Methods to transform microarray data for cancer prediction

Anuchate Pattanateepapon; Watcharapan Suwansantisuk; Pinit Kumhom

doi:10.1109/CIBCB.2016.7758104

Methods to transform microarray data for cancer prediction

Anuchate Pattanateepapon
, Watcharapan Suwansantisuk
, Pinit Kumhom

K. Mongkut's Univ. Technol. Thonburi

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

2 Citations (Scopus)

Abstract

Cancer classification based on microarray data has gained attention in recent years from the bioinformatics community, due to a high death toll of cancer and the significance of early diagnosis. Among the many steps in cancer classification, one that is underexplored and can significantly affect the classification performance is data transformation. We develop two transformation techniques, called the unity-based normalization with min-max interval (UBMI) and the standard score with trimmed mean (SSTM), and compare them with existing techniques in terms of accuracy, sensitivity and specificity. The results show that our proposed methods outperform the methods tested. Overall, for example, the SSTM achieves the highest values of accuracy, sensitivity, and specificity in 73 out of 138 cases. The UBMI is the runner up, with 51 winning cases. This advantage confirms the ability of the UBMI and SSTM to accentuate the difference between samples of distinct classes, and highlights the importance of data transformation, a step that otherwise is usually overlooked.

Original language	English
Title of host publication	CIBCB 2016 - Annual IEEE International Conference on Computational Intelligence in Bioinformatics and Computational Biology
Publisher	Institute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)	9781467394727
DOIs	https://doi.org/10.1109/CIBCB.2016.7758104
Publication status	Published - 28 Nov 2016
Externally published	Yes
Event	13th IEEE International Conference on Computational Intelligence in Bioinformatics and Computational Biology, CIBCB 2016 - Chiang Mai, Thailand Duration: 5 Oct 2016 → 7 Oct 2016

Publication series

Name	CIBCB 2016 - Annual IEEE International Conference on Computational Intelligence in Bioinformatics and Computational Biology

Conference

Conference	13th IEEE International Conference on Computational Intelligence in Bioinformatics and Computational Biology, CIBCB 2016
Country/Territory	Thailand
City	Chiang Mai
Period	5/10/16 → 7/10/16

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

SDG 3 Good Health and Well-being

Keywords

data transform
feature selection
gene-expression microarray data
support vector machine

Access to Document

10.1109/CIBCB.2016.7758104

Cite this

Pattanateepapon, A., Suwansantisuk, W., & Kumhom, P. (2016). Methods to transform microarray data for cancer prediction. In CIBCB 2016 - Annual IEEE International Conference on Computational Intelligence in Bioinformatics and Computational Biology Article 7758104 (CIBCB 2016 - Annual IEEE International Conference on Computational Intelligence in Bioinformatics and Computational Biology). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/CIBCB.2016.7758104

Pattanateepapon, Anuchate ; Suwansantisuk, Watcharapan ; Kumhom, Pinit. / Methods to transform microarray data for cancer prediction. CIBCB 2016 - Annual IEEE International Conference on Computational Intelligence in Bioinformatics and Computational Biology. Institute of Electrical and Electronics Engineers Inc., 2016. (CIBCB 2016 - Annual IEEE International Conference on Computational Intelligence in Bioinformatics and Computational Biology).

@inproceedings{df17a6bcc12a42f98b3805c463a010c6,

title = "Methods to transform microarray data for cancer prediction",

abstract = "Cancer classification based on microarray data has gained attention in recent years from the bioinformatics community, due to a high death toll of cancer and the significance of early diagnosis. Among the many steps in cancer classification, one that is underexplored and can significantly affect the classification performance is data transformation. We develop two transformation techniques, called the unity-based normalization with min-max interval (UBMI) and the standard score with trimmed mean (SSTM), and compare them with existing techniques in terms of accuracy, sensitivity and specificity. The results show that our proposed methods outperform the methods tested. Overall, for example, the SSTM achieves the highest values of accuracy, sensitivity, and specificity in 73 out of 138 cases. The UBMI is the runner up, with 51 winning cases. This advantage confirms the ability of the UBMI and SSTM to accentuate the difference between samples of distinct classes, and highlights the importance of data transformation, a step that otherwise is usually overlooked.",

keywords = "data transform, feature selection, gene-expression microarray data, support vector machine",

author = "Anuchate Pattanateepapon and Watcharapan Suwansantisuk and Pinit Kumhom",

note = "Publisher Copyright: {\textcopyright} 2016 IEEE.; 13th IEEE International Conference on Computational Intelligence in Bioinformatics and Computational Biology, CIBCB 2016 ; Conference date: 05-10-2016 Through 07-10-2016",

year = "2016",

month = nov,

day = "28",

doi = "10.1109/CIBCB.2016.7758104",

language = "English",

series = "CIBCB 2016 - Annual IEEE International Conference on Computational Intelligence in Bioinformatics and Computational Biology",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

booktitle = "CIBCB 2016 - Annual IEEE International Conference on Computational Intelligence in Bioinformatics and Computational Biology",

