Neighbor Method to the Classification of Renal Cell Carcinoma

Dongqing Liu; Ting Shi; John A. DiDonato; Joseph D. Carpten; Jianping Zhu; Zhong-Hui Duan

doi:10.1109/CSB.2004.1332494

Neighbor Method to the Classification of Renal Cell Carcinoma

Dongqing Liu, Ting Shi, John A. DiDonato, Joseph D. Carpten, Jianping Zhu, Zhong-Hui Duan

Research output: Other contribution

Abstract

In this study, we use a genetic algorithm and k-nearest neighbor method to classify two subtypes of renal cell carcinoma using a set of microarray gene expression profiles of nine samples (three clear cell tumors and six papillary tumors). We show that the genetic algorithm/k-nearest neighbor method can be efficiently used in identifying a panel of discriminator genes. To test the robustness of the algorithm, we perform a bootstrapping analysis that removes one sample from the data set at a time and uses the remaining samples for gene selection. We show that each of the removed samples can be classified correctly. We also analyze the stability of the algorithm and the sensitivity of the algorithm with respect to different samples.

Original language	American English
DOIs	https://doi.org/10.1109/CSB.2004.1332494
State	Published - Aug 1 2004

Disciplines

Applied Mathematics

Access to Document

10.1109/CSB.2004.1332494License: CC BY

Cite this

@misc{56956f41e69d41ac9000b9f08c668a9f,

title = "Neighbor Method to the Classification of Renal Cell Carcinoma",

abstract = " In this study, we use a genetic algorithm and k-nearest neighbor method to classify two subtypes of renal cell carcinoma using a set of microarray gene expression profiles of nine samples (three clear cell tumors and six papillary tumors). We show that the genetic algorithm/k-nearest neighbor method can be efficiently used in identifying a panel of discriminator genes. To test the robustness of the algorithm, we perform a bootstrapping analysis that removes one sample from the data set at a time and uses the remaining samples for gene selection. We show that each of the removed samples can be classified correctly. We also analyze the stability of the algorithm and the sensitivity of the algorithm with respect to different samples.",

author = "Dongqing Liu and Ting Shi and DiDonato, \{John A.\} and Carpten, \{Joseph D.\} and Jianping Zhu and Zhong-Hui Duan",

note = "Liu, D., Shi, T., DiDonato, J., Carpten, J., Zhu, J., and Duan, Z. (2004), Application of genetic algorithm/K-nearest neighbor method to the classification of renal cell carcinoma, in Proceedings of Computational Systems Bioinformatics Conference, 558 – 559, IEEE Computer Society Press, Los Alamitos, CA.",

year = "2004",

month = aug,

day = "1",

doi = "10.1109/CSB.2004.1332494",

language = "American English",

type = "Other",

}

TY - GEN

T1 - Neighbor Method to the Classification of Renal Cell Carcinoma

AU - Liu, Dongqing

AU - Shi, Ting

AU - DiDonato, John A.

AU - Carpten, Joseph D.

AU - Zhu, Jianping

AU - Duan, Zhong-Hui

N1 - Liu, D., Shi, T., DiDonato, J., Carpten, J., Zhu, J., and Duan, Z. (2004), Application of genetic algorithm/K-nearest neighbor method to the classification of renal cell carcinoma, in Proceedings of Computational Systems Bioinformatics Conference, 558 – 559, IEEE Computer Society Press, Los Alamitos, CA.

PY - 2004/8/1

Y1 - 2004/8/1

N2 - In this study, we use a genetic algorithm and k-nearest neighbor method to classify two subtypes of renal cell carcinoma using a set of microarray gene expression profiles of nine samples (three clear cell tumors and six papillary tumors). We show that the genetic algorithm/k-nearest neighbor method can be efficiently used in identifying a panel of discriminator genes. To test the robustness of the algorithm, we perform a bootstrapping analysis that removes one sample from the data set at a time and uses the remaining samples for gene selection. We show that each of the removed samples can be classified correctly. We also analyze the stability of the algorithm and the sensitivity of the algorithm with respect to different samples.

AB - In this study, we use a genetic algorithm and k-nearest neighbor method to classify two subtypes of renal cell carcinoma using a set of microarray gene expression profiles of nine samples (three clear cell tumors and six papillary tumors). We show that the genetic algorithm/k-nearest neighbor method can be efficiently used in identifying a panel of discriminator genes. To test the robustness of the algorithm, we perform a bootstrapping analysis that removes one sample from the data set at a time and uses the remaining samples for gene selection. We show that each of the removed samples can be classified correctly. We also analyze the stability of the algorithm and the sensitivity of the algorithm with respect to different samples.

UR - https://engagedscholarship.csuohio.edu/scimath_facpub/89

UR - http://ieeexplore.ieee.org/xpl/freeabs_all.jsp?arnumber=1332494&abstractAccess=no&userType=inst

U2 - 10.1109/CSB.2004.1332494

DO - 10.1109/CSB.2004.1332494

M3 - Other contribution

ER -

Neighbor Method to the Classification of Renal Cell Carcinoma

Abstract

Disciplines

Access to Document

Other files and links

Cite this