Feature Identification Using Hypotheses of Relevance and a 2D-Cascade of SEQENS Ensembles

Abstract

SEQENS is an ensemble method aimed at feature identification that has demonstrated strong performance in identifying relevant genes in high-dimensional spaces, across different synthetic tasks. In this paper, we first introduce the differences between feature importance, feature selection (FS) and feature identification concepts. Following this, we present a framework based on SEQENS covering the following contributions: (1) computing the hypergeometric p-value of the features of a SEQENS output ranking in order to be able to establish a threshold between relevant and non-relevant features; (2) extending SEQENS by introducing the use of preselected features as hypotheses of relevance in the sequential FS, which may help to attract other features that might exhibit weak correlation with the target on their own, but gain relevance when combined with the preselected ones and; (3) designing an automated process based on a 2D-cascade of SEQENS ensembles to obtain a purged feature set, or PFS, that is, having as many relevant features, and as few non-relevant, as possible. The framework presented, named pc–SEQENS, integrates the former techniques so that the PFS is used as a hypothesis of relevance in a SEQENS ensemble. Performance is analysed in a gene expression identification task using the E-MTAB-3732 public database and synthetic targets. pc–SEQENS is compared to other state-of-the-art methods, including SEQENS to check the effect of using hypotheses of relevance. On average, the proposed framework identifies better the relevant genes, especially in unfavourable sample-to-dimension rates, and exhibits a stronger stability.