scATAnno

scATAnno automatically annotates single-cell assay for transposase-accessible chromatin using sequencing (scATAC-seq) data by integrating query data with large-scale scATAC-seq reference atlases without using single-cell RNA sequencing (scRNA-seq) data.

Key Features:

• Reference Atlas Generation: scATAnno generates reference atlases from publicly available scATAC-seq datasets.
• Uncertainty Scoring: scATAnno incorporates k-nearest neighbors (KNN)-based and weighted distance-based uncertainty scores to detect query cell populations that are distinct from all cell types in the reference data.
• Cross-Platform Benchmarking: scATAnno was benchmarked against five other published cell annotation approaches, demonstrating superior performance across multiple datasets and metrics.

Scientific Applications:

• Peripheral Blood Mononuclear Cell Annotation: scATAnno accurately annotates cell types in peripheral blood mononuclear cell (PBMC) scATAC-seq datasets.
• Cancer Tissue Analysis: scATAnno accurately annotates cell types in triple-negative breast cancer (TNBC) and basal cell carcinoma (BCC) scATAC-seq datasets across diverse biological conditions.
• Complex Biological System Interpretation: scATAnno facilitates the interpretation of new scATAC-seq datasets in complex biological systems through automated cell type annotation.

Methodology:

scATAnno integrates query scATAC-seq data with reference atlases and applies k-nearest neighbors (KNN)-based and weighted distance-based uncertainty scores for annotation.