scBFA

The software tool 'scBFA' addresses technical variation in large-scale single-cell genomic datasets, specifically in scRNA-seq and scATAC-seq datasets. The approach analyzes feature detection patterns alone, disregarding feature quantification measurements. This strategy effectively mitigates technical variation, especially in datasets with low detection noise compared to quantification noise. The scBFA framework demonstrates state-of-the-art performance in cell type identification and trajectory inference, offering potential improvements in existing pipelines with minimal adjustments.