Universiti Teknologi Malaysia Institutional Repository

Weighted voting-based consensus clustering for chemical structure databases

Saeed, Faisal and Ahmed, Ali Husain and Omar, Mohd. Shahir Shamsir and Salim, Naomie (2014) Weighted voting-based consensus clustering for chemical structure databases. Journal of Computer-Aided Molecular Design, 28 (6). pp. 675-684. ISSN 0920-654X

Full text not available from this repository.

Official URL: http://dx.doi.org/10.1007/s10822-014-9750-2

Abstract

The cluster-based compound selection is used in the lead identification process of drug discovery and design. Many clustering methods have been used for chemical databases, but there is no clustering method that can obtain the best results under all circumstances. However, little attention has been focused on the use of combination methods for chemical structure clustering, which is known as consensus clustering. Recently, consensus clustering has been used in many areas including bioinformatics, machine learning and information theory. This process can improve the robustness, stability, consistency and novelty of clustering. For chemical databases, different consensus clustering methods have been used including the co-association matrix-based, graph-based, hypergraph-based and voting-based methods. In this paper, a weighted cumulative voting-based aggregation algorithm (W-CVAA) was developed. The MDL Drug Data Report (MDDR) benchmark chemical dataset was used in the experiments and represented by the AlogP and ECPF-4 descriptors. The results from the clustering methods were evaluated by the ability of the clustering to separate biologically active molecules in each cluster from inactive ones using different criteria, and the effectiveness of the consensus clustering was compared to that of Ward's method, which is the current standard clustering method in chemoinformatics. This study indicated that weighted voting-based consensus clustering can overcome the limitations of the existing voting-based methods and improve the effectiveness of combining multiple clusterings of chemical structures.

Item Type:Article
Uncontrolled Keywords:cumulative voting, weighting schemes
Subjects:Q Science > QH Natural history
Divisions:Biosciences and Medical Engineering
ID Code:63240
Deposited By: Siti Nor Hashidah Zakaria
Deposited On:19 Jun 2017 11:06
Last Modified:19 Jun 2017 11:06

Repository Staff Only: item control page