scMC learns biological variation through the alignment of multiple single-cell genomics datasets

TLDR

Distinguishing biological from technical variation is crucial for integrating single‑cell genomics datasets, yet existing methods often fail to separate them, leading to loss of both. Here, we present scMC, an integration method that removes technical variation while preserving intrinsic biological variation. scMC learns biological variation through variance analysis and subtracts technical variation inferred in an unsupervised manner. Application of scMC to simulated and real single‑cell RNA‑seq and ATAC‑seq datasets demonstrates its ability to detect context‑shared and context‑specific biological signals via accurate alignment.

Abstract

Distinguishing biological from technical variation is crucial when integrating and comparing single-cell genomics datasets across different experiments. Existing methods lack the capability in explicitly distinguishing these two variations, often leading to the removal of both variations. Here, we present an integration method scMC to remove the technical variation while preserving the intrinsic biological variation. scMC learns biological variation via variance analysis to subtract technical variation inferred in an unsupervised manner. Application of scMC to both simulated and real datasets from single-cell RNA-seq and ATAC-seq experiments demonstrates its capability of detecting context-shared and context-specific biological signals via accurate alignment.