spatCor: Compute Spatial Autocorrelation for SpatialExperiment objects

In rcastelo/GSVA: Gene Set Variation Analysis for Microarray and RNA-Seq Data

Compute Spatial Autocorrelation for SpatialExperiment objects

Description

Computes spatial autocorrelation using Moran's I statistic for a SpatialExperiment object, using an inverse squared distance weight matrix as default, or an inverse distance weight matrix as an alternative. It also tests for spatial autocorrelation assuming normality.

Usage

## S4 method for signature 'SpatialExperiment'
spatCor(
  spe,
  assay = NA_character_,
  na.rm = FALSE,
  alternative = "two.sided",
  squared = TRUE,
  verbose = TRUE,
  BPPARAM = SerialParam(progressbar = verbose)
)

Arguments

spe	An object of SpatialExperiment class.
assay	Character vector of length 1, specifying the name of the assay to use. By default, an assay called 'logcounts' will be used if present, otherwise the first assay is used.
na.rm	A logical indicating whether missing values should be removed.
alternative	A character string specifying the alternative hypothesis tested against the null hypothesis of no spatial autocorrelation; must be one of "two.sided", "less", or "greater", or any unambiguous abbreviation of these.
squared	A logical indicating whether the inverse distance weight matrix should be squared or not.
verbose	Gives information about each calculation step. Default: TRUE.
BPPARAM	An object of class BiocParallelParam specifying parameters related to the parallel execution of some of the tasks and calculations within this function.

Value

A data.frame with the same row names as the original SpatialExperiment object. Columns include the observed Moran's I statistic, the expected Moran's I statistic under no spatial autocorrelation, the expected standard deviation under no spatial autocorrelation, and the p-value of the test.

See Also

BiocParallelParam

rcastelo/GSVA documentation built on June 14, 2025, 6:38 p.m.