A0840
Title: Partially characterized topology guides reliable anchor-free scRNA-integration
Authors: Leying Guan - Yale University (United States) [presenting]
Abstract: Single-cell RNA sequencing (scRNA-seq) is increasingly applied to obtain biological insights at cellular resolution, with scRNA-seq batch integration a key step before downstream statistical analysis. Despite the plethora of methods proposed, achieving reliable batch correction while preserving the heterogeneity of biological signals that define cell type continues to pose a challenge, with existing methods' performance varying significantly across different scenarios and datasets. ScCRAFT, a deep-learning model designed to segregate cell-state-related biological signals from batch effects for reliable multi-batch scRNA-seq integration, is proposed. ScCRAFT comprises three main components: an autoencoder that targets the extraction of biological signals, a multi-domain adaptation loss aimed at eliminating batch effects and an innovative dual-resolution triplet loss component for preserving topology within each batch, which is introduced as an effective mechanism to counteract the over-correction effect of domain adaptation loss amid heterogeneous cell distributions across batches. It is shown that scCRAFT effectively manages unbalanced batches, rare cell types, and batch-specific cell phenotypes in simulations and surpasses state-of-the-art methods in a diverse set of real datasets.
