Visualization-Aided Classification Ensembles Discriminate Lung Adenocarcinoma and Squamous Cell Carcinoma Samples Using Their Gene Expression Profiles

Ao Zhang,Liang Li,Suyan Tian,Shiji Wang,Zhongmin Liu,Chi Wang

doi:10.1371/journal.pone.0110052

Ao Zhang, Liang Li + Show 4 more

Open Access

PDF Available

https://doi.org/10.1371/journal.pone.0110052

Copy DOI

Export

Save

Cite

Abstract
Highlights/Summary
Full-Text PDF
Similar Papers

Abstract

Listen

IntroductionThe widespread application of microarray experiments to cancer research is astounding including lung cancer, one of the most common fatal human tumors. Among non-small cell lung carcinoma (NSCLC), there are two major histological types of NSCLC, adenocarcinoma (AC) and squamous cell carcinoma (SCC).ResultsIn this paper, we proposed to integrate a visualization method called Radial Coordinate Visualization (Radviz) with a suitable classifier, aiming at discriminating two NSCLC subtypes using patients' gene expression profiles. Our analyses on simulated data and a real microarray dataset show that combining with a classification method, Radviz may play a role in selecting relevant features and ameliorating parsimony, while the final model suffers no or least loss of accuracy. Most importantly, a graphic representation is more easily understandable and implementable for a clinician than statistical methods and/or mathematic equations.ConclusionTo conclude, using the NSCLC microarray data presented here as a benchmark, the comprehensive understanding of the underlying mechanism associated with NSCLC and of the mechanisms with its subtypes and respective stages will become reality in the near future.

Highlights

The widespread application of microarray experiments to cancer research is astounding including lung cancer, one of the most common fatal human tumors
We proposed to combine a visualization method called Radial Coordinate Visualization (RadViz) [15] with a suitable classifier to discriminate these two non-small cell lung carcinoma (NSCLC) subtypes, basing on patients’ gene expression profiles
Synthesized data In order to evaluate the empirical performance of RadViz in terms of selecting informative features and eliminating irrelevant features, we used the simulations presented in one previous study [14]

Summary

Introduction

The widespread application of microarray experiments to cancer research is astounding including lung cancer, one of the most common fatal human tumors. Among non-small cell lung carcinoma (NSCLC), there are two major histological types of NSCLC, adenocarcinoma (AC) and squamous cell carcinoma (SCC). About 85% of lung cancers are nonsmall cell lung carcinoma (NSCLC), and two major histological types of NSCLC, adenocarcinoma (AC) and squamous cell carcinoma (SCC), represents about 40% of NSCLC cases, respectively [2]. The recent-developed molecular targeted therapies such as an antiepidermal growth factor receptor (EGFR) antibody are effective in patients harboring mutations in corresponding genes, which are exclusively found in AC. This indicates fundamental differences in the underlying mechanisms of tumor development, growth and invasion between the two subtypes. The successful classification of NSCLC patients into their corresponding subtypes and stages is of clinical significance

Methods

Results

Conclusion