Common peak approach using mass spectrometry data sets for predicting the effects of anticancer drugs on breast cancer

Masaru Ushijima, Satoshi Miyata, Shinto Eguchi, Masanori Kawakita, Masataka Yoshimoto, Takuji Iwase, Futoshi Akiyama, Goi Sakamoto, Koichi Nagasaki, Yoshio Miki, Tetsuo Noda, Yutaka Hoshikawa, Masaaki Matsuura

Research output: Contribution to journalArticle

4 Citations (Scopus)

Abstract

We propose a method for biomarker discovery from mass spectrometry data, improving the common peak approach developed by Fushiki et al. (BMC Bioinformatics, 7:358, 2006). The common peak method is a simple way to select the sensible peaks that are shared with many subjects among all detected peaks by combining a standard spectrum alignment and kernel density estimates. The key idea of our proposed method is to apply the common peak approach to each class label separately. Hence, the proposed method gains more informative peaks for predicting class labels, while minor peaks associated with specific subjects are deleted correctly. We used a SELDI-TOF MS data set from laser microdissected cancer tissues for predicting the treatment effects of neoadjuvant therapy using an anticancer drug on breast cancer patients. The AdaBoost algorithm is adopted for pattern recognition, based on the set of candidate peaks selected by the proposed method. The analysis gives good performance in the sense of test errors for classifying the class labels for a given feature vector of selected peak values.

Original languageEnglish
Pages (from-to)285-293
Number of pages9
JournalCancer Informatics
Volume3
Publication statusPublished - Dec 1 2007

Fingerprint

Mass Spectrometry
Breast Neoplasms
Pharmaceutical Preparations
Neoadjuvant Therapy
Matrix-Assisted Laser Desorption-Ionization Mass Spectrometry
Computational Biology
Lasers
Biomarkers
Datasets
Neoplasms
Therapeutics

All Science Journal Classification (ASJC) codes

  • Oncology
  • Cancer Research

Cite this

Ushijima, M., Miyata, S., Eguchi, S., Kawakita, M., Yoshimoto, M., Iwase, T., ... Matsuura, M. (2007). Common peak approach using mass spectrometry data sets for predicting the effects of anticancer drugs on breast cancer. Cancer Informatics, 3, 285-293.

Common peak approach using mass spectrometry data sets for predicting the effects of anticancer drugs on breast cancer. / Ushijima, Masaru; Miyata, Satoshi; Eguchi, Shinto; Kawakita, Masanori; Yoshimoto, Masataka; Iwase, Takuji; Akiyama, Futoshi; Sakamoto, Goi; Nagasaki, Koichi; Miki, Yoshio; Noda, Tetsuo; Hoshikawa, Yutaka; Matsuura, Masaaki.

In: Cancer Informatics, Vol. 3, 01.12.2007, p. 285-293.

