A generalised OMP algorithm for feature selection with application to gene expression data

TL;DR

This paper introduces gOMP, a scalable and versatile feature selection algorithm that outperforms LASSO in various gene expression data analyses, including classification, regression, and survival prediction.

Contribution

The paper presents gOMP, a generalized and scalable version of Orthogonal Matching Pursuit, applicable to multiple outcome types and models, with theoretical advantages and superior performance.

Findings

gOMP outperforms LASSO in binary classification tasks.

gOMP is effective for regression and survival analysis.

gOMP is simple, easy to implement, and generalizable.

Abstract

Feature selection for predictive analytics is the problem of identifying a minimal-size subset of features that is maximally predictive of an outcome of interest. To apply to molecular data, feature selection algorithms need to be scalable to tens of thousands of available features. In this paper, we propose gOMP, a highly-scalable generalisation of the Orthogonal Matching Pursuit feature selection algorithm to several directions: (a) different types of outcomes, such as continuous, binary, nominal, and time-to-event, (b) different types of predictive models (e.g., linear least squares, logistic regression), (c) different types of predictive features (continuous, categorical), and (d) different, statistical-based stopping criteria. We compare the proposed algorithm against LASSO, a prototypical, widely used algorithm for high-dimensional data. On dozens of simulated datasets, as well as, real gene expression datasets, gOMP is on par, or outperforms LASSO for case-control binary classification, quantified outcomes (regression), and (censored) survival times (time-to-event) analysis. gOMP has also several theoretical advantages that are discussed. While gOMP is based on quite simple and basic statistical ideas, easy to implement and to generalize, we also show in an extensive evaluation that it is also quite effective in bioinformatics analysis settings.