K-means clustering with infinite feature selection for classification tasks in gene expression data

Muhammad Akmal Remli; Kauthar Mohd Daud; Hui Wen Nies; Mohd Saberi Mohamad; Safaai Deris; Sigeru Omatu; Shahreen Kasim; Ghazali Sulong

doi:10.1007/978-3-319-60816-7_7

K-means clustering with infinite feature selection for classification tasks in gene expression data

Muhammad Akmal Remli
, Kauthar Mohd Daud
, Hui Wen Nies
, Mohd Saberi Mohamad
, Safaai Deris
, Sigeru Omatu
, Shahreen Kasim
, Ghazali Sulong

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

11 Citations (Scopus)

Abstract

In the bioinformatics and clinical research areas, microarray technology has been widely used to distinguish a cancer dataset between normal and tumour samples. However, the high dimensionality of gene expression data affects the classification accuracy of an experiment. Thus, feature selection is needed to select informative genes and remove non-informative genes. Some of the feature selection methods, yet, ignore the interaction between genes. Therefore, the similar genes are clustered together and dissimilar genes are clustered in other groups. Hence, to provide a higher classification accuracy, this research proposed k-means clustering and infinite feature selection for identifying informative genes in the selected subset. This research has been applied to colorectal cancer and small round blue cell tumors datasets. Eventually, this research successfully obtained higher classification accuracy than the previous work.

Original language	English
Title of host publication	11th International Conference on Practical Applications of Computational Biology and Bioinformatics, 2017
Editors	Miguel Rocha, Juan F. De Paz, Tiago Pinto, Florentino Fdez-Riverola, Mohd Saberi Mohamad
Publisher	Springer Verlag
Pages	50-57
Number of pages	8
ISBN (Print)	9783319608150
DOIs	https://doi.org/10.1007/978-3-319-60816-7_7
Publication status	Published - 2017
Externally published	Yes
Event	11th International Conference on Practical Applications of Computational Biology and Bioinformatics, PACBB 2017 - Porto, Portugal Duration: Jun 21 2017 → Jun 23 2017

Publication series

Name	Advances in Intelligent Systems and Computing
Volume	616
ISSN (Print)	2194-5357

Conference

Conference	11th International Conference on Practical Applications of Computational Biology and Bioinformatics, PACBB 2017
Country/Territory	Portugal
City	Porto
Period	6/21/17 → 6/23/17

UN SDGs

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

SDG 3 Good Health and Well-being

Keywords

Artificial intelligence
Cancer classification
Gene expression data
Infinite feature selection
Informative genes
K-means clustering
Small round blue cell tumors

ASJC Scopus subject areas

Control and Systems Engineering
General Computer Science

Access to Document

10.1007/978-3-319-60816-7_7

Cite this

Remli, M. A., Daud, K. M., Nies, H. W., Mohamad, M. S., Deris, S., Omatu, S., Kasim, S., & Sulong, G. (2017). K-means clustering with infinite feature selection for classification tasks in gene expression data. In M. Rocha, J. F. De Paz, T. Pinto, F. Fdez-Riverola, & M. S. Mohamad (Eds.), 11th International Conference on Practical Applications of Computational Biology and Bioinformatics, 2017 (pp. 50-57). (Advances in Intelligent Systems and Computing; Vol. 616). Springer Verlag. https://doi.org/10.1007/978-3-319-60816-7_7

K-means clustering with infinite feature selection for classification tasks in gene expression data. / Remli, Muhammad Akmal; Daud, Kauthar Mohd; Nies, Hui Wen et al.
11th International Conference on Practical Applications of Computational Biology and Bioinformatics, 2017. ed. / Miguel Rocha; Juan F. De Paz; Tiago Pinto; Florentino Fdez-Riverola; Mohd Saberi Mohamad. Springer Verlag, 2017. p. 50-57 (Advances in Intelligent Systems and Computing; Vol. 616).

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

Remli, MA, Daud, KM, Nies, HW, Mohamad, MS, Deris, S, Omatu, S, Kasim, S & Sulong, G 2017, K-means clustering with infinite feature selection for classification tasks in gene expression data. in M Rocha, JF De Paz, T Pinto, F Fdez-Riverola & MS Mohamad (eds), 11th International Conference on Practical Applications of Computational Biology and Bioinformatics, 2017. Advances in Intelligent Systems and Computing, vol. 616, Springer Verlag, pp. 50-57, 11th International Conference on Practical Applications of Computational Biology and Bioinformatics, PACBB 2017, Porto, Portugal, 6/21/17. https://doi.org/10.1007/978-3-319-60816-7_7

Remli MA, Daud KM, Nies HW, Mohamad MS, Deris S, Omatu S et al. K-means clustering with infinite feature selection for classification tasks in gene expression data. In Rocha M, De Paz JF, Pinto T, Fdez-Riverola F, Mohamad MS, editors, 11th International Conference on Practical Applications of Computational Biology and Bioinformatics, 2017. Springer Verlag. 2017. p. 50-57. (Advances in Intelligent Systems and Computing). doi: 10.1007/978-3-319-60816-7_7

Remli, Muhammad Akmal ; Daud, Kauthar Mohd ; Nies, Hui Wen et al. / K-means clustering with infinite feature selection for classification tasks in gene expression data. 11th International Conference on Practical Applications of Computational Biology and Bioinformatics, 2017. editor / Miguel Rocha ; Juan F. De Paz ; Tiago Pinto ; Florentino Fdez-Riverola ; Mohd Saberi Mohamad. Springer Verlag, 2017. pp. 50-57 (Advances in Intelligent Systems and Computing).

