Learn R Programming

MSeasy (version 5.3.3)

Data_testclust: Demonstration dataset for MS.test.clust

Description

To test for the best unsupervised clustering method, a dataset where molecules are already identified is created. Each molecule is represented by several samples mass spectrum. Here, the dataset contains 10 molecules obtained in different samples (84 Lavandula GC-MS analyses). In the function MS.test.clust, different clustering methods are tested for their abilities to find the correct structure of the dataset. Three different cluster validity indices are calculated to evaluate the results: the matching coefficient, the silhouette width and the Dunn index (see MS.test.clust for details)

Usage

data(Data_testclust)

Arguments

Format

A data frame with 10 molecules from 84 GC-MS analyses.
  • header line the first row must contains the columns' names
  • first column name of the molecule
  • second column sample name
  • third column retention time
  • following columns mean relative mass spectrum of the molecule (the intensity of one mass fragment (m/z) per column; Mean mass spectrum calculated by averaging 5 percent of the mass spectra surrounding the apex; The intensity of each mass fragment is transformed to a relative percentage of the highest mass fragment per spectrum)

Examples

Run this code
data(Data_testclust)

Run the code above in your browser using DataLab