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
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: The code is available at https://github.com/imsb-uke/nichepca.
Topics & Concepts
Identification (biology)State (computer science)Domain (mathematical analysis)Computer sciencePattern recognition (psychology)Artificial intelligenceData miningAlgorithmMathematicsBiologyBotanyMathematical analysisSingle-cell and spatial transcriptomicsFerroptosis and cancer prognosisDomain Adaptation and Few-Shot Learning