Classification of proteomic data with multiclass Logistic Partial Least Squares algorithm

Zhenqiu Liu, Dechang Chen, Jianjun Paul Tian

Research output: Contribution to journalArticle

2 Citations (Scopus)

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.

Original languageEnglish (US)
Pages (from-to)1-10
Number of pages10
JournalInternational Journal of Bioinformatics Research and Applications
Volume4
Issue number1
DOIs
StatePublished - Feb 1 2008

Fingerprint

Least-Squares Analysis
Proteomics
Logistics
Wavelet decomposition
Mass spectrometry
Mass Spectrometry
Early Detection of Cancer
Neoplasms
Logistic Models
Processing

All Science Journal Classification (ASJC) codes

  • Biomedical Engineering
  • Health Informatics
  • Clinical Biochemistry
  • Health Information Management

Cite this

@article{1d40b4835c5b4ebe84d20ac6ebe291d5,
title = "Classification of proteomic data with multiclass Logistic Partial Least Squares algorithm",
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.",
author = "Zhenqiu Liu and Dechang Chen and Tian, {Jianjun Paul}",
year = "2008",
month = "2",
day = "1",
doi = "10.1504/IJBRA.2008.017160",
language = "English (US)",
volume = "4",
pages = "1--10",
journal = "International Journal of Bioinformatics Research and Applications",
issn = "1744-5485",
publisher = "Inderscience Enterprises Ltd",
number = "1",

}

Classification of proteomic data with multiclass Logistic Partial Least Squares algorithm. / Liu, Zhenqiu; Chen, Dechang; Tian, Jianjun Paul.

In: International Journal of Bioinformatics Research and Applications, Vol. 4, No. 1, 01.02.2008, p. 1-10.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Classification of proteomic data with multiclass Logistic Partial Least Squares algorithm

AU - Liu, Zhenqiu

AU - Chen, Dechang

AU - Tian, Jianjun Paul

PY - 2008/2/1

Y1 - 2008/2/1

N2 - 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.

AB - 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.

UR - http://www.scopus.com/inward/record.url?scp=39449097867&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=39449097867&partnerID=8YFLogxK

U2 - 10.1504/IJBRA.2008.017160

DO - 10.1504/IJBRA.2008.017160

M3 - Article

C2 - 18283025

AN - SCOPUS:39449097867

VL - 4

SP - 1

EP - 10

JO - International Journal of Bioinformatics Research and Applications

JF - International Journal of Bioinformatics Research and Applications

SN - 1744-5485

IS - 1

ER -