Fast cancer classification based on mass spectrometry analysis in robust stationary wavelet domain

Phuong Pham, Li Yu, Minh Nguyen, Nha H. Nguyen

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Mass spectrometry (MS) is a technology recently used for high dimensionality detection of proteins in proteomics. However, due to the high resolution and noise of MS data (MALDI-TOF), almost existing MS analysis algorithms are not robust with noise and run slowly. Developing new ones is necessary to analyze such data. In this paper, we propose a novel feature extraction method considering the inherent noise of mass spectra. The proposed method combines stationary wavelet transformation (SWT) and bivariate shrinkage estimator for MS feature extraction and denoising. Then, statistical feature testing is applied to denoised wavelet coefficients to select significant features used for biomarker identification. To evaluate the effectiveness of proposed method, a double cross-validation support vector machine classifier, which has high generalizability, and a fast Modest AdaBoost classifier, which improves significantly experimental runtime, are applied for cancer classification based on selected features by proposed method. Several experiments are carried out to evaluate the performance of our proposed methods. The results show that our proposed method can be an effective tool for analyzing MS data.

Original languageEnglish (US)
Title of host publicationIT Convergence and Services, ITCS 2011 and IRoA 2011
Pages189-199
Number of pages11
DOIs
StatePublished - Jan 1 2012
Externally publishedYes
Event3rd International Conference on Information Technology Convergence and Services, ITCS 2011 and 2011 FTRA International Conference on Intelligent Robotics, Automations, Telecommunication Facilities, and Applications, IRoA 2011 - Gwangju, Korea, Republic of
Duration: Oct 20 2011Oct 22 2011

Publication series

NameLecture Notes in Electrical Engineering
Volume107 LNEE
ISSN (Print)1876-1100
ISSN (Electronic)1876-1119

Other

Other3rd International Conference on Information Technology Convergence and Services, ITCS 2011 and 2011 FTRA International Conference on Intelligent Robotics, Automations, Telecommunication Facilities, and Applications, IRoA 2011
CountryKorea, Republic of
CityGwangju
Period10/20/1110/22/11

Fingerprint

Mass spectrometry
Feature extraction
Classifiers
Adaptive boosting
Biomarkers
Support vector machines
Proteins
Testing
Experiments

Keywords

  • Bivariate shrinkage
  • Boosting
  • Feature extraction
  • Mass spectrometry
  • SVM
  • SWT

ASJC Scopus subject areas

  • Industrial and Manufacturing Engineering

Cite this

Pham, P., Yu, L., Nguyen, M., & Nguyen, N. H. (2012). Fast cancer classification based on mass spectrometry analysis in robust stationary wavelet domain. In IT Convergence and Services, ITCS 2011 and IRoA 2011 (pp. 189-199). (Lecture Notes in Electrical Engineering; Vol. 107 LNEE). https://doi.org/10.1007/978-94-007-2598-0_21

Fast cancer classification based on mass spectrometry analysis in robust stationary wavelet domain. / Pham, Phuong; Yu, Li; Nguyen, Minh; Nguyen, Nha H.

