CTEC: a cross-tabulation ensemble clustering approach for single-cell RNA sequencing data analysis.

Area of Science:

• Computational Biology
• Genomics
• Bioinformatics

Background:

• Cell-type clustering is fundamental for single-cell RNA-seq (scRNA-seq) data analysis.
• Existing clustering methods lack consistency due to variations in pre-processing, distance metrics, and feature extraction.

Purpose of the Study:

• To introduce a novel ensemble clustering method, Cross-Tabulation Ensemble Clustering (CTEC), for improved scRNA-seq data analysis.
• To address the limitations of existing methods by providing more robust and reproducible cluster assignments.

Main Methods:

• CTEC formulates two re-clustering strategies: distribution-based and outlier-based, utilizing cross-tabulation.
• The method was benchmarked on five diverse scRNA-seq datasets.

Main Results:

• CTEC demonstrated significant improvements over individual clustering methods.
• CTEC-DB outperformed state-of-the-art ensemble methods, showing 45.4% and 17.1% improvement over SAFE and SAME, respectively.
• Enhanced accuracy and consistency in cell-type identification were observed.

Conclusions:

• CTEC offers a superior approach to single-cell data clustering.
• The method enhances the reliability and practical applicability of scRNA-seq analysis.
• Source code is available for reproducibility and further research.