Derivation of cancer diagnostic and prognostic signatures from gene expression data

Abstract

The ability to compare genome-wide expression profiles in human tissue samples has the potential to add an invaluable molecular pathology aspect to the detection and evaluation of multiple diseases. Applications include initial diagnosis, evaluation of disease subtype, monitoring of response to therapy and the prediction of disease recurrence. The derivation of molecular signatures that can predict tumor recurrence in breast cancer has been a particularly intense area of investigation and a number of studies have shown that molecular signatures can outperform currently used clinicopathologic factors in predicting relapse in this disease. However, many of these predictive models have been derived using relatively simple computational algorithms and whether these models are at a stage of development worthy of large-cohort clinical trial validation is currently a subject of debate. In this review, we focus on the derivation of optimal molecular signatures from high-dimensional data and discuss some of the expected future developments in the field.

Figure 1. Computational experimental procedure used to derive predictive molecular signatures for prostate cancer recurrence using gene expression data

The experimental protocol consists of inner and outer loops. In the inner loop, LOOCV is performed to estimate the optimal classifier parameters based on the training data provided by the outer loop and in the outer loop, a held-out sample is classified using the best parameters from the inner loop. The experiment is repeated until each sample has been tested. The held-out testing sample is not involved in any stage of the training process. LOOCV: Leave-one-out cross validation.