scATAnno: Automated Cell Type Annotation for Single-cell ATAC Sequencing Data.

Area of Science:

• Genomics
• Computational Biology
• Bioinformatics

Background:

• Single-cell epigenomic techniques like scATAC-seq are advancing rapidly.
• Accurate cell type identification from scATAC-seq data is crucial for biological interpretation.
• Existing methods may require complementary data or lack robustness.

Purpose of the Study:

• To introduce scATAnno, a Python package for automated scATAC-seq data annotation.
• To enable cell type identification using large-scale scATAC-seq reference atlases.
• To provide a robust tool for scATAC-seq reference building and cell annotation.

Main Methods:

• Developed scATAnno, a Python package integrating query scATAC-seq data with reference atlases.
• Generated reference atlases from publicly available scATAC-seq datasets.
• Incorporated KNN-based and weighted distance-based uncertainty scores for enhanced accuracy.
• Benchmarked scATAnno against five other cell annotation approaches.

Main Results:

• scATAnno demonstrated superior performance across multiple datasets and metrics compared to existing methods.
• The tool accurately annotates cell types in peripheral blood mononuclear cells (PBMC), triple-negative breast cancer (TNBC), and basal cell carcinoma (BCC).
• Uncertainty scores effectively identified distinct cell populations not present in reference data.

Conclusions:

• scATAnno provides an accurate and efficient method for scATAC-seq cell type annotation.
• The package facilitates scATAC-seq reference atlas construction and data interpretation.
• scATAnno is a valuable tool for analyzing complex biological systems using scATAC-seq data.