IT Convergence and Services, ITCS 2011 and IRoA 2011. 2012. p. 189-199 (Lecture Notes in Electrical Engineering; Vol. 107 LNEE).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Pham, P, Yu, L, Nguyen, M & Nguyen, NH 2012, Fast cancer classification based on mass spectrometry analysis in robust stationary wavelet domain. in IT Convergence and Services, ITCS 2011 and IRoA 2011. Lecture Notes in Electrical Engineering, vol. 107 LNEE, pp. 189-199, 3rd International Conference on Information Technology Convergence and Services, ITCS 2011 and 2011 FTRA International Conference on Intelligent Robotics, Automations, Telecommunication Facilities, and Applications, IRoA 2011, Gwangju, Korea, Republic of, 10/20/11. https://doi.org/10.1007/978-94-007-2598-0_21
Pham P, Yu L, Nguyen M, Nguyen NH. Fast cancer classification based on mass spectrometry analysis in robust stationary wavelet domain. In IT Convergence and Services, ITCS 2011 and IRoA 2011. 2012. p. 189-199. (Lecture Notes in Electrical Engineering). https://doi.org/10.1007/978-94-007-2598-0_21
Pham, Phuong ; Yu, Li ; Nguyen, Minh ; Nguyen, Nha H. / Fast cancer classification based on mass spectrometry analysis in robust stationary wavelet domain. IT Convergence and Services, ITCS 2011 and IRoA 2011. 2012. pp. 189-199 (Lecture Notes in Electrical Engineering).
@inproceedings{790bb0f32e124c86afcf19a70b22c6fa,
title = "Fast cancer classification based on mass spectrometry analysis in robust stationary wavelet domain",
abstract = "Mass spectrometry (MS) is a technology recently used for high dimensionality detection of proteins in proteomics. However, due to the high resolution and noise of MS data (MALDI-TOF), almost existing MS analysis algorithms are not robust with noise and run slowly. Developing new ones is necessary to analyze such data. In this paper, we propose a novel feature extraction method considering the inherent noise of mass spectra. The proposed method combines stationary wavelet transformation (SWT) and bivariate shrinkage estimator for MS feature extraction and denoising. Then, statistical feature testing is applied to denoised wavelet coefficients to select significant features used for biomarker identification. To evaluate the effectiveness of proposed method, a double cross-validation support vector machine classifier, which has high generalizability, and a fast Modest AdaBoost classifier, which improves significantly experimental runtime, are applied for cancer classification based on selected features by proposed method. Several experiments are carried out to evaluate the performance of our proposed methods. The results show that our proposed method can be an effective tool for analyzing MS data.",
keywords = "Bivariate shrinkage, Boosting, Feature extraction, Mass spectrometry, SVM, SWT",
author = "Phuong Pham and Li Yu and Minh Nguyen and Nguyen, {Nha H.}",
year = "2012",
month = "1",
day = "1",
doi = "10.1007/978-94-007-2598-0_21",
language = "English (US)",
isbn = "9789400725973",
series = "Lecture Notes in Electrical Engineering",
pages = "189--199",
booktitle = "IT Convergence and Services, ITCS 2011 and IRoA 2011",

}

TY - GEN

T1 - Fast cancer classification based on mass spectrometry analysis in robust stationary wavelet domain

AU - Pham, Phuong

AU - Yu, Li

AU - Nguyen, Minh

AU - Nguyen, Nha H.

PY - 2012/1/1

Y1 - 2012/1/1

N2 - Mass spectrometry (MS) is a technology recently used for high dimensionality detection of proteins in proteomics. However, due to the high resolution and noise of MS data (MALDI-TOF), almost existing MS analysis algorithms are not robust with noise and run slowly. Developing new ones is necessary to analyze such data. In this paper, we propose a novel feature extraction method considering the inherent noise of mass spectra. The proposed method combines stationary wavelet transformation (SWT) and bivariate shrinkage estimator for MS feature extraction and denoising. Then, statistical feature testing is applied to denoised wavelet coefficients to select significant features used for biomarker identification. To evaluate the effectiveness of proposed method, a double cross-validation support vector machine classifier, which has high generalizability, and a fast Modest AdaBoost classifier, which improves significantly experimental runtime, are applied for cancer classification based on selected features by proposed method. Several experiments are carried out to evaluate the performance of our proposed methods. The results show that our proposed method can be an effective tool for analyzing MS data.

AB - Mass spectrometry (MS) is a technology recently used for high dimensionality detection of proteins in proteomics. However, due to the high resolution and noise of MS data (MALDI-TOF), almost existing MS analysis algorithms are not robust with noise and run slowly. Developing new ones is necessary to analyze such data. In this paper, we propose a novel feature extraction method considering the inherent noise of mass spectra. The proposed method combines stationary wavelet transformation (SWT) and bivariate shrinkage estimator for MS feature extraction and denoising. Then, statistical feature testing is applied to denoised wavelet coefficients to select significant features used for biomarker identification. To evaluate the effectiveness of proposed method, a double cross-validation support vector machine classifier, which has high generalizability, and a fast Modest AdaBoost classifier, which improves significantly experimental runtime, are applied for cancer classification based on selected features by proposed method. Several experiments are carried out to evaluate the performance of our proposed methods. The results show that our proposed method can be an effective tool for analyzing MS data.

KW - Bivariate shrinkage

KW - Boosting

KW - Feature extraction

KW - Mass spectrometry

KW - SVM

KW - SWT

UR - http://www.scopus.com/inward/record.url?scp=81255176747&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=81255176747&partnerID=8YFLogxK

U2 - 10.1007/978-94-007-2598-0_21

DO - 10.1007/978-94-007-2598-0_21

M3 - Conference contribution

SN - 9789400725973

T3 - Lecture Notes in Electrical Engineering

SP - 189

EP - 199

BT - IT Convergence and Services, ITCS 2011 and IRoA 2011

ER -