Dataset Information

Visualization-aided classification ensembles discriminate lung adenocarcinoma and squamous cell carcinoma samples using their gene expression profiles.

ABSTRACT:

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).

Results

In 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.

Conclusion

To 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.

SUBMITTER: Zhang A

PROVIDER: S-EPMC4198193 | biostudies-literature | 2014

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Visualization-aided classification ensembles discriminate lung adenocarcinoma and squamous cell carcinoma samples using their gene expression profiles.

Zhang Ao A Wang Chi C Wang Shiji S Li Liang L Liu Zhongmin Z Tian Suyan S

PloS one 20141015 10

<h4>Introduction</h4>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).<h4>Results</h4>In this paper, we proposed to integrate a visualization method called Radial Coordinate Visualization (Radviz) with a suitable classifier, aiming at discriminating ...[more]

PMID: 25335090

Similar Datasets

Project description:UnlabelledThis study was conducted to investigate whether functions encoded in the metagenome could improve our ability to understand the link between microbial community structures and functions in activated sludge. By analyzing data sets from six industrial and six municipal wastewater treatment plants (WWTPs), covering different configurations, operational conditions, and geographic regions, we found that wastewater influent composition was an overriding factor shaping the metagenomic composition of the activated sludge samples. Community GC content profiles were conserved within treatment plants on a time scale of years and between treatment plants with similar influent wastewater types. Interestingly, GC contents of the represented phyla covaried with the average GC contents of the corresponding WWTP metagenome. This suggests that the factors influencing nucleotide composition act similarly across taxa and thus the variation in nucleotide contents is driven by environmental differences between WWTPs. While taxonomic richness and functional richness were correlated, shotgun metagenomics complemented taxon-based analyses in the task of classifying microbial communities involved in wastewater treatment systems. The observed taxonomic dissimilarity between full-scale WWTPs receiving influent types with varied compositions, as well as the inferred taxonomic and functional assignment of recovered genomes from each metagenome, were consistent with underlying differences in the abundance of distinctive sets of functional categories. These conclusions were robust with respect to plant configuration, operational and environmental conditions, and even differences in laboratory protocols.ImportanceThis work contributes to the elucidation of drivers of microbial community assembly in wastewater treatment systems. Our results are significant because they provide clear evidence that bacterial communities in WWTPs assemble mainly according to influent wastewater characteristics. Differences in bacterial community structures between WWTPs were consistent with differences in the abundance of distinctive sets of functional categories, which were related to the metabolic potential that would be expected according to the source of the wastewater.

Dataset Information

Visualization-aided classification ensembles discriminate lung adenocarcinoma and squamous cell carcinoma samples using their gene expression profiles.

Introduction

Results

Conclusion

Publications

Visualization-aided classification ensembles discriminate lung adenocarcinoma and squamous cell carcinoma samples using their gene expression profiles.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets