TY - JOUR
T1 - Finding minimum gene subsets with heuristic breadth-first search algorithm for robust tumor classification
AU - Wang, Shu Lin
AU - Li, Xue Ling
AU - Fang, Jianwen
N1 - Funding Information:
We sincerely thank Gustavo A. Stolovitzky (IBM Computational Biology Center) for providing us the DLBCL21 dataset. And we also cordially thank Prof. Ji Wang (School of Computer Science, National University of Defense Technology, China) for his inspiring suggestion. We also thank Chungui Xu, Junfeng Xia and Meiling Hou for their contribution to the analysis of part of genes. This work was supported by the National Science Foundation of China (grant nos. 60973153, 61133010, 31071168, 60873012), the China Postdoctoral Science Foundation (grant no. 20090450825), and Anhui Provincial Natural Science Foundation (grant no. 1208085MF96).
PY - 2012/7/25
Y1 - 2012/7/25
N2 - Background: Previous studies on tumor classification based on gene expression profiles suggest that gene selection plays a key role in improving the classification performance. Moreover, finding important tumor-related genes with the highest accuracy is a very important task because these genes might serve as tumor biomarkers, which is of great benefit to not only tumor molecular diagnosis but also drug development.Results: This paper proposes a novel gene selection method with rich biomedical meaning based on Heuristic Breadth-first Search Algorithm (HBSA) to find as many optimal gene subsets as possible. Due to the curse of dimensionality, this type of method could suffer from over-fitting and selection bias problems. To address these potential problems, a HBSA-based ensemble classifier is constructed using majority voting strategy from individual classifiers constructed by the selected gene subsets, and a novel HBSA-based gene ranking method is designed to find important tumor-related genes by measuring the significance of genes using their occurrence frequencies in the selected gene subsets. The experimental results on nine tumor datasets including three pairs of cross-platform datasets indicate that the proposed method can not only obtain better generalization performance but also find many important tumor-related genes.Conclusions: It is found that the frequencies of the selected genes follow a power-law distribution, indicating that only a few top-ranked genes can be used as potential diagnosis biomarkers. Moreover, the top-ranked genes leading to very high prediction accuracy are closely related to specific tumor subtype and even hub genes. Compared with other related methods, the proposed method can achieve higher prediction accuracy with fewer genes. Moreover, they are further justified by analyzing the top-ranked genes in the context of individual gene function, biological pathway, and protein-protein interaction network.
AB - Background: Previous studies on tumor classification based on gene expression profiles suggest that gene selection plays a key role in improving the classification performance. Moreover, finding important tumor-related genes with the highest accuracy is a very important task because these genes might serve as tumor biomarkers, which is of great benefit to not only tumor molecular diagnosis but also drug development.Results: This paper proposes a novel gene selection method with rich biomedical meaning based on Heuristic Breadth-first Search Algorithm (HBSA) to find as many optimal gene subsets as possible. Due to the curse of dimensionality, this type of method could suffer from over-fitting and selection bias problems. To address these potential problems, a HBSA-based ensemble classifier is constructed using majority voting strategy from individual classifiers constructed by the selected gene subsets, and a novel HBSA-based gene ranking method is designed to find important tumor-related genes by measuring the significance of genes using their occurrence frequencies in the selected gene subsets. The experimental results on nine tumor datasets including three pairs of cross-platform datasets indicate that the proposed method can not only obtain better generalization performance but also find many important tumor-related genes.Conclusions: It is found that the frequencies of the selected genes follow a power-law distribution, indicating that only a few top-ranked genes can be used as potential diagnosis biomarkers. Moreover, the top-ranked genes leading to very high prediction accuracy are closely related to specific tumor subtype and even hub genes. Compared with other related methods, the proposed method can achieve higher prediction accuracy with fewer genes. Moreover, they are further justified by analyzing the top-ranked genes in the context of individual gene function, biological pathway, and protein-protein interaction network.
KW - Gene expression profiles
KW - Gene selection
KW - Heuristic breadth-first search
KW - Power-law distribution
KW - Tumor classification
UR - http://www.scopus.com/inward/record.url?scp=84864145739&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=84864145739&partnerID=8YFLogxK
U2 - 10.1186/1471-2105-13-178
DO - 10.1186/1471-2105-13-178
M3 - Article
C2 - 22830977
AN - SCOPUS:84864145739
SN - 1471-2105
VL - 13
JO - BMC bioinformatics
JF - BMC bioinformatics
IS - 1
M1 - 178
ER -