An Efficient Algorithm for Microbiome Sample Visualization Based on UniFrac Distance and Laplace Matrix

Visualization is an important method of data analysis in the study of microbiome, with the dimensionality reduction techniques as its prerequisites for high-dimensional data. Multidimensional scaling (MDS), as a popular method for data visualization, can provide a low-dimensional representation of the original data utilizing its distance matrix. Meanwhile, the unique fraction metric (UniFrac) is a very reasonable and biologically meaningful metric for calculating distance matrices through a phylogenetic tree constructed from microbiome data. However, due to the complexity of the phylogenetic tree and the notable high dimensionality of the microbiome data, applying the MDS with UniFrac would require costly calculations. In this paper, we propose a novel dimensionality reduction algorithm based on Laplace matrix (DRLM) for microbiome data analysis. The experimental results from both synthesized and real microbiome data demonstrate the proposed DRLM is able to conduct more distinct clustering while significantly reducing the computational cost for the dimensionality reduction and visualization in the microbiome data analysis.