multi.data.cor: Calculates differential correlation statistics for all the...

In emily5/exCorr: An R package for differential correlation analyses

Description

Requires grouping variable to contain 2 groups. Requires same samples across datasets (arranged in same order). Declare columns (descriptors) column to both datasets.

Usage

multi.data.cor(data1, data2, sample_col, common_cols, group,
  ordered = "fisher", limit = NA)

Arguments

data1	first dataframe
data2	second dataframe
sample_col	character string defining the sample or identifying column in both dataframes
group	character string defining the grouping variable for comparative differential correlations
ordered	character string defining the variable to order output by. Choose from g1cor, g1p, g2cor, g2r, fisher (default) and BH.
limit	numeric input to limit number of output correlation pairings

Value

a table (or dataframe) with the correlation coefficients, p-values, fisher r-to-z statistic and BH p-value correlation for each correlation pair

Author(s)

Emily Mears, [e-mail], Matthew Grant, [e-mail]

Ben Day, [e-mail]

Examples

## Load example dataframes
df1 <- read.csv("example_data/excorr_df1.csv")
df2 <- read.csv("example_data/excorr_df2.csv")

## Run function
multi.data.cor(df1, df2, sample_col = "sample", common_cols = c("sex", "sample"), group = "sex")
multi.data.cor(df1, df2, sample_col = "sample", common_cols = c("sex", "sample"), group = "sex", ordered = "Group_2_Pvalue", limit = 100)

emily5/exCorr documentation built on May 22, 2020, 1:01 p.m.