Developing cancer prediction model based on stepwise selection by AUC measure for proteomics data

Yongkang Kim, Seungyeoun Lee, Min Seok Kwon, Ahrum Na, Yonghwan Choi, Sung Gon Yi, Junghyun Namkung, Sangjo Han, Meejoo Kang, Sun Whe Kim, Jin-Young Jang, Yikwon Kim, Youngsoo Kim, Taesung Park

Research output: Chapter in Book/Report/Conference proceedingConference contributionResearchpeer-review

2 Citations (Scopus)

Abstract

Since most of the cancer markers that have been reported are obtained directly from cancer tissues, it is difficult to use them for early diagnosis of cancer without surgery. Thus, development of markers that can be detected by blood is crucial for making early diagnosis of cancer easier. One of the most feasible types of markers that can be detected by blood is a protein marker. Here, we focus on building prediction methods using the protein markers for early diagnosis of cancer. To develop a prediction model with high prediction ability, it is critical to choose appropriate markers first. Here, we consider a stepwise selection method using area under the receiver operating characteristic curve (Step-AUC) in order to construct a multi-protein prediction model. We showed that the performance of Step-AUC highly depends on the tuning parameter. We compared our proposed Step-AUC method to stepwise selection using information criteria and support vector machine recursive feature extraction (SVM-RFE). We observed that Step-AUC and stepwise selection using Bayesian information criteria (Step-BIC) perform better than other methods. The importance of each marker can be chosen using a new stepwise selection consistency (SSC) measure. The final models include the markers with high SSC measures. We applied our stepwise procedure to pancreatic cancer data and found two markers of interest.

Original languageEnglish
Title of host publicationProceedings - 2015 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2015
Editorslng. Matthieu Schapranow, Jiayu Zhou, Xiaohua Tony Hu, Bin Ma, Sanguthevar Rajasekaran, Satoru Miyano, Illhoi Yoo, Brian Pierce, Amarda Shehu, Vijay K. Gombar, Brian Chen, Vinay Pai, Jun Huan
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages1345-1350
Number of pages6
ISBN (Electronic)9781467367981
DOIs
StatePublished - 16 Dec 2015
EventIEEE International Conference on Bioinformatics and Biomedicine, BIBM 2015 - Washington, United States
Duration: 9 Nov 201512 Nov 2015

Other

OtherIEEE International Conference on Bioinformatics and Biomedicine, BIBM 2015
CountryUnited States
CityWashington
Period9/11/1512/11/15

Fingerprint

Proteomics
Area Under Curve
Early Detection of Cancer
Proteins
Neoplasms
Blood
Surgery
Support vector machines
Feature extraction
Pancreatic Neoplasms
ROC Curve
Tuning
Tissue

Keywords

  • area under the curve (AUC)
  • early diagnosis of cancer
  • multiple reaction monitoring (MRM)
  • protein marker
  • Receiver operating characteristic (ROC) curve
  • stepwise selection
  • support vector machine

