# Spatial autocorrelation (Moran's I)

Source: https://onco.cc/terms/spatial-autocorrelation/  
OnCo record `spatial-autocorrelation` (Term). Data CC BY-NC 4.0, attribute "Data from OnCo (onco.cc)"; commercial use needs a licence.

## TL;DR

Spatial autocorrelation means that nearby spots in a tissue section tend to have similar values; Moran's I is the standard number for how strong that tendency is.

## Summary

Moran's I is a measure of spatial autocorrelation, the correlation of a signal among nearby locations in space, developed by P. A. P. Moran (Wikipedia). Values near +1 mean neighbouring spots agree, near 0 no spatial pattern, and a permutation test gives the p-value. In spatial transcriptomics it is used to show that predicted risk, subtype or expression forms coherent domains rather than noise, and methods such as SpaGCN build the neighbourhood structure into clustering.

## Fields

- Kind: Term
- Last checked: 2026-09-24
- Also known as: spatial autocorrelation; Moran's I; Morans I; spatially autocorrelated; spatial domain; spatial domains
- Tags: cansim-terms

## Notes

- Listed in the CanSim terms map 1.0.0 (docs/onco/terms.json, generated 2026-09-24), CC BY 4.0, attribution: CanSim project, an open, public-data-first cancer foundation-model programme; CanSim page path /terms/spatial-autocorrelation.

## Sources

- Wikipedia: https://en.wikipedia.org/wiki/Moran's_I
- Wikipedia: https://en.wikipedia.org/wiki/Moran's_I

## Connected records

- terms: [Cancer AI vocabulary (CanSim terms map)](https://onco.cc/terms/cancer-ai-vocabulary/), [Permutation test and the Mann-Whitney U test](https://onco.cc/terms/permutation-test/), [Spatial transcriptomics platforms (Visium HD, Xenium, MERFISH, CosMx, CODEX)](https://onco.cc/terms/spatial-transcriptomics-platforms/), [Spatially aware clustering (SpaGCN, KNN smoothing)](https://onco.cc/terms/spagcn/)
- technologies: [Spatial transcriptomics](https://onco.cc/technologies/spatial-transcriptomics/)

---
JSON: https://onco.cc/api/v1/entities/spatial-autocorrelation.json