A web-based platform for cross-modality translation between single-cell RNA-seq and single-cell ATAC-seq
No Thumbnail Available
Authors
Meeting name
Sponsors
Date
Journal Title
Format
Thesis
Subject
Abstract
In recent years, there has been growing interest in profiling multiple omics modalities simultaneously within individual cells. A prominent example of this involves the integration of single-cell RNA sequencing (scRNA-seq) with single-cell assay for transposase-accessible chromatin using sequencing (scATAC-seq). Such paired measurements enable a more comprehensive view of cellular states and regulatory mechanisms than single-modality analyses alone. By jointly analyzing these modalities, researchers can make more accurate predictions and gain deeper biological insights. However, generating multimodal single-cell data remains technically challenging and expensive, leading to limited availability of such datasets. To address this, we introduce a model specifically designed for crossmodal prediction between transcriptomic and chromatin accessibility profiles at the single-cell level. Our method is based on a deep neural network framework that learns latent representations from one modality and accurately predicts the other. We demonstrate the eXectiveness of our model across a variety of human datasets containing paired scATAC-seq and scRNA-seq measurements, showing strong performance in translating between modalities. To make this capability widely accessible, we developed CrossMP, a web-based portal that enables researchers to upload single-modality data and generate cross-modal predictions through an intuitive interface. The platform is supported by high-performance computing infrastructure and is publicly available at https://crossmp.missouri.edu.
Table of Contents
DOI
PubMed ID
Degree
Ph. D.