Kandinsky: enabling neighbourhood analysis of spatial omics data for functional insights on cell ecosystems
Andrei, P.; Grieco, M.; Acha-Sagredo, A.; Dhami, P.; Fung, K.; Rodriguez-Justo, M.; Cereda, M.; Ciccarelli, F. D.
Show abstract
Spatially resolved omics technologies enable investigation of how cells interact within their local environments or neighbourhoods directly in situ. Although a few computational methods have been developed to aid this analysis, significant limitations still exist in the way neighbourhoods are defined and exploited for downstream analyses. Here, we present Kandinsky, a computational tool that implements multiple approaches for neighbourhood identification, enabling high flexibility and versatility to address a variety of biological questions. Once identified, Kandinsky applies neighbourhoods for downstream studies, including proximity-based cell grouping for functional comparisons, spatial co-localisation and dispersion, and identification of hot and cold expression areas within the tissue. We apply Kandinsky to transcriptomic and proteomic data from different spatial technologies to showcase how it can reveal functional interactions between cells across multiple biological contexts. Availability and implementationKandinsky is freely available as an R package at https://github.com/ciccalab/Kandinsky.
Matching journals
The top 4 journals account for 50% of the predicted probability mass.
Similar papers in this journal
- Neighborhood nonnegative matrix factorization identifies patterns and spatially-variable genes in large-scale spatial transcriptomics data 96%
- Giotto, a toolbox for integrative analysis and visualization of spatial expression data 95%
- geneBasis: an iterative approach for unsupervised selection of targeted gene panels from scRNA-seq. 95%
Similar papers in this journal
- Characterizing cell-type spatial relationships across length scales in spatially resolved omics data 95%
- A SIMPLI (Single-cell Identification from MultiPLexed Images) approach for spatially resolved tissue phenotypingat single-cell resolution. 95%
- stLearn: integrating spatial location, tissue morphology and gene expression to find cell types, cell-cell interactions and spatial trajectories within undissociated tissues 95%
Similar papers in this journal
- KDML: a machine-learning framework for inference of multi-scale gene functions from genetic perturbation screens 95%
- Pan-Cancer landscape of protein activities identifies drivers of signalling dysregulation and patient survival 95%
- Explainable Machine Learning Identifies Dosage Compensation Factors in Aneuploid Human Cancer Cells 94%
Similar papers in this journal
"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.