transform_data: Normalise data

In villegar/MetaPipe: A High-Performance Computing Pipeline for QTL Mapping of Large Ionomic and Metabolomic Datasets

Normalise data

Description

Normalise data using different methods: log, power, and root, with a different number of parameters to find out which one transforms the data into a normal-ish set.

Usage

transform_data(
  data,
  trait = "DATA",
  alpha = 0.05,
  index = NULL,
  transf_vals = c(2, exp(1), 3, 4, 5, 6, 7, 8, 9, 10),
  plots_prefix = "HIST",
  digits = 6
)

Arguments

data	Original data.
trait	Trait name.
alpha	Significance level.
index	Index of the current trait.
transf_vals	Transformation values.
plots_prefix	Prefix for plots with or without path.
digits	Significant digits to compare p-values of transformations.

Value

Transformed record.

Examples

set.seed(123)
data <- rnorm(100, 5)
out_exp2 <- MetaPipe::transform_data(2 ^ data, "EXP_2")
out_root2 <- MetaPipe::transform_data(sqrt(data), "ROOT_2")
out_pow2 <- MetaPipe::transform_data(data ^ 2, "POW_2")

knitr::kable(head(out_exp2))
knitr::kable(head(out_root2))
knitr::kable(head(out_pow2))

# Clean up example outputs
MetaPipe:::tidy_up("HIST")

villegar/MetaPipe documentation built on Nov. 22, 2022, 10:44 p.m.