Back

cellGeometry: ultra-fast single-cell deconvolution of bulk RNA-Seq using a geometric solution

Lau, R.; Cubuk, C.; Spiliopoulou, A.; Martinez-Paz, P.; Surace, A. E. A.; Fossati-Jimack, L.; Raychaudhuri, S.; Pitzalis, C.; Lewis, M. J.

2026-01-26 bioinformatics
10.64898/2026.01.24.701240 bioRxiv
Show abstract

Single-cell analysis has rapidly expanded to produce cell atlases encompassing all human tissues. However, computational methods to deconvolute bulk samples using single-cell reference data have failed to keep pace with the increasing data size. Here we present cellGeometry, which uses non-negative geometric deconvolution (NGD), an intuitive vector projection method featuring non-negative matrix regularisation. Using matrix operations, cellGeometry scales to massive datasets and is ultrafast. Benchmarked using simulations from single-cell RNA-Seq datasets with >3 million cells, cellGeometry is more accurate than existing methods. It is robust to biases introduced by different sequencing chemistries. It identifies outlying residual genes which may unveil pathogenic changes in gene expression and the presence of cell types absent from the reference. cellGeometrys flexible architecture allows merging of single-cell reference signatures to expand the range of cell types being deconvoluted. Validated against real bulk RNA blood and tissue samples, cellGeometry produces more accurate and realistic results.

Published in Nature Communications (predicted rank #1) · training set

Matching journals

The top 3 journals account for 50% of the predicted probability mass.

Nature Communications · published here
○ 5641 papers in training set
Top 4%
27.1%
Similar papers in this journal
2
Genome Biology
○ 637 papers in training set
Top 0.2%
22.8%
Similar papers in this journal
3
Nature Methods
○ 385 papers in training set
Top 1%
8.1%
Similar papers in this journal
50% of probability mass above
4
Nature Biotechnology
○ 172 papers in training set
Top 0.4%
6.9%
Similar papers in this journal
5
Bioinformatics
◐ 1204 papers in training set
Top 4%
4.5%
Similar papers in this journal
6
Communications Biology
○ 993 papers in training set
Top 5%
3.3%
7
Cell Reports Methods
○ 165 papers in training set
Top 0.6%
3.3%
8
Nucleic Acids Research
◐ 1281 papers in training set
Top 8%
2.0%
9
Briefings in Bioinformatics
◐ 354 papers in training set
Top 4%
1.9%
10
Molecular Systems Biology
○ 162 papers in training set
Top 1%
1.7%
11
PLOS Computational Biology
● 1863 papers in training set
Top 15%
1.5%
12
Nature Genetics
○ 286 papers in training set
Top 4%
1.2%
13
Scientific Reports
○ 3612 papers in training set
Top 62%
1.2%
14
Cell Genomics
○ 172 papers in training set
Top 3%
1.2%
15
iScience
○ 1154 papers in training set
Top 30%
1.1%
16
eLife
● 5828 papers in training set
Top 61%
1.1%
17
Genome Medicine
○ 183 papers in training set
Top 5%
0.9%
18
NAR Genomics and Bioinformatics
◐ 242 papers in training set
Top 4%
0.9%
19
Nature Protocols
○ 33 papers in training set
Top 0.5%
0.9%
20
npj Systems Biology and Applications
○ 125 papers in training set
Top 2%
0.6%
21
BMC Bioinformatics
○ 457 papers in training set
Top 6%
0.6%
22
Patterns
○ 78 papers in training set
Top 3%
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.