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

Identifying rare cell populations is key to understanding cancer progression and response to therapy. This study introduces MarsGT, an end-to-end deep learning model for rare cell population identification from scMulti-omics data.
MarsGT: Multi-omics analysis for rare population inference  using single-cell graph transformer
Like

Share this post

Choose a social network to share with, or copy the URL to share elsewhere

This is a representation of how your post may appear on social media. The actual post will vary between social networks

Rare cell introduction

We have developed a new tool named MarsGT that is specifically for identifying rare cell populations.

Imagine your body as a huge city with billions of cells as its citizens. Most of these cells are like common residents — they do daily tasks and are easy to spot. But among these, there are some very special ‘rare’ cells. Think of them as elusive, unique characters in the city, not often seen but having a big impact on what happens around them.

In cancer research, these rare cells are super important but not very well-known. They are like hidden influencers in how cancer grows and reacts to treatments. Because they are not in the spotlight very often, it is harder to find and study them, like trying to find a needle in a haystack.

That is why computational biologists are working on special tools to find and learn more about these rare cells. By understanding these undercover agents, we might get better at figuring out cancer mechanisms and how to treat it.

Input and output

MarsGT incorporates scRNA-seq and/or scATAC-seq data and yields rare cell populations along with their respective gene regulatory signatures.

Strengthen of MarsGT

    • MarsGT was tested on over 550 simulated datasets and real human blood cell datasets. It was highly effective in identifying both rare and major cell types in these samples.
    • We used MarsGT on mouse retina cells, and it successfully found rare cell types and their unique functions, which other tools often miss.
    • In cancer research, MarsGT identified a rare cell type named BLS1 (B lymphoma-state-1) in lymphoma, which offers new insights into stopping the disease's progression.
    • MarsGT was applied to blood cell samples from melanoma patients and healthy individuals. It discovered rare cell types and explained why some patients respond differently to a specific immunotherapy.

Application

We recommend MarsGT if you particularly want to

  • identify rare cell populations and focus on the gene regulatory mechanism within these populations.
  • elucidate the transition state and the dynamic changes of the cell development process in a biological system.
  • study why a group of samples has different "labels", such as immune responses and prognosis.

Please sign in or register for FREE

If you are a registered user on Research Communities by Springer Nature, please sign in

Follow the Topic

Mathematical Applications in Computer Science
Mathematics and Computing > Mathematics > Applications of Mathematics > Mathematical Applications in Computer Science
Bioinformatics
Mathematics and Computing > Computer Science > Computer and Information Systems Applications > Bioinformatics

Related Collections

With collections, you can get published faster and increase your visibility.

Applications of Artificial Intelligence in Cancer

In this cross-journal collection between Nature Communications, npj Digital Medicine, npj Precision Oncology, Communications Medicine, Communications Biology, and Scientific Reports, we invite submissions with a focus on artificial intelligence in cancer.

Publishing Model: Open Access

Deadline: Mar 31, 2025

Biology of rare genetic disorders

This cross-journal Collection between Nature Communications, Communications Biology, npj Genomic Medicine and Scientific Reports brings together research articles that provide new insights into the biology of rare genetic disorders, also known as Mendelian or monogenic disorders.

Publishing Model: Open Access

Deadline: Apr 30, 2025