Scalable Biclustering Algorithm Considers the Presence or Absence of Properties

Scalable Biclustering Algorithm Considers the Presence or Absence of Properties

Abdelilah Balamane
Copyright: © 2021 |Pages: 18
DOI: 10.4018/IJDWM.2021010103
OnDemand:
(Individual Articles)
Available
$37.50
No Current Special Offers
TOTAL SAVINGS: $37.50

Abstract

Most existing biclustering algorithms take into account the properties that hold for a set of objects. However, it could be beneficial in several application domains such as organized crimes, genetics, or digital marketing to identify homogeneous groups of similar objects in terms of both the presence and the absence of attributes. In this paper, the author proposes a scalable and efficient algorithm of biclustering that exploits a binary matrix to produce at least three types of biclusters where the cell's column (1) are filled with 1's, (2) are filled with 0's, and (3) some columns filled with 1's and/or with 0's. This procedure is scalable and it's executed without having to consider the complementary of the initial binary context. The implementation and validation of the method on data sets illustrates its potential in the discovery of relevant patterns.
Article Preview
Top

2. Example Of Biclusters Produced By Bip

Several datamining and machine learning algorithms have been proposed to unveil the interactions between genes and conditions from a gene expression matrix. These algorithms require in many cases that the interaction matrix be discretized. Our algorithm is one of them. In this section we start using Table 1 as example of discretized matrix obtained from a gene expression matrix using an appropriate method of discretization (Cristian et al., 2016). The author applied the algorithm BiP on Table 1 to produce three biclusters of type 2, 1 and 3 respectively represented in Table 2, Table 3 and Table 4.

Table 1.
Discretized gene expression matrix K1
K1C1C2C3C4C5
g1 1 1 1 1 1
g2 1 1 1 1 1
g3-1 1-1 -1 1
g4-1 1-1 -1 1
g5-1 1-1 -1 1
g6 1-1-1 -1-1

Complete Article List

Search this Journal:
Reset
Volume 20: 1 Issue (2024)
Volume 19: 6 Issues (2023)
Volume 18: 4 Issues (2022): 2 Released, 2 Forthcoming
Volume 17: 4 Issues (2021)
Volume 16: 4 Issues (2020)
Volume 15: 4 Issues (2019)
Volume 14: 4 Issues (2018)
Volume 13: 4 Issues (2017)
Volume 12: 4 Issues (2016)
Volume 11: 4 Issues (2015)
Volume 10: 4 Issues (2014)
Volume 9: 4 Issues (2013)
Volume 8: 4 Issues (2012)
Volume 7: 4 Issues (2011)
Volume 6: 4 Issues (2010)
Volume 5: 4 Issues (2009)
Volume 4: 4 Issues (2008)
Volume 3: 4 Issues (2007)
Volume 2: 4 Issues (2006)
Volume 1: 4 Issues (2005)
View Complete Journal Contents Listing