Multi-Objective Optimized Fuzzy Clustering for Detecting Cell Clusters from Single-Cell Expression Profiles.

Saurav Mallik,Zhongming Zhao

doi:10.3390/genes10080611

Abstract

Rapid advance in single-cell RNA sequencing (scRNA-seq) allows measurement of the expression of genes at single-cell resolution in complex disease or tissue. While many methods have been developed to detect cell clusters from the scRNA-seq data, this task currently remains a main challenge. We proposed a multi-objective optimization-based fuzzy clustering approach for detecting cell clusters from scRNA-seq data. First, we conducted initial filtering and SCnorm normalization. We considered various case studies by selecting different cluster numbers ( = 2 to a user-defined number), and applied fuzzy c-means clustering algorithm individually. From each case, we evaluated the scores of four cluster validity index measures, Partition Entropy (), Partition Coefficient (), Modified Partition Coefficient (), and Fuzzy Silhouette Index (). Next, we set the first measure as minimization objective (↓) and the remaining three as maximization objectives (↑), and then applied a multi-objective decision-making technique, TOPSIS, to identify the best optimal solution. The best optimal solution (case study) that had the highest TOPSIS score was selected as the final optimal clustering. Finally, we obtained differentially expressed genes (DEGs) using Limma through the comparison of expression of the samples between each resultant cluster and the remaining clusters. We applied our approach to a scRNA-seq dataset for the rare intestinal cell type in mice [GEO ID: GSE62270, 23,630 features (genes) and 288 cells]. The optimal cluster result (TOPSIS optimal score= 0.858) comprised two clusters, one with 115 cells and the other 91 cells. The evaluated scores of the four cluster validity indices, , , , and for the optimized fuzzy clustering were 0.482, 0.578, 0.607, and 0.215, respectively. The Limma analysis identified 1240 DEGs (cluster 1 vs. cluster 2). The top ten gene markers were Rps21, Slc5a1, Crip1, Rpl15, Rpl3, Rpl27a, Khk, Rps3a1, Aldob and Rps17. In this list, Khk (encoding ketohexokinase) is a novel marker for the rare intestinal cell type. In summary, this method is useful to detect cell clusters from scRNA-seq data.

Highlights

Rapid technology development in sequencing over the last two decades has made the transcriptomic analysis of cells and tissues more reliable and informative [1]
In the TOPSIS algorithm, we provided the scores of the four cluster validity index measures for the number case studies, where Partition Coefficient, Modified Partition
We first proposed single-cell cluster identification method based on multi-objective optimization for scRNA-seq gene expression data

Summary

Introduction

Rapid technology development in sequencing over the last two decades has made the transcriptomic analysis of cells and tissues more reliable and informative [1]. Quantification of the mRNA transcripts in genome-wide basis is useful to characterize the molecular circuitries as well as cellular states. Such datasets are accumulated with higher spatial resolution, whereas. Genes 2019, 10, 611 the single-cell RNA sequencing (scRNA-seq) permits to conduct the transcriptome-wide analyses of single cells to discover the interesting biomedical insights as well as biological perception [1,2]. As a heterogeneous cell population, scRNA-seq shows the levels of gene expression for each individual cell, while in bulk-tissue RNA sequencing, mean value of the expression signature in the basis of their cell population level has been evaluated. ScRNA-seq needs the isolation as well as lysis of the single cells, the transformation of their corresponding RNA to cDNA, and the amplification of the cDNA to produce the high-throughput sequencing libraries

Methods

Results

Discussion

Conclusion