PCA-based spatial domain identification with state-of-the-art performance

Darius P. Schaub; Behnam Yousefi; Nico Kaiser; Robin Khatri; Victor G. Puelles; Christian F. Krebs; Ulf Panzer; Stefan Bonn

doi:10.1093/bioinformatics/btaf005

PCA-based spatial domain identification with state-of-the-art performance

Darius P. Schaub^*, Behnam Yousefi, Nico Kaiser, Robin Khatri, Victor G. Puelles, Christian F. Krebs, Ulf Panzer, Stefan Bonn^*

^*Corresponding author for this work

Department of Clinical Medicine - The Department of Pathology

Research output: Contribution to journal/Conference contribution in journal/Contribution to newspaper › Journal article › Research › peer-review

Abstract

Motivation: The identification of biologically meaningful domains is a central step in the analysis of spatial transcriptomic data. Results: Following Occam’s razor, we show that a simple PCA-based algorithm for unsupervised spatial domain identification rivals the performance of ten competing state-of-the-art methods across six single-cell spatial transcriptomic datasets. Our reductionist approach, NichePCA, provides researchers with intuitive domain interpretation and excels in execution speed, robustness, and scalability. Availability and implementation.

Original language	English
Article number	btaf005
Journal	Bioinformatics
Volume	41
Issue	1
ISSN	1367-4803
DOIs	https://doi.org/10.1093/bioinformatics/btaf005
Publication status	Published - Jan 2025

Access to Document

10.1093/bioinformatics/btaf005Licence: CC BY

Cite this

@article{151b875b5b844ba59f840a6cb81d2133,

title = "PCA-based spatial domain identification with state-of-the-art performance",

abstract = "Motivation: The identification of biologically meaningful domains is a central step in the analysis of spatial transcriptomic data. Results: Following Occam{\textquoteright}s razor, we show that a simple PCA-based algorithm for unsupervised spatial domain identification rivals the performance of ten competing state-of-the-art methods across six single-cell spatial transcriptomic datasets. Our reductionist approach, NichePCA, provides researchers with intuitive domain interpretation and excels in execution speed, robustness, and scalability. Availability and implementation.",

author = "Schaub, {Darius P.} and Behnam Yousefi and Nico Kaiser and Robin Khatri and Puelles, {Victor G.} and Krebs, {Christian F.} and Ulf Panzer and Stefan Bonn",

note = "Publisher Copyright: {\textcopyright} The Author(s) 2025. Published by Oxford University Press.",

year = "2025",

month = jan,

doi = "10.1093/bioinformatics/btaf005",

language = "English",

volume = "41",

journal = "Bioinformatics",

issn = "1367-4803",

publisher = "Oxford University Press",

number = "1",

}

TY - JOUR

T1 - PCA-based spatial domain identification with state-of-the-art performance

AU - Schaub, Darius P.

AU - Yousefi, Behnam

AU - Kaiser, Nico

AU - Khatri, Robin

AU - Puelles, Victor G.

AU - Krebs, Christian F.

AU - Panzer, Ulf

AU - Bonn, Stefan

PY - 2025/1

Y1 - 2025/1

N2 - Motivation: The identification of biologically meaningful domains is a central step in the analysis of spatial transcriptomic data. Results: Following Occam’s razor, we show that a simple PCA-based algorithm for unsupervised spatial domain identification rivals the performance of ten competing state-of-the-art methods across six single-cell spatial transcriptomic datasets. Our reductionist approach, NichePCA, provides researchers with intuitive domain interpretation and excels in execution speed, robustness, and scalability. Availability and implementation.

AB - Motivation: The identification of biologically meaningful domains is a central step in the analysis of spatial transcriptomic data. Results: Following Occam’s razor, we show that a simple PCA-based algorithm for unsupervised spatial domain identification rivals the performance of ten competing state-of-the-art methods across six single-cell spatial transcriptomic datasets. Our reductionist approach, NichePCA, provides researchers with intuitive domain interpretation and excels in execution speed, robustness, and scalability. Availability and implementation.

UR - http://www.scopus.com/inward/record.url?scp=85216468643&partnerID=8YFLogxK

U2 - 10.1093/bioinformatics/btaf005

DO - 10.1093/bioinformatics/btaf005

M3 - Journal article

C2 - 39775801

AN - SCOPUS:85216468643

SN - 1367-4803

VL - 41

JO - Bioinformatics

JF - Bioinformatics

IS - 1

M1 - btaf005

ER -

PCA-based spatial domain identification with state-of-the-art performance

Abstract

Access to Document

Other files and links

Fingerprint

Cite this