Title: Combining multiple clusterings of chemical structures using cluster-based similarity partitioning algorithm
Authors: Faisal Saeed; Naomie Salim; Ammar Abdo
Addresses: Faculty of Computing, Universiti Teknologi Malaysia, Malaysia; Information Technology Department, Sanhan Community College, Sana'a, Yemen ' Faculty of Computing, Universiti Teknologi Malaysia, Malaysia ' Faculty of Computing, Universiti Teknologi Malaysia, Malaysia; Computer Science Department, Hodeidah University, Hodeidah, Yemen
Abstract: Many types of clustering techniques for chemical structures have been used in the literature, but it is known that any single method will not always give the best results for all types of applications. Recent work on consensus clustering methods is motivated because of the successes of combining multiple classifiers in many areas and the ability of consensus clustering to improve the robustness, novelty, consistency and stability of individual clusterings. In this paper, the Cluster-based Similarity Partitioning Algorithm (CSPA) was examined for improving the quality of chemical structures clustering. The effectiveness of clustering was evaluated based on the ability to separate active from inactive molecules in each cluster and the results were compared with the Ward's clustering method. The chemical dataset MDL Drug Data Report (MDDR) database was used for experiments. The results, obtained by combining multiple clusterings, showed that the consensus clustering method can improve the robustness, novelty and stability of chemical structures clustering.
Keywords: consensus clustering; distance measures; graph partitioning; similarity matrix; Ward's method; chemical structures; similarity partitioning; chemical structure clusters.
International Journal of Computational Biology and Drug Design, 2014 Vol.7 No.1, pp.31 - 44
Received: 14 Sep 2012
Accepted: 20 Jan 2013
Published online: 08 Jan 2014 *