Abstract

BackgroundDifferential expression and feature selection analyses are essential steps for the development of accurate diagnostic/prognostic classifiers of complicated human diseases using transcriptomics data. These steps are particularly challenging due to the curse of dimensionality and the presence of technical and biological noise. A promising strategy for overcoming these challenges is the incorporation of pre-existing transcriptomics data in the identification of differentially expressed (DE) genes. This approach has the potential to improve the quality of selected genes, increase classification performance, and enhance biological interpretability. While a number of methods have been developed that use pre-existing data for differential expression analysis, existing methods do not leverage the identities of experimental conditions to create a robust metric for identifying DE genes.ResultsIn this study, we propose a novel differential expression and feature selection method—GEOlimma—which combines pre-existing microarray data from the Gene Expression Omnibus (GEO) with the widely-applied Limma method for differential expression analysis. We first quantify differential gene expression across 2481 pairwise comparisons from 602 curated GEO Datasets, and we convert differential expression frequencies to DE prior probabilities. Genes with high DE prior probabilities show enrichment in cell growth and death, signal transduction, and cancer-related biological pathways, while genes with low prior probabilities were enriched in sensory system pathways. We then applied GEOlimma to four differential expression comparisons within two human disease datasets and performed differential expression, feature selection, and supervised classification analyses. Our results suggest that use of GEOlimma provides greater experimental power to detect DE genes compared to Limma, due to its increased effective sample size. Furthermore, in a supervised classification analysis using GEOlimma as a feature selection method, we observed similar or better classification performance than Limma given small, noisy subsets of an asthma dataset.ConclusionsOur results demonstrate that GEOlimma is a more effective method for differential gene expression and feature selection analyses compared to the standard Limma method. Due to its focus on gene-level differential expression, GEOlimma also has the potential to be applied to other high-throughput biological datasets.

Highlights

  • Differential expression and feature selection analyses are essential steps for the development of accurate diagnostic/prognostic classifiers of complicated human diseases using transcriptomics data

  • In this study, we developed a gene expression feature selection method, GEOlimma, in which gene-level differential expression (DE) prior probabilities were derived from large-scale microarray data freely available from the Gene Expression Omnibus (GEO)

  • We developed and applied GEOlimma, which uses a large collection of GEO datasets to compute gene level differentially expressed (DE) prior probabilities

Read more

Summary

Introduction

Differential expression and feature selection analyses are essential steps for the development of accurate diagnostic/prognostic classifiers of complicated human diseases using transcriptomics data. A promising strategy for overcoming these challenges is the incorporation of pre-existing transcriptomics data in the identification of differentially expressed (DE) genes This approach has the potential to improve the quality of selected genes, increase classification performance, and enhance biological interpretability. DNA microarrays and RNA sequencing (RNA-Seq) have become indispensable experimental tools for characterizing the effects of biological interventions on genome-wide gene expression (“transcriptomics”) [1, 2] Applications of these tools have been transformative in many areas of biological research, including cancer biology, biomarker discovery, and drug target identification [3,4,5]. Common applications of transcriptomics-derived biomarkers include predicting diagnosis, prognosis, and therapeutic response for a disease of interest through a process known as supervised classification [9] In this context, DE gene identification can be viewed as a means of performing feature selection for classification. Feature selection is a process for dimensionality reduction that removes redundant or irrelevant features (genes), reduces classification model complexity, and improves classification performance [10]

Methods
Results
Discussion
Conclusion
Full Text
Published version (Free)

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call