@inproceedings{24ecab1455174911bd8ca7b2142b5246,

title = "K-means clustering with infinite feature selection for classification tasks in gene expression data",

abstract = "In the bioinformatics and clinical research areas, microarray technology has been widely used to distinguish a cancer dataset between normal and tumour samples. However, the high dimensionality of gene expression data affects the classification accuracy of an experiment. Thus, feature selection is needed to select informative genes and remove non-informative genes. Some of the feature selection methods, yet, ignore the interaction between genes. Therefore, the similar genes are clustered together and dissimilar genes are clustered in other groups. Hence, to provide a higher classification accuracy, this research proposed k-means clustering and infinite feature selection for identifying informative genes in the selected subset. This research has been applied to colorectal cancer and small round blue cell tumors datasets. Eventually, this research successfully obtained higher classification accuracy than the previous work.",

keywords = "Artificial intelligence, Cancer classification, Gene expression data, Infinite feature selection, Informative genes, K-means clustering, Small round blue cell tumors",

author = "Remli, \{Muhammad Akmal\} and Daud, \{Kauthar Mohd\} and Nies, \{Hui Wen\} and Mohamad, \{Mohd Saberi\} and Safaai Deris and Sigeru Omatu and Shahreen Kasim and Ghazali Sulong",

note = "Publisher Copyright: {\textcopyright} Springer International Publishing AG 2017.; 11th International Conference on Practical Applications of Computational Biology and Bioinformatics, PACBB 2017 ; Conference date: 21-06-2017 Through 23-06-2017",

year = "2017",

doi = "10.1007/978-3-319-60816-7\_7",

language = "English",

isbn = "9783319608150",

series = "Advances in Intelligent Systems and Computing",

publisher = "Springer Verlag",

pages = "50--57",

editor = "Miguel Rocha and \{De Paz\}, \{Juan F.\} and Tiago Pinto and Florentino Fdez-Riverola and Mohamad, \{Mohd Saberi\}",

booktitle = "11th International Conference on Practical Applications of Computational Biology and Bioinformatics, 2017",

}

TY - GEN

T1 - K-means clustering with infinite feature selection for classification tasks in gene expression data

AU - Remli, Muhammad Akmal

AU - Daud, Kauthar Mohd

AU - Nies, Hui Wen

AU - Mohamad, Mohd Saberi

AU - Deris, Safaai

AU - Omatu, Sigeru

AU - Kasim, Shahreen

AU - Sulong, Ghazali

N1 - Publisher Copyright: © Springer International Publishing AG 2017.

PY - 2017

Y1 - 2017

N2 - In the bioinformatics and clinical research areas, microarray technology has been widely used to distinguish a cancer dataset between normal and tumour samples. However, the high dimensionality of gene expression data affects the classification accuracy of an experiment. Thus, feature selection is needed to select informative genes and remove non-informative genes. Some of the feature selection methods, yet, ignore the interaction between genes. Therefore, the similar genes are clustered together and dissimilar genes are clustered in other groups. Hence, to provide a higher classification accuracy, this research proposed k-means clustering and infinite feature selection for identifying informative genes in the selected subset. This research has been applied to colorectal cancer and small round blue cell tumors datasets. Eventually, this research successfully obtained higher classification accuracy than the previous work.

AB - In the bioinformatics and clinical research areas, microarray technology has been widely used to distinguish a cancer dataset between normal and tumour samples. However, the high dimensionality of gene expression data affects the classification accuracy of an experiment. Thus, feature selection is needed to select informative genes and remove non-informative genes. Some of the feature selection methods, yet, ignore the interaction between genes. Therefore, the similar genes are clustered together and dissimilar genes are clustered in other groups. Hence, to provide a higher classification accuracy, this research proposed k-means clustering and infinite feature selection for identifying informative genes in the selected subset. This research has been applied to colorectal cancer and small round blue cell tumors datasets. Eventually, this research successfully obtained higher classification accuracy than the previous work.

KW - Artificial intelligence

KW - Cancer classification

KW - Gene expression data

KW - Infinite feature selection

KW - Informative genes

KW - K-means clustering

KW - Small round blue cell tumors

UR - https://www.scopus.com/pages/publications/85025136538

UR - https://www.scopus.com/pages/publications/85025136538#tab=citedBy

U2 - 10.1007/978-3-319-60816-7_7

DO - 10.1007/978-3-319-60816-7_7

M3 - Conference contribution

AN - SCOPUS:85025136538

SN - 9783319608150

T3 - Advances in Intelligent Systems and Computing

SP - 50

EP - 57

BT - 11th International Conference on Practical Applications of Computational Biology and Bioinformatics, 2017

A2 - Rocha, Miguel

A2 - De Paz, Juan F.

A2 - Pinto, Tiago

A2 - Fdez-Riverola, Florentino

A2 - Mohamad, Mohd Saberi

PB - Springer Verlag

T2 - 11th International Conference on Practical Applications of Computational Biology and Bioinformatics, PACBB 2017

Y2 - 21 June 2017 through 23 June 2017

ER -

K-means clustering with infinite feature selection for classification tasks in gene expression data

Abstract

Publication series

Conference

UN SDGs

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this