Back

ClusToRa: A niche-centric framework for identifying structural recruitment and infiltration in spatial omics

Githaka, J. M.; Lerner, E. P.

2026-05-27 bioinformatics
10.64898/2026.05.23.727398 bioRxiv
Show abstract

Spatial omics maps cellular landscapes, yet current tools might conflate stochastic proximity with organized niches. We present ClusToRa (Cluster-to-Randomization), a framework that identifies high-density cellular territories and quantifies cell-type recruitment using a fixed-position null model. Benchmarked against graph-based neighborhood-enrichment and point-pattern statistics, ClusToRa reduced false-positive enrichment in simulations and resolved core-vs-boundary interactions. Applied to cirrhotic MASH liver, ClusToRa identifies stellate-cell territories with immune/endothelial infiltration and stress-, Notch-, and PPAR-associated programs, providing a niche-centric framework for distinguishing structural cellular infiltration from boundary adjacency or density-driven colocalization.

Matching journals

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

1
Nature Communications
○ 5641 papers in training set
Top 4%
28.5%
Similar papers in this journal
2
Bioinformatics
◐ 1204 papers in training set
Top 3%
6.7%
Similar papers in this journal
3
Molecular Systems Biology
○ 162 papers in training set
Top 0.2%
6.7%
Similar papers in this journal
4
Cell Systems
○ 201 papers in training set
Top 0.7%
5.5%
Similar papers in this journal
5
eLife
● 5828 papers in training set
Top 35%
3.2%
Similar papers in this journal
50% of probability mass above
6
Briefings in Bioinformatics
◐ 354 papers in training set
Top 3%
3.1%
7
Cell Reports Methods
○ 165 papers in training set
Top 0.8%
2.6%
8
Genome Biology
○ 637 papers in training set
Top 4%
2.6%
9
Communications Biology
○ 993 papers in training set
Top 8%
2.4%
10
Nature Biotechnology
○ 172 papers in training set
Top 2%
2.4%
11
Advanced Science
○ 286 papers in training set
Top 3%
2.4%
12
Nature Cell Biology
○ 118 papers in training set
Top 1%
2.1%
13
Nature Genetics
○ 286 papers in training set
Top 3%
2.1%
14
Nature
○ 645 papers in training set
Top 6%
2.0%
15
Genome Medicine
○ 183 papers in training set
Top 3%
1.7%
16
Nature Methods
○ 385 papers in training set
Top 5%
1.5%
17
PLOS Computational Biology
● 1863 papers in training set
Top 16%
1.3%
18
Scientific Reports
○ 3612 papers in training set
Top 63%
1.1%
19
Cell Genomics
○ 172 papers in training set
Top 3%
1.1%
20
Cell Reports
○ 1498 papers in training set
Top 23%
1.1%
21
iScience
○ 1154 papers in training set
Top 26%
1.1%
22
Science Advances
● 1243 papers in training set
Top 27%
1.0%
23
Current Biology
○ 665 papers in training set
Top 9%
1.0%
24
Science Immunology
● 88 papers in training set
Top 2%
0.8%
25
Life Science Alliance
● 285 papers in training set
Top 9%
0.6%
26
Molecular Biology of the Cell
● 311 papers in training set
Top 4%
0.6%
27
Proceedings of the National Academy of Sciences
● 2444 papers in training set
Top 44%
0.6%
28
JCI Insight
● 277 papers in training set
Top 9%
0.6%
29
PLOS Biology
● 486 papers in training set
Top 13%
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.