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.
Document Type
Article
Publication Date
10-15-2014
Digital Object Identifier (DOI)
http://dx.doi.org/10.1371/journal.pone.0110052
Funding Information
This study was supported by a seed fund from Jilin University (No 450060491885). Co-author Dr. Liang Li is affiliated with LLX Solutions LLC. LLX Solutions LLC. provided support in the form of salary for author LL, but did not have any additional role in the study design, data collection and analysis, decision to publish, or preparation of the manuscript. The specific role of this author is articulated in the ‘author contributions’ section.
Repository Citation
Zhang, Ao; Wang, Chi; Wang, Shiji; Li, Liang; Liu, Zhongmin; and Tian, Suyan, "Visualization-Aided Classification Ensembles Discriminate Lung Adenocarcinoma and Squamous Cell Carcinoma Samples Using Their Gene Expression Profiles" (2014). Markey Cancer Center Faculty Publications. 37.
https://uknowledge.uky.edu/markey_facpub/37
Supplementary Materials
journal.pone.0110052.g001.png (555 kB)
Figure 1 (PNG). Study flowchart.
journal.pone.0110052.g001.ppt (136 kB)
Figure 1 (PPT). Study flowchart.
journal.pone.0110052.g001.TIF (1010 kB)
Figure 1 (TIFF). Study flowchart.
journal.pone.0110052.g002.png (981 kB)
Figure 2 (PNG). ROC curves for 3-gene signature combinations.
journal.pone.0110052.g002.ppt (118 kB)
Figure 2 (PPT). ROC curves for 3-gene signature combinations.
journal.pone.0110052.g002.TIF (1667 kB)
Figure 2 (TIFF). ROC curves for 3-gene signature combinations.
journal.pone.0110052.g003.png (727 kB)
Figure 3 (PNG). Scatterplots on the training data and test data.
journal.pone.0110052.g003.ppt (116 kB)
Figure 3 (PPT). Scatterplots on the training data and test data.
journal.pone.0110052.g003.TIF (1179 kB)
Figure 3 (TIFF). Scatterplots on the training data and test data.
journal.pone.0110052.g004.png (531 kB)
Figure 4 (PNG). RadViz plots using 8-gene signature on the training data and test data.
journal.pone.0110052.g004.ppt (56 kB)
Figure 4 (PPT). RadViz plots using 8-gene signature on the training data and test data.
journal.pone.0110052.g004.TIF (913 kB)
Figure 4 (TIFF). RadViz plots using 8-gene signature on the training data and test data.
journal.pone.0110052.t001.png (59 kB)
Table 1 (PNG). Results of simulation studies.
journal.pone.0110052.t001.ppt (46 kB)
Table 1 (PPT). Results of simulation studies.
journal.pone.0110052.t001.TIF (225 kB)
Table 1 (TIFF). Results of simulation studies.
journal.pone.0110052.t002.png (81 kB)
Table 2 (PNG). Performance metrics of classifiers on the lung cancer test set (AC and SCC subtype classification).
journal.pone.0110052.t002.ppt (55 kB)
Table 2 (PPT). Performance metrics of classifiers on the lung cancer test set (AC and SCC subtype classification).
journal.pone.0110052.t002.TIF (309 kB)
Table 2 (TIFF). Performance metrics of classifiers on the lung cancer test set (AC and SCC subtype classification).
journal.pone.0110052.t003.png (31 kB)
Table 3 (PNG). Might-be wrongly labeled samples identified by Ben-Hamo's study.
journal.pone.0110052.t003.ppt (29 kB)
Table 3 (PPT). Might-be wrongly labeled samples identified by Ben-Hamo's study.
journal.pone.0110052.t003.TIF (149 kB)
Table 3 (TIFF). Might-be wrongly labeled samples identified by Ben-Hamo's study.
journal.pone.0110052.t004.png (59 kB)
Table 4 (PNG). Performance metrics of classifiers on the lung cancer test set (subtype and stage classification).
journal.pone.0110052.t004.ppt (42 kB)
Table 4 (PPT). Performance metrics of classifiers on the lung cancer test set (subtype and stage classification).
journal.pone.0110052.t004.TIF (285 kB)
Table 4 (TIFF). Performance metrics of classifiers on the lung cancer test set (subtype and stage classification).
Notes/Citation Information
Published in PLOS One, v. 9, no. 10, article e110052, p. 1-9.
© 2014 Zhang et al.
This is an open-access article distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.