Study on Ensemble based Clustering Algorithm for Gene Expression Data

Cluster analysis, one of the most powerful tools for analysing gene expression data, has been frequently used to obtain information and knowledge for supporting decision-making for the diagnosis and treatment of diseases. Recently, more scholars are dedicated to ensemble-based clustering algorithms...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Journal of physics. Conference series 2018-08, Vol.1069 (1), p.12121
Hauptverfasser: Chu, Zhenfang, Cao, Buyang, Yu, Fang
Format: Artikel
Sprache:eng
Schlagworte:
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:Cluster analysis, one of the most powerful tools for analysing gene expression data, has been frequently used to obtain information and knowledge for supporting decision-making for the diagnosis and treatment of diseases. Recently, more scholars are dedicated to ensemble-based clustering algorithms for gene datasets. The consensus function is the key of ensemble clustering to integrate clustering results of the base clustering algorithms. In this paper, we propose a new consensus function that transforms multiple clustering results into a co-association matrix according to the weighted voting derived from the mutual information, where the values determining whether two samples belong to the same cluster. The computational experiments on multi-dataset of gene expression using the ensemble clustering algorithm based the new consensus function are conducted. Comparing to the base clustering algorithms including K-Means, DBSCAN and hierarchical clustering as benchmarks, our algorithm presents its superiority.
ISSN:1742-6588
1742-6596
DOI:10.1088/1742-6596/1069/1/012121