scXpand: Pan-cancer detection of T-cell clonal expansion from single-cell RNA sequencing without paired single-cell TCR sequencing

Read the full article See related articles

Discuss this preprint

Start a discussion What are Sciety discussions?

Listed in

This article is not in any list yet, why not save it to one of your lists.
Log in to save this article

Abstract

Advances in single-cell sequencing have enabled detailed characterization of T-cell clonal dynamics in cancer. However, analyses aiming to link transcriptional landscape to T-cell clonality remain limited by confounding factors unequally controlled in different studies. To address this challenge, we developed scXpand, the first machine learning framework for pan-cancer detection of T-cell clonal expansion directly from single-cell RNA sequencing (scRNA-seq), without paired T-cell receptor (TCR) sequencing. Trained and tested using our in-house-constructed human pan-cancer database of paired scRNA/TCR-seq profiles from 2.6 million T cells, scXpand demonstrates robust and accurate detection of clonal expansion across tissues and T-cell subtypes. Applied to datasets lacking TCR sequencing, scXpand predictions correspond with known characteristics of the tumor microenvironment. Overall, scXpand is the first framework to detect T-cell clonal expansion across cancers directly from scRNA-seq, enabling broad use on datasets lacking scTCR-seq, while supporting scalable, memory-efficient processing, including pre-trained models with user-friendly documentation for flexible applications.

Article activity feed