Incorporating Pathway Information into Feature Selection towards Better Performed Gene Signatures.

Suyan Tian,Bing Wang,Chi Wang

doi:10.1155/2019/2497509

Abstract

To analyze gene expression data with sophisticated grouping structures and to extract hidden patterns from such data, feature selection is of critical importance. It is well known that genes do not function in isolation but rather work together within various metabolic, regulatory, and signaling pathways. If the biological knowledge contained within these pathways is taken into account, the resulting method is a pathway-based algorithm. Studies have demonstrated that a pathway-based method usually outperforms its gene-based counterpart in which no biological knowledge is considered. In this article, a pathway-based feature selection is firstly divided into three major categories, namely, pathway-level selection, bilevel selection, and pathway-guided gene selection. With bilevel selection methods being regarded as a special case of pathway-guided gene selection process, we discuss pathway-guided gene selection methods in detail and the importance of penalization in such methods. Last, we point out the potential utilizations of pathway-guided gene selection in one active research avenue, namely, to analyze longitudinal gene expression data. We believe this article provides valuable insights for computational biologists and biostatisticians so that they can make biology more computable.

Highlights

Data obtained from the high-throughput technologies such as microarrays or RNA-sequencing (RNA-seq) is a recurring theme in many fields such as computational biology and bioinformatics
By searching in the PubMed using the keywords of feature selection, pathway/network, gene expression, and cancer and inspecting their relevance, we found roughly 40 articles which utilize pathway-guided gene selection algorithms to study a variety of cancers
We present a review on pathway-based feature selection algorithms

Summary

Introduction

Data obtained from the high-throughput technologies such as microarrays or RNA-sequencing (RNA-seq) is a recurring theme in many fields such as computational biology and bioinformatics Given these advanced technologies are expensive, the number of observations/subjects is usually small, i.e., on the scales of several to hundreds. The classic feature selection, we call it “genebased feature selection” to avoid ambiguity in this article, is stratified into three subtypes, say, filter, embedded, and wrapper methods [1, 2]. These three categories have their own unique characteristics. Such a method can simultaneously select relevant features and estimate those coefficients (the effect size of those features) in the final model; in addition to that it consumes less computing time than a wrapper method

Objectives

Methods

Conclusion