TY - JOUR
T1 - A review of computational methods for clustering genes with similar biological functions
AU - Nies, Hui Wen
AU - Zakaria, Zalmiyah
AU - Mohamad, Mohd Saberi
AU - Chan, Weng Howe
AU - Zaki, Nazar
AU - Sinnott, Richard O.
AU - Napis, Suhaimi
AU - Chamoso, Pablo
AU - Omatu, Sigeru
AU - Corchado, Juan Manuel
N1 - Funding Information:
This research was funded by Fundamental Research Grant Scheme-Malaysia's Research Star Award (FRGS-MRSA) and Fundamental Research Grant Scheme (R.J130000.7828.4F973) from Ministry of Education Malaysia, ICT funding agency from United Arab Emirates University (G00001472), and Research University Grant from Universiti Teknologi Malaysia (Q.J130000.2628.14J68). The authors also would like to thank Universiti Teknologi Malaysia (UTM) for the support of UTM's Zamalah Scholarship. The authors acknowledge support from the Ministry of Education Malaysia, United Arab Emirates University (UAEU), University of Salamanca (USAL), and Universiti Teknologi Malaysia (UTM).
Publisher Copyright:
© 2019 by the authors.
PY - 2019/9/1
Y1 - 2019/9/1
N2 - Clustering techniques can group genes based on similarity in biological functions. However, the drawback of using clustering techniques is the inability to identify an optimal number of potential clusters beforehand. Several existing optimization techniques can address the issue. Besides, clustering validation can predict the possible number of potential clusters and hence increase the chances of identifying biologically informative genes. This paper reviews and provides examples of existing methods for clustering genes, optimization of the objective function, and clustering validation. Clustering techniques can be categorized into partitioning, hierarchical, grid-based, and density-based techniques. We also highlight the advantages and the disadvantages of each category. To optimize the objective function, here we introduce the swarm intelligence technique and compare the performances of other methods. Moreover, we discuss the differences of measurements between internal and external criteria to validate a cluster quality. We also investigate the performance of several clustering techniques by applying them on a leukemia dataset. The results show that grid-based clustering techniques provide better classification accuracy; however, partitioning clustering techniques are superior in identifying prognostic markers of leukemia. Therefore, this review suggests combining clustering techniques such as CLIQUE and k-means to yield high-quality gene clusters.
AB - Clustering techniques can group genes based on similarity in biological functions. However, the drawback of using clustering techniques is the inability to identify an optimal number of potential clusters beforehand. Several existing optimization techniques can address the issue. Besides, clustering validation can predict the possible number of potential clusters and hence increase the chances of identifying biologically informative genes. This paper reviews and provides examples of existing methods for clustering genes, optimization of the objective function, and clustering validation. Clustering techniques can be categorized into partitioning, hierarchical, grid-based, and density-based techniques. We also highlight the advantages and the disadvantages of each category. To optimize the objective function, here we introduce the swarm intelligence technique and compare the performances of other methods. Moreover, we discuss the differences of measurements between internal and external criteria to validate a cluster quality. We also investigate the performance of several clustering techniques by applying them on a leukemia dataset. The results show that grid-based clustering techniques provide better classification accuracy; however, partitioning clustering techniques are superior in identifying prognostic markers of leukemia. Therefore, this review suggests combining clustering techniques such as CLIQUE and k-means to yield high-quality gene clusters.
KW - Biological functions detection
KW - Gene clustering
KW - Informative genes
KW - Swarm intelligence
UR - http://www.scopus.com/inward/record.url?scp=85072193310&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85072193310&partnerID=8YFLogxK
U2 - 10.3390/pr7090550
DO - 10.3390/pr7090550
M3 - Review article
AN - SCOPUS:85072193310
SN - 2227-9717
VL - 7
JO - Processes
JF - Processes
IS - 9
M1 - 550
ER -