logo
ResearchBunny Logo
MarsGT: Multi-omics analysis for rare population inference using single-cell graph transformer

Medicine and Health

MarsGT: Multi-omics analysis for rare population inference using single-cell graph transformer

X. Wang, M. Duan, et al.

MarsGT, an innovative deep learning model, excels in pinpointing rare cell populations critical for understanding disease progression and therapy responses. This groundbreaking approach offers unprecedented insights into unique subpopulations in various datasets, highlighting potential avenues for early detection and therapeutic intervention. This research was conducted by Xiaoying Wang, Maoteng Duan, Jingxian Li, Anjun Ma, Gang Xin, Dong Xu, Zihai Li, Bingqiang Liu, and Qin Ma.

00:00
00:00
Playback language: English
Abstract
Identifying rare cell populations is crucial in understanding disease progression and response to therapy. MarsGT, a novel deep learning model, uses a probability-based heterogeneous graph transformer to analyze single-cell multi-omics data (scRNA-seq and scATAC-seq). It outperforms existing tools in identifying rare cells across various simulated and real datasets, revealing unique subpopulations in mouse retina and human lymph node and melanoma data, offering potential insights for early detection and therapeutic intervention.
Publisher
Nature Communications
Published On
Jan 06, 2024
Authors
Xiaoying Wang, Maoteng Duan, Jingxian Li, Anjun Ma, Gang Xin, Dong Xu, Zihai Li, Bingqiang Liu, Qin Ma
Tags
deep learning
rare cell populations
single-cell multi-omics
neurology
therapy response
Listen, Learn & Level Up
Over 10,000 hours of research content in 25+ fields, available in 12+ languages.
No more digging through PDFs, just hit play and absorb the world's latest research in your language, on your time.
listen to research audio papers with researchbunny