Performance of gene expression–based single sample predictors for assessment of clinicopathological subgroups and molecular subtypes in cancers: a case comparison study in non-small cell lung cancer. (4th February 2019)

• Record Type: Journal Article
• Authors: Cirenajwis, Helena; Lauss, Martin; Planck, Maria; Vallon-Christersson, Johan; Staaf, Johan
• Is Part Of: Briefings in bioinformatics. Volume 21:Number 2(2020)
• Page Start: 729
• Page End: 740
• Publication Date: 2019-02-04
• Subjects: single sample predictor -- non-small cell lung cancer -- classification -- gene pair -- molecular subtype -- tumor histology; Genetics -- Data processing -- Periodicals; Molecular biology -- Data processing -- Periodicals; Genomes -- Data processing -- Periodicals; 572.80285
• DOI: 10.1093/bib/bbz008
• Languages: English
• ISSNs: 1467-5463

Abstract

Abstract: The development of multigene classifiers for cancer prognosis, treatment prediction, molecular subtypes or clinicopathological groups has been a cornerstone in transcriptomic analyses of human malignancies for nearly two decades. However, many reported classifiers are critically limited by different preprocessing needs like normalization and data centering. In response, a new breed of classifiers, single sample predictors (SSPs), has emerged. SSPs classify samples in an N-of-1 fashion, relying on, e.g. gene rules comparing expression values within a sample. To date, several methods have been reported, but there is a lack of head-to-head performance comparison for typical cancer classification problems, representing an unmet methodological need in cancer bioinformatics. To resolve this need, we performed an evaluation of two SSPs [k-top-scoring pair classifier (kTSP) and absolute intrinsic molecular subtyping (AIMS)] for two case examples of different magnitude of difficulty in non-small cell lung cancer: gene expression–based classification of (i) tumor histology and (ii) molecular subtype. Through the analysis of ~2000 lung cancer samples for each case example ( n = 1918 and n = 2106, respectively), we compared the performance of the methods for different sample compositions, training data set sizes, gene expression platforms and gene rule selections. Three main conclusions are drawn from the comparisons: both methods are platform independent, they select largely overlapping gene rules associated with actual underlying tumor biology and, for large training data sets, they behave interchangeably performance-wise. While SSPs like AIMS and kTSP offer new possibilities to move gene expression signatures/predictors closer to a clinical context, they are still importantly limited by the difficultness of the classification problem at hand.