Back

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

Shorer, O.; Amit, R.; Yizhak, K.

2025-09-17 bioinformatics
10.1101/2025.09.14.676069 bioRxiv
Show 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.

Published in Cell Genomics (predicted rank #9) · training set

Matching journals

The top 5 journals account for 50% of the predicted probability mass.

1
Nature Communications
○ 5641 papers in training set
Top 3%
30.5%
Similar papers in this journal
2
Nature Machine Intelligence
○ 70 papers in training set
Top 0.2%
7.7%
Similar papers in this journal
3
Communications Biology
○ 993 papers in training set
Top 2%
5.4%
Similar papers in this journal
4
Nature Biomedical Engineering
○ 47 papers in training set
Top 0.3%
3.4%
Similar papers in this journal
5
Nature Methods
○ 385 papers in training set
Top 3%
3.4%
Similar papers in this journal
50% of probability mass above
6
Cell Reports
○ 1498 papers in training set
Top 12%
3.2%
7
iScience
○ 1154 papers in training set
Top 8%
3.1%
8
Briefings in Bioinformatics
◐ 354 papers in training set
Top 3%
2.7%
Cell Genomics · published here
○ 172 papers in training set
Top 2%
2.4%
10
Advanced Science
○ 286 papers in training set
Top 3%
2.3%
11
Nucleic Acids Research
◐ 1281 papers in training set
Top 7%
2.3%
12
Cell Systems
○ 201 papers in training set
Top 2%
2.1%
13
Nature Biotechnology
○ 172 papers in training set
Top 2%
2.1%
14
Bioinformatics
◐ 1204 papers in training set
Top 6%
1.9%
15
Genome Biology
○ 637 papers in training set
Top 5%
1.9%
16
Scientific Reports
○ 3612 papers in training set
Top 49%
1.9%
17
Science Advances
● 1243 papers in training set
Top 21%
1.7%
18
Cell Reports Methods
○ 165 papers in training set
Top 2%
1.7%
19
PLOS Computational Biology
● 1863 papers in training set
Top 15%
1.5%
20
eLife
● 5828 papers in training set
Top 54%
1.5%
21
Cell Reports Medicine
○ 153 papers in training set
Top 3%
1.5%
22
Patterns
○ 78 papers in training set
Top 2%
1.3%
23
Nature Genetics
○ 286 papers in training set
Top 5%
1.0%
24
Genome Medicine
○ 183 papers in training set
Top 4%
1.0%
25
npj Precision Oncology
○ 53 papers in training set
Top 2%
0.8%
26
Molecular Systems Biology
○ 162 papers in training set
Top 3%
0.8%
27
Proceedings of the National Academy of Sciences
● 2444 papers in training set
Top 42%
0.8%
28
Cancer Research Communications
● 51 papers in training set
Top 2%
0.6%
29
Cell
○ 431 papers in training set
Top 11%
0.6%
30
Computational and Structural Biotechnology Journal
● 242 papers in training set
Top 8%
0.6%

"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.