Latent network-based representations for large-scale gene expression data analysis

Wajdi Dhifli,Aurélien Dispot,Mohamed Elati,Julia Puig

doi:10.1186/s12859-018-2481-y

Abstract

BackgroundWith the recent advancements in high-throughput experimental procedures, biologists are gathering huge quantities of data. A main priority in bioinformatics and computational biology is to provide system level analytical tools capable of meeting an ever-growing production of high-throughput biological data while taking into account its biological context. In gene expression data analysis, genes have widely been considered as independent components. However, a systemic view shows that they act synergistically in living cells, forming functional complexes and more generally a biological system.ResultsIn this paper, we propose LatNet, a signal transformation framework that, starting from an initial large-scale gene expression data, allows to generate new representations based on latent network-based relationships between the genes. LatNet aims to leverage system level relations between the genes as an underlying hidden structure to derive the new transformed latent signals. We present a concrete implementation of our framework, based on a gene regulatory network structure and two signal transformation approaches, to quantify latent network-based activity of regulators, as well as gene perturbation signals. The new gene/regulator signals are at the level of each sample of the input data and, thus, could directly be used instead of the initial expression signals for major bioinformatics analysis, including diagnosis and personalized medicine.ConclusionMultiple patterns could be hidden or weakly observed in expression data. LatNet helps in uncovering latent signals that could emphasize hidden patterns based on the relations between the genes and, thus, enhancing the performance of gene expression-based analysis algorithms. We use LatNet for the analysis of real-world gene expression data of bladder cancer and we show the efficiency of our transformation framework as compared to using the initial expression data.

Highlights

With the recent advancements in high-throughput experimental procedures, biologists are gathering huge quantities of data
We use our framework for the analysis of real-world gene expression data of bladder and breast cancer and we show the efficiency of our transformation framework as compared to using the initial expression data as well as other state-of-the-art approaches for extracting latent features
We propose to consider a Gene regulatory network (GRN) as a background network structure that defines the relations between genes and to exploit this structure to perform a transformation of the input signal of expression for unravelling latent signals that are more informative than the initial expression data

Summary

Introduction

With the recent advancements in high-throughput experimental procedures, biologists are gathering huge quantities of data. Dhifli et al BMC Bioinformatics 2019, 19(Suppl 13):466 in harmony forming functional networks and more generally a biological system In this context, multiple inference methods of regulatory networks have been developed, and were recently reviewed in [1]. Linear and non-linear transformations of expression data could be derived from specific mechanistic models (e.g, regulatory networks [3, 4]) and statistical measurements (e.g, Matrix Factorization (MF) [5]), and could play a key role in capturing such indirect and latent relationships. The main drawback with MF approaches is that they suffer a difficulty in the interpretability of the resulting factorized components This has imposed a serious focus on the analysis of these components in the form of metagenes and metasamples, to facilitate their interpretability and association to biologically relevant mechanisms [9, 10]

Objectives

Methods

Results

Conclusion