2017 IEEE International Conference on Bioinformatics and Biomedicine (BIBM) (2017)
Kansas City, MO, USA
Nov. 13, 2017 to Nov. 16, 2017
Asuda Sharma , College of Information Science and Technology, University of Nebraska at Omaha, Omaha, NE 68182, USA
Hesham H. Ali , College of Information Science and Technology, University of Nebraska at Omaha, Omaha, NE 68182, USA
Biological data is often represented as networks, as in the case of protein-protein interactions and metabolic pathways. Modeling, analyzing, and visualizing networks can help make sense of large volumes of data generated by high-throughput experiments. However, due to their size and complex structure, biological networks can be difficult to interpret without further processing. Cluster analysis is a widely-used approach to extract meaningful information from biological networks. In this work, we provide a study that surveys some of the widely used clustering algorithms used for clustering biological data. We identify the advantages and disadvantages of each algorithm and attempt to identify features associated with datasets that align well with each approach. We also propose a new clustering method based on graph matching and node merging techniques in an attempt to fill the gap left by the current clustering approaches.
Clustering algorithms, Algorithm design and analysis, Proteins, Clustering methods, Data models, Partitioning algorithms
A. Sharma and H. H. Ali, "Analysis of clustering algorithms in biological networks," 2017 IEEE International Conference on Bioinformatics and Biomedicine (BIBM), Kansas City, MO, USA, 2017, pp. 2303-2305.