Sample size determination for training cancer classifiers from microarray and RNA-seq data

Abstract

The objective of many high-dimensional microarray and RNA-seq studies is to develop a classifier of cancer patients based on characteristics of their disease. The germinal center B-cell (GCB) classifier study in lymphoma and the National Cancer Institute's Director's Challenge lung (DC-lung) study are two examples. In recent years, such classifiers are often developed using regularized regression, such as the lasso. A critical question is whether a better classifier can be developed from a larger training set size and, if so, how large the training set should be. This paper examines these two questions using an existing sample size method and a novel sample size method developed here specifically for lasso logistic regression. Both methods are based on pilot data. We reexamine the lymphoma and lung cancer data sets to evaluate the sample sizes, and use resampling to assess the estimation methods. We also study application to an RNA-seq data set. We find that it is feasible to estimate sample size for regularized logistic regression if an adequate pilot data set exists. The GCB and the DC-lung data sets appear adequate, under specific assumptions. Existing human RNA-seq data sets are by and large inadequate, and cannot be used as pilot data. Pilot RNA-seq data can be simulated, and the methods in this paper can be used for sample size estimation. A MATLAB program is made available.