlation > 0.75, with thresholds to determine the top 100 and top 200 genes indicated by red and blue vertical lines, respectively.

Figure-3:

Bar chart and table showing 4-class accuracy of CMS classifiers, along with number (proportion) of samples classified to each CMS. We assess accuracy for classifier with top 100 genes in terms of FF/FFPE correlation for FFPE and FF, computed based on Nanostring measurements for FFPE and FF in current study (Nano FFPE-100, Nano FF-100) and based on Affymetrix measurements for FF in the Affy CRCSC validation data set (V2a, Affy FF-100), and for the full 472 gene classifier applied to FF samples run on Nanostring platform for current study (Nano FF-472) and FF samples run on Affymetrix in the Affymetrix CRCSC validation data set (Affy FF-472). Performance is summarized overall and for subsets of samples with high classification confidence (α>0.50, 0.80 or 0.90).

Figure-4:

Distribution of KRAS and BRAF mutations across CMS (4A) and correlation of CMS with overall survival (4B) in stage IV colorectal cancer.