scMamba: A Pre-Trained Model for Single-Nucleus RNA Sequencing Analysis in Neurodegenerative Disorders

TL;DR

scMamba is a pre-trained model that enhances single-nucleus RNA sequencing analysis for neurodegenerative diseases by improving data quality and analysis accuracy through a novel architecture and generalizable feature learning.

Contribution

The paper introduces scMamba, a novel pre-trained model with a unique architecture that effectively processes snRNA-seq data without dimension reduction, improving multiple downstream analysis tasks.

Findings

Outperforms benchmark methods in cell type annotation

Improves doublet detection accuracy

Enhances identification of differentially expressed genes

Abstract

Single-nucleus RNA sequencing (snRNA-seq) has significantly advanced our understanding of the disease etiology of neurodegenerative disorders. However, the low quality of specimens derived from postmortem brain tissues, combined with the high variability caused by disease heterogeneity, makes it challenging to integrate snRNA-seq data from multiple sources for precise analyses. To address these challenges, we present scMamba, a pre-trained model designed to improve the quality and utility of snRNA-seq analysis, with a particular focus on neurodegenerative diseases. Inspired by the recent Mamba model, scMamba introduces a novel architecture that incorporates a linear adapter layer, gene embeddings, and bidirectional Mamba blocks, enabling efficient processing of snRNA-seq data while preserving information from the raw input. Notably, scMamba learns generalizable features of cells and genes through pre-training on snRNA-seq data, without relying on dimension reduction or selection of highly variable genes. We demonstrate that scMamba outperforms benchmark methods in various downstream tasks, including cell type annotation, doublet detection, imputation, and the identification of differentially expressed genes.