Challenges from Clustering Analysis to Knowledge Discovery in Molecular Biomechanics

Loh      Wei Ping

Abstract

Throughout endless experimental work, short records of dynamic molecular data are generated from time to time. Biomechanics data mining and knowledge discovery have become an important study area to turn the abundance of generated raw data into pieces of information. In data mining, researchers often encounter challenging issues and constraints, ranging from nature of the collected microarray data and developed clustering algorithms to informative discovery for rhythmic data decision-making processes. This article presents the review of the commonly practiced clustering techniques in molecular biomechanical systems towards better applications in bioengineering research. It highlights the constraints and challenges encountered in temporal molecular bioengineering mechanisms. The findings revealed that the molecular data are commonly analyzed based on data mining computation and mathematical applications to link both developmental stages interfaces and the mechanical principles of living organisms. In this area, mathematical analyses are extensively carried out to investigate dynamic microarray using clustering techniques. The main goal is to extract informative knowledge. Therefore, in order to derive collective patterns and reliable information from microarray, there is a need to consider effects from the nature of data, clustering algorithms and knowledge discovery processes which require substantial understanding on biological systems.

Keywords: Clustering, data mining, gene expression, information, knowledge discovery, molecular biomechanics, molecular data, bioengineering mechanisms, mathematical applications, microarray data, Clustering Algorithms.