Cite this

Kim, Y., Lee, S., Kwon, M. S., Na, A., Choi, Y., Yi, S. G., ... Park, T. (2015). Developing cancer prediction model based on stepwise selection by AUC measure for proteomics data. In L. M. Schapranow, J. Zhou, X. T. Hu, B. Ma, S. Rajasekaran, S. Miyano, I. Yoo, B. Pierce, A. Shehu, V. K. Gombar, B. Chen, V. Pai, ... J. Huan (Eds.), Proceedings - 2015 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2015 (pp. 1345-1350). [7359874] Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/BIBM.2015.7359874
Kim, Yongkang ; Lee, Seungyeoun ; Kwon, Min Seok ; Na, Ahrum ; Choi, Yonghwan ; Yi, Sung Gon ; Namkung, Junghyun ; Han, Sangjo ; Kang, Meejoo ; Kim, Sun Whe ; Jang, Jin-Young ; Kim, Yikwon ; Kim, Youngsoo ; Park, Taesung. / Developing cancer prediction model based on stepwise selection by AUC measure for proteomics data. Proceedings - 2015 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2015. editor / lng. Matthieu Schapranow ; Jiayu Zhou ; Xiaohua Tony Hu ; Bin Ma ; Sanguthevar Rajasekaran ; Satoru Miyano ; Illhoi Yoo ; Brian Pierce ; Amarda Shehu ; Vijay K. Gombar ; Brian Chen ; Vinay Pai ; Jun Huan. Institute of Electrical and Electronics Engineers Inc., 2015. pp. 1345-1350
@inproceedings{988af85c43c54dae8988538d120790e7,
title = "Developing cancer prediction model based on stepwise selection by AUC measure for proteomics data",
abstract = "Since most of the cancer markers that have been reported are obtained directly from cancer tissues, it is difficult to use them for early diagnosis of cancer without surgery. Thus, development of markers that can be detected by blood is crucial for making early diagnosis of cancer easier. One of the most feasible types of markers that can be detected by blood is a protein marker. Here, we focus on building prediction methods using the protein markers for early diagnosis of cancer. To develop a prediction model with high prediction ability, it is critical to choose appropriate markers first. Here, we consider a stepwise selection method using area under the receiver operating characteristic curve (Step-AUC) in order to construct a multi-protein prediction model. We showed that the performance of Step-AUC highly depends on the tuning parameter. We compared our proposed Step-AUC method to stepwise selection using information criteria and support vector machine recursive feature extraction (SVM-RFE). We observed that Step-AUC and stepwise selection using Bayesian information criteria (Step-BIC) perform better than other methods. The importance of each marker can be chosen using a new stepwise selection consistency (SSC) measure. The final models include the markers with high SSC measures. We applied our stepwise procedure to pancreatic cancer data and found two markers of interest.",
keywords = "area under the curve (AUC), early diagnosis of cancer, multiple reaction monitoring (MRM), protein marker, Receiver operating characteristic (ROC) curve, stepwise selection, support vector machine",
author = "Yongkang Kim and Seungyeoun Lee and Kwon, {Min Seok} and Ahrum Na and Yonghwan Choi and Yi, {Sung Gon} and Junghyun Namkung and Sangjo Han and Meejoo Kang and Kim, {Sun Whe} and Jin-Young Jang and Yikwon Kim and Youngsoo Kim and Taesung Park",
year = "2015",
month = "12",
day = "16",
doi = "10.1109/BIBM.2015.7359874",
language = "English",
pages = "1345--1350",
editor = "Schapranow, {lng. Matthieu} and Jiayu Zhou and Hu, {Xiaohua Tony} and Bin Ma and Sanguthevar Rajasekaran and Satoru Miyano and Illhoi Yoo and Brian Pierce and Amarda Shehu and Gombar, {Vijay K.} and Brian Chen and Vinay Pai and Jun Huan",
booktitle = "Proceedings - 2015 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2015",
publisher = "Institute of Electrical and Electronics Engineers Inc.",

}

Kim, Y, Lee, S, Kwon, MS, Na, A, Choi, Y, Yi, SG, Namkung, J, Han, S, Kang, M, Kim, SW, Jang, J-Y, Kim, Y, Kim, Y & Park, T 2015, Developing cancer prediction model based on stepwise selection by AUC measure for proteomics data. in LM Schapranow, J Zhou, XT Hu, B Ma, S Rajasekaran, S Miyano, I Yoo, B Pierce, A Shehu, VK Gombar, B Chen, V Pai & J Huan (eds), Proceedings - 2015 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2015., 7359874, Institute of Electrical and Electronics Engineers Inc., pp. 1345-1350, IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2015, Washington, United States, 9/11/15. https://doi.org/10.1109/BIBM.2015.7359874

Developing cancer prediction model based on stepwise selection by AUC measure for proteomics data. / Kim, Yongkang; Lee, Seungyeoun; Kwon, Min Seok; Na, Ahrum; Choi, Yonghwan; Yi, Sung Gon; Namkung, Junghyun; Han, Sangjo; Kang, Meejoo; Kim, Sun Whe; Jang, Jin-Young; Kim, Yikwon; Kim, Youngsoo; Park, Taesung.

Proceedings - 2015 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2015. ed. / lng. Matthieu Schapranow; Jiayu Zhou; Xiaohua Tony Hu; Bin Ma; Sanguthevar Rajasekaran; Satoru Miyano; Illhoi Yoo; Brian Pierce; Amarda Shehu; Vijay K. Gombar; Brian Chen; Vinay Pai; Jun Huan. Institute of Electrical and Electronics Engineers Inc., 2015. p. 1345-1350 7359874.

