SERRF: Systematic error removal using random forest (SERRF)...

In MASHUOA/MassOmics: Data extraction pipeline for large-scale GC-MS metabolomics datasets

Systematic error removal using random forest (SERRF) normalization

Description

This systematic error removal method using random forest algorithm to detect molecule cluster based on sequential intensities profile and use median intensity of this cluster to normalize the data and eliminat the unwanted systematic variations in large sample sets.

Usage

SERRF(
  input = "Area.csv",
  Predict_level = "QC",
  data = NULL,
  datatype = c("MSDIAL", "MASSOMICS"),
  infopath = NULL,
  Log_trans = F,
  zero_imputaion = T,
  vis_norm_result = F
)

Arguments

input	locate the molecule intensities data
Predict_level	specify the sample class that will used for cluster prediction

Value

None

Examples

SERRF(input = "Area.csv",Predict_level=c("QC","Sample"))

MASHUOA/MassOmics documentation built on Nov. 3, 2023, 10:48 p.m.