Automatic density clustering with multiple kernels for high-dimension bioinformatics data

Clustering is an effective method for data analysis and can be exploited to unknown features of data samples, its applications range from data mining to bioinformatics analysis. Several clustering approaches have been proposed in order to obtain a better trade-off between accuracy and efficiency of the clustering process. It is well-known that no existing clustering algorithm completely satisfies both accuracy and efficiency requirements, thus we propose a clustering algorithm called ADCMK (for Automatic Density Clustering with Multiple Kernels) exhibiting higher quality than the density ones proposed so far, while allowing users to cluster efficiently without determining parameters manually. The algorithm consists of learning optimal combined kernel, reducing dimensionality with the optimal kernel, automatically detecting cluster centroids with outliers test, assigning clusters and visualizing results. The proposed clustering algorithm is extensively tested on several well-known high-dimensional dataset in biomedical and bioinformatics field. The results show that the new algorithm tends to automatically produce clusters of better quality than other density clustering algorithms.