Research output: Chapter in Book/Report/Conference proceedingConference contributionResearchpeer-review

TY - GEN

T1 - Developing cancer prediction model based on stepwise selection by AUC measure for proteomics data

AU - Kim, Yongkang

AU - Lee, Seungyeoun

AU - Kwon, Min Seok

AU - Na, Ahrum

AU - Choi, Yonghwan

AU - Yi, Sung Gon

AU - Namkung, Junghyun

AU - Han, Sangjo

AU - Kang, Meejoo

AU - Kim, Sun Whe

AU - Jang, Jin-Young

AU - Kim, Yikwon

AU - Kim, Youngsoo

AU - Park, Taesung

PY - 2015/12/16

Y1 - 2015/12/16

N2 - Since most of the cancer markers that have been reported are obtained directly from cancer tissues, it is difficult to use them for early diagnosis of cancer without surgery. Thus, development of markers that can be detected by blood is crucial for making early diagnosis of cancer easier. One of the most feasible types of markers that can be detected by blood is a protein marker. Here, we focus on building prediction methods using the protein markers for early diagnosis of cancer. To develop a prediction model with high prediction ability, it is critical to choose appropriate markers first. Here, we consider a stepwise selection method using area under the receiver operating characteristic curve (Step-AUC) in order to construct a multi-protein prediction model. We showed that the performance of Step-AUC highly depends on the tuning parameter. We compared our proposed Step-AUC method to stepwise selection using information criteria and support vector machine recursive feature extraction (SVM-RFE). We observed that Step-AUC and stepwise selection using Bayesian information criteria (Step-BIC) perform better than other methods. The importance of each marker can be chosen using a new stepwise selection consistency (SSC) measure. The final models include the markers with high SSC measures. We applied our stepwise procedure to pancreatic cancer data and found two markers of interest.

AB - Since most of the cancer markers that have been reported are obtained directly from cancer tissues, it is difficult to use them for early diagnosis of cancer without surgery. Thus, development of markers that can be detected by blood is crucial for making early diagnosis of cancer easier. One of the most feasible types of markers that can be detected by blood is a protein marker. Here, we focus on building prediction methods using the protein markers for early diagnosis of cancer. To develop a prediction model with high prediction ability, it is critical to choose appropriate markers first. Here, we consider a stepwise selection method using area under the receiver operating characteristic curve (Step-AUC) in order to construct a multi-protein prediction model. We showed that the performance of Step-AUC highly depends on the tuning parameter. We compared our proposed Step-AUC method to stepwise selection using information criteria and support vector machine recursive feature extraction (SVM-RFE). We observed that Step-AUC and stepwise selection using Bayesian information criteria (Step-BIC) perform better than other methods. The importance of each marker can be chosen using a new stepwise selection consistency (SSC) measure. The final models include the markers with high SSC measures. We applied our stepwise procedure to pancreatic cancer data and found two markers of interest.

KW - area under the curve (AUC)

KW - early diagnosis of cancer

KW - multiple reaction monitoring (MRM)

KW - protein marker

KW - Receiver operating characteristic (ROC) curve

KW - stepwise selection

KW - support vector machine

UR - http://www.scopus.com/inward/record.url?scp=84962346084&partnerID=8YFLogxK

U2 - 10.1109/BIBM.2015.7359874

DO - 10.1109/BIBM.2015.7359874

M3 - Conference contribution

SP - 1345

EP - 1350

BT - Proceedings - 2015 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2015

A2 - Schapranow, lng. Matthieu

A2 - Zhou, Jiayu

A2 - Hu, Xiaohua Tony

A2 - Ma, Bin

A2 - Rajasekaran, Sanguthevar

A2 - Miyano, Satoru

A2 - Yoo, Illhoi

A2 - Pierce, Brian

A2 - Shehu, Amarda

A2 - Gombar, Vijay K.

A2 - Chen, Brian

A2 - Pai, Vinay

A2 - Huan, Jun

PB - Institute of Electrical and Electronics Engineers Inc.

ER -

Kim Y, Lee S, Kwon MS, Na A, Choi Y, Yi SG et al. Developing cancer prediction model based on stepwise selection by AUC measure for proteomics data. In Schapranow LM, Zhou J, Hu XT, Ma B, Rajasekaran S, Miyano S, Yoo I, Pierce B, Shehu A, Gombar VK, Chen B, Pai V, Huan J, editors, Proceedings - 2015 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2015. Institute of Electrical and Electronics Engineers Inc. 2015. p. 1345-1350. 7359874 https://doi.org/10.1109/BIBM.2015.7359874