Single-Cell RNA Sequencing Data Interpretation by Evolutionary Multiobjective Clustering.

Area of Science:

• Genomics
• Bioinformatics
• Computational Biology

Background:

• Single-cell RNA sequencing (scRNA-seq) provides high-resolution cellular genetic data.
• Identifying distinct cell subtypes, like hematopoietic stem cell subpopulations, is crucial.
• Existing algorithms struggle with the high dimensionality and sparsity of scRNA-seq data.

Purpose of the Study:

• To propose a novel multiobjective evolutionary clustering algorithm for scRNA-seq data.
• To address the challenges of high dimensionality and sparsity in scRNA-seq analysis.
• To improve the accuracy and effectiveness of cell subtype identification.

Main Methods:

• Developed adaptive non-negative matrix factorization for feature extraction.
• Implemented a multiobjective clustering algorithm based on learning vector quantization.
• Benchmarked the proposed MCANMF against 15 state-of-the-art methods on six scRNA-seq datasets.

Main Results:

• MCANMF demonstrated superior performance compared to 15 existing methods across multiple evaluation metrics.
• The algorithm effectively handles the complexities of scRNA-seq data for clustering.
• Component, time complexity, and parameter analyses confirmed MCANMF's properties.

Conclusions:

• MCANMF offers an effective solution for scRNA-seq data clustering and cell subtype identification.
• The proposed method advances the analysis of complex single-cell genomic data.
• MCANMF provides a robust and high-performing alternative for bioinformatics research.