Classification of proteomic data with multiclass Logistic Partial Least Squares algorithm. (18th February 2008)

• Record Type: Journal Article
• Authors: Liu, Zhenqiu; Chen, Dechang; Tian, Jianjun Paul
• Is Part Of: International journal of bioinformatics research and applications. Volume 4:Number 1(2008)
• Page Start: 1
• Page End: 10
• Publication Date: 2008-02-18
• Subjects: mass spectrometry -- wavelet decomposition -- logistic regression -- partial least squares -- PLS -- bioinformatics -- classification -- proteomic data -- cancer detection -- early detection; Bioinformatics -- Periodicals; 570.285
• Languages: English
• ISSNs: 1744-5485

Abstract

Early detection of cancer is crucial for successful treatments. In this paper, we propose a multiclass Logistic Partial Least Squares (LPLS) algorithm for classification of normal vs. cancer using Mass Spectrometry (MS). LPLS combines the multiclass logistic regression with Partial Least Squares (PLS) algorithm. Wavelet decomposition is also proposed for pre-processing of original data. Wavelet decomposition and the proposed LPLS are applied to real life cancer data. Experimental comparisons show that LPLS with wavelet decomposition outperforms other methods in the analysis of MS data.