Back

SuperCell2.0 enables semi-supervised construction of multimodal metacell atlases

Herault, L.; Gabriel, A. A.; Duc, B.; Dolfi, B.; Shah, A.; Joyce, J. A.; Gfeller, D.

2026-02-20 bioinformatics
10.64898/2026.02.19.706848 bioRxiv
Show abstract

Multimodal single-cell atlases comprising hundreds of thousands of cells provide unique resources for exploring complex biological tissues and generating testable hypotheses. To streamline the analysis of such large datasets, we introduce SuperCell2.0, a robust workflow to build (semi-)supervised multimodal metacells. We demonstrate that multimodal metacells outperform metacells built with a single modality, improve inter-modality consistency, and facilitate integration of multiomic single-cell datasets. SuperCell2.0 can further leverage full or partial cell type annotations to improve metacell quality. This workflow enables us to construct multimodal metacell atlases from blood and tumor samples and identifies interferon-primed monocytes and macrophages in the circulation and in the tumor microenvironment. Markers derived from the metacell analysis enable us to sort and phenotypically characterize this population in healthy donors. Overall, our work demonstrates how SuperCell2.0 facilitates the analysis of large multimodal single-cell atlases.

Matching journals

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

1
Nature Communications
○ 5641 papers in training set
Top 1%
38.2%
Similar papers in this journal
2
Genome Biology
○ 637 papers in training set
Top 1%
9.4%
Similar papers in this journal
3
Nature Methods
○ 385 papers in training set
Top 1%
7.6%
Similar papers in this journal
50% of probability mass above
4
Nature Biotechnology
○ 172 papers in training set
Top 0.5%
6.5%
Similar papers in this journal
5
Cell Genomics
○ 172 papers in training set
Top 1%
3.9%
Similar papers in this journal
6
Communications Biology
○ 993 papers in training set
Top 6%
3.1%
7
Nucleic Acids Research
◐ 1281 papers in training set
Top 6%
3.1%
8
Advanced Science
○ 286 papers in training set
Top 3%
2.7%
9
Briefings in Bioinformatics
◐ 354 papers in training set
Top 4%
1.9%
10
NAR Genomics and Bioinformatics
◐ 242 papers in training set
Top 3%
1.7%
11
Nature Genetics
○ 286 papers in training set
Top 4%
1.4%
12
iScience
○ 1154 papers in training set
Top 24%
1.3%
13
GigaScience
◐ 212 papers in training set
Top 3%
1.1%
14
Cell Reports
○ 1498 papers in training set
Top 24%
1.1%
15
Molecular Systems Biology
○ 162 papers in training set
Top 2%
1.1%
16
Bioinformatics
◐ 1204 papers in training set
Top 8%
1.1%
17
Genome Medicine
○ 183 papers in training set
Top 4%
1.1%
18
Genome Research
● 468 papers in training set
Top 5%
1.0%
19
eLife
● 5828 papers in training set
Top 64%
1.0%
20
Science Advances
● 1243 papers in training set
Top 29%
0.9%
21
PLOS Computational Biology
● 1863 papers in training set
Top 20%
0.8%
22
Scientific Reports
○ 3612 papers in training set
Top 74%
0.8%
23
Cell Reports Methods
○ 165 papers in training set
Top 5%
0.6%
24
Scientific Data
○ 209 papers in training set
Top 3%
0.6%
25
Cell Systems
○ 201 papers in training set
Top 6%
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.