}

Pattanateepapon, A, Suwansantisuk, W & Kumhom, P 2016, Methods to transform microarray data for cancer prediction. in CIBCB 2016 - Annual IEEE International Conference on Computational Intelligence in Bioinformatics and Computational Biology., 7758104, CIBCB 2016 - Annual IEEE International Conference on Computational Intelligence in Bioinformatics and Computational Biology, Institute of Electrical and Electronics Engineers Inc., 13th IEEE International Conference on Computational Intelligence in Bioinformatics and Computational Biology, CIBCB 2016, Chiang Mai, Thailand, 5/10/16. https://doi.org/10.1109/CIBCB.2016.7758104

Methods to transform microarray data for cancer prediction. / Pattanateepapon, Anuchate; Suwansantisuk, Watcharapan; Kumhom, Pinit.
CIBCB 2016 - Annual IEEE International Conference on Computational Intelligence in Bioinformatics and Computational Biology. Institute of Electrical and Electronics Engineers Inc., 2016. 7758104 (CIBCB 2016 - Annual IEEE International Conference on Computational Intelligence in Bioinformatics and Computational Biology).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Methods to transform microarray data for cancer prediction

AU - Pattanateepapon, Anuchate

AU - Suwansantisuk, Watcharapan

AU - Kumhom, Pinit

PY - 2016/11/28

Y1 - 2016/11/28

N2 - Cancer classification based on microarray data has gained attention in recent years from the bioinformatics community, due to a high death toll of cancer and the significance of early diagnosis. Among the many steps in cancer classification, one that is underexplored and can significantly affect the classification performance is data transformation. We develop two transformation techniques, called the unity-based normalization with min-max interval (UBMI) and the standard score with trimmed mean (SSTM), and compare them with existing techniques in terms of accuracy, sensitivity and specificity. The results show that our proposed methods outperform the methods tested. Overall, for example, the SSTM achieves the highest values of accuracy, sensitivity, and specificity in 73 out of 138 cases. The UBMI is the runner up, with 51 winning cases. This advantage confirms the ability of the UBMI and SSTM to accentuate the difference between samples of distinct classes, and highlights the importance of data transformation, a step that otherwise is usually overlooked.

AB - Cancer classification based on microarray data has gained attention in recent years from the bioinformatics community, due to a high death toll of cancer and the significance of early diagnosis. Among the many steps in cancer classification, one that is underexplored and can significantly affect the classification performance is data transformation. We develop two transformation techniques, called the unity-based normalization with min-max interval (UBMI) and the standard score with trimmed mean (SSTM), and compare them with existing techniques in terms of accuracy, sensitivity and specificity. The results show that our proposed methods outperform the methods tested. Overall, for example, the SSTM achieves the highest values of accuracy, sensitivity, and specificity in 73 out of 138 cases. The UBMI is the runner up, with 51 winning cases. This advantage confirms the ability of the UBMI and SSTM to accentuate the difference between samples of distinct classes, and highlights the importance of data transformation, a step that otherwise is usually overlooked.

KW - data transform

KW - feature selection

KW - gene-expression microarray data

KW - support vector machine

UR - https://www.scopus.com/pages/publications/85011409192

U2 - 10.1109/CIBCB.2016.7758104

DO - 10.1109/CIBCB.2016.7758104

M3 - Conference contribution

AN - SCOPUS:85011409192

T3 - CIBCB 2016 - Annual IEEE International Conference on Computational Intelligence in Bioinformatics and Computational Biology

BT - CIBCB 2016 - Annual IEEE International Conference on Computational Intelligence in Bioinformatics and Computational Biology

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 13th IEEE International Conference on Computational Intelligence in Bioinformatics and Computational Biology, CIBCB 2016

Y2 - 5 October 2016 through 7 October 2016

ER -

Pattanateepapon A, Suwansantisuk W, Kumhom P. Methods to transform microarray data for cancer prediction. In CIBCB 2016 - Annual IEEE International Conference on Computational Intelligence in Bioinformatics and Computational Biology. Institute of Electrical and Electronics Engineers Inc. 2016. 7758104. (CIBCB 2016 - Annual IEEE International Conference on Computational Intelligence in Bioinformatics and Computational Biology). doi: 10.1109/CIBCB.2016.7758104

Methods to transform microarray data for cancer prediction

Abstract

Publication series

Conference

UN SDGs

Keywords

Access to Document

Other files and links

Fingerprint

Cite this