Research output: Contribution to journalArticle

Ushijima, M, Miyata, S, Eguchi, S, Kawakita, M, Yoshimoto, M, Iwase, T, Akiyama, F, Sakamoto, G, Nagasaki, K, Miki, Y, Noda, T, Hoshikawa, Y & Matsuura, M 2007, 'Common peak approach using mass spectrometry data sets for predicting the effects of anticancer drugs on breast cancer', Cancer Informatics, vol. 3, pp. 285-293.
Ushijima M, Miyata S, Eguchi S, Kawakita M, Yoshimoto M, Iwase T et al. Common peak approach using mass spectrometry data sets for predicting the effects of anticancer drugs on breast cancer. Cancer Informatics. 2007 Dec 1;3:285-293.
Ushijima, Masaru ; Miyata, Satoshi ; Eguchi, Shinto ; Kawakita, Masanori ; Yoshimoto, Masataka ; Iwase, Takuji ; Akiyama, Futoshi ; Sakamoto, Goi ; Nagasaki, Koichi ; Miki, Yoshio ; Noda, Tetsuo ; Hoshikawa, Yutaka ; Matsuura, Masaaki. / Common peak approach using mass spectrometry data sets for predicting the effects of anticancer drugs on breast cancer. In: Cancer Informatics. 2007 ; Vol. 3. pp. 285-293.
@article{eba649b2f30a468c9c60d83b44fba09f,
title = "Common peak approach using mass spectrometry data sets for predicting the effects of anticancer drugs on breast cancer",
abstract = "We propose a method for biomarker discovery from mass spectrometry data, improving the common peak approach developed by Fushiki et al. (BMC Bioinformatics, 7:358, 2006). The common peak method is a simple way to select the sensible peaks that are shared with many subjects among all detected peaks by combining a standard spectrum alignment and kernel density estimates. The key idea of our proposed method is to apply the common peak approach to each class label separately. Hence, the proposed method gains more informative peaks for predicting class labels, while minor peaks associated with specific subjects are deleted correctly. We used a SELDI-TOF MS data set from laser microdissected cancer tissues for predicting the treatment effects of neoadjuvant therapy using an anticancer drug on breast cancer patients. The AdaBoost algorithm is adopted for pattern recognition, based on the set of candidate peaks selected by the proposed method. The analysis gives good performance in the sense of test errors for classifying the class labels for a given feature vector of selected peak values.",
author = "Masaru Ushijima and Satoshi Miyata and Shinto Eguchi and Masanori Kawakita and Masataka Yoshimoto and Takuji Iwase and Futoshi Akiyama and Goi Sakamoto and Koichi Nagasaki and Yoshio Miki and Tetsuo Noda and Yutaka Hoshikawa and Masaaki Matsuura",
year = "2007",
month = "12",
day = "1",
language = "English",
volume = "3",
pages = "285--293",
journal = "Cancer Informatics",
issn = "1176-9351",
publisher = "Libertas Academica Ltd.",

}

TY - JOUR

T1 - Common peak approach using mass spectrometry data sets for predicting the effects of anticancer drugs on breast cancer

AU - Ushijima, Masaru

AU - Miyata, Satoshi

AU - Eguchi, Shinto

AU - Kawakita, Masanori

AU - Yoshimoto, Masataka

AU - Iwase, Takuji

AU - Akiyama, Futoshi

AU - Sakamoto, Goi

AU - Nagasaki, Koichi

AU - Miki, Yoshio

AU - Noda, Tetsuo

AU - Hoshikawa, Yutaka

AU - Matsuura, Masaaki

PY - 2007/12/1

Y1 - 2007/12/1

N2 - We propose a method for biomarker discovery from mass spectrometry data, improving the common peak approach developed by Fushiki et al. (BMC Bioinformatics, 7:358, 2006). The common peak method is a simple way to select the sensible peaks that are shared with many subjects among all detected peaks by combining a standard spectrum alignment and kernel density estimates. The key idea of our proposed method is to apply the common peak approach to each class label separately. Hence, the proposed method gains more informative peaks for predicting class labels, while minor peaks associated with specific subjects are deleted correctly. We used a SELDI-TOF MS data set from laser microdissected cancer tissues for predicting the treatment effects of neoadjuvant therapy using an anticancer drug on breast cancer patients. The AdaBoost algorithm is adopted for pattern recognition, based on the set of candidate peaks selected by the proposed method. The analysis gives good performance in the sense of test errors for classifying the class labels for a given feature vector of selected peak values.

AB - We propose a method for biomarker discovery from mass spectrometry data, improving the common peak approach developed by Fushiki et al. (BMC Bioinformatics, 7:358, 2006). The common peak method is a simple way to select the sensible peaks that are shared with many subjects among all detected peaks by combining a standard spectrum alignment and kernel density estimates. The key idea of our proposed method is to apply the common peak approach to each class label separately. Hence, the proposed method gains more informative peaks for predicting class labels, while minor peaks associated with specific subjects are deleted correctly. We used a SELDI-TOF MS data set from laser microdissected cancer tissues for predicting the treatment effects of neoadjuvant therapy using an anticancer drug on breast cancer patients. The AdaBoost algorithm is adopted for pattern recognition, based on the set of candidate peaks selected by the proposed method. The analysis gives good performance in the sense of test errors for classifying the class labels for a given feature vector of selected peak values.

UR - http://www.scopus.com/inward/record.url?scp=49649107415&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=49649107415&partnerID=8YFLogxK

M3 - Article

C2 - 19455248

AN - SCOPUS:49649107415

VL - 3

SP - 285

EP - 293

JO - Cancer Informatics

JF - Cancer Informatics

SN - 1176-9351

ER -