Comprehensive vertical sample-based KNN/LSVM classification for gene expression analysis

Authors:
Fei Pan;Baoying Wang;Xin Hu;William Perrizo
Affiliations:
Department of Computer Science, North Dakota State University, Fargo, ND;Department of Computer Science, North Dakota State University, Fargo, ND;Laboratory of Structural Microbiology, The Rockefeller University, New York, NY;Department of Computer Science, North Dakota State University, Fargo, ND
Venue:
Journal of Biomedical Informatics - Special issue: Biomedical machine learning
Year:
2004

Citing 6
Cited 8

Instance-Based Learning Algorithms

Machine Learning
The nature of statistical learning theory

The nature of statistical learning theory
Statistical Pattern Recognition: A Review

IEEE Transactions on Pattern Analysis and Machine Intelligence
The P-tree algebra

Proceedings of the 2002 ACM symposium on Applied computing
Machine Learning

Machine Learning
P-tree classification of yeast gene deletion data

ACM SIGKDD Explorations Newsletter

Guest editorial: research on machine learning issues in biomedical informatics modeling

Journal of Biomedical Informatics - Special issue: Biomedical machine learning
Prediction of cis/trans isomerization using feature selection and support vector machines

Journal of Biomedical Informatics
Prediction of Cancer Class with Majority Voting Genetic Programming Classifier Using Gene Expression Data

IEEE/ACM Transactions on Computational Biology and Bioinformatics (TCBB)
The classification of cancer based on DNA microarray data that uses diverse ensemble genetic programming

Artificial Intelligence in Medicine
A novel cancer classifier based on differentially expressed gene network

Proceedings of the First ACM International Conference on Bioinformatics and Computational Biology
TC-VGC: A Tumor Classification System using Variations in Genes' Correlation

Computer Methods and Programs in Biomedicine
Gene expression classification using binary rule majority voting genetic programming classifier

International Journal of Advanced Intelligence Paradigms
Selecting significant genes by randomization test for cancer classification using gene expression data

Journal of Biomedical Informatics

Quantified Score

Hi-index	0.00

Visualization

Abstract

Classification analysis of microarray gene expression data has been widely used to uncover biological features and to distinguish closely related cell types that often appear in the diagnosis of cancer. However, the number of dimensions of gene expression data is often very high, e.g., in the hundreds or thousands. Accurate and efficient classification of such high-dimensional data remains a contemporary challenge. In this paper, we propose a comprehensive vertical sample-based KNN/LSVM classification approach with weights optimized by genetic algorithms for high-dimensional data. Experiments on common gene expression datasets demonstrated that our approach can achieve high accuracy and efficiency at the same time. The improvement of speed is mainly related to the vertical data representation, P-tree, and its optimized logical algebra. The high accuracy is due to the combination of a KNN majority voting approach and a local support vector machine approach that makes optimal decisions at the local level. As a result, our approach could be a powerful tool for high-dimensional gene expression data analysis.