Nanostring CMS Classifier Performance: Performance of Nanostring 100 gene CMS classifier applied to FFPE samples (6A and 6C) and FF samples (6B and 63D). The top two figures plot 4-class accuracy vs. classification confidence, with the dots marking individual samples either correctly (1.0) or incorrectly (0.0), with color indicat-ing correct CMS. The line contains a generalized additive model (GAM) fit to these data with 95% pointwise confidence bands, and demonstrates that samples classified with greater confidence were more likely to be cor-rectly classified. Figure 6C and 6D plot 4-class accuracy vs. RNA quality, defined as 0nt (FFPE) or RIN (FF). Note that there is little if any association of CMS accuracy with RNA quality, suggesting that the perfor-mance of classifier is robust to RNA quality in this study.
ARTICLE ABSTRACT
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.
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.
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).
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.
