Large compendia of gene expression data have proven valuable for the discovery of novel biological relationships. The majority of available RNA assays are run on microarray, while RNA-seq is becoming the platform of choice for new experiments. The data structure and distributions between the platforms differ, making it challenging to combine them.
University of Pennsylvania researchers performed supervised and unsupervised machine learning evaluations, as well as differential expression analyses, to assess which normalization methods are best suited for combining microarray and RNA-seq data. They found that quantile and Training Distribution Matching normalization allow for supervised and unsupervised model training on microarray and RNA-seq data simultaneously. Nonparanormal normalization and z-scores are also appropriate for some applications, including differential expression analysis.
Overview of supervised and unsupervised machine learning experiments
(A) 520 TCGA Breast Cancer samples run on both microarray and RNA-seq were split into a training (2/3) and holdout set (1/3). (B) RNA-seq’d samples were ‘titrated’ into the training set, 10% at a time (0-100%) resulting in eleven training sets for each normalization method. (C) Machine learning applications. The researchers used three supervised algorithms to train multi-class (BRCA PAM50 subtype) classifiers on each training set and tested on the microarray and RNA-seq holdout sets. The holdout sets were projected onto and back out of the training set space using two unsupervised techniques, Independent and Principal Components Analysis, to obtain reconstructed holdout sets. The classifiers used in 4A were used to predict on the reconstructed